system

Abstract

The system according to this embodiment aims to generate a 3D avatar and utilize it as an AI conversational assistant through AR glasses. [Solution] The system according to the embodiment comprises a generation unit, a storage unit, a dialogue unit, and a display unit. The generation unit generates a 3D avatar. The storage unit saves and outputs the 3D avatar generated by the generation unit. The dialogue unit performs an AI dialogue assistant using the 3D avatar saved by the storage unit. The display unit displays the AI ​​dialogue assistant performed by the dialogue unit through AR glasses.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, the generation and utilization of 3D avatars are limited, and there is room for improvement particularly in realizing an AI dialogue assistant using AR glasses.

[0005] The system according to the embodiment aims to generate a 3D avatar and utilize it as an AI dialogue assistant through AR glasses.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a generation unit, a storage unit, a dialogue unit, and a display unit. The generation unit generates a 3D avatar. The storage unit saves and outputs the 3D avatar generated by the generation unit. The dialogue unit performs AI dialogue assistance using the 3D avatar saved by the storage unit. The display unit displays the AI ​​dialogue assistance performed by the dialogue unit through AR glasses. [Effects of the Invention]

[0007] The system according to this embodiment can generate a 3D avatar and utilize it as an AI conversational assistant through AR glasses. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

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

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are 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 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction 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 a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The system according to an embodiment of the present invention is a system that utilizes a smartphone's generation AI to create a 3D model of a user's own avatar usable in various metaverses. This system allows users to generate 3D avatars in various styles, such as photorealistic or moe-style, using a smartphone app. By combining the generation AI with existing avatar generation algorithms, higher quality avatars can be created. Furthermore, the generation AI can be used to generate an unlimited number of items, including clothing, accessories, shoes, and other accessories. The created 3D avatars are saved and output in major formats such as VRM, and can be used in various metaverses and online meeting tools. Next, the created 3D avatars can also be used as AI conversational assistants. Users can use the 3D avatar as an AI conversational assistant with functions such as everyday conversation, consultation, news delivery, ordering, schedule management, and translation. Additionally, an assistant app for AR glasses has been developed simultaneously, allowing the 3D avatar AI conversational assistant to be displayed through AR glasses. This is available to the user themselves or authorized individuals, and when multiple people use the same app, the avatar is overlaid on the user's avatar as seen by others, and their full-body movements are synchronized. A key feature of this technology is its ability to create unique avatars by utilizing generative AI. By adding generative AI to existing avatar generation technologies, it becomes an even more powerful system. Furthermore, it can generate an infinite number of patterns for items such as clothing and accessories, and the resulting avatars can track not only the entire body but also facial expressions and hand movements. This allows users to have a more realistic experience. The system enables users to generate and save high-quality 3D avatars using their smartphones and utilize them as AI conversational assistants. It is also possible to display 3D avatars using AR glasses, allowing users to control the avatars in real time and interact with others.

[0029] The avatar generation system according to the embodiment comprises a generation unit, a storage unit, a dialogue unit, and a display unit. The generation unit generates 3D avatars. The generation unit generates 3D avatars in various styles, such as photorealistic and moe-style. The generation unit uses a generation AI to receive user photos and videos as input and generates 3D avatars based on them. For example, the generation AI analyzes the features of the user's face and generates a realistic 3D model. The generation unit can also use the generation AI to generate an unlimited number of items such as clothes, accessories, shoes, and other items. For example, the generation AI generates clothes and accessories in various designs based on the user's preferences and trends. The storage unit saves and outputs the 3D avatars generated by the generation unit. The storage unit saves the 3D avatars in major formats such as VRM. The storage unit saves the generated 3D avatars to cloud storage so that the user can access them at any time. The storage unit can also save the generated 3D avatars to a local device. The dialogue unit uses the 3D avatars saved by the storage unit to perform AI dialogue assistance. The dialogue unit acts as an AI conversational assistant with functions such as everyday conversation, consultation, news delivery, ordering, schedule management, and translation. The dialogue unit uses a generative AI to generate appropriate responses in response to user input. For example, the dialogue unit generates an appropriate answer to a user's question using the generative AI and displays it through a 3D avatar. The display unit displays the AI ​​conversational assistant performed by the dialogue unit through AR glasses. For example, the display unit displays the 3D avatar AI conversational assistant using AR glasses. The display unit overlays the 3D avatar onto the user's field of view, allowing for real-time interaction. If multiple people are using the same app, the display unit can also overlay the avatar on themselves as seen by others and synchronize their full-body movements. As a result, the avatar generation system according to this embodiment allows users to generate and save high-quality 3D avatars using their smartphones and utilize them as an AI conversational assistant. It is also possible to display the 3D avatar using AR glasses, allowing users to manipulate the avatar in real time and interact with others.

[0030] The generation unit can generate 3D avatars in multiple styles, including photorealistic and moe-style. For example, the generation unit can generate photorealistic 3D avatars. Photorealistic 3D avatars reproduce the user's facial features in detail and have a realistic appearance. The generation unit uses a generation AI to analyze the user's photograph and generate a realistic 3D model. For example, the generation AI analyzes the user's facial contours and skin texture to generate a photorealistic 3D avatar. The generation unit can also generate moe-style 3D avatars. Moe-style 3D avatars have an anime-like design and emphasize the character's features. The generation unit uses a generation AI to generate moe-style 3D avatars according to the user's preferences. For example, the generation AI learns the user's preferred character designs and generates moe-style 3D avatars based on that. This allows the generation unit to generate a variety of 3D avatar styles. Some or all of the above-described processes in the generation unit are performed using a generation AI. For example, the generation unit inputs a user's photo into the generation AI and generates a photorealistic or moe-style 3D avatar. The generation AI analyzes the user's photo and generates a realistic 3D model. The generation AI learns the user's preferred character design and generates a moe-style 3D avatar based on that. In this way, the generation unit can generate a variety of 3D avatar styles according to the user's preferences.

[0031] The generation unit can generate multiple items such as clothing, accessories, shoes, and other items. For example, the generation unit can generate clothing. Using a generation AI, the generation unit generates clothing in various designs based on the user's preferences and trends. For example, the generation AI can generate casual or formal style clothing. The generation unit can also generate accessories. Using a generation AI, the generation unit generates accessories such as hats and bags. For example, the generation AI generates hats and bags with designs that suit the user's preferences. Furthermore, the generation unit can also generate shoes. Using a generation AI, the generation unit generates shoes such as sneakers and boots. For example, the generation AI generates sneakers and boots with designs that suit the user's preferences. The generation unit can also generate accessories. Using a generation AI, the generation unit generates accessories such as necklaces and earrings. For example, the generation AI generates necklaces and earrings with designs that suit the user's preferences. As a result, the generation unit can generate an infinite number of items. Some or all of the above-described processes in the generation unit are performed using a generation AI. For example, the generation unit instructs the generation AI to create clothing, accessories, shoes, and other items based on the user's preferences and trends. The generation AI learns the user's preferences and trends and generates items of various designs based on them. This allows the generation unit to generate an infinite number of items tailored to the user's preferences.

[0032] The storage unit can save and output 3D avatars in the major VRM format. For example, the storage unit saves 3D avatars in the VRM format. The VRM format is a standard format for efficiently saving 3D avatar data and is widely used in various metaverses and online meeting tools. The storage unit saves the generated 3D avatar in the VRM format, making it accessible to the user at any time. The storage unit can also save the generated 3D avatar in other major formats. For example, the storage unit can save 3D avatars in the GLB format and FBX format. This allows the storage unit to make 3D avatars usable on various platforms. Some or all of the above processing in the storage unit is performed using a generation AI. For example, the storage unit inputs the generated 3D avatar into the generation AI and performs saving in the VRM format. The generation AI analyzes the 3D avatar data and selects the optimal format for efficient saving. This allows the storage unit to save and make available user-generated 3D avatars in various formats.

[0033] The dialogue unit can function as an AI conversational assistant with multiple functions, including everyday conversation, consultation, news provision, ordering, schedule management, and translation. For example, the dialogue unit can engage in everyday conversation. Using generative AI, the dialogue unit generates appropriate responses based on the user's everyday conversation. For example, in response to a user's question, the generative AI generates an appropriate answer and displays it through a 3D avatar. The dialogue unit can also provide consultation. Using generative AI, the dialogue unit provides appropriate advice based on the user's consultation. For example, in response to a user's worries or problems, the generative AI generates appropriate advice and displays it through a 3D avatar. Furthermore, the dialogue unit can provide news. Using generative AI, the dialogue unit collects the latest news and provides it to the user. For example, the generative AI generates a news summary and displays it through a 3D avatar. The dialogue unit can also place orders. Using generative AI, the dialogue unit performs appropriate processing based on the user's order. For example, the dialogue unit accepts the user's order, the generative AI performs the appropriate processing, and the results are displayed through a 3D avatar. Furthermore, the dialogue unit can also manage schedules. Using generative AI, the dialogue unit manages the user's schedule and provides appropriate reminders. For example, the dialogue unit uses generative AI to analyze the user's schedule, generate reminders, and display them through a 3D avatar. The dialogue unit can also perform translations. Using generative AI, the dialogue unit translates user input and displays it in the appropriate language. For example, the dialogue unit uses generative AI to analyze user input, translate it into the appropriate language, and display it through a 3D avatar. This allows the dialogue unit to provide a multi-functional AI conversational assistant. Some or all of the above-mentioned processes in the dialogue unit are performed using generative AI. For example, the dialogue unit inputs user input into the generative AI, which then performs appropriate responses, advice, news, order processing, schedule management, and translation. The generative AI analyzes user input and generates appropriate responses, advice, news, order processing, schedule management, and translations. This allows the dialogue unit to provide an AI conversational assistant that meets the diverse needs of users.

[0034] The display unit can display a 3D avatar AI conversation assistant through AR glasses. For example, the display unit displays a 3D avatar AI conversation assistant using AR glasses. The display unit can overlay the 3D avatar onto the user's field of view and engage in real-time conversation. For example, when the user is wearing AR glasses, the display unit displays the 3D avatar in their field of view and engages in conversation. Furthermore, if multiple people are using the same app, the display unit can overlay the avatar onto how others see them and synchronize their full-body movements. For example, when another person is wearing AR glasses, the display unit displays the user's 3D avatar in their field of view and synchronizes their full-body movements. This allows the display unit to display the AI ​​conversation assistant through AR glasses. Some or all of the above processing in the display unit is performed using a generation AI. For example, the display unit inputs the 3D avatar to be displayed in the user's field of view into the generation AI and causes the generation AI to execute the appropriate display. The generation AI analyzes the 3D avatar to be displayed in the user's field of view and generates the appropriate display. This allows the display unit to overlay a 3D avatar onto the user's field of view, enabling real-time interaction.

