System

Abstract

An object of a system according to an embodiment is to provide a means for an elderly person to connect to a person without feeling lonely.SOLUTION: A system includes an input unit, a generation unit, a conversation unit, and a recognition unit. The input unit allows a user to input a photograph or a moving image. The generation unit generates a AI using an image generation technique based on the photograph or the moving image inputted by the inputting unit. The conversation unit allows the user to converse with the AI generated by the generation unit. The recognition unit recognizes a voice and an expression of a user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has the problem that elderly people often feel lonely and have limited means of connecting with others.

[0005] The system according to the embodiment aims to provide a means for elderly people to connect with others without feeling lonely. [Means for solving the problem]

[0006] The system according to the embodiment includes an input unit, a generation unit, a conversation unit, and a recognition unit. The input unit allows a user to input photos and videos. The generation unit generates an AI using image generation technology based on the photos and videos input by the input unit. The conversation unit allows a user to converse with the AI ​​generated by the generation unit. The recognition unit recognizes the user's voice and facial expressions. [Effects of the Invention]

[0007] The system according to the embodiment can provide a means for elderly people to connect with others without feeling lonely. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) An appliance according to an embodiment of the present invention is a system designed to address the elderly's desire to connect with others. This system allows a user to input photos and videos of their grandchildren, and uses DeepFake technology to generate an AI that looks exactly like the grandchild. The AI ​​can then engage in natural conversations with the user. For example, when the user asks, "How was your day?", the AI ​​responds with, "I had a lot of fun at school today." This allows the user to experience a conversation as if they were actually having a conversation with their grandchild. Furthermore, the system can recognize the user's voice and facial expressions and appropriately adjust the content of the conversation. For example, when the user speaks with a smile, the AI ​​also responds with a smile. This mechanism allows the elderly to feel connected to their grandchildren and reduce their feelings of loneliness. It is also expected that this will increase communication with family members and improve their mental health. This appliance allows the elderly to feel connected to their grandchildren and reduce their feelings of loneliness. It is also expected that this will increase communication with family members and improve their mental health.

[0029] An appliance according to an embodiment includes an input unit, a generation unit, a conversation unit, and a recognition unit. The input unit allows a user to input photos and videos. For example, the input unit can accept photos and videos in formats such as JPEG, PNG, and MP4. Furthermore, when a user inputs photos and videos by voice, the input unit can also use voice recognition technology to perform the input. The generation unit generates an AI based on the input photos and videos using Deep Fake technology. For example, the generation unit uses a deep learning algorithm to generate an AI that looks exactly like a grandchild from the input photos and videos. The generation unit can also generate an AI based on the input photos and videos using face swap technology. The conversation unit allows a user to converse with the generated AI. For example, the conversation unit recognizes the user's utterances using voice recognition technology and generates appropriate responses using natural language processing technology. The conversation unit can also adjust the fluency of the conversation and the appropriateness of the responses based on the user's utterances. The recognition unit recognizes the user's voice and facial expressions and adjusts the content of the conversation. For example, the recognition unit recognizes the user's voice using a voice recognition algorithm and recognizes the user's facial expressions using facial expression recognition technology. The recognition unit can also recognize user gestures using gesture recognition technology. As a result, the appliance according to the embodiment allows elderly people to have natural conversations with AI that looks just like their grandchild, thereby reducing feelings of loneliness and improving their mental health.

[0030] The generation unit can use image generation technology to generate AI based on input photos and videos. The generation unit can also use Deep Fake technology to generate AI based on input photos and videos. For example, the generation unit can use a deep learning algorithm to generate an AI that looks exactly like a grandchild from input photos and videos. The generation unit can also use face swapping technology to generate AI based on input photos and videos. In this way, Deep Fake technology can be used to generate more realistic AI.

[0031] The conversation unit allows the user to have a conversation with the generated AI. For example, the conversation unit uses voice recognition technology to recognize what the user says and natural language processing technology to generate an appropriate response. The conversation unit can also adjust the fluency of the conversation and the appropriateness of the response based on what the user says. This allows the user to have a natural conversation with the generated AI, giving them the experience of talking as if they were talking to their grandchild.

[0032] The recognition unit can recognize the user's voice and facial expressions and adjust the content of the conversation. The recognition unit, for example, recognizes the user's voice and facial expressions and adjusts the content of the conversation. For example, the recognition unit recognizes the user's voice using a voice recognition algorithm and recognizes the user's facial expressions using facial expression recognition technology. The recognition unit can also recognize the user's gestures using gesture recognition technology. This allows for more natural conversation by recognizing the user's voice and facial expressions.

[0033] The appliance includes a conversation adjustment unit that adjusts the content of the conversation so that the generated AI can have a natural conversation. The conversation adjustment unit, for example, adjusts the content of the conversation so that the generated AI can have a natural conversation. For example, the conversation adjustment unit changes responses and selects conversation topics based on the user's reactions. The conversation adjustment unit can also adjust the fluency of the conversation and the appropriateness of responses based on the user's utterances. In this way, adjusting the content of the conversation enables a more natural conversation.

[0034] The appliance includes a response adjustment unit that adjusts the content of the conversation according to the user's voice and facial expression. The response adjustment unit adjusts the content of the conversation according to, for example, the user's voice and facial expression. For example, the response adjustment unit changes the response based on the user's tone of voice and facial expression. The response adjustment unit can also adjust the fluency of the conversation and the appropriateness of the response based on the user's utterances. This allows for more appropriate responses by adjusting the content of the conversation according to the user's voice and facial expression.

[0035] The appliance includes a data protection unit that protects input photos and videos from leaking to the outside. The data protection unit protects, for example, input photos and videos from leaking to the outside. For example, the data protection unit protects data using encryption technology. The data protection unit can also perform access control to prevent unauthorized access to data. In this way, the data protection unit protects the privacy of users.

[0036] The appliance includes an input unit that analyzes the user's past input history and selects the optimal input method. The input unit, for example, analyzes the user's past input history and selects the optimal input method. For example, the input unit preferentially suggests input methods (voice, text, etc.) that the user has frequently used in the past. The input unit can also analyze trends in photos and videos that the user has entered in the past and suggest the optimal input method. The input unit can also predict and suggest the input method that will be used during a specific time period based on the user's past input history. In this way, the optimal input method can be suggested to the user by analyzing the past input history.

[0037] The appliance includes an input unit that filters photos and videos based on the user's current living situation and areas of interest when the photos and videos are input. For example, the input unit filters photos and videos based on the user's current living situation and areas of interest when the photos and videos are input. For example, the input unit prioritizes input of photos and videos related to the user's current living situation. The input unit can also filter and input related photos and videos based on the user's areas of interest. The input unit can also analyze the user's living situation and areas of interest and suggest optimal photos and videos. As a result, filtering based on the user's living situation and areas of interest allows more relevant photos and videos to be input.

[0038] The appliance includes an input unit that selects the optimal input means depending on the user's input method when inputting photos or videos. For example, when inputting photos or videos, the input unit selects the optimal input means depending on the user's input method. For example, when the user inputs photos or videos by voice, the input unit performs input using voice recognition technology. Furthermore, when the user inputs photos or videos using text, the input unit can also perform input using text analysis technology. Furthermore, when the user inputs photos or videos using images, the input unit can also perform input using image recognition technology. This improves input efficiency by selecting the optimal input means depending on the user's input method.

[0039] The appliance includes an input unit that, when inputting photos or videos, prioritizes input of highly relevant data taking into account the user's geographical location information. For example, when inputting photos or videos, the input unit prioritizes input of highly relevant data taking into account the user's geographical location information. For example, the input unit prioritizes input of photos and videos related to the user's current location. The input unit can also filter and input related photos and videos based on the user's geographical location information. The input unit can also analyze the user's geographical location information and suggest optimal photos and videos. In this way, more relevant data can be prioritized by taking the user's geographical location information into account.

[0040] The appliance includes an input unit that analyzes a user's social media activity and inputs related data when a photo or video is input. For example, when a photo or video is input, the input unit analyzes the user's social media activity and inputs related data. For example, the input unit prioritizes input of photos and videos shared by the user on social media. The input unit can also analyze the user's social media activity and filter and input related photos and videos. The input unit can also suggest optimal photos and videos based on the user's social media activity. This allows for efficient input of related data by analyzing the user's social media activity.

[0041] The appliance includes an input unit that customizes an input method by reflecting a user's past feedback when inputting a photo or video. The input unit customizes the input method by reflecting a user's past feedback when inputting a photo or video, for example. For example, the input unit suggests an optimal input method based on feedback provided by the user in the past. The input unit can also analyze the user's past feedback and customize the input method. The input unit can also optimize the input procedure by reflecting the user's past feedback. In this way, the input method can be optimized by reflecting the user's past feedback.

[0042] The appliance includes a generation unit that adjusts the level of detail of the generated AI based on the importance of the photos and videos when generating the AI. For example, the generation unit adjusts the level of detail of the generated AI based on the importance of the photos and videos when generating the AI. For example, the generation unit uses detailed representations for important photos and videos. The generation unit can also use simplified representations for photos and videos with low importance. The generation unit can also analyze the importance of photos and videos and adjust the level of detail of the generated AI. This allows for the generation of more appropriate AI by adjusting the level of detail of the generated AI based on the importance of the photos and videos.

[0043] The appliance includes a generation unit that applies different generation algorithms depending on the photo or video category when generating AI. For example, the generation unit applies different generation algorithms depending on the photo or video category when generating AI. For example, the generation unit uses a specific algorithm for family photos. The generation unit can also use a different algorithm for travel videos. The generation unit can also analyze the photo or video category and apply the optimal generation algorithm. This allows for the generation of more appropriate AI by applying the optimal generation algorithm depending on the photo or video category.

[0044] The appliance includes a generation unit that, when generating AI, improves the accuracy of generation by referring to the user's past generation results. For example, when generating AI, the generation unit improves the accuracy of generation by referring to the user's past generation results. For example, the generation unit analyzes the user's past generation results, and the generation AI improves accuracy. The generation unit can also select an optimal generation method based on the user's past generation results. The generation unit can also improve the accuracy of the generation AI by referring to the user's past generation results. In this way, the accuracy of generation can be improved by referring to the user's past generation results.

[0045] The appliance includes a generation unit that determines the generation priority based on the time of submission of photos and videos during AI generation. For example, the generation unit determines the generation priority based on the time of submission of photos and videos during AI generation. For example, the generation unit prioritizes the generation of recently submitted photos and videos. The generation unit can also postpone the generation of photos and videos that were submitted earlier. The generation unit can also determine the generation priority taking the time of submission into consideration. In this way, by determining the generation priority based on the time of submission, the latest data can be generated preferentially.

[0046] The appliance includes a generation unit that adjusts the order of generation based on the relevance of photos and videos during AI generation. For example, the generation unit adjusts the order of generation based on the relevance of photos and videos during AI generation. For example, the generation unit prioritizes generating highly relevant photos and videos. The generation unit can also postpone generating less relevant photos and videos. The generation unit can also analyze the relevance of photos and videos and adjust the order of generation. In this way, by adjusting the order of generation based on relevance, more relevant data can be generated preferentially.

[0047] The appliance includes a generation unit that adjusts the use of technical terminology in the generated AI according to the user's level of expertise. For example, when generating the AI, the generation unit adjusts the use of technical terminology in the generated AI according to the user's level of expertise. For example, if the user has technical expertise, the generation unit uses a lot of technical terminology. Also, if the user does not have technical expertise, the generation unit can avoid technical terminology. The generation unit can also analyze the user's level of expertise and select the most appropriate terminology. In this way, by adjusting the use of technical terminology according to the user's level of expertise, more understandable conversations can be achieved.

[0048] The appliance includes a conversation unit that adjusts the level of detail of a conversation based on the importance of the AI ​​during the conversation. For example, the conversation unit adjusts the level of detail of a conversation based on the importance of the AI ​​during the conversation. For example, the conversation unit provides a detailed explanation for an important conversation. The conversation unit can also provide a simplified explanation for a conversation with a low importance. The conversation unit can also analyze the importance of the conversation and adjust the level of detail of the conversation. As a result, by adjusting the level of detail based on the importance of the conversation, more appropriate conversations can be achieved.

[0049] The appliance includes a conversation unit that applies different conversation algorithms depending on the AI ​​category during a conversation. The conversation unit applies different conversation algorithms depending on the AI ​​category during a conversation, for example. For example, the conversation unit uses a specific algorithm when talking with family. The conversation unit can also use a different algorithm when talking with friends. The conversation unit can also analyze the category of the conversation and apply the most appropriate conversation algorithm. In this way, more appropriate conversations can be achieved by applying the most appropriate conversation algorithm depending on the category of the conversation.

[0050] The appliance includes a conversation unit that, during a conversation, improves the accuracy of the conversation by referring to the user's past conversation results. For example, the conversation unit improves the accuracy of the conversation by referring to the user's past conversation results. For example, the conversation unit analyzes the user's past conversation results, and the conversation AI improves the accuracy. The conversation unit can also select an optimal conversation method based on the user's past conversation results. The conversation unit can also improve the accuracy of the conversation by referring to the user's past conversation results. In this way, the accuracy of the conversation can be improved by referring to the user's past conversation results.

[0051] The appliance includes a conversation unit that, during a conversation, determines the priority of the conversation based on the time of submission by the AI. For example, during a conversation, the conversation unit determines the priority of the conversation based on the time of submission by the AI. For example, the conversation unit prioritizes processing of recently submitted conversation content. The conversation unit can also postpone conversation content that was submitted earlier. The conversation unit can also determine the priority of the conversation taking the time of submission into consideration. In this way, by determining the priority of the conversation based on the time of submission, the most recent conversation content can be processed preferentially.

[0052] The appliance includes a conversation unit that adjusts the order of conversations based on the relevance of the AI ​​during a conversation. The conversation unit, for example, adjusts the order of conversations based on the relevance of the AI ​​during a conversation. For example, the conversation unit prioritizes processing of highly relevant conversation content. The conversation unit can also postpone conversation content with low relevance. The conversation unit can also analyze the relevance of the conversation content and adjust the order of conversations. In this way, by adjusting the order of conversations based on relevance, more relevant conversations can be prioritized for processing.

[0053] The appliance includes a conversation unit that adjusts the use of technical terms in a conversation according to the user's level of expertise. The conversation unit, for example, adjusts the use of technical terms in a conversation according to the user's level of expertise. For example, if the user has technical expertise, the conversation unit uses a lot of technical terms. Also, if the user does not have technical expertise, the conversation unit can avoid technical terms. The conversation unit can also analyze the user's level of expertise and select optimal terms. In this way, by adjusting the use of technical terms according to the user's level of expertise, a conversation that is easier to understand is realized.

[0054] The appliance includes a recognition unit that optimizes a recognition algorithm by referring to the user's past voice and facial expression data during recognition. The recognition unit, for example, optimizes the recognition algorithm by referring to the user's past voice and facial expression data during recognition. For example, the recognition unit selects an optimal algorithm based on the user's past voice data. The recognition unit can also improve accuracy based on the user's past facial expression data. The recognition unit can also optimize the recognition algorithm by referring to the user's past voice and facial expression data. In this way, by referring to the past voice and facial expression data, the recognition algorithm can be optimized and recognition accuracy can be improved.

[0055] The appliance includes a recognition unit that performs recognition taking into account user attribute information. For example, the recognition unit performs recognition taking into account user attribute information. For example, the recognition unit selects the optimal recognition method taking into account the user's age and gender. The recognition unit can also improve accuracy based on the user attribute information. The recognition unit can also analyze the user attribute information and suggest the optimal recognition method. This allows for more accurate recognition by taking into account the user attribute information.

[0056] The appliance includes a recognition unit that weights recognition based on the frequency of user submissions during recognition. The recognition unit, for example, weights recognition based on the frequency of user submissions during recognition. For example, the recognition unit prioritizes recognition of data of users with high submission frequencies. The recognition unit can also postpone recognition of data of users with low submission frequencies. The recognition unit can also weight recognition taking into account submission frequency. In this way, by weighting recognition based on submission frequency, more important data can be prioritized for recognition.

[0057] The appliance includes a recognition unit that performs recognition taking into account the geographical distribution of users. For example, the recognition unit performs recognition taking into account the geographical distribution of users. For example, the recognition unit selects an optimal recognition method based on the geographical distribution of users. The recognition unit can also analyze the geographical distribution of users to improve accuracy. The recognition unit can also perform recognition taking into account the geographical distribution of users. This allows for more accurate recognition by taking into account the geographical distribution of users.

[0058] The appliance includes a recognition unit that improves the accuracy of recognition by referring to the user's related literature during recognition. The recognition unit, for example, improves the accuracy of recognition by referring to the user's related literature during recognition. For example, the recognition unit selects an optimal recognition method based on the user's related literature. The recognition unit can also analyze the user's related literature to improve accuracy. The recognition unit can also improve the accuracy of recognition by referring to the user's related literature. In this way, the accuracy of recognition can be improved by referring to the related literature.

[0059] The appliance includes a recognition unit that performs recognition taking into account the market value of the user. For example, the recognition unit performs recognition taking into account the market value of the user. For example, the recognition unit selects an optimal recognition method based on the market value of the user. The recognition unit can also analyze the market value of the user and improve accuracy. The recognition unit can also perform recognition taking into account the market value of the user. This allows for more appropriate recognition by taking into account the market value of the user.

[0060] The appliance includes a conversation adjustment unit that, during conversation adjustment, optimizes the current conversation by referring to past conversation data. The conversation adjustment unit, for example, optimizes the current conversation by referring to past conversation data during conversation adjustment. For example, the conversation adjustment unit selects an optimal adjustment method based on the user's past conversation data. The conversation adjustment unit can also analyze the user's past conversation data to improve accuracy. The conversation adjustment unit can also optimize the current conversation by referring to the user's past conversation data. In this way, by referring to the past conversation data, the current conversation can be optimized and accuracy can be improved.

[0061] The appliance includes a conversation adjustment unit that applies different adjustment methods to each AI category when adjusting a conversation. The conversation adjustment unit applies different adjustment methods to each AI category when adjusting a conversation. For example, the conversation adjustment unit uses a specific adjustment method when talking with family. The conversation adjustment unit can also use a different adjustment method when talking with friends. The conversation adjustment unit can also analyze the category of the conversation and apply the optimal adjustment method. In this way, by applying different adjustment methods to each AI category, more appropriate conversations can be achieved.