[0035] The display unit can overlay an avatar onto the user's appearance from the perspective of others when multiple users are using the same app, and synchronize their full-body movements. For example, when another user is wearing AR glasses, the display unit can display the user's 3D avatar in their field of view and synchronize their full-body movements. The display unit uses a generation AI to analyze the user's movements and reflect them in the 3D avatar. For example, the display unit detects the user's movements with a camera or sensors, the generation AI analyzes those movements, and reflects them in the 3D avatar. The display unit can also overlay an avatar onto the user's appearance from the perspective of others when multiple users are using the same app, and synchronize their full-body movements. For example, when another user is wearing AR glasses, the display unit can display the user's 3D avatar in their field of view and synchronize their full-body movements. This allows the display unit to overlay an avatar onto the user's appearance from the perspective of others and synchronize their full-body movements. Some or all of the above processing in the display unit is performed using a generation AI. For example, the display unit inputs the user's movements into the generation AI and reflects them in the 3D avatar. The generating AI analyzes the user's movements and reflects them in the 3D avatar. This allows the display to overlay the avatar as seen by others, and to synchronize the movements of the entire body.

[0036] The generation unit can analyze the user's past avatar generation history and select an appropriate generation algorithm. For example, the generation unit can analyze the style of avatars the user has generated in the past and generate new avatars based on the user's preferences. The generation unit uses a generation AI to analyze the user's past avatar generation history and select the optimal generation algorithm based on that analysis. For example, the generation AI analyzes data on avatars the user has generated in the past and learns the user's preferences. The generation unit generates new avatars based on the preferences learned by the generation AI. The generation unit can also extract the characteristics of avatars that the user frequently uses and optimize the generation algorithm based on that. For example, the generation AI analyzes data on avatars that the user frequently uses and extracts their characteristics. The generation unit optimizes the generation algorithm based on the characteristics extracted by the generation AI and generates new avatars. Furthermore, the generation unit can also refer to data on avatars that the user has generated during specific events or seasons to generate avatars suitable for those seasons or events. For example, the generation AI analyzes data on avatars generated by the user during specific events or seasons and generates new avatars based on that analysis. This allows the generation unit to analyze the user's past avatar generation history and select the optimal generation algorithm. Some or all of the above-described processes in the generation unit are performed using the generation AI. For example, the generation unit inputs the user's past avatar generation history into the generation AI and has it select the optimal generation algorithm. The generation AI analyzes the user's past avatar generation history and selects the optimal generation algorithm based on that analysis. This allows the generation unit to analyze the user's past avatar generation history and select the optimal generation algorithm.

[0037] The generation unit can customize the generated avatar based on the user's current fashion and trends. For example, the generation unit can recognize the user's current clothing using a camera and generate an avatar in a similar style. The generation unit uses a generation AI to analyze the user's current fashion and trends and customize the generated avatar based on that analysis. For example, the generation AI recognizes the user's current clothing using a camera and generates an avatar in a similar style based on that analysis. The generation unit can also retrieve the latest fashion trends from a database and generate the avatar's clothing and accessories based on that analysis. For example, the generation AI retrieves the latest fashion trends from a database and generates the avatar's clothing and accessories based on that analysis. Furthermore, the generation unit can analyze fashion photos shared by the user on social media and generate an avatar that reflects that style. For example, the generation AI analyzes fashion photos shared by the user on social media and determines the avatar's style based on that analysis. This allows the generation unit to customize the generated avatar based on the user's current fashion and trends. Some or all of the above processes in the generation unit are performed using a generation AI. For example, the generation unit inputs the user's current fashion and trends into the generation AI, which then customizes the generated avatar. The generation AI analyzes the user's current fashion and trends and customizes the generated avatar based on that analysis. This allows the generation unit to customize the generated avatar based on the user's current fashion and trends.

[0038] The avatar generation unit can prioritize generating highly relevant styles based on the user's geographical location information. For example, if the user is in an urban area, the generation unit will generate an urban-style avatar. The generation unit uses a generation AI to analyze the user's geographical location information and prioritize generating highly relevant styles based on that information. For example, if the generation AI obtains the user's geographical location information and determines that the user is in an urban area, it will generate an urban-style avatar. The generation unit can also generate a casual and relaxed style avatar if the user is in a place with abundant nature. For example, if the generation AI obtains the user's geographical location information and determines that the user is in a place with abundant nature, it will generate a casual and relaxed style avatar. Furthermore, if the user is in a specific country or region, the generation unit can also generate an avatar based on the culture and fashion of that region. For example, if the generation AI obtains the user's geographical location information and determines that the user is in a specific country or region, it will generate an avatar based on the culture and fashion of that region. This allows the generation unit to prioritize generating highly relevant styles based on the user's geographical location information. Some or all of the above-described processes in the generation unit are performed using a generation AI. For example, the generation unit inputs the user's geographical location information into the generation AI and generates highly relevant styles. The generation AI analyzes the user's geographical location information and generates highly relevant styles based on it. This allows the generation unit to prioritize the generation of highly relevant styles based on the user's geographical location information.

[0039] The generation unit can analyze the user's social media activity and generate relevant styles when generating avatars. For example, the generation unit analyzes photos and posts shared by the user on social media and determines the avatar's style based on that. The generation unit uses a generation AI to analyze the user's social media activity and generate relevant styles based on that. For example, the generation AI analyzes photos and posts shared by the user on social media and determines the avatar's style based on that. The generation unit can also generate avatars by referencing the styles of influencers the user follows. For example, the generation AI analyzes posts from influencers the user follows and determines the avatar's style based on that. Furthermore, the generation unit can analyze the trends of online communities the user participates in and generate avatars based on that. For example, the generation AI analyzes the topics of online communities the user participates in and determines the avatar's style based on that. In this way, the generation unit can generate relevant styles based on the user's social media activity. Some or all of the above processes in the generation unit are performed using a generation AI. For example, the generation unit inputs the user's social media activity into the generation AI and has it generate relevant styles. The generation AI analyzes the user's social media activity and generates relevant styles based on that analysis. This allows the generation unit to generate relevant styles based on the user's social media activity.

[0040] The storage unit can determine the priority of saving avatars based on their usage frequency. For example, the storage unit can prioritize saving avatars that users frequently use. The storage unit uses a generation AI to analyze the usage frequency of avatars and determine the priority of saving based on that. For example, the generation AI analyzes the data of avatars that users frequently use and evaluates their usage frequency. The storage unit prioritizes saving frequently used avatars based on the usage frequency evaluated by the generation AI. The storage unit can also prioritize saving avatars that users use for specific events. For example, the generation AI analyzes the data of avatars that users use for specific events and evaluates their usage frequency. The storage unit prioritizes saving avatars used for specific events based on the usage frequency evaluated by the generation AI. Furthermore, the storage unit can postpone saving avatars that users have not used for a long period of time. For example, the generation AI analyzes the data of avatars that users have not used for a long period of time and evaluates their usage frequency. The storage unit postpones saving avatars that have not been used for a long period of time based on the usage frequency evaluated by the generation AI. This allows the storage unit to determine the priority of saving based on the frequency of avatar use. Some or all of the above-described processes in the storage unit are performed using a generating AI. For example, the storage unit inputs the frequency of avatar use into the generating AI and has it determine the priority of saving. The generating AI analyzes the frequency of avatar use and determines the priority of saving based on that. This allows the storage unit to determine the priority of saving based on the frequency of avatar use.

[0041] The storage unit can apply different storage algorithms depending on the avatar's category during storage. For example, the storage unit can save photorealistic avatars in high resolution and moe-style avatars in a lightweight format. The storage unit uses a generation AI to analyze the avatar's category and select an appropriate storage algorithm based on that. For example, the generation AI analyzes the avatar's category and selects an algorithm for saving in high resolution if it is a photorealistic avatar. The storage unit can also select an algorithm for saving in a lightweight format if it is a moe-style avatar. For example, the generation AI analyzes the avatar's category and selects an algorithm for saving in a lightweight format if it is a moe-style avatar. Furthermore, the storage unit can also save items such as clothing and accessories individually for later reuse. For example, the generation AI analyzes the avatar data and selects an algorithm for saving items such as clothing and accessories individually. This allows the storage unit to apply different storage algorithms depending on the avatar's category. Some or all of the above processing in the storage unit is performed using a generation AI. For example, the storage unit inputs the avatar category into the generation AI, which then selects an appropriate storage algorithm. The generation AI analyzes the avatar category and selects an appropriate storage algorithm based on that analysis. This allows the storage unit to apply different storage algorithms depending on the avatar category.

[0042] The storage unit can determine the priority of saving avatars based on when they were created. For example, the storage unit can prioritize saving recently created avatars. The storage unit uses a generation AI to analyze when avatars were created and determine the priority of saving based on that. For example, the generation AI analyzes when avatars were created and prioritizes saving recently created avatars. The storage unit can also prioritize saving avatars created during specific events or seasons. For example, the generation AI analyzes when avatars were created and prioritizes saving avatars created during specific events or seasons. Furthermore, the storage unit can postpone saving avatars that have not been used for a long time. For example, the generation AI analyzes when avatars were created and postpones saving avatars that have not been used for a long time. This allows the storage unit to determine the priority of saving based on when avatars were created. Some or all of the above processes in the storage unit are performed using the generation AI. For example, the storage unit inputs the creation date of avatars into the generation AI and has it determine the priority of saving. The generation AI analyzes when the avatar was created and determines the saving priority based on that. This allows the storage unit to determine the saving priority based on when the avatar was created.

[0043] The storage unit can adjust the order of saving avatars based on their relevance during the saving process. For example, the storage unit can prioritize saving avatars that the user frequently uses. The storage unit uses a generative AI to analyze the relevance of avatars and adjust the saving order accordingly. For example, the generative AI analyzes the data of avatars that the user frequently uses and evaluates their relevance. Based on the relevance evaluated by the generative AI, the storage unit prioritizes saving frequently used avatars. The storage unit can also prioritize saving avatars that the user uses for specific events. For example, the generative AI analyzes the data of avatars that the user uses for specific events and evaluates their relevance. Based on the relevance evaluated by the generative AI, the storage unit prioritizes saving avatars that are used for specific events. Furthermore, the storage unit can postpone saving avatars that the user has not used for a long period of time. For example, the generative AI analyzes the data of avatars that the user has not used for a long period of time and evaluates their relevance. Based on the relevance evaluated by the generative AI, the storage unit postpones saving avatars that have not been used for a long period of time. This allows the storage unit to adjust the order of saving avatars based on their relevance. Some or all of the above-described processes in the storage unit are performed using a generation AI. For example, the storage unit inputs the relationships between avatars into the generation AI and adjusts the storage order. The generation AI analyzes the relationships between avatars and adjusts the storage order based on that. In this way, the storage unit can adjust the storage order based on the relationships between avatars.

[0044] The dialogue unit can analyze the user's past dialogue history and select the optimal dialogue algorithm during a conversation. For example, the dialogue unit prioritizes using expressions and phrases that the user has frequently used in the past. The dialogue unit uses generative AI to analyze the user's past dialogue history and select the optimal dialogue algorithm based on that analysis. For example, the generative AI analyzes the user's past dialogue history and learns expressions and phrases that the user has frequently used. The dialogue unit then conducts a conversation based on the expressions and phrases learned by the generative AI. The dialogue unit can also provide relevant information based on topics that the user has frequently discussed in the past. For example, the generative AI analyzes the user's past dialogue history and learns topics that the user has frequently discussed. The dialogue unit then provides relevant information based on what the generative AI has learned. Furthermore, the dialogue unit can prioritize conversations on specific topics based on the user's past dialogue history. For example, the generative AI analyzes the user's past dialogue history and learns conversations on specific topics. The dialogue unit then conducts a conversation based on the topics learned by the generative AI. This allows the dialogue unit to analyze the user's past dialogue history and select the optimal dialogue algorithm. Some or all of the above processing in the dialogue unit is performed using a generative AI. For example, the dialogue unit inputs the user's past dialogue history into the generative AI and has it select the optimal dialogue algorithm. The generative AI analyzes the user's past dialogue history and selects the optimal dialogue algorithm based on that analysis. This allows the dialogue unit to analyze the user's past dialogue history and select the optimal dialogue algorithm.

[0045] The dialogue unit can customize the content of the conversation based on the user's current situation and interests. For example, if the user is interested in the current weather, the dialogue unit will provide information about the weather. The dialogue unit uses generative AI to analyze the user's current situation and interests and customize the content of the conversation based on that analysis. For example, if the generative AI analyzes the user's current situation and interests and determines that the user is interested in the weather, it will provide information about the weather. The dialogue unit can also provide information related to an event if the user is participating in that event. For example, if the generative AI analyzes the user's current situation and interests and determines that the user is participating in that event, it will provide information related to that event. Furthermore, if the dialogue unit is interested in a particular news story, it can provide information about that news story. For example, if the generative AI analyzes the user's current situation and interests and determines that the user is interested in that news story, it will provide information about that news story. In this way, the dialogue unit can customize the content of the conversation based on the user's current situation and interests. Some or all of the above processing in the dialogue unit is performed using generative AI. For example, the dialogue unit inputs the user's current situation and interests into the generating AI, which then customizes the dialogue content. The generating AI analyzes the user's current situation and interests and customizes the dialogue content based on that. This allows the dialogue unit to customize the dialogue content based on the user's current situation and interests.

[0046] The dialogue unit can prioritize providing highly relevant dialogue content based on the user's geographical location information during a conversation. For example, if the user is in a specific region, the dialogue unit will provide information related to that region. The dialogue unit uses generative AI to analyze the user's geographical location information and prioritize providing highly relevant dialogue content based on that analysis. For example, the generative AI acquires the user's geographical location information, and if it determines that the user is in a specific region, it provides information related to that region. The dialogue unit can also provide information about the user's travel destination if the user is traveling. For example, the generative AI acquires the user's geographical location information, and if it determines that the user is traveling, it provides information about the travel destination. Furthermore, if the user is participating in a specific event, the dialogue unit can also provide information related to that event. For example, the generative AI acquires the user's geographical location information, and if it determines that the user is participating in a specific event, it provides information related to that event. This allows the dialogue unit to prioritize providing highly relevant dialogue content based on the user's geographical location information. Some or all of the above processing in the dialogue unit is performed using generative AI. For example, the dialogue unit inputs the user's geographical location information into the generative AI and causes it to provide highly relevant dialogue content. The generating AI analyzes the user's geographical location information and provides highly relevant dialogue based on that information. This allows the dialogue unit to prioritize providing dialogue that is relevant to the user's geographical location.

[0047] The dialogue unit can analyze the user's social media activity during a conversation and provide relevant dialogue content. For example, the dialogue unit can determine dialogue content based on posts the user has shared on social media. The dialogue unit uses generative AI to analyze the user's social media activity and provide relevant dialogue content based on that analysis. For example, the generative AI analyzes posts the user has shared on social media and determines dialogue content based on that analysis. The dialogue unit can also provide dialogue content based on posts from influencers the user follows. For example, the generative AI analyzes posts from influencers the user follows and determines dialogue content based on that analysis. Furthermore, the dialogue unit can also provide dialogue content based on topics in online communities the user participates in. For example, the generative AI analyzes topics in online communities the user participates in and determines dialogue content based on that analysis. This allows the dialogue unit to provide relevant dialogue content based on the user's social media activity. Some or all of the above processing in the dialogue unit is performed using generative AI. For example, the dialogue unit inputs the user's social media activity into the generative AI and has it provide relevant dialogue content. The generative AI analyzes the user's social media activity and provides relevant dialogue content based on that analysis. This allows the dialogue unit to provide relevant dialogue content based on the user's social media activity.

[0048] The display unit can analyze the user's past viewing history and select the optimal display algorithm when displaying information. For example, the display unit may prioritize display styles that the user has previously preferred. The display unit uses a generative AI to analyze the user's past viewing history and select the optimal display algorithm based on that analysis. For example, the generative AI analyzes the user's past viewing history and learns the display styles that the user has preferred. The display unit then displays information based on the display styles learned by the generative AI. The display unit can also prioritize displaying relevant information based on information that the user has frequently viewed in the past. For example, the generative AI analyzes the user's past viewing history and learns the information that has been frequently viewed. The display unit then prioritizes displaying relevant information based on the information learned by the generative AI. Furthermore, the display unit can also prioritize displaying information related to specific topics based on the user's past viewing history. For example, the generative AI analyzes the user's past viewing history and learns information related to specific topics. The display unit then displays information based on the topics learned by the generative AI. This allows the display unit to analyze the user's past viewing history and select the optimal display algorithm. Some or all of the above processing in the display unit is performed using a generating AI. For example, the display unit inputs the user's past viewing history into the generating AI and has it select the optimal display algorithm. The generating AI analyzes the user's past viewing history and selects the optimal display algorithm based on that analysis. This allows the display unit to analyze the user's past viewing history and select the optimal display algorithm.

[0049] The display unit can customize the displayed content based on the user's current situation and interests. For example, if the user is interested in the current weather, the display unit will prioritize displaying weather-related information. The display unit uses generative AI to analyze the user's current situation and interests and customize the displayed content accordingly. For example, if the generative AI analyzes the user's current situation and interests and determines that the user is interested in the weather, it will prioritize displaying weather-related information. The display unit can also prioritize displaying information related to a specific event if the user is participating in that event. For example, if the generative AI analyzes the user's current situation and interests and determines that the user is participating in that event, it will prioritize displaying information related to that event. Furthermore, if the user is interested in a specific news story, the display unit can also prioritize displaying information related to that news story. For example, if the generative AI analyzes the user's current situation and interests and determines that the user is interested in that news story, it will prioritize displaying information related to that news story. In this way, the display unit can customize the displayed content based on the user's current situation and interests. Some or all of the above processing in the display unit is performed using generative AI. For example, the display unit inputs the user's current situation and interests into a generating AI, which then customizes the displayed content. The generating AI analyzes the user's current situation and interests and customizes the displayed content based on that analysis. This allows the display unit to customize the displayed content based on the user's current situation and interests.

[0050] The display unit can prioritize displaying content that is highly relevant to the user, taking into account the user's geographical location information. For example, if the user is in a specific region, the display unit will prioritize displaying information related to that region. The display unit uses a generation AI to analyze the user's geographical location information and, based on that, prioritizes displaying content that is highly relevant. For example, the generation AI acquires the user's geographical location information, and if it determines that the user is in a specific region, it will prioritize displaying information related to that region. The display unit can also prioritize displaying information related to the user's travel destination if the user is traveling. For example, the generation AI acquires the user's geographical location information, and if it determines that the user is traveling, it will prioritize displaying information related to the travel destination. Furthermore, if the user is participating in a specific event, the display unit can also prioritize displaying information related to that event. For example, the generation AI acquires the user's geographical location information, and if it determines that the user is participating in a specific event, it will prioritize displaying information related to that event. In this way, the display unit can prioritize displaying content that is highly relevant to the user's geographical location information. Some or all of the above processing in the display unit is performed using a generation AI. For example, the display unit inputs the user's geographical location information into a generating AI, which then provides highly relevant display content. The generating AI analyzes the user's geographical location information and provides highly relevant display content based on that analysis. This allows the display unit to prioritize providing highly relevant display content based on the user's geographical location information.

[0051] The display unit can analyze the user's social media activity and provide relevant display content when displaying content. For example, the display unit determines the display content based on posts shared by the user on social media. The display unit uses a generative AI to analyze the user's social media activity and provide relevant display content based on that analysis. For example, the generative AI analyzes posts shared by the user on social media and determines the display content based on that analysis. The display unit can also provide display content based on posts from influencers followed by the user. For example, the generative AI analyzes posts from influencers followed by the user and determines the display content based on that analysis. Furthermore, the display unit can also provide display content based on topics in online communities in which the user participates. For example, the generative AI analyzes topics in online communities in which the user participates and determines the display content based on that analysis. In this way, the display unit can provide relevant display content based on the user's social media activity. Some or all of the above processing in the display unit is performed using a generative AI. For example, the display unit inputs the user's social media activity into the generative AI and causes it to provide relevant display content. The generative AI analyzes the user's social media activity and provides relevant display content based on that analysis. This allows the display unit to provide relevant content based on the user's social media activity.

[0052] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0053] The generation unit can analyze a user's past avatar creation history and learn their preferences and trends. For example, it can analyze the style and characteristics of avatars a user has created in the past and generate a new avatar based on that. Using generation AI, the generation unit can learn the user's preference trends and optimize avatar design accordingly. It can also refer to data on avatars a user has created during specific events or seasons to generate avatars suitable for those seasons or events. In this way, the generation unit can leverage a user's past avatar creation history to provide more personalized avatars.

[0054] The storage unit can save a user's avatar creation history to cloud storage, making it accessible from other devices. For example, the storage unit can save avatars created by a user on their smartphone to the cloud, making them accessible from PCs and tablets. The storage unit can use generation AI to optimize and efficiently manage avatar data stored in cloud storage. Furthermore, the storage unit can integrate and centrally manage avatars created by a user on different devices. This allows the storage unit to enable users to access and use their avatars from any device.

[0055] The display unit can utilize the user's geographical location information to display relevant information. For example, if the user is traveling, the display unit can display tourist information and restaurant information for their travel destination. The display unit uses a generation AI to analyze the user's geographical location information and provides relevant information based on that analysis. Furthermore, if the user is participating in a specific event, the display unit can display information related to that event. Additionally, if the user is in a specific region, the display unit can display weather and traffic information for that region. In this way, the display unit can provide relevant information based on the user's geographical location information.