[0062] The appliance includes a conversation adjustment unit that, when adjusting a conversation, takes into account the attribute information of the person submitting the AI. The conversation adjustment unit, for example, when adjusting a conversation, takes into account the attribute information of the person submitting the AI. For example, the conversation adjustment unit selects the optimal adjustment method by taking into account the age and gender of the person submitting the conversation. The conversation adjustment unit can also improve accuracy based on the attribute information of the person submitting the conversation. The conversation adjustment unit can also analyze the attribute information of the person submitting the conversation and propose the optimal adjustment method. This enables more appropriate conversation adjustment by taking into account the attribute information of the person submitting the conversation.

[0063] The appliance includes a conversation adjustment unit that analyzes conversation changes based on the time of submission of the AI ​​during conversation adjustment. The conversation adjustment unit, for example, analyzes conversation changes based on the time of submission of the AI ​​during conversation adjustment. For example, the conversation adjustment unit prioritizes analysis of recently submitted conversation content. The conversation adjustment unit can also postpone conversation content that was submitted earlier. The conversation adjustment unit can also analyze conversation changes taking the time of submission into consideration. In this way, more appropriate conversations can be achieved by analyzing conversation changes based on the time of submission.

[0064] The appliance includes a conversation adjustment unit that adjusts the conversation by referring to market data related to the AI ​​when adjusting the conversation. The conversation adjustment unit, for example, adjusts the conversation by referring to market data related to the AI ​​when adjusting the conversation. For example, the conversation adjustment unit selects an optimal adjustment method based on the market data. The conversation adjustment unit can also analyze the market data and improve accuracy. The conversation adjustment unit can also adjust the conversation by referring to the market data. In this way, by referring to the related market data, the accuracy of the conversation can be improved.

[0065] The appliance includes a conversation adjustment unit that adjusts the conversation taking into account the technological maturity of the AI ​​when adjusting the conversation. The conversation adjustment unit adjusts the conversation taking into account the technological maturity of the AI ​​when adjusting the conversation. For example, the conversation adjustment unit performs detailed adjustment when the technological maturity is high. The conversation adjustment unit can also perform simplified adjustment when the technological maturity is low. The conversation adjustment unit can also select the optimal adjustment method taking into account the technological maturity. This makes it possible to perform more appropriate conversation adjustment by taking into account the technological maturity.

[0066] The appliance includes a response adjustment unit that improves the accuracy of responses by taking into account the interrelationships between AIs when adjusting a response. The response adjustment unit improves the accuracy of responses by taking into account the interrelationships between AIs when adjusting a response, for example. For example, the response adjustment unit analyzes the interrelationships with other AIs and provides an optimal response. The response adjustment unit can also improve accuracy by referring to the responses of other AIs. The response adjustment unit can also improve the accuracy of responses by taking into account the interrelationships. In this way, the accuracy of responses can be improved by taking into account the interrelationships between AIs.

[0067] The appliance includes a response adjustment unit that, when adjusting a response, takes into account the attribute information of the AI ​​submitter. For example, when adjusting a response, the response adjustment unit takes into account the attribute information of the AI ​​submitter. For example, the response adjustment unit selects the optimal response method by taking into account the submitter's age and gender. The response adjustment unit can also improve accuracy based on the submitter's attribute information. The response adjustment unit can also analyze the submitter's attribute information and propose the optimal response method. This enables a more appropriate response by taking into account the submitter's attribute information.

[0068] The appliance includes a response adjustment unit that weights responses based on the frequency of submission by the AI ​​during response adjustment. The response adjustment unit, for example, weights responses based on the frequency of submission by the AI ​​during response adjustment. For example, the response adjustment unit prioritizes responses to data from users with a high submission frequency. The response adjustment unit can also postpone data from users with a low submission frequency. The response adjustment unit can also weight responses taking into account the frequency of submission. In this way, by weighting responses based on the frequency of submission, more important data can be prioritized in responses.

[0069] The appliance includes a response adjustment unit that, when adjusting a response, takes into account the geographical distribution of the AI. For example, when adjusting a response, the response adjustment unit takes into account the geographical distribution of the AI. For example, the response adjustment unit selects an optimal response method based on the geographical distribution of users. The response adjustment unit can also analyze the geographical distribution of users to improve accuracy. The response adjustment unit can also take into account the geographical distribution of users when making a response. This allows for a more appropriate response by taking into account the geographical distribution.

[0070] The appliance includes a response adjustment unit that, when adjusting a response, refers to literature related to the AI ​​to improve the accuracy of the response. The response adjustment unit, for example, when adjusting a response, refers to literature related to the AI ​​to improve the accuracy of the response. For example, the response adjustment unit selects an optimal response method based on literature related to the user. The response adjustment unit can also analyze literature related to the user to improve accuracy. The response adjustment unit can also improve the accuracy of the response by referring to literature related to the user. In this way, the accuracy of the response can be improved by referring to related literature.

[0071] The appliance includes a response adjustment unit that, when adjusting a response, takes into account the market value of the AI ​​to make a response. For example, when adjusting a response, the response adjustment unit takes into account the market value of the AI ​​to make a response. For example, the response adjustment unit selects the optimal response method based on the market value of the user. The response adjustment unit can also analyze the market value of the user and improve accuracy. The response adjustment unit can also make a response taking into account the market value of the user. In this way, by taking market value into account, a more appropriate response is possible.

[0072] The appliance includes a data protection unit that, when protecting data, refers to past data protection history to select an optimal protection method. For example, when protecting data, the data protection unit refers to past data protection history to select an optimal protection method. For example, the data protection unit selects an optimal protection method based on past data protection history. The data protection unit can also analyze past data protection history to improve accuracy. The data protection unit can also select an optimal protection method by referring to past data protection history. In this way, by referring to past data protection history, an optimal protection method can be selected and accuracy can be improved.

[0073] The appliance includes a data protection unit that takes user attribute information into consideration when protecting data. For example, the data protection unit takes user attribute information into consideration when protecting data. For example, the data protection unit selects the optimal protection method by taking the user's age and gender into consideration. The data protection unit can also improve accuracy based on the user's attribute information. The data protection unit can also analyze the user's attribute information and propose the optimal protection method. This makes it possible to provide more appropriate data protection by taking user attribute information into consideration.

[0074] The appliance includes a data protection unit that adjusts the level of detail of protection based on the importance of the data when protecting the data. For example, the data protection unit adjusts the level of detail of protection based on the importance of the data when protecting the data. For example, the data protection unit uses a detailed protection method for important data. The data protection unit can also use a simplified protection method for data with low importance. The data protection unit can also analyze the importance of the data and adjust the level of detail of protection. In this way, adjusting the level of detail of protection based on the importance of the data enables more appropriate data protection.

[0075] The appliance includes a data protection unit that takes into account the geographic distribution of data when protecting the data. For example, the data protection unit selects the optimal protection method based on the geographic distribution of the data. The data protection unit can also analyze the geographic distribution of the data to improve accuracy. The data protection unit can also protect the data by taking into account the geographic distribution of the data. This makes it possible to provide more appropriate data protection by taking into account the geographic distribution of the data.

[0076] The appliance includes a data protection unit that improves the accuracy of protection by referring to relevant laws and regulations when protecting data. The data protection unit, for example, improves the accuracy of protection by referring to relevant laws and regulations when protecting data. For example, the data protection unit selects an optimal protection method based on relevant laws and regulations. The data protection unit can also analyze relevant laws and regulations and improve the accuracy. The data protection unit can also improve the accuracy of protection by referring to relevant laws and regulations. In this way, the accuracy of data protection can be improved by referring to relevant laws and regulations.

[0077] The appliance includes a data protection unit that takes into account the market value of the data when protecting the data. For example, the data protection unit selects the optimal protection method based on the market value of the data. The data protection unit can also analyze the market value of the data and improve accuracy. The data protection unit can also protect the data by taking into account the market value of the data. This enables more appropriate data protection by taking into account the market value of the data.

[0078] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0079] The appliance may also include a hobby and interest analysis unit that selects conversation topics based on the user's hobbies and interests. For example, the hobby and interest analysis unit may analyze data previously entered by the user and conversation history to identify topics that interest the user. The hobby and interest analysis unit may also provide related conversation content based on topics in which the user has recently shown interest. Furthermore, the hobby and interest analysis unit may suggest new topics based on the user's hobbies and interests. This allows for more interesting conversations by providing conversation content that matches the user's hobbies and interests.

[0080] The appliance may also include a conversation prediction unit that analyzes the user's past conversation history and predicts the flow of the conversation. For example, the conversation prediction unit may analyze the user's past conversation patterns and predict the next topic to talk about. The conversation prediction unit may also generate an appropriate response based on the user's utterances. Furthermore, the conversation prediction unit may make suggestions to smooth the flow of the conversation based on the user's past conversation history. In this way, by utilizing the user's past conversation history, a more natural conversation can be realized.