[0056] The generation unit can analyze a user's social media activity and suggest relevant avatar styles. For example, it can analyze photos and posts shared by a user on social media and suggest avatar styles based on that analysis. The generation unit uses generation AI to analyze a user's social media activity and optimize avatar styles based on that analysis. It can also generate avatars by referencing the styles of influencers the user follows. Furthermore, the generation unit can analyze trends in online communities the user participates in and suggest avatar styles based on that analysis. In this way, the generation unit can suggest relevant avatar styles based on the user's social media activity.

[0057] The dialogue unit can analyze the user's past conversation history and customize the conversation content based on the user's preferences and interests. For example, the dialogue unit can prioritize topics that the user has enjoyed discussing in the past. The dialogue unit uses generative AI to analyze the user's past conversation history and optimize the conversation content accordingly. The dialogue unit can also provide relevant advice based on what the user has previously consulted. Furthermore, the dialogue unit can provide information about news and events that the user has shown interest in in the past. In this way, the dialogue unit can customize the conversation content based on the user's past conversation history.

[0058] The generation unit can customize the avatar's style based on the user's current fashion and trends. For example, the generation unit can recognize the clothing the user is currently wearing using a camera and generate an avatar with a similar style. The generation unit uses generation AI to analyze the user's current fashion and trends and optimize the avatar's style accordingly. The generation unit can also retrieve the latest fashion trends from a database and generate clothing and accessories for the avatar based on them. Furthermore, the generation unit can analyze fashion photos shared by the user on social media and generate an avatar that reflects that style. In this way, the generation unit can customize the avatar's style based on the user's current fashion and trends.

[0059] The following briefly describes the processing flow for example form 1.

[0060] Step 1: The generation unit generates 3D avatars. The generation unit generates 3D avatars in various styles, such as photorealistic and moe-style. Using generation AI, the generation unit receives user photos and videos as input and generates 3D avatars based on them. For example, the generation AI analyzes the user's facial features and generates a realistic 3D model. The generation unit can also use generation AI to generate an unlimited number of items such as clothes, accessories, shoes, and other accessories. For example, the generation AI generates clothes and accessories in various designs based on the user's preferences and trends. Step 2: The storage unit saves and outputs the 3D avatar generated by the generation unit. The storage unit saves the 3D avatar in a major format such as VRM. The storage unit saves the generated 3D avatar to cloud storage so that the user can access it at any time. The storage unit can also save the generated 3D avatar to a local device. Step 3: The dialogue unit acts as an AI conversational assistant using the 3D avatar saved by the storage unit. The dialogue unit acts as an AI conversational assistant with functions such as everyday conversation, consultation, news provision, ordering, schedule management, and translation. The dialogue unit uses generative AI to generate appropriate responses in response to user input. For example, in response to a user's question, the dialogue unit uses generative AI to generate an appropriate answer and displays it through the 3D avatar. Step 4: The display unit shows the AI ​​conversational assistant, which is operated by the dialogue unit, through the AR glasses. The display unit uses the AR glasses to display the 3D avatar of the AI ​​conversational assistant. The display unit overlays the 3D avatar into the user's field of view, allowing for real-time interaction. If multiple people are using the same app, the display unit can also overlay the avatar onto how others see them and synchronize their full-body movements.

[0061] (Example of form 2) The system according to an embodiment of the present invention is a system that utilizes a smartphone's generation AI to create a 3D model of a user's own avatar usable in various metaverses. This system allows users to generate 3D avatars in various styles, such as photorealistic or moe-style, using a smartphone app. By combining the generation AI with existing avatar generation algorithms, higher quality avatars can be created. Furthermore, the generation AI can be used to generate an unlimited number of items, including clothing, accessories, shoes, and other accessories. The created 3D avatars are saved and output in major formats such as VRM, and can be used in various metaverses and online meeting tools. Next, the created 3D avatars can also be used as AI conversational assistants. Users can use the 3D avatar as an AI conversational assistant with functions such as everyday conversation, consultation, news delivery, ordering, schedule management, and translation. Additionally, an assistant app for AR glasses has been developed simultaneously, allowing the 3D avatar AI conversational assistant to be displayed through AR glasses. This is available to the user themselves or authorized individuals, and when multiple people use the same app, the avatar is overlaid on the user's avatar as seen by others, and their full-body movements are synchronized. A key feature of this technology is its ability to create unique avatars by utilizing generative AI. By adding generative AI to existing avatar generation technologies, it becomes an even more powerful system. Furthermore, it can generate an infinite number of patterns for items such as clothing and accessories, and the resulting avatars can track not only the entire body but also facial expressions and hand movements. This allows users to have a more realistic experience. The system enables users to generate and save high-quality 3D avatars using their smartphones and utilize them as AI conversational assistants. It is also possible to display 3D avatars using AR glasses, allowing users to control the avatars in real time and interact with others.

[0062] The avatar generation system according to the embodiment comprises a generation unit, a storage unit, a dialogue unit, and a display unit. The generation unit generates 3D avatars. The generation unit generates 3D avatars in various styles, such as photorealistic and moe-style. The generation unit uses a generation AI to receive user photos and videos as input and generates 3D avatars based on them. For example, the generation AI analyzes the features of the user's face and generates a realistic 3D model. The generation unit can also use the generation AI to generate an unlimited number of items such as clothes, accessories, shoes, and other items. For example, the generation AI generates clothes and accessories in various designs based on the user's preferences and trends. The storage unit saves and outputs the 3D avatars generated by the generation unit. The storage unit saves the 3D avatars in major formats such as VRM. The storage unit saves the generated 3D avatars to cloud storage so that the user can access them at any time. The storage unit can also save the generated 3D avatars to a local device. The dialogue unit uses the 3D avatars saved by the storage unit to perform AI dialogue assistance. The dialogue unit acts as an AI conversational assistant with functions such as everyday conversation, consultation, news delivery, ordering, schedule management, and translation. The dialogue unit uses a generative AI to generate appropriate responses in response to user input. For example, the dialogue unit generates an appropriate answer to a user's question using the generative AI and displays it through a 3D avatar. The display unit displays the AI ​​conversational assistant performed by the dialogue unit through AR glasses. For example, the display unit displays the 3D avatar AI conversational assistant using AR glasses. The display unit overlays the 3D avatar onto the user's field of view, allowing for real-time interaction. If multiple people are using the same app, the display unit can also overlay the avatar on themselves as seen by others and synchronize their full-body movements. As a result, the avatar generation system according to this embodiment allows users to generate and save high-quality 3D avatars using their smartphones and utilize them as an AI conversational assistant. It is also possible to display the 3D avatar using AR glasses, allowing users to manipulate the avatar in real time and interact with others.

[0063] The generation unit can generate 3D avatars in multiple styles, including photorealistic and moe-style. For example, the generation unit can generate photorealistic 3D avatars. Photorealistic 3D avatars reproduce the user's facial features in detail and have a realistic appearance. The generation unit uses a generation AI to analyze the user's photograph and generate a realistic 3D model. For example, the generation AI analyzes the user's facial contours and skin texture to generate a photorealistic 3D avatar. The generation unit can also generate moe-style 3D avatars. Moe-style 3D avatars have an anime-like design and emphasize the character's features. The generation unit uses a generation AI to generate moe-style 3D avatars according to the user's preferences. For example, the generation AI learns the user's preferred character designs and generates moe-style 3D avatars based on that. This allows the generation unit to generate a variety of 3D avatar styles. Some or all of the above-described processes in the generation unit are performed using a generation AI. For example, the generation unit inputs a user's photo into the generation AI and generates a photorealistic or moe-style 3D avatar. The generation AI analyzes the user's photo and generates a realistic 3D model. The generation AI learns the user's preferred character design and generates a moe-style 3D avatar based on that. In this way, the generation unit can generate a variety of 3D avatar styles according to the user's preferences.

[0064] The generation unit can generate multiple items such as clothing, accessories, shoes, and other items. For example, the generation unit can generate clothing. Using a generation AI, the generation unit generates clothing in various designs based on the user's preferences and trends. For example, the generation AI can generate casual or formal style clothing. The generation unit can also generate accessories. Using a generation AI, the generation unit generates accessories such as hats and bags. For example, the generation AI generates hats and bags with designs that suit the user's preferences. Furthermore, the generation unit can also generate shoes. Using a generation AI, the generation unit generates shoes such as sneakers and boots. For example, the generation AI generates sneakers and boots with designs that suit the user's preferences. The generation unit can also generate accessories. Using a generation AI, the generation unit generates accessories such as necklaces and earrings. For example, the generation AI generates necklaces and earrings with designs that suit the user's preferences. As a result, the generation unit can generate an infinite number of items. Some or all of the above-described processes in the generation unit are performed using a generation AI. For example, the generation unit instructs the generation AI to create clothing, accessories, shoes, and other items based on the user's preferences and trends. The generation AI learns the user's preferences and trends and generates items of various designs based on them. This allows the generation unit to generate an infinite number of items tailored to the user's preferences.

[0065] The storage unit can save and output 3D avatars in the major VRM format. For example, the storage unit saves 3D avatars in the VRM format. The VRM format is a standard format for efficiently saving 3D avatar data and is widely used in various metaverses and online meeting tools. The storage unit saves the generated 3D avatar in the VRM format, making it accessible to the user at any time. The storage unit can also save the generated 3D avatar in other major formats. For example, the storage unit can save 3D avatars in the GLB format and FBX format. This allows the storage unit to make 3D avatars usable on various platforms. Some or all of the above processing in the storage unit is performed using a generation AI. For example, the storage unit inputs the generated 3D avatar into the generation AI and performs saving in the VRM format. The generation AI analyzes the 3D avatar data and selects the optimal format for efficient saving. This allows the storage unit to save and make available user-generated 3D avatars in various formats.

[0066] The dialogue unit can function as an AI conversational assistant with multiple functions, including everyday conversation, consultation, news provision, ordering, schedule management, and translation. For example, the dialogue unit can engage in everyday conversation. Using generative AI, the dialogue unit generates appropriate responses based on the user's everyday conversation. For example, in response to a user's question, the generative AI generates an appropriate answer and displays it through a 3D avatar. The dialogue unit can also provide consultation. Using generative AI, the dialogue unit provides appropriate advice based on the user's consultation. For example, in response to a user's worries or problems, the generative AI generates appropriate advice and displays it through a 3D avatar. Furthermore, the dialogue unit can provide news. Using generative AI, the dialogue unit collects the latest news and provides it to the user. For example, the generative AI generates a news summary and displays it through a 3D avatar. The dialogue unit can also place orders. Using generative AI, the dialogue unit performs appropriate processing based on the user's order. For example, the dialogue unit accepts the user's order, the generative AI performs the appropriate processing, and the results are displayed through a 3D avatar. Furthermore, the dialogue unit can also manage schedules. Using generative AI, the dialogue unit manages the user's schedule and provides appropriate reminders. For example, the dialogue unit uses generative AI to analyze the user's schedule, generate reminders, and display them through a 3D avatar. The dialogue unit can also perform translations. Using generative AI, the dialogue unit translates user input and displays it in the appropriate language. For example, the dialogue unit uses generative AI to analyze user input, translate it into the appropriate language, and display it through a 3D avatar. This allows the dialogue unit to provide a multi-functional AI conversational assistant. Some or all of the above-mentioned processes in the dialogue unit are performed using generative AI. For example, the dialogue unit inputs user input into the generative AI, which then performs appropriate responses, advice, news, order processing, schedule management, and translation. The generative AI analyzes user input and generates appropriate responses, advice, news, order processing, schedule management, and translations. This allows the dialogue unit to provide an AI conversational assistant that meets the diverse needs of users.

[0067] The display unit can display a 3D avatar AI conversation assistant through AR glasses. For example, the display unit displays a 3D avatar AI conversation assistant using AR glasses. The display unit can overlay the 3D avatar onto the user's field of view and engage in real-time conversation. For example, when the user is wearing AR glasses, the display unit displays the 3D avatar in their field of view and engages in conversation. Furthermore, if multiple people are using the same app, the display unit can overlay the avatar onto how others see them and synchronize their full-body movements. For example, when another person is wearing AR glasses, the display unit displays the user's 3D avatar in their field of view and synchronizes their full-body movements. This allows the display unit to display the AI ​​conversation assistant through AR glasses. Some or all of the above processing in the display unit is performed using a generation AI. For example, the display unit inputs the 3D avatar to be displayed in the user's field of view into the generation AI and causes the generation AI to execute the appropriate display. The generation AI analyzes the 3D avatar to be displayed in the user's field of view and generates the appropriate display. This allows the display unit to overlay a 3D avatar onto the user's field of view, enabling real-time interaction.

[0068] The display unit can overlay an avatar onto the user's appearance from the perspective of others when multiple users are using the same app, and synchronize their full-body movements. For example, when another user is wearing AR glasses, the display unit can display the user's 3D avatar in their field of view and synchronize their full-body movements. The display unit uses a generation AI to analyze the user's movements and reflect them in the 3D avatar. For example, the display unit detects the user's movements with a camera or sensors, the generation AI analyzes those movements, and reflects them in the 3D avatar. The display unit can also overlay an avatar onto the user's appearance from the perspective of others when multiple users are using the same app, and synchronize their full-body movements. For example, when another user is wearing AR glasses, the display unit can display the user's 3D avatar in their field of view and synchronize their full-body movements. This allows the display unit to overlay an avatar onto the user's appearance from the perspective of others and synchronize their full-body movements. Some or all of the above processing in the display unit is performed using a generation AI. For example, the display unit inputs the user's movements into the generation AI and reflects them in the 3D avatar. The generating AI analyzes the user's movements and reflects them in the 3D avatar. This allows the display to overlay the avatar as seen by others, and to synchronize the movements of the entire body.

[0069] The generation unit can estimate the user's emotions and automatically adjust the avatar's style based on the estimated emotions. For example, if the user is relaxed, the generation AI will generate an avatar with a calm expression and soft colors. The generation unit uses the generation AI to analyze the user's emotions and adjust the avatar's style based on that analysis. For example, if the generation AI analyzes the user's facial expressions and voice and determines that the user is relaxed, it will generate an avatar with a calm expression and soft colors. The generation unit can also generate an avatar with an energetic expression and vibrant colors if the user is excited. For example, if the generation AI analyzes the user's facial expressions and voice and determines that the user is excited, it will generate an avatar with an energetic expression and vibrant colors. Furthermore, if the user is sad, the generation AI can generate an avatar with a calm expression and dark colors. For example, if the generation AI analyzes the user's facial expressions and voice and determines that the user is sad, it will generate an avatar with a calm expression and dark colors. In this way, the generation unit can automatically adjust the avatar's style based on the user's emotions. Some or all of the above-described processes in the generation unit are performed using a generation AI. For example, the generation unit inputs the user's emotions into the generation AI, which then adjusts the avatar's style. The generation AI analyzes the user's emotions and adjusts the avatar's style based on that analysis. This allows the generation unit to automatically adjust the avatar's style based on the user's emotions.

[0070] The generation unit can analyze the user's past avatar generation history and select an appropriate generation algorithm. For example, the generation unit can analyze the style of avatars the user has generated in the past and generate new avatars based on the user's preferences. The generation unit uses a generation AI to analyze the user's past avatar generation history and select the optimal generation algorithm based on that analysis. For example, the generation AI analyzes data on avatars the user has generated in the past and learns the user's preferences. The generation unit generates new avatars based on the preferences learned by the generation AI. The generation unit can also extract the characteristics of avatars that the user frequently uses and optimize the generation algorithm based on that. For example, the generation AI analyzes data on avatars that the user frequently uses and extracts their characteristics. The generation unit optimizes the generation algorithm based on the characteristics extracted by the generation AI and generates new avatars. Furthermore, the generation unit can also refer to data on avatars that the user has generated during specific events or seasons to generate avatars suitable for those seasons or events. For example, the generation AI analyzes data on avatars generated by the user during specific events or seasons and generates new avatars based on that analysis. This allows the generation unit to analyze the user's past avatar generation history and select the optimal generation algorithm. Some or all of the above-described processes in the generation unit are performed using the generation AI. For example, the generation unit inputs the user's past avatar generation history into the generation AI and has it select the optimal generation algorithm. The generation AI analyzes the user's past avatar generation history and selects the optimal generation algorithm based on that analysis. This allows the generation unit to analyze the user's past avatar generation history and select the optimal generation algorithm.

[0071] The generation unit can customize the generated avatar based on the user's current fashion and trends. For example, the generation unit can recognize the user's current clothing using a camera and generate an avatar in a similar style. The generation unit uses a generation AI to analyze the user's current fashion and trends and customize the generated avatar based on that analysis. For example, the generation AI recognizes the user's current clothing using a camera and generates an avatar in a similar style based on that analysis. The generation unit can also retrieve the latest fashion trends from a database and generate the avatar's clothing and accessories based on that analysis. For example, the generation AI retrieves the latest fashion trends from a database and generates the avatar's clothing and accessories based on that analysis. Furthermore, the generation unit can analyze fashion photos shared by the user on social media and generate an avatar that reflects that style. For example, the generation AI analyzes fashion photos shared by the user on social media and determines the avatar's style based on that analysis. This allows the generation unit to customize the generated avatar based on the user's current fashion and trends. Some or all of the above processes in the generation unit are performed using a generation AI. For example, the generation unit inputs the user's current fashion and trends into the generation AI, which then customizes the generated avatar. The generation AI analyzes the user's current fashion and trends and customizes the generated avatar based on that analysis. This allows the generation unit to customize the generated avatar based on the user's current fashion and trends.

[0072] The generation unit can estimate the user's emotions and determine the priority of avatars to generate based on those estimated emotions. For example, if the user is stressed, the generation unit will prioritize generating avatars that have a relaxing effect. The generation unit uses a generation AI to analyze the user's emotions and determine the priority of avatars to generate based on that analysis. For example, the generation AI analyzes the user's facial expressions and voice, and if it determines that the user is stressed, it will prioritize generating avatars that have a relaxing effect. The generation unit can also prioritize generating highly entertaining avatars if the user is having fun. For example, the generation AI analyzes the user's facial expressions and voice, and if it determines that the user is having fun, it will prioritize generating highly entertaining avatars. Furthermore, if the user is in a hurry, the generation unit can also prioritize generating avatars that are simple and can be generated quickly. For example, the generation AI analyzes the user's facial expressions and voice, and if it determines that the user is in a hurry, it will prioritize generating avatars that are simple and can be generated quickly. In this way, the generation unit can determine the priority of avatars to generate based on the user's emotions. Some or all of the above-described processes in the generation unit are performed using a generation AI. For example, the generation unit inputs the user's emotions into the generation AI, which then determines the priority of the avatars to be generated. The generation AI analyzes the user's emotions and determines the priority of the avatars to be generated based on that analysis. This allows the generation unit to determine the priority of the avatars to be generated based on the user's emotions.

[0073] The avatar generation unit can prioritize generating highly relevant styles based on the user's geographical location information. For example, if the user is in an urban area, the generation unit will generate an urban-style avatar. The generation unit uses a generation AI to analyze the user's geographical location information and prioritize generating highly relevant styles based on that information. For example, if the generation AI obtains the user's geographical location information and determines that the user is in an urban area, it will generate an urban-style avatar. The generation unit can also generate a casual and relaxed style avatar if the user is in a place with abundant nature. For example, if the generation AI obtains the user's geographical location information and determines that the user is in a place with abundant nature, it will generate a casual and relaxed style avatar. Furthermore, if the user is in a specific country or region, the generation unit can also generate an avatar based on the culture and fashion of that region. For example, if the generation AI obtains the user's geographical location information and determines that the user is in a specific country or region, it will generate an avatar based on the culture and fashion of that region. This allows the generation unit to prioritize generating highly relevant styles based on the user's geographical location information. Some or all of the above-described processes in the generation unit are performed using a generation AI. For example, the generation unit inputs the user's geographical location information into the generation AI and generates highly relevant styles. The generation AI analyzes the user's geographical location information and generates highly relevant styles based on it. This allows the generation unit to prioritize the generation of highly relevant styles based on the user's geographical location information.

[0074] The generation unit can analyze the user's social media activity and generate relevant styles when generating avatars. For example, the generation unit analyzes photos and posts shared by the user on social media and determines the avatar's style based on that. The generation unit uses a generation AI to analyze the user's social media activity and generate relevant styles based on that. For example, the generation AI analyzes photos and posts shared by the user on social media and determines the avatar's style based on that. The generation unit can also generate avatars by referencing the styles of influencers the user follows. For example, the generation AI analyzes posts from influencers the user follows and determines the avatar's style based on that. Furthermore, the generation unit can analyze the trends of online communities the user participates in and generate avatars based on that. For example, the generation AI analyzes the topics of online communities the user participates in and determines the avatar's style based on that. In this way, the generation unit can generate relevant styles based on the user's social media activity. Some or all of the above processes in the generation unit are performed using a generation AI. For example, the generation unit inputs the user's social media activity into the generation AI and has it generate relevant styles. The generation AI analyzes the user's social media activity and generates relevant styles based on that analysis. This allows the generation unit to generate relevant styles based on the user's social media activity.

[0075] The storage unit can estimate the user's emotions and select a storage format based on the estimated emotions. For example, if the user is relaxed, the storage unit will save the data in a standard format. The storage unit uses generative AI to analyze the user's emotions and select a storage format based on that analysis. For example, if the generative AI analyzes the user's facial expressions and voice and determines that the user is relaxed, it will save the data in a standard format. The storage unit can also select a lightweight, fast storage format if the user is in a hurry. For example, if the generative AI analyzes the user's facial expressions and voice and determines that the user is in a hurry, it will select a lightweight, fast storage format. Furthermore, if the user desires detailed customization, the storage unit can also save the data in an extensible format. For example, if the generative AI analyzes the user's facial expressions and voice and determines that detailed customization is desired, it will save the data in an extensible format. This allows the storage unit to select a storage format based on the user's emotions. Some or all of the above processing in the storage unit is performed using generative AI. For example, the storage unit inputs the user's emotions into a generating AI, which then selects a storage format. The generating AI analyzes the user's emotions and selects a storage format based on that analysis. This allows the storage unit to select a storage format based on the user's emotions.