[0081] The appliance may also include a lifestyle rhythm adjustment unit that adjusts the timing of conversations based on the user's lifestyle rhythm. For example, if the user prefers lively conversations in the morning, the lifestyle rhythm adjustment unit may provide conversation content suitable for the morning. Alternatively, if the user prefers relaxed conversations in the evening, the lifestyle rhythm adjustment unit may provide conversation content suitable for the evening. Furthermore, the lifestyle rhythm adjustment unit may adjust the frequency and length of conversations based on the user's lifestyle rhythm. This allows for more comfortable conversations by providing conversation timings that match the user's lifestyle rhythm.

[0082] The appliance may also include a behavior analysis unit that analyzes the user's past behavioral data and suggests conversation content based on the behavioral patterns. For example, the behavior analysis unit may analyze the user's frequent past behaviors and provide related conversation content. The behavior analysis unit may also suggest new behaviors based on the user's behavioral patterns. Furthermore, the behavior analysis unit may also provide advice or suggestions for behavioral improvements based on the user's behavioral data. This allows for more practical conversations by providing conversation content that matches the user's behavioral patterns.

[0083] The appliance may also include a location information adjustment unit that utilizes the user's geographic location information to adjust the content of the conversation based on the location information. For example, if the user is traveling, the location information adjustment unit may provide information and advice related to the user's travel destination. Alternatively, if the user is at home, the location information adjustment unit may provide local news and event information. Furthermore, the location information adjustment unit may suggest optimal conversation content based on the user's location information. This allows for more relevant conversations by providing conversation content tailored to the user's geographic location information.

[0084] The processing flow of the first embodiment will be briefly explained below.

[0085] Step 1: The input unit receives a photo or video from the user. For example, the input unit can accept photos or videos in formats such as JPEG, PNG, and MP4. The input unit can also use voice recognition technology to input photos or videos using voice commands. Step 2: The generator uses Deep Fake technology to generate an AI based on the input photos and videos. For example, the generator uses a deep learning algorithm to generate an AI that looks exactly like your grandchild from the input photos and videos. The generator can also use face swapping technology to generate an AI based on the input photos and videos. Step 3: The conversation unit allows the user to converse with the generated AI. For example, the conversation unit uses voice recognition technology to recognize what the user says and natural language processing technology to generate an appropriate response. The conversation unit can also adjust the fluency of the conversation and the appropriateness of the response based on what the user says. Step 4: The recognition unit recognizes the user's voice and facial expressions and adjusts the content of the conversation. For example, the recognition unit may recognize the user's voice using a voice recognition algorithm and the user's facial expressions using facial expression recognition technology. The recognition unit may also recognize the user's gestures using gesture recognition technology.

[0086] (Example 2) An appliance according to an embodiment of the present invention is a system designed to address the elderly's desire to connect with others. This system allows a user to input photos and videos of their grandchildren, and uses DeepFake technology to generate an AI that looks exactly like the grandchild. The AI ​​can then engage in natural conversations with the user. For example, when the user asks, "How was your day?", the AI ​​responds with, "I had a lot of fun at school today." This allows the user to experience a conversation as if they were actually having a conversation with their grandchild. Furthermore, the system can recognize the user's voice and facial expressions and appropriately adjust the content of the conversation. For example, when the user speaks with a smile, the AI ​​also responds with a smile. This mechanism allows the elderly to feel connected to their grandchildren and reduce their feelings of loneliness. It is also expected that this will increase communication with family members and improve their mental health. This appliance allows the elderly to feel connected to their grandchildren and reduce their feelings of loneliness. It is also expected that this will increase communication with family members and improve their mental health.

[0087] An appliance according to an embodiment includes an input unit, a generation unit, a conversation unit, and a recognition unit. The input unit allows a user to input photos and videos. For example, the input unit can accept photos and videos in formats such as JPEG, PNG, and MP4. Furthermore, when a user inputs photos and videos by voice, the input unit can also use voice recognition technology to perform the input. The generation unit generates an AI based on the input photos and videos using Deep Fake technology. For example, the generation unit uses a deep learning algorithm to generate an AI that looks exactly like a grandchild from the input photos and videos. The generation unit can also generate an AI based on the input photos and videos using face swap technology. The conversation unit allows a user to converse with the generated AI. For example, the conversation unit recognizes the user's utterances using voice recognition technology and generates appropriate responses using natural language processing technology. The conversation unit can also adjust the fluency of the conversation and the appropriateness of the responses based on the user's utterances. The recognition unit recognizes the user's voice and facial expressions and adjusts the content of the conversation. For example, the recognition unit recognizes the user's voice using a voice recognition algorithm and recognizes the user's facial expressions using facial expression recognition technology. The recognition unit can also recognize user gestures using gesture recognition technology. As a result, the appliance according to the embodiment allows elderly people to have natural conversations with AI that looks just like their grandchild, thereby reducing feelings of loneliness and improving their mental health.

[0088] The generation unit can use image generation technology to generate AI based on input photos and videos. The generation unit can also use Deep Fake technology to generate AI based on input photos and videos. For example, the generation unit can use a deep learning algorithm to generate an AI that looks exactly like a grandchild from input photos and videos. The generation unit can also use face swapping technology to generate AI based on input photos and videos. In this way, Deep Fake technology can be used to generate more realistic AI.

[0089] The conversation unit allows the user to have a conversation with the generated AI. For example, the conversation unit uses voice recognition technology to recognize what the user says and natural language processing technology to generate an appropriate response. The conversation unit can also adjust the fluency of the conversation and the appropriateness of the response based on what the user says. This allows the user to have a natural conversation with the generated AI, giving them the experience of talking as if they were talking to their grandchild.

[0090] The recognition unit can recognize the user's voice and facial expressions and adjust the content of the conversation. The recognition unit, for example, recognizes the user's voice and facial expressions and adjusts the content of the conversation. For example, the recognition unit recognizes the user's voice using a voice recognition algorithm and recognizes the user's facial expressions using facial expression recognition technology. The recognition unit can also recognize the user's gestures using gesture recognition technology. This allows for more natural conversation by recognizing the user's voice and facial expressions.

[0091] The appliance includes a conversation adjustment unit that adjusts the content of the conversation so that the generated AI can have a natural conversation. The conversation adjustment unit, for example, adjusts the content of the conversation so that the generated AI can have a natural conversation. For example, the conversation adjustment unit changes responses and selects conversation topics based on the user's reactions. The conversation adjustment unit can also adjust the fluency of the conversation and the appropriateness of responses based on the user's utterances. In this way, adjusting the content of the conversation enables a more natural conversation.

[0092] The appliance includes a response adjustment unit that adjusts the content of the conversation according to the user's voice and facial expression. The response adjustment unit adjusts the content of the conversation according to, for example, the user's voice and facial expression. For example, the response adjustment unit changes the response based on the user's tone of voice and facial expression. The response adjustment unit can also adjust the fluency of the conversation and the appropriateness of the response based on the user's utterances. This allows for more appropriate responses by adjusting the content of the conversation according to the user's voice and facial expression.

[0093] The appliance includes a data protection unit that protects input photos and videos from leaking to the outside. The data protection unit protects, for example, input photos and videos from leaking to the outside. For example, the data protection unit protects data using encryption technology. The data protection unit can also perform access control to prevent unauthorized access to data. In this way, the data protection unit protects the privacy of users.

[0094] The appliance includes an input unit that estimates a user's emotion and adjusts the timing of photo and video input based on the estimated user emotion. The input unit, for example, estimates the user's emotion and adjusts the timing of photo and video input based on the estimated user emotion. For example, the input unit uses an emotion engine to detect when the user is sad and delays the timing of prompting the user to input photos and videos. The input unit can also use an emotion engine to detect when the user is excited and prompt the user to input photos and videos quickly. The input unit can also use an emotion engine to detect when the user is relaxed and prompt the user to input photos and videos at a natural timing. This allows the input timing to be adjusted according to the user's emotion, allowing the user to input photos and videos at a more appropriate timing.

[0095] The appliance includes an input unit that analyzes the user's past input history and selects the optimal input method. The input unit, for example, analyzes the user's past input history and selects the optimal input method. For example, the input unit preferentially suggests input methods (voice, text, etc.) that the user has frequently used in the past. The input unit can also analyze trends in photos and videos that the user has entered in the past and suggest the optimal input method. The input unit can also predict and suggest the input method that will be used during a specific time period based on the user's past input history. In this way, the optimal input method can be suggested to the user by analyzing the past input history.

[0096] The appliance includes an input unit that filters photos and videos based on the user's current living situation and areas of interest when the photos and videos are input. For example, the input unit filters photos and videos based on the user's current living situation and areas of interest when the photos and videos are input. For example, the input unit prioritizes input of photos and videos related to the user's current living situation. The input unit can also filter and input related photos and videos based on the user's areas of interest. The input unit can also analyze the user's living situation and areas of interest and suggest optimal photos and videos. As a result, filtering based on the user's living situation and areas of interest allows more relevant photos and videos to be input.

[0097] The appliance includes an input unit that selects the optimal input means depending on the user's input method when inputting photos or videos. For example, when inputting photos or videos, the input unit selects the optimal input means depending on the user's input method. For example, when the user inputs photos or videos by voice, the input unit performs input using voice recognition technology. Furthermore, when the user inputs photos or videos using text, the input unit can also perform input using text analysis technology. Furthermore, when the user inputs photos or videos using images, the input unit can also perform input using image recognition technology. This improves input efficiency by selecting the optimal input means depending on the user's input method.

[0098] The appliance includes an input unit that estimates a user's emotions and determines the priority of photos and videos to be input based on the estimated user emotions. The input unit, for example, estimates a user's emotions and determines the priority of photos and videos to be input based on the estimated user emotions. For example, the input unit uses an emotion engine to detect when the user is sad and prioritizes input of photos and videos of happy memories. The input unit can also detect when the user is excited and prioritize input of photos and videos with calm content. The input unit can also detect when the user is relaxed and prioritize input of photos and videos in a natural flow. In this way, by determining the priority of photos and videos according to the user's emotions, more appropriate data can be input preferentially.

[0099] The appliance includes an input unit that, when inputting photos or videos, prioritizes input of highly relevant data taking into account the user's geographical location information. For example, when inputting photos or videos, the input unit prioritizes input of highly relevant data taking into account the user's geographical location information. For example, the input unit prioritizes input of photos and videos related to the user's current location. The input unit can also filter and input related photos and videos based on the user's geographical location information. The input unit can also analyze the user's geographical location information and suggest optimal photos and videos. In this way, more relevant data can be prioritized by taking the user's geographical location information into account.

[0100] The appliance includes an input unit that analyzes a user's social media activity and inputs related data when a photo or video is input. For example, when a photo or video is input, the input unit analyzes the user's social media activity and inputs related data. For example, the input unit prioritizes input of photos and videos shared by the user on social media. The input unit can also analyze the user's social media activity and filter and input related photos and videos. The input unit can also suggest optimal photos and videos based on the user's social media activity. This allows for efficient input of related data by analyzing the user's social media activity.

[0101] The appliance includes an input unit that customizes an input method by reflecting a user's past feedback when inputting a photo or video. The input unit customizes the input method by reflecting a user's past feedback when inputting a photo or video, for example. For example, the input unit suggests an optimal input method based on feedback provided by the user in the past. The input unit can also analyze the user's past feedback and customize the input method. The input unit can also optimize the input procedure by reflecting the user's past feedback. In this way, the input method can be optimized by reflecting the user's past feedback.

[0102] The appliance includes a generation unit that estimates a user's emotions and adjusts the expression method of the generated AI based on the estimated user emotions. The generation unit, for example, estimates a user's emotions and adjusts the expression method of the generated AI based on the estimated user emotions. For example, the generation unit causes the generation AI to use a gentle expression method when the user is relaxed. Also, the generation unit can cause the generation AI to use a lively expression method when the user is excited. Also, the generation unit can cause the generation AI to use a gentle expression method when the user is sad. In this way, by adjusting the expression method of the AI ​​according to the user's emotions, more natural conversations are realized.

[0103] The appliance includes a generation unit that adjusts the level of detail of the generated AI based on the importance of the photos and videos when generating the AI. For example, the generation unit adjusts the level of detail of the generated AI based on the importance of the photos and videos when generating the AI. For example, the generation unit uses detailed representations for important photos and videos. The generation unit can also use simplified representations for photos and videos with low importance. The generation unit can also analyze the importance of photos and videos and adjust the level of detail of the generated AI. This allows for the generation of more appropriate AI by adjusting the level of detail of the generated AI based on the importance of the photos and videos.

[0104] The appliance includes a generation unit that applies different generation algorithms depending on the photo or video category when generating AI. For example, the generation unit applies different generation algorithms depending on the photo or video category when generating AI. For example, the generation unit uses a specific algorithm for family photos. The generation unit can also use a different algorithm for travel videos. The generation unit can also analyze the photo or video category and apply the optimal generation algorithm. This allows for the generation of more appropriate AI by applying the optimal generation algorithm depending on the photo or video category.

[0105] The appliance includes a generation unit that, when generating AI, improves the accuracy of generation by referring to the user's past generation results. For example, when generating AI, the generation unit improves the accuracy of generation by referring to the user's past generation results. For example, the generation unit analyzes the user's past generation results, and the generation AI improves accuracy. The generation unit can also select an optimal generation method based on the user's past generation results. The generation unit can also improve the accuracy of the generation AI by referring to the user's past generation results. In this way, the accuracy of generation can be improved by referring to the user's past generation results.

[0106] The appliance includes a generation unit that estimates a user's emotions and adjusts the length of the AI ​​to be generated based on the estimated user emotions. The generation unit, for example, estimates a user's emotions and adjusts the length of the AI ​​to be generated based on the estimated user emotions. For example, the generation unit generates a longer conversation when the user is relaxed. The generation unit can also generate a shorter conversation when the user is in a hurry. The generation unit can also generate a conversation of an appropriate length when the user is excited. In this way, by adjusting the length of the AI ​​according to the user's emotions, more appropriate conversations can be achieved.

[0107] The appliance includes a generation unit that determines the generation priority based on the time of submission of photos and videos during AI generation. For example, the generation unit determines the generation priority based on the time of submission of photos and videos during AI generation. For example, the generation unit prioritizes the generation of recently submitted photos and videos. The generation unit can also postpone the generation of photos and videos that were submitted earlier. The generation unit can also determine the generation priority taking the time of submission into consideration. In this way, by determining the generation priority based on the time of submission, the latest data can be generated preferentially.

[0108] The appliance includes a generation unit that adjusts the order of generation based on the relevance of photos and videos during AI generation. For example, the generation unit adjusts the order of generation based on the relevance of photos and videos during AI generation. For example, the generation unit prioritizes generating highly relevant photos and videos. The generation unit can also postpone generating less relevant photos and videos. The generation unit can also analyze the relevance of photos and videos and adjust the order of generation. In this way, by adjusting the order of generation based on relevance, more relevant data can be generated preferentially.

[0109] The appliance includes a generation unit that adjusts the use of technical terminology in the generated AI according to the user's level of expertise. For example, when generating the AI, the generation unit adjusts the use of technical terminology in the generated AI according to the user's level of expertise. For example, if the user has technical expertise, the generation unit uses a lot of technical terminology. Also, if the user does not have technical expertise, the generation unit can avoid technical terminology. The generation unit can also analyze the user's level of expertise and select the most appropriate terminology. In this way, by adjusting the use of technical terminology according to the user's level of expertise, more understandable conversations can be achieved.

[0110] The appliance includes a conversation unit that estimates a user's emotion and adjusts a conversation expression style based on the estimated user's emotion. The conversation unit, for example, estimates a user's emotion and adjusts a conversation expression style based on the estimated user's emotion. For example, the conversation unit uses a calm expression style when the user is relaxed. The conversation unit can also use a lively expression style when the user is excited. The conversation unit can also use a gentle expression style when the user is sad. In this way, by adjusting the conversation expression style according to the user's emotion, a more natural conversation is realized.

[0111] The appliance includes a conversation unit that adjusts the level of detail of a conversation based on the importance of the AI ​​during the conversation. For example, the conversation unit adjusts the level of detail of a conversation based on the importance of the AI ​​during the conversation. For example, the conversation unit provides a detailed explanation for an important conversation. The conversation unit can also provide a simplified explanation for a conversation with a low importance. The conversation unit can also analyze the importance of the conversation and adjust the level of detail of the conversation. As a result, by adjusting the level of detail based on the importance of the conversation, more appropriate conversations can be achieved.

[0112] The appliance includes a conversation unit that applies different conversation algorithms depending on the AI ​​category during a conversation. The conversation unit applies different conversation algorithms depending on the AI ​​category during a conversation, for example. For example, the conversation unit uses a specific algorithm when talking with family. The conversation unit can also use a different algorithm when talking with friends. The conversation unit can also analyze the category of the conversation and apply the most appropriate conversation algorithm. In this way, more appropriate conversations can be achieved by applying the most appropriate conversation algorithm depending on the category of the conversation.

[0113] The appliance includes a conversation unit that, during a conversation, improves the accuracy of the conversation by referring to the user's past conversation results. For example, the conversation unit improves the accuracy of the conversation by referring to the user's past conversation results. For example, the conversation unit analyzes the user's past conversation results, and the conversation AI improves the accuracy. The conversation unit can also select an optimal conversation method based on the user's past conversation results. The conversation unit can also improve the accuracy of the conversation by referring to the user's past conversation results. In this way, the accuracy of the conversation can be improved by referring to the user's past conversation results.

[0114] The appliance includes a conversation unit that estimates a user's emotion and adjusts the length of a conversation based on the estimated user's emotion. The conversation unit, for example, estimates a user's emotion and adjusts the length of a conversation based on the estimated user's emotion. For example, the conversation unit provides a longer conversation when the user is relaxed. The conversation unit can also provide a shorter conversation when the user is in a hurry. The conversation unit can also provide a conversation of an appropriate length when the user is excited. In this way, a more appropriate conversation can be achieved by adjusting the length of the conversation according to the user's emotion.