[0076] The storage unit can determine the priority of saving avatars based on their usage frequency. For example, the storage unit can prioritize saving avatars that users frequently use. The storage unit uses a generation AI to analyze the usage frequency of avatars and determine the priority of saving based on that. For example, the generation AI analyzes the data of avatars that users frequently use and evaluates their usage frequency. The storage unit prioritizes saving frequently used avatars based on the usage frequency evaluated by the generation AI. The storage unit can also prioritize saving avatars that users use for specific events. For example, the generation AI analyzes the data of avatars that users use for specific events and evaluates their usage frequency. The storage unit prioritizes saving avatars used for specific events based on the usage frequency evaluated by the generation AI. Furthermore, the storage unit can postpone saving avatars that users have not used for a long period of time. For example, the generation AI analyzes the data of avatars that users have not used for a long period of time and evaluates their usage frequency. The storage unit postpones saving avatars that have not been used for a long period of time based on the usage frequency evaluated by the generation AI. This allows the storage unit to determine the priority of saving based on the frequency of avatar use. Some or all of the above-described processes in the storage unit are performed using a generating AI. For example, the storage unit inputs the frequency of avatar use into the generating AI and has it determine the priority of saving. The generating AI analyzes the frequency of avatar use and determines the priority of saving based on that. This allows the storage unit to determine the priority of saving based on the frequency of avatar use.

[0077] The storage unit can apply different storage algorithms depending on the avatar's category during storage. For example, the storage unit can save photorealistic avatars in high resolution and moe-style avatars in a lightweight format. The storage unit uses a generation AI to analyze the avatar's category and select an appropriate storage algorithm based on that. For example, the generation AI analyzes the avatar's category and selects an algorithm for saving in high resolution if it is a photorealistic avatar. The storage unit can also select an algorithm for saving in a lightweight format if it is a moe-style avatar. For example, the generation AI analyzes the avatar's category and selects an algorithm for saving in a lightweight format if it is a moe-style avatar. Furthermore, the storage unit can also save items such as clothing and accessories individually for later reuse. For example, the generation AI analyzes the avatar data and selects an algorithm for saving items such as clothing and accessories individually. This allows the storage unit to apply different storage algorithms depending on the avatar's category. Some or all of the above processing in the storage unit is performed using a generation AI. For example, the storage unit inputs the avatar category into the generation AI, which then selects an appropriate storage algorithm. The generation AI analyzes the avatar category and selects an appropriate storage algorithm based on that analysis. This allows the storage unit to apply different storage algorithms depending on the avatar category.

[0078] The storage unit can estimate the user's emotions and adjust the order in which avatars are saved based on the estimated emotions. For example, if the user is relaxed, the storage unit will prioritize saving frequently used avatars. The storage unit uses a generative AI to analyze the user's emotions and adjust the order in which avatars are saved based on that analysis. For example, the generative AI analyzes the user's facial expressions and voice, and if it determines that the user is relaxed, it will prioritize saving frequently used avatars. The storage unit can also prioritize saving recently used avatars if the user is in a hurry. For example, the generative AI analyzes the user's facial expressions and voice, and if it determines that the user is in a hurry, it will prioritize saving recently used avatars. Furthermore, the storage unit can also prioritize saving customized avatars if the user is having fun. For example, the generative AI analyzes the user's facial expressions and voice, and if it determines that the user is having fun, it will prioritize saving customized avatars. In this way, the storage unit can adjust the order in which avatars are saved based on the user's emotions. Some or all of the above processing in the storage unit is performed using a generative AI. For example, the storage unit inputs the user's emotions into a generating AI, which then adjusts the order in which the avatars are saved. The generating AI analyzes the user's emotions and adjusts the order of the saved avatars based on that analysis. This allows the storage unit to adjust the order of the saved avatars based on the user's emotions.

[0079] The storage unit can determine the priority of saving avatars based on when they were created. For example, the storage unit can prioritize saving recently created avatars. The storage unit uses a generation AI to analyze when avatars were created and determine the priority of saving based on that. For example, the generation AI analyzes when avatars were created and prioritizes saving recently created avatars. The storage unit can also prioritize saving avatars created during specific events or seasons. For example, the generation AI analyzes when avatars were created and prioritizes saving avatars created during specific events or seasons. Furthermore, the storage unit can postpone saving avatars that have not been used for a long time. For example, the generation AI analyzes when avatars were created and postpones saving avatars that have not been used for a long time. This allows the storage unit to determine the priority of saving based on when avatars were created. Some or all of the above processes in the storage unit are performed using the generation AI. For example, the storage unit inputs the creation date of avatars into the generation AI and has it determine the priority of saving. The generation AI analyzes when the avatar was created and determines the saving priority based on that. This allows the storage unit to determine the saving priority based on when the avatar was created.

[0080] The storage unit can adjust the order of saving avatars based on their relevance during the saving process. For example, the storage unit can prioritize saving avatars that the user frequently uses. The storage unit uses a generative AI to analyze the relevance of avatars and adjust the saving order accordingly. For example, the generative AI analyzes the data of avatars that the user frequently uses and evaluates their relevance. Based on the relevance evaluated by the generative AI, the storage unit prioritizes saving frequently used avatars. The storage unit can also prioritize saving avatars that the user uses for specific events. For example, the generative AI analyzes the data of avatars that the user uses for specific events and evaluates their relevance. Based on the relevance evaluated by the generative AI, the storage unit prioritizes saving avatars that are used for specific events. Furthermore, the storage unit can postpone saving avatars that the user has not used for a long period of time. For example, the generative AI analyzes the data of avatars that the user has not used for a long period of time and evaluates their relevance. Based on the relevance evaluated by the generative AI, the storage unit postpones saving avatars that have not been used for a long period of time. This allows the storage unit to adjust the order of saving avatars based on their relevance. Some or all of the above-described processes in the storage unit are performed using a generation AI. For example, the storage unit inputs the relationships between avatars into the generation AI and adjusts the storage order. The generation AI analyzes the relationships between avatars and adjusts the storage order based on that. In this way, the storage unit can adjust the storage order based on the relationships between avatars.

[0081] The dialogue unit can estimate the user's emotions and adjust the way it expresses itself based on those emotions. For example, if the user is nervous, the dialogue unit will use a calm voice and gentle expressions. The dialogue unit uses generative AI to analyze the user's emotions and adjust the way it expresses itself based on that analysis. For example, the generative AI analyzes the user's facial expressions and voice, and if it determines that the user is nervous, it will use a calm voice and gentle expressions. The dialogue unit can also use a cheerful voice and friendly expressions if the user is relaxed. For example, the generative AI analyzes the user's facial expressions and voice, and if it determines that the user is relaxed, it will use a cheerful voice and friendly expressions. Furthermore, if the user is in a hurry, the dialogue unit can use quick and concise expressions. For example, the generative AI analyzes the user's facial expressions and voice, and if it determines that the user is in a hurry, it will use quick and concise expressions. In this way, the dialogue unit can adjust the way it expresses itself based on the user's emotions. Some or all of the above processing in the dialogue unit is performed using generative AI. For example, the dialogue unit inputs the user's emotions into a generative AI, which then adjusts the way the dialogue is expressed. The generative AI analyzes the user's emotions and adjusts the way the dialogue is expressed based on that analysis. This allows the dialogue unit to adjust the way the dialogue is expressed based on the user's emotions.

[0082] The dialogue unit can analyze the user's past dialogue history and select the optimal dialogue algorithm during a conversation. For example, the dialogue unit prioritizes using expressions and phrases that the user has frequently used in the past. The dialogue unit uses generative AI to analyze the user's past dialogue history and select the optimal dialogue algorithm based on that analysis. For example, the generative AI analyzes the user's past dialogue history and learns expressions and phrases that the user has frequently used. The dialogue unit then conducts a conversation based on the expressions and phrases learned by the generative AI. The dialogue unit can also provide relevant information based on topics that the user has frequently discussed in the past. For example, the generative AI analyzes the user's past dialogue history and learns topics that the user has frequently discussed. The dialogue unit then provides relevant information based on what the generative AI has learned. Furthermore, the dialogue unit can prioritize conversations on specific topics based on the user's past dialogue history. For example, the generative AI analyzes the user's past dialogue history and learns conversations on specific topics. The dialogue unit then conducts a conversation based on the topics learned by the generative AI. This allows the dialogue unit to analyze the user's past dialogue history and select the optimal dialogue algorithm. Some or all of the above processing in the dialogue unit is performed using a generative AI. For example, the dialogue unit inputs the user's past dialogue history into the generative AI and has it select the optimal dialogue algorithm. The generative AI analyzes the user's past dialogue history and selects the optimal dialogue algorithm based on that analysis. This allows the dialogue unit to analyze the user's past dialogue history and select the optimal dialogue algorithm.

[0083] The dialogue unit can customize the content of the conversation based on the user's current situation and interests. For example, if the user is interested in the current weather, the dialogue unit will provide information about the weather. The dialogue unit uses generative AI to analyze the user's current situation and interests and customize the content of the conversation based on that analysis. For example, if the generative AI analyzes the user's current situation and interests and determines that the user is interested in the weather, it will provide information about the weather. The dialogue unit can also provide information related to an event if the user is participating in that event. For example, if the generative AI analyzes the user's current situation and interests and determines that the user is participating in that event, it will provide information related to that event. Furthermore, if the dialogue unit is interested in a particular news story, it can provide information about that news story. For example, if the generative AI analyzes the user's current situation and interests and determines that the user is interested in that news story, it will provide information about that news story. In this way, the dialogue unit can customize the content of the conversation based on the user's current situation and interests. Some or all of the above processing in the dialogue unit is performed using generative AI. For example, the dialogue unit inputs the user's current situation and interests into the generating AI, which then customizes the dialogue content. The generating AI analyzes the user's current situation and interests and customizes the dialogue content based on that. This allows the dialogue unit to customize the dialogue content based on the user's current situation and interests.