[0115] The appliance includes a conversation unit that, during a conversation, determines the priority of the conversation based on the time of submission by the AI. For example, during a conversation, the conversation unit determines the priority of the conversation based on the time of submission by the AI. For example, the conversation unit prioritizes processing of recently submitted conversation content. The conversation unit can also postpone conversation content that was submitted earlier. The conversation unit can also determine the priority of the conversation taking the time of submission into consideration. In this way, by determining the priority of the conversation based on the time of submission, the most recent conversation content can be processed preferentially.

[0116] The appliance includes a conversation unit that adjusts the order of conversations based on the relevance of the AI ​​during a conversation. The conversation unit, for example, adjusts the order of conversations based on the relevance of the AI ​​during a conversation. For example, the conversation unit prioritizes processing of highly relevant conversation content. The conversation unit can also postpone conversation content with low relevance. The conversation unit can also analyze the relevance of the conversation content and adjust the order of conversations. In this way, by adjusting the order of conversations based on relevance, more relevant conversations can be prioritized for processing.

[0117] The appliance includes a conversation unit that adjusts the use of technical terms in a conversation according to the user's level of expertise. The conversation unit, for example, adjusts the use of technical terms in a conversation according to the user's level of expertise. For example, if the user has technical expertise, the conversation unit uses a lot of technical terms. Also, if the user does not have technical expertise, the conversation unit can avoid technical terms. The conversation unit can also analyze the user's level of expertise and select optimal terms. In this way, by adjusting the use of technical terms according to the user's level of expertise, a conversation that is easier to understand is realized.

[0118] The appliance includes a recognition unit that estimates a user's emotion and adjusts the accuracy of recognition based on the estimated user's emotion. The recognition unit, for example, estimates a user's emotion and adjusts the accuracy of recognition based on the estimated user's emotion. For example, the recognition unit uses a recognition AI to increase accuracy when the user is relaxed. The recognition unit can also perform rapid recognition when the user is excited. The recognition unit can also use a gentle recognition method when the user is sad. This allows for more accurate recognition by adjusting the accuracy of recognition according to the user's emotion.

[0119] The appliance includes a recognition unit that optimizes a recognition algorithm by referring to the user's past voice and facial expression data during recognition. The recognition unit, for example, optimizes the recognition algorithm by referring to the user's past voice and facial expression data during recognition. For example, the recognition unit selects an optimal algorithm based on the user's past voice data. The recognition unit can also improve accuracy based on the user's past facial expression data. The recognition unit can also optimize the recognition algorithm by referring to the user's past voice and facial expression data. In this way, by referring to the past voice and facial expression data, the recognition algorithm can be optimized and recognition accuracy can be improved.

[0120] The appliance includes a recognition unit that performs recognition taking into account user attribute information. For example, the recognition unit performs recognition taking into account user attribute information. For example, the recognition unit selects the optimal recognition method taking into account the user's age and gender. The recognition unit can also improve accuracy based on the user attribute information. The recognition unit can also analyze the user attribute information and suggest the optimal recognition method. This allows for more accurate recognition by taking into account the user attribute information.

[0121] The appliance includes a recognition unit that weights recognition based on the frequency of user submissions during recognition. The recognition unit, for example, weights recognition based on the frequency of user submissions during recognition. For example, the recognition unit prioritizes recognition of data of users with high submission frequencies. The recognition unit can also postpone recognition of data of users with low submission frequencies. The recognition unit can also weight recognition taking into account submission frequency. In this way, by weighting recognition based on submission frequency, more important data can be prioritized for recognition.

[0122] The appliance includes a recognition unit that estimates a user's emotion and adjusts the order in which the recognition results are displayed based on the estimated user's emotion. The recognition unit, for example, estimates a user's emotion and adjusts the order in which the recognition results are displayed based on the estimated user's emotion. For example, the recognition unit displays the recognition results in detail when the user is relaxed. The recognition unit can also display the recognition results briefly when the user is in a hurry. The recognition unit can also display the recognition results appropriately when the user is excited. In this way, by adjusting the display order of the recognition results according to the user's emotion, more appropriate information can be provided.

[0123] The appliance includes a recognition unit that performs recognition taking into account the geographical distribution of users. For example, the recognition unit performs recognition taking into account the geographical distribution of users. For example, the recognition unit selects an optimal recognition method based on the geographical distribution of users. The recognition unit can also analyze the geographical distribution of users to improve accuracy. The recognition unit can also perform recognition taking into account the geographical distribution of users. This allows for more accurate recognition by taking into account the geographical distribution of users.

[0124] The appliance includes a recognition unit that improves the accuracy of recognition by referring to the user's related literature during recognition. The recognition unit, for example, improves the accuracy of recognition by referring to the user's related literature during recognition. For example, the recognition unit selects an optimal recognition method based on the user's related literature. The recognition unit can also analyze the user's related literature to improve accuracy. The recognition unit can also improve the accuracy of recognition by referring to the user's related literature. In this way, the accuracy of recognition can be improved by referring to the related literature.

[0125] The appliance includes a recognition unit that performs recognition taking into account the market value of the user. For example, the recognition unit performs recognition taking into account the market value of the user. For example, the recognition unit selects an optimal recognition method based on the market value of the user. The recognition unit can also analyze the market value of the user and improve accuracy. The recognition unit can also perform recognition taking into account the market value of the user. This allows for more appropriate recognition by taking into account the market value of the user.

[0126] The appliance includes a conversation adjustment unit that estimates a user's emotion and determines a conversation adjustment method based on the estimated user's emotion. The conversation adjustment unit, for example, estimates a user's emotion and determines a conversation adjustment method based on the estimated user's emotion. For example, the conversation adjustment unit uses a gentle adjustment method when the user is relaxed. Also, the conversation adjustment unit can use a vigorous adjustment method when the user is excited. Also, the conversation adjustment unit can use a gentle adjustment method when the user is sad. In this way, by determining a conversation adjustment method according to the user's emotion, a more appropriate conversation is realized.

[0127] The appliance includes a conversation adjustment unit that, during conversation adjustment, optimizes the current conversation by referring to past conversation data. The conversation adjustment unit, for example, optimizes the current conversation by referring to past conversation data during conversation adjustment. For example, the conversation adjustment unit selects an optimal adjustment method based on the user's past conversation data. The conversation adjustment unit can also analyze the user's past conversation data to improve accuracy. The conversation adjustment unit can also optimize the current conversation by referring to the user's past conversation data. In this way, by referring to the past conversation data, the current conversation can be optimized and accuracy can be improved.

[0128] The appliance includes a conversation adjustment unit that applies different adjustment methods to each AI category when adjusting a conversation. The conversation adjustment unit applies different adjustment methods to each AI category when adjusting a conversation. For example, the conversation adjustment unit uses a specific adjustment method when talking with family. The conversation adjustment unit can also use a different adjustment method when talking with friends. The conversation adjustment unit can also analyze the category of the conversation and apply the optimal adjustment method. In this way, by applying different adjustment methods to each AI category, more appropriate conversations can be achieved.

[0129] The appliance includes a conversation adjustment unit that, when adjusting a conversation, takes into account the attribute information of the person submitting the AI. The conversation adjustment unit, for example, when adjusting a conversation, takes into account the attribute information of the person submitting the AI. For example, the conversation adjustment unit selects the optimal adjustment method by taking into account the age and gender of the person submitting the conversation. The conversation adjustment unit can also improve accuracy based on the attribute information of the person submitting the conversation. The conversation adjustment unit can also analyze the attribute information of the person submitting the conversation and propose the optimal adjustment method. This enables more appropriate conversation adjustment by taking into account the attribute information of the person submitting the conversation.

[0130] The appliance includes a conversation adjustment unit that estimates a user's emotions and adjusts the importance of a conversation based on the estimated user's emotions. The conversation adjustment unit, for example, estimates a user's emotions and adjusts the importance of a conversation based on the estimated user's emotions. For example, the conversation adjustment unit provides a conversation with a high level of importance when the user is relaxed. The conversation adjustment unit can also provide a conversation with a low level of importance when the user is in a hurry. The conversation adjustment unit can also provide a conversation with an appropriate level of importance when the user is excited. In this way, by adjusting the importance of a conversation according to the user's emotions, a more appropriate conversation can be realized.

[0131] The appliance includes a conversation adjustment unit that analyzes conversation changes based on the time of submission of the AI ​​during conversation adjustment. The conversation adjustment unit, for example, analyzes conversation changes based on the time of submission of the AI ​​during conversation adjustment. For example, the conversation adjustment unit prioritizes analysis of recently submitted conversation content. The conversation adjustment unit can also postpone conversation content that was submitted earlier. The conversation adjustment unit can also analyze conversation changes taking the time of submission into consideration. In this way, more appropriate conversations can be achieved by analyzing conversation changes based on the time of submission.

[0132] The appliance includes a conversation adjustment unit that adjusts the conversation by referring to market data related to the AI ​​when adjusting the conversation. The conversation adjustment unit, for example, adjusts the conversation by referring to market data related to the AI ​​when adjusting the conversation. For example, the conversation adjustment unit selects an optimal adjustment method based on the market data. The conversation adjustment unit can also analyze the market data and improve accuracy. The conversation adjustment unit can also adjust the conversation by referring to the market data. In this way, by referring to the related market data, the accuracy of the conversation can be improved.

[0133] The appliance includes a conversation adjustment unit that adjusts the conversation taking into account the technological maturity of the AI ​​when adjusting the conversation. The conversation adjustment unit adjusts the conversation taking into account the technological maturity of the AI ​​when adjusting the conversation. For example, the conversation adjustment unit performs detailed adjustment when the technological maturity is high. The conversation adjustment unit can also perform simplified adjustment when the technological maturity is low. The conversation adjustment unit can also select the optimal adjustment method taking into account the technological maturity. This makes it possible to perform more appropriate conversation adjustment by taking into account the technological maturity.

[0134] The appliance includes a response adjuster that estimates a user's emotion and determines the priority of responses based on the estimated user's emotion. The response adjuster, for example, estimates the user's emotion and determines the priority of responses based on the estimated user's emotion. For example, the response adjuster provides a response with a high level of importance when the user is relaxed. The response adjuster can also provide a response with a low level of importance when the user is in a hurry. The response adjuster can also provide a response with a moderate level of importance when the user is excited. This enables a more appropriate response by determining the priority of responses according to the user's emotion.

[0135] The appliance includes a response adjustment unit that improves the accuracy of responses by taking into account the interrelationships between AIs when adjusting a response. The response adjustment unit improves the accuracy of responses by taking into account the interrelationships between AIs when adjusting a response, for example. For example, the response adjustment unit analyzes the interrelationships with other AIs and provides an optimal response. The response adjustment unit can also improve accuracy by referring to the responses of other AIs. The response adjustment unit can also improve the accuracy of responses by taking into account the interrelationships. In this way, the accuracy of responses can be improved by taking into account the interrelationships between AIs.

[0136] The appliance includes a response adjustment unit that, when adjusting a response, takes into account the attribute information of the AI ​​submitter. For example, when adjusting a response, the response adjustment unit takes into account the attribute information of the AI ​​submitter. For example, the response adjustment unit selects the optimal response method by taking into account the submitter's age and gender. The response adjustment unit can also improve accuracy based on the submitter's attribute information. The response adjustment unit can also analyze the submitter's attribute information and propose the optimal response method. This enables a more appropriate response by taking into account the submitter's attribute information.

[0137] The appliance includes a response adjustment unit that weights responses based on the frequency of submission by the AI ​​during response adjustment. The response adjustment unit, for example, weights responses based on the frequency of submission by the AI ​​during response adjustment. For example, the response adjustment unit prioritizes responses to data from users with a high submission frequency. The response adjustment unit can also postpone data from users with a low submission frequency. The response adjustment unit can also weight responses taking into account the frequency of submission. In this way, by weighting responses based on the frequency of submission, more important data can be prioritized in responses.

[0138] The appliance includes a response adjustment unit that estimates a user's emotion and adjusts a response display method based on the estimated user's emotion. The response adjustment unit, for example, estimates a user's emotion and adjusts a response display method based on the estimated user's emotion. For example, the response adjustment unit provides a detailed display method when the user is relaxed. The response adjustment unit can also provide a concise display method when the user is in a hurry. The response adjustment unit can also provide a moderate display method when the user is excited. In this way, by adjusting the response display method according to the user's emotion, more appropriate information can be provided.

[0139] The appliance includes a response adjustment unit that, when adjusting a response, takes into account the geographical distribution of the AI. For example, when adjusting a response, the response adjustment unit takes into account the geographical distribution of the AI. For example, the response adjustment unit selects an optimal response method based on the geographical distribution of users. The response adjustment unit can also analyze the geographical distribution of users to improve accuracy. The response adjustment unit can also take into account the geographical distribution of users when making a response. This allows for a more appropriate response by taking into account the geographical distribution.

[0140] The appliance includes a response adjustment unit that, when adjusting a response, refers to literature related to the AI ​​to improve the accuracy of the response. The response adjustment unit, for example, when adjusting a response, refers to literature related to the AI ​​to improve the accuracy of the response. For example, the response adjustment unit selects an optimal response method based on literature related to the user. The response adjustment unit can also analyze literature related to the user to improve accuracy. The response adjustment unit can also improve the accuracy of the response by referring to literature related to the user. In this way, the accuracy of the response can be improved by referring to related literature.

[0141] The appliance includes a response adjustment unit that, when adjusting a response, takes into account the market value of the AI ​​to make a response. For example, when adjusting a response, the response adjustment unit takes into account the market value of the AI ​​to make a response. For example, the response adjustment unit selects the optimal response method based on the market value of the user. The response adjustment unit can also analyze the market value of the user and improve accuracy. The response adjustment unit can also make a response taking into account the market value of the user. In this way, by taking market value into account, a more appropriate response is possible.

[0142] The appliance includes a data protection unit that estimates a user's emotion and adjusts a data protection method based on the estimated user's emotion. The data protection unit, for example, estimates a user's emotion and adjusts a data protection method based on the estimated user's emotion. For example, the data protection unit uses a standard protection method when the user is relaxed. Furthermore, the data protection unit can use an enhanced protection method when the user is nervous. Furthermore, the data protection unit can use a moderate protection method when the user is excited. In this way, by adjusting the data protection method according to the user's emotion, more appropriate data protection is possible.

[0143] The appliance includes a data protection unit that, when protecting data, refers to past data protection history to select an optimal protection method. For example, when protecting data, the data protection unit refers to past data protection history to select an optimal protection method. For example, the data protection unit selects an optimal protection method based on past data protection history. The data protection unit can also analyze past data protection history to improve accuracy. The data protection unit can also select an optimal protection method by referring to past data protection history. In this way, by referring to past data protection history, an optimal protection method can be selected and accuracy can be improved.

[0144] The appliance includes a data protection unit that takes user attribute information into consideration when protecting data. For example, the data protection unit takes user attribute information into consideration when protecting data. For example, the data protection unit selects the optimal protection method by taking the user's age and gender into consideration. The data protection unit can also improve accuracy based on the user's attribute information. The data protection unit can also analyze the user's attribute information and propose the optimal protection method. This makes it possible to provide more appropriate data protection by taking user attribute information into consideration.

[0145] The appliance includes a data protection unit that adjusts the level of detail of protection based on the importance of the data when protecting the data. For example, the data protection unit adjusts the level of detail of protection based on the importance of the data when protecting the data. For example, the data protection unit uses a detailed protection method for important data. The data protection unit can also use a simplified protection method for data with low importance. The data protection unit can also analyze the importance of the data and adjust the level of detail of protection. In this way, adjusting the level of detail of protection based on the importance of the data enables more appropriate data protection.

[0146] The appliance includes a data protection unit that estimates a user's emotions and determines the priority of data protection based on the estimated user emotions. The data protection unit, for example, estimates a user's emotions and determines the priority of data protection based on the estimated user emotions. For example, when the user is relaxed, the data protection unit prioritizes protection of highly important data. Furthermore, when the user is in a hurry, the data protection unit can also prioritize protection of less important data. Furthermore, when the user is excited, the data protection unit can protect data with a moderate priority. In this way, by determining the priority of data protection according to the user's emotions, more appropriate data protection is possible.

[0147] The appliance includes a data protection unit that takes into account the geographic distribution of data when protecting the data. For example, the data protection unit selects the optimal protection method based on the geographic distribution of the data. The data protection unit can also analyze the geographic distribution of the data to improve accuracy. The data protection unit can also protect the data by taking into account the geographic distribution of the data. This makes it possible to provide more appropriate data protection by taking into account the geographic distribution of the data.

[0148] The appliance includes a data protection unit that improves the accuracy of protection by referring to relevant laws and regulations when protecting data. The data protection unit, for example, improves the accuracy of protection by referring to relevant laws and regulations when protecting data. For example, the data protection unit selects an optimal protection method based on relevant laws and regulations. The data protection unit can also analyze relevant laws and regulations and improve the accuracy. The data protection unit can also improve the accuracy of protection by referring to relevant laws and regulations. In this way, the accuracy of data protection can be improved by referring to relevant laws and regulations.

[0149] The appliance includes a data protection unit that takes into account the market value of the data when protecting the data. For example, the data protection unit selects the optimal protection method based on the market value of the data. The data protection unit can also analyze the market value of the data and improve accuracy. The data protection unit can also protect the data by taking into account the market value of the data. This enables more appropriate data protection by taking into account the market value of the data. === Hard Collateral 1-1 === Each of the multiple elements including the input unit, generation unit, conversation unit, and recognition unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the input unit can input photos and videos using the reception device 38 or camera 42 of the smart device 14. The generation unit generates AI using Deep Fake technology by the specific processing unit 290 of the data processing device 12. The conversation unit realizes a conversation between the user and the AI ​​by the control unit 46A of the smart device 14. The recognition unit recognizes the user's voice and facial expression using the microphone 38B or camera 42 of the smart device 14, and adjusts the content of the conversation by the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned input unit, generation unit, conversation unit, and recognition unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the input unit can input photos and videos using the microphone 238 and camera 42 of the smart glasses 214. The generation unit generates AI using Deep Fake technology by the specific processing unit 290 of the data processing device 12. The conversation unit realizes a conversation between the user and the AI ​​by the control unit 46A of the smart glasses 214. The recognition unit recognizes the user's voice and facial expression using the microphone 238 and camera 42 of the smart glasses 214, and adjusts the content of the conversation by the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned input unit, generation unit, conversation unit, and recognition unit is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the input unit can input photos and videos using the microphone 238 or camera 42 of the headset-type terminal 314. The generation unit generates AI using Deep Fake technology by the specific processing unit 290 of the data processing device 12. The conversation unit realizes a conversation between the user and the AI ​​by the control unit 46A of the headset-type terminal 314. The recognition unit recognizes the user's voice and facial expression using the microphone 238 or camera 42 of the headset-type terminal 314, and adjusts the content of the conversation by the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned input unit, generation unit, conversation unit, and recognition unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the input unit can input photos and videos using the microphone 238 and camera 42 of the robot 414. The generation unit generates AI using Deep Fake technology by the specific processing unit 290 of the data processing device 12. The conversation unit realizes a conversation between the user and the AI ​​by the control unit 46A of the robot 414. The recognition unit recognizes the user's voice and facial expressions using the microphone 238 and camera 42 of the robot 414, and adjusts the content of the conversation by the specific processing unit 290 of the data processing device 12.