[0084] The dialogue unit can estimate the user's emotions and determine the priority of the dialogue based on those emotions. For example, if the user is stressed, the dialogue unit will prioritize relaxing dialogue. The dialogue unit uses generative AI to analyze the user's emotions and determine the priority of the dialogue based on that analysis. For example, the generative AI analyzes the user's facial expressions and voice, and if it determines that the user is stressed, it will prioritize relaxing dialogue. The dialogue unit can also prioritize entertaining dialogue if the user is enjoying themselves. For example, the generative AI analyzes the user's facial expressions and voice, and if it determines that the user is enjoying themselves, it will prioritize entertaining dialogue. Furthermore, the dialogue unit can prioritize quick and concise dialogue if the user is in a hurry. For example, the generative AI analyzes the user's facial expressions and voice, and if it determines that the user is in a hurry, it will prioritize quick and concise dialogue. In this way, the dialogue unit can determine the priority of the dialogue based on the user's emotions. Some or all of the above processing in the dialogue unit is performed using generative AI. For example, the dialogue unit inputs the user's emotions into a generative AI, which then determines the priority of the dialogue. The generative AI analyzes the user's emotions and determines the priority of the dialogue based on that analysis. This allows the dialogue unit to determine the priority of the dialogue based on the user's emotions.

[0085] The dialogue unit can prioritize providing highly relevant dialogue content based on the user's geographical location information during a conversation. For example, if the user is in a specific region, the dialogue unit will provide information related to that region. The dialogue unit uses generative AI to analyze the user's geographical location information and prioritize providing highly relevant dialogue content based on that analysis. For example, the generative AI acquires the user's geographical location information, and if it determines that the user is in a specific region, it provides information related to that region. The dialogue unit can also provide information about the user's travel destination if the user is traveling. For example, the generative AI acquires the user's geographical location information, and if it determines that the user is traveling, it provides information about the travel destination. Furthermore, if the user is participating in a specific event, the dialogue unit can also provide information related to that event. For example, the generative AI acquires the user's geographical location information, and if it determines that the user is participating in a specific event, it provides information related to that event. This allows the dialogue unit to prioritize providing highly relevant dialogue content based on the user's geographical location information. Some or all of the above processing in the dialogue unit is performed using generative AI. For example, the dialogue unit inputs the user's geographical location information into the generative AI and causes it to provide highly relevant dialogue content. The generating AI analyzes the user's geographical location information and provides highly relevant dialogue based on that information. This allows the dialogue unit to prioritize providing dialogue that is relevant to the user's geographical location.

[0086] The dialogue unit can analyze the user's social media activity during a conversation and provide relevant dialogue content. For example, the dialogue unit can determine dialogue content based on posts the user has shared on social media. The dialogue unit uses generative AI to analyze the user's social media activity and provide relevant dialogue content based on that analysis. For example, the generative AI analyzes posts the user has shared on social media and determines dialogue content based on that analysis. The dialogue unit can also provide dialogue content based on posts from influencers the user follows. For example, the generative AI analyzes posts from influencers the user follows and determines dialogue content based on that analysis. Furthermore, the dialogue unit can also provide dialogue content based on topics in online communities the user participates in. For example, the generative AI analyzes topics in online communities the user participates in and determines dialogue content based on that analysis. This allows the dialogue unit to provide relevant dialogue content based on the user's social media activity. Some or all of the above processing in the dialogue unit is performed using generative AI. For example, the dialogue unit inputs the user's social media activity into the generative AI and has it provide relevant dialogue content. The generative AI analyzes the user's social media activity and provides relevant dialogue content based on that analysis. This allows the dialogue unit to provide relevant dialogue content based on the user's social media activity.

[0087] The display unit can estimate the user's emotions and adjust the display method based on the estimated emotions. For example, if the user is nervous, the display unit will display in calm colors and a simple design. The display unit uses generative AI to analyze the user's emotions and adjust the display method based on that analysis. For example, the generative AI analyzes the user's facial expressions and voice, and if it determines that the user is nervous, it will display in calm colors and a simple design. The display unit can also display in bright colors and a friendly design if the user is relaxed. For example, the generative AI analyzes the user's facial expressions and voice, and if it determines that the user is relaxed, it will display in bright colors and a friendly design. Furthermore, if the user is in a hurry, the display unit can display in a concise design to quickly provide information. For example, the generative AI analyzes the user's facial expressions and voice, and if it determines that the user is in a hurry, it will display in a concise design to quickly provide information. In this way, the display unit can adjust the display method based on the user's emotions. Some or all of the above processing in the display unit is performed using generative AI. For example, the display unit inputs the user's emotions into the generative AI and has it adjust the display method. The generating AI analyzes the user's emotions and adjusts the display method accordingly. This allows the display unit to adjust its display method based on the user's emotions.

[0088] The display unit can analyze the user's past viewing history and select the optimal display algorithm when displaying information. For example, the display unit may prioritize display styles that the user has previously preferred. The display unit uses a generative AI to analyze the user's past viewing history and select the optimal display algorithm based on that analysis. For example, the generative AI analyzes the user's past viewing history and learns the display styles that the user has preferred. The display unit then displays information based on the display styles learned by the generative AI. The display unit can also prioritize displaying relevant information based on information that the user has frequently viewed in the past. For example, the generative AI analyzes the user's past viewing history and learns the information that has been frequently viewed. The display unit then prioritizes displaying relevant information based on the information learned by the generative AI. Furthermore, the display unit can also prioritize displaying information related to specific topics based on the user's past viewing history. For example, the generative AI analyzes the user's past viewing history and learns information related to specific topics. The display unit then displays information based on the topics learned by the generative AI. This allows the display unit to analyze the user's past viewing history and select the optimal display algorithm. Some or all of the above processing in the display unit is performed using a generating AI. For example, the display unit inputs the user's past viewing history into the generating AI and has it select the optimal display algorithm. The generating AI analyzes the user's past viewing history and selects the optimal display algorithm based on that analysis. This allows the display unit to analyze the user's past viewing history and select the optimal display algorithm.

[0089] The display unit can customize the displayed content based on the user's current situation and interests. For example, if the user is interested in the current weather, the display unit will prioritize displaying weather-related information. The display unit uses generative AI to analyze the user's current situation and interests and customize the displayed content accordingly. For example, if the generative AI analyzes the user's current situation and interests and determines that the user is interested in the weather, it will prioritize displaying weather-related information. The display unit can also prioritize displaying information related to a specific event if the user is participating in that event. For example, if the generative AI analyzes the user's current situation and interests and determines that the user is participating in that event, it will prioritize displaying information related to that event. Furthermore, if the user is interested in a specific news story, the display unit can also prioritize displaying information related to that news story. For example, if the generative AI analyzes the user's current situation and interests and determines that the user is interested in that news story, it will prioritize displaying information related to that news story. In this way, the display unit can customize the displayed content based on the user's current situation and interests. Some or all of the above processing in the display unit is performed using generative AI. For example, the display unit inputs the user's current situation and interests into a generating AI, which then customizes the displayed content. The generating AI analyzes the user's current situation and interests and customizes the displayed content based on that analysis. This allows the display unit to customize the displayed content based on the user's current situation and interests.

[0090] The display unit can estimate the user's emotions and determine the display priority based on the estimated emotions. For example, if the user is stressed, the display unit will prioritize displaying information that has a relaxing effect. The display unit uses generative AI to analyze the user's emotions and determine the display priority based on that analysis. For example, the generative AI analyzes the user's facial expressions and voice, and if it determines that the user is stressed, it will prioritize displaying information that has a relaxing effect. The display unit can also prioritize displaying highly entertaining information if the user is enjoying themselves. For example, the generative AI analyzes the user's facial expressions and voice, and if it determines that the user is enjoying themselves, it will prioritize displaying highly entertaining information. Furthermore, the display unit can also prioritize displaying quick and concise information if the user is in a hurry. For example, the generative AI analyzes the user's facial expressions and voice, and if it determines that the user is in a hurry, it will prioritize displaying quick and concise information. In this way, the display unit can determine the display priority based on the user's emotions. Some or all of the above processing in the display unit is performed using generative AI. For example, the display unit inputs the user's emotions into a generating AI, which then determines the display priority. The generating AI analyzes the user's emotions and determines the display priority based on that analysis. This allows the display unit to determine the display priority based on the user's emotions.

[0091] The display unit can prioritize displaying content that is highly relevant to the user, taking into account the user's geographical location information. For example, if the user is in a specific region, the display unit will prioritize displaying information related to that region. The display unit uses a generation AI to analyze the user's geographical location information and, based on that, prioritizes displaying content that is highly relevant. For example, the generation AI acquires the user's geographical location information, and if it determines that the user is in a specific region, it will prioritize displaying information related to that region. The display unit can also prioritize displaying information related to the user's travel destination if the user is traveling. For example, the generation AI acquires the user's geographical location information, and if it determines that the user is traveling, it will prioritize displaying information related to the travel destination. Furthermore, if the user is participating in a specific event, the display unit can also prioritize displaying information related to that event. For example, the generation AI acquires the user's geographical location information, and if it determines that the user is participating in a specific event, it will prioritize displaying information related to that event. In this way, the display unit can prioritize displaying content that is highly relevant to the user's geographical location information. Some or all of the above processing in the display unit is performed using a generation AI. For example, the display unit inputs the user's geographical location information into a generating AI, which then provides highly relevant display content. The generating AI analyzes the user's geographical location information and provides highly relevant display content based on that analysis. This allows the display unit to prioritize providing highly relevant display content based on the user's geographical location information.

[0092] The display unit can analyze the user's social media activity and provide relevant display content when displaying content. For example, the display unit determines the display content based on posts shared by the user on social media. The display unit uses a generative AI to analyze the user's social media activity and provide relevant display content based on that analysis. For example, the generative AI analyzes posts shared by the user on social media and determines the display content based on that analysis. The display unit can also provide display content based on posts from influencers followed by the user. For example, the generative AI analyzes posts from influencers followed by the user and determines the display content based on that analysis. Furthermore, the display unit can also provide display content based on topics in online communities in which the user participates. For example, the generative AI analyzes topics in online communities in which the user participates and determines the display content based on that analysis. In this way, the display unit can provide relevant display content based on the user's social media activity. Some or all of the above processing in the display unit is performed using a generative AI. For example, the display unit inputs the user's social media activity into the generative AI and causes it to provide relevant display content. The generative AI analyzes the user's social media activity and provides relevant display content based on that analysis. This allows the display unit to provide relevant content based on the user's social media activity. === Hard Collateral 1-1 === Each of the multiple elements described above, including the generation unit, storage unit, dialogue unit, and display unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the generation unit is implemented by the processor 46 of the smart device 14, which receives user photos and videos as input and generates a 3D avatar based on them. The storage unit is implemented by the specific processing unit 290 of the data processing unit 12, which saves the generated 3D avatar to cloud storage. The dialogue unit is implemented by the specific processing unit 290 of the data processing unit 12, which acts as an AI dialogue assistant with functions such as everyday conversation and news provision. The display unit is implemented by the control unit 46A of the smart device 14, which displays the 3D avatar AI dialogue assistant using AR glasses. === Hard Collateral 1-2 === Each of the multiple elements described above, including the generation unit, storage unit, dialogue unit, and display unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the generation unit is implemented by the processor 46 of the smart glasses 214, which receives user photos and videos as input and generates a 3D avatar based on them. The storage unit is implemented by the specific processing unit 290 of the data processing unit 12, which saves the generated 3D avatar to cloud storage. The dialogue unit is implemented by the specific processing unit 290 of the data processing unit 12, which performs an AI dialogue assistant with functions such as everyday conversation and news provision. The display unit is implemented by the control unit 46A of the smart glasses 214, which displays the 3D avatar AI dialogue assistant using AR glasses. === Hard Collateral 1-3 === Each of the multiple elements described above, including the generation unit, storage unit, dialogue unit, and display unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the generation unit is implemented by the processor 46 of the headset terminal 314, which receives user photos and videos as input and generates a 3D avatar based on them. The storage unit is implemented by the specific processing unit 290 of the data processing unit 12, which saves the generated 3D avatar to cloud storage. The dialogue unit is implemented by the specific processing unit 290 of the data processing unit 12, which performs AI dialogue assistance with functions such as everyday conversation and news provision. The display unit is implemented by the control unit 46A of the headset terminal 314, which displays the 3D avatar AI dialogue assistant using AR glasses. === Hard Collateral 1-4 === Each of the multiple elements described above, including the generation unit, storage unit, dialogue unit, and display unit, is implemented in, for example, at least one of the robot 414 and the data processing unit 12. For example, the generation unit is implemented by the processor 46 of the robot 414, which receives user photos and videos as input and generates a 3D avatar based on them. The storage unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12, which saves the generated 3D avatar to cloud storage. The dialogue unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12, which acts as an AI dialogue assistant with functions such as everyday conversation and news provision. The display unit is implemented by, for example, the control unit 46A of the robot 414, which displays the 3D avatar AI dialogue assistant using AR glasses.