[0150] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0151] The appliance may also include a health monitoring unit that monitors the user's health status and adjusts the conversation content based on the user's health status. For example, the health monitoring unit may measure the user's heart rate and blood pressure, and if the user's health status is poor, provide topics that will help them relax. If the user is feeling stressed, the health monitoring unit may also provide advice to help reduce stress. Furthermore, the health monitoring unit may suggest appropriate exercise and dietary recommendations based on the user's health status. This allows for a more personalized experience by providing conversation content that is tailored to the user's health status.

[0152] The appliance may also include a hobby and interest analysis unit that selects conversation topics based on the user's hobbies and interests. For example, the hobby and interest analysis unit may analyze data previously entered by the user and conversation history to identify topics that interest the user. The hobby and interest analysis unit may also provide related conversation content based on topics in which the user has recently shown interest. Furthermore, the hobby and interest analysis unit may suggest new topics based on the user's hobbies and interests. This allows for more interesting conversations by providing conversation content that matches the user's hobbies and interests.

[0153] The appliance may also include a conversation prediction unit that analyzes the user's past conversation history and predicts the flow of the conversation. For example, the conversation prediction unit may analyze the user's past conversation patterns and predict the next topic to talk about. The conversation prediction unit may also generate an appropriate response based on the user's utterances. Furthermore, the conversation prediction unit may make suggestions to smooth the flow of the conversation based on the user's past conversation history. In this way, by utilizing the user's past conversation history, a more natural conversation can be realized.

[0154] The appliance may also include a tone adjustment unit that estimates the user's emotions and adjusts the tone of the conversation based on the estimated emotions. For example, the tone adjustment unit may use a gentle tone when the user is sad. The tone adjustment unit may also use a lively tone when the user is excited. Furthermore, the tone adjustment unit may use a gentle tone when the user is relaxed. In this way, a more empathetic conversation can be achieved by using a tone that corresponds to the user's emotions.

[0155] The appliance may also include a lifestyle rhythm adjustment unit that adjusts the timing of conversations based on the user's lifestyle rhythm. For example, if the user prefers lively conversations in the morning, the lifestyle rhythm adjustment unit may provide conversation content suitable for the morning. Alternatively, if the user prefers relaxed conversations in the evening, the lifestyle rhythm adjustment unit may provide conversation content suitable for the evening. Furthermore, the lifestyle rhythm adjustment unit may adjust the frequency and length of conversations based on the user's lifestyle rhythm. This allows for more comfortable conversations by providing conversation timings that match the user's lifestyle rhythm.

[0156] The appliance may also include a content personalization unit that estimates the user's emotions and personalizes the content of the conversation based on the estimated emotions. For example, if the user is sad, the content personalization unit may provide encouraging words or fun topics. If the user is excited, the content personalization unit may also provide interesting information or news. Furthermore, if the user is relaxed, the content personalization unit may provide relaxing topics or advice. In this way, personalized conversation content according to the user's emotions is provided, thereby realizing more appropriate conversation.

[0157] The appliance may also include a behavior analysis unit that analyzes the user's past behavioral data and suggests conversation content based on the behavioral patterns. For example, the behavior analysis unit may analyze the user's frequent past behaviors and provide related conversation content. The behavior analysis unit may also suggest new behaviors based on the user's behavioral patterns. Furthermore, the behavior analysis unit may also provide advice or suggestions for behavioral improvements based on the user's behavioral data. This allows for more practical conversations by providing conversation content that matches the user's behavioral patterns.

[0158] The appliance may also include a speed adjustment unit that estimates the user's emotions and adjusts the speed of the conversation based on the estimated emotions. For example, the speed adjustment unit may conduct the conversation at a slow speed when the user is relaxed. Alternatively, the speed adjustment unit may conduct the conversation at a fast speed when the user is in a hurry. Furthermore, the speed adjustment unit may conduct the conversation at a moderate speed when the user is excited. This allows for a more comfortable conversation by conducting the conversation at a speed that corresponds to the user's emotions.

[0159] The appliance may also include a location information adjustment unit that utilizes the user's geographic location information to adjust the content of the conversation based on the location information. For example, if the user is traveling, the location information adjustment unit may provide information and advice related to the user's travel destination. Alternatively, if the user is at home, the location information adjustment unit may provide local news and event information. Furthermore, the location information adjustment unit may suggest optimal conversation content based on the user's location information. This allows for more relevant conversations by providing conversation content tailored to the user's geographic location information.

[0160] The appliance may also include an end timing adjustment unit that estimates the user's emotions and adjusts the timing to end the conversation based on the estimated emotions. For example, the end timing adjustment unit may continue the conversation for a longer period of time if the user is relaxed. The end timing adjustment unit may also end the conversation earlier if the user is in a hurry. Furthermore, the end timing adjustment unit may end the conversation at an appropriate time if the user is excited. This allows for a more appropriate conversation by providing an end timing for the conversation that corresponds to the user's emotions.

[0161] The processing flow of the second embodiment will be briefly explained below.

[0162] Step 1: The input unit receives a photo or video from the user. For example, the input unit can accept photos or videos in formats such as JPEG, PNG, and MP4. The input unit can also use voice recognition technology to input photos or videos using voice commands. Step 2: The generator uses Deep Fake technology to generate an AI based on the input photos and videos. For example, the generator uses a deep learning algorithm to generate an AI that looks exactly like your grandchild from the input photos and videos. The generator can also use face swapping technology to generate an AI based on the input photos and videos. Step 3: The conversation unit allows the user to converse with the generated AI. For example, the conversation unit uses voice recognition technology to recognize what the user says and natural language processing technology to generate an appropriate response. The conversation unit can also adjust the fluency of the conversation and the appropriateness of the response based on what the user says. Step 4: The recognition unit recognizes the user's voice and facial expressions and adjusts the content of the conversation. For example, the recognition unit may recognize the user's voice using a voice recognition algorithm and the user's facial expressions using facial expression recognition technology. The recognition unit may also recognize the user's gestures using gesture recognition technology.

[0163] 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.

[0164] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0165] 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.

[0166] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0167] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0168] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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).

[0173] 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.

[0174] 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.

[0175] 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.

[0176] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0177] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0178] 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.

[0179] 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.

[0180] 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 AI 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.

[0181] 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.

[0182] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0183] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0184] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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).

[0189] 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.

[0190] 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.

[0191] 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.

[0192] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0193] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0194] 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.

[0195] 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.

[0196] 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 AI 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.

[0197] 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.

[0198] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0199] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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).

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0210] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0211] 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.

[0212] 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.

[0213] 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 AI 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.

[0214] 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.

[0215] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0216] 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.

[0217] 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.

[0218] 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.

[0219] 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).

[0220] 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 "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0221] 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."

[0222] 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.

[0223] 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.

[0224] 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.

[0225] 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.

[0226] 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.

[0227] 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.

[0228] 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.

[0229] 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.

[0230] 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.

[0231] 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.

[0232] 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.

[0233] 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.

[0234] [Explanation of symbols]

[0235] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A system comprising an input unit through which a user inputs photos and videos, a generation unit that generates AI using image generation technology based on the photos and videos input by the input unit, a conversation unit through which the user converses with the AI ​​generated by the generation unit, and a recognition unit that recognizes the user's voice and facial expressions.

2. The system according to claim 1, wherein the generation unit uses image generation technology to generate AI based on input photos and videos.

3. The system according to claim 1 , wherein the conversation unit allows the user to converse with the generated AI.

4. The system according to claim 1 , wherein the recognition unit recognizes the user's voice and facial expressions and adjusts the content of the conversation.

5. The system is equipped with a conversation adjustment unit that adjusts the content of the conversation so that the generated AI can have a natural conversation.

2. The system of claim 1.

6. Equipped with a response adjustment unit that adjusts the content of conversation according to the user's voice and facial expressions 2. The system of claim 1.

7. Equipped with a data protection unit that protects input photos and videos from leaking to the outside 2. The system of claim 1.

8. The input unit Estimates the user's emotions and adjusts the timing of photo and video input based on the estimated user emotions.

2. The system of claim 1.

9. The input unit Analyze the user's past input history and select the optimal input method 2. The system of claim 1.

Images