[0093] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0094] The generation unit can analyze a user's past avatar creation history and learn their preferences and trends. For example, it can analyze the style and characteristics of avatars a user has created in the past and generate a new avatar based on that. Using generation AI, the generation unit can learn the user's preference trends and optimize avatar design accordingly. It can also refer to data on avatars a user has created during specific events or seasons to generate avatars suitable for those seasons or events. In this way, the generation unit can leverage a user's past avatar creation history to provide more personalized avatars.

[0095] The generation unit can estimate the user's emotions and adjust the avatar's facial expressions and movements in real time based on the estimated emotions. For example, if the user is happy, the generation unit can display a smile on the avatar. The generation unit uses generation AI to analyze the user's facial expressions and voice and adjusts the avatar's facial expressions and movements based on that. Furthermore, if the user is sad, the generation unit can display a sad expression on the avatar. In addition, if the user is surprised, the generation unit can display a surprised expression on the avatar. In this way, the generation unit can adjust the avatar's facial expressions and movements in real time according to the user's emotions.

[0096] The storage unit can save a user's avatar creation history to cloud storage, making it accessible from other devices. For example, the storage unit can save avatars created by a user on their smartphone to the cloud, making them accessible from PCs and tablets. The storage unit can use generation AI to optimize and efficiently manage avatar data stored in cloud storage. Furthermore, the storage unit can integrate and centrally manage avatars created by a user on different devices. This allows the storage unit to enable users to access and use their avatars from any device.

[0097] The dialogue unit can estimate the user's emotions and adjust the tone and content of the conversation based on those estimates. For example, if the user is tired, the dialogue unit can engage in conversation in a calm, relaxing tone. The dialogue unit uses generative AI to analyze the user's facial expressions and voice and adjust the tone and content of the conversation accordingly. Furthermore, if the user is excited, the dialogue unit can engage in conversation in an energetic tone. In addition, if the user is sad, the dialogue unit can engage in conversation in a comforting tone. In this way, the dialogue unit can adjust the tone and content of the conversation according to the user's emotions.

[0098] The display unit can utilize the user's geographical location information to display relevant information. For example, if the user is traveling, the display unit can display tourist information and restaurant information for their travel destination. The display unit uses a generation AI to analyze the user's geographical location information and provides relevant information based on that analysis. Furthermore, if the user is participating in a specific event, the display unit can display information related to that event. Additionally, if the user is in a specific region, the display unit can display weather and traffic information for that region. In this way, the display unit can provide relevant information based on the user's geographical location information.

[0099] The generation unit can analyze a user's social media activity and suggest relevant avatar styles. For example, it can analyze photos and posts shared by a user on social media and suggest avatar styles based on that analysis. The generation unit uses generation AI to analyze a user's social media activity and optimize avatar styles based on that analysis. It can also generate avatars by referencing the styles of influencers the user follows. Furthermore, the generation unit can analyze trends in online communities the user participates in and suggest avatar styles based on that analysis. In this way, the generation unit can suggest relevant avatar styles based on the user's social media activity.

[0100] The dialogue unit can analyze the user's past conversation history and customize the conversation content based on the user's preferences and interests. For example, the dialogue unit can prioritize topics that the user has enjoyed discussing in the past. The dialogue unit uses generative AI to analyze the user's past conversation history and optimize the conversation content accordingly. The dialogue unit can also provide relevant advice based on what the user has previously consulted. Furthermore, the dialogue unit can provide information about news and events that the user has shown interest in in the past. In this way, the dialogue unit can customize the conversation content based on the user's past conversation history.

[0101] The display unit can estimate the user's emotions and adjust the displayed content based on those emotions. For example, if the user is relaxed, the display unit can display information in calm colors and a simple design. The display unit uses generative AI to analyze the user's facial expressions and voice and adjust the displayed content accordingly. Furthermore, if the user is excited, the display unit can display information in vibrant colors and a dynamic design. In addition, if the user is sad, the display unit can display information in calm colors and a simple design. In this way, the display unit can adjust the displayed content according to the user's emotions.

[0102] The generation unit can customize the avatar's style based on the user's current fashion and trends. For example, the generation unit can recognize the clothing the user is currently wearing using a camera and generate an avatar with a similar style. The generation unit uses generation AI to analyze the user's current fashion and trends and optimize the avatar's style accordingly. The generation unit can also retrieve the latest fashion trends from a database and generate clothing and accessories for the avatar based on them. Furthermore, the generation unit can analyze fashion photos shared by the user on social media and generate an avatar that reflects that style. In this way, the generation unit can customize the avatar's style based on the user's current fashion and trends.

[0103] The dialogue unit can estimate the user's emotions and prioritize conversations based on those emotions. For example, if the user is stressed, the dialogue unit can prioritize conversations that promote relaxation. The dialogue unit uses generative AI to analyze the user's facial expressions and voice and prioritize conversations based on that. Furthermore, if the user is enjoying themselves, the dialogue unit can prioritize entertaining conversations. Additionally, if the user is in a hurry, the dialogue unit can prioritize quick and concise conversations. In this way, the dialogue unit can prioritize conversations based on the user's emotions.

[0104] The following briefly describes the processing flow for example form 2.

[0105] Step 1: The generation unit generates 3D avatars. The generation unit generates 3D avatars in various styles, such as photorealistic and moe-style. Using generation AI, the generation unit receives user photos and videos as input and generates 3D avatars based on them. For example, the generation AI analyzes the user's facial features and generates a realistic 3D model. The generation unit can also use generation AI to generate an unlimited number of items such as clothes, accessories, shoes, and other accessories. For example, the generation AI generates clothes and accessories in various designs based on the user's preferences and trends. Step 2: The storage unit saves and outputs the 3D avatar generated by the generation unit. The storage unit saves the 3D avatar in a major format such as VRM. The storage unit saves the generated 3D avatar to cloud storage so that the user can access it at any time. The storage unit can also save the generated 3D avatar to a local device. Step 3: The dialogue unit acts as an AI conversational assistant using the 3D avatar saved by the storage unit. The dialogue unit acts as an AI conversational assistant with functions such as everyday conversation, consultation, news provision, ordering, schedule management, and translation. The dialogue unit uses generative AI to generate appropriate responses in response to user input. For example, in response to a user's question, the dialogue unit uses generative AI to generate an appropriate answer and displays it through the 3D avatar. Step 4: The display unit shows the AI ​​conversational assistant, which is operated by the dialogue unit, through the AR glasses. The display unit uses the AR glasses to display the 3D avatar of the AI ​​conversational assistant. The display unit overlays the 3D avatar into the user's field of view, allowing for real-time interaction. If multiple people are using the same app, the display unit can also overlay the avatar onto how others see them and synchronize their full-body movements.

[0106] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0107] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (for example, still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or Naive Bayes, and can perform a variety of operations, but is not limited to these examples. Furthermore, AI may also be an AI agent. Also, when the operations described above are performed by AI, the operations may be performed partially or entirely by AI, but is not limited to these examples. Additionally, operations performed by AI, including generative AI, may be replaced by rule-based operations, and rule-based operations may be replaced by operations performed by AI, including generative AI.

[0108] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, 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.

[0109] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0110] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0111] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0112] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0113] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0114] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0115] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0116] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0117] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0118] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0119] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0120] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0121] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0122] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0123] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0124] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0125] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0126] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0127] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0128] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0129] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0130] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0131] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0132] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0133] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0134] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0135] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0136] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0137] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0138] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0139] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0140] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

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

[0142] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0143] As shown in Figure 7, the 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.

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

[0145] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

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

[0147] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0148] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0149] The controlled 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 robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0150] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0151] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0152] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0153] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0154] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0155] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0156] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0157] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0158] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0159] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0160] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0161] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0162] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0163] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0164] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0165] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0166] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0167] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0168] 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.

[0169] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0170] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0171] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0172] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0173] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0174] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0175] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0176] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0177] [Explanation of Symbols]

[0178] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A generation unit that generates 3D avatars, A storage unit that saves and outputs the 3D avatar generated by the generation unit, A dialogue unit that performs AI dialogue assistance using the 3D avatar stored by the storage unit, A display unit that displays the AI ​​dialogue assistant performed by the aforementioned dialogue unit through AR glasses, Equipped with A system characterized by the following features.

2. The generating unit is Generate 3D avatars in multiple styles, from photorealistic to moe-style. The system according to feature 1.

3. The generating unit is Generate multiple items of clothing, accessories, shoes, etc. The system according to feature 1.

4. The aforementioned storage unit is Save and export 3D avatars in major VRM formats. The system according to feature 1.

5. The aforementioned dialogue unit, This AI conversational assistant offers multiple functions, including everyday conversation, advice, news delivery, ordering, schedule management, and translation. The system according to feature 1.

6. The aforementioned display unit is Displaying a 3D avatar AI conversational assistant through AR glasses. The system according to feature 1.

7. The aforementioned display unit is If multiple people are using the same app, an avatar will be overlaid on the user's avatar as seen by others, and their full-body movements will be synchronized. The system according to feature 1.

8. The generating unit is It estimates the user's emotions and automatically adjusts the avatar's style based on those estimated emotions. The system according to feature 1.

Images