system

Abstract

The system according to this embodiment aims to generate a virtual human based on the data of a deceased person and to allow interaction with the deceased person in a metaverse space. [Solution] The system according to the embodiment comprises a data collection unit, a generation unit, and a dialogue unit. The data collection unit collects data such as appearance, voice, and episodes. The generation unit generates a 3D virtual human based on the data collected by the data collection unit. The dialogue unit engages in dialogue with the virtual human generated by the generation unit in a metaverse space.

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 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 character of the chatbot, 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, there is a problem that it is difficult to realize interaction with the deceased and it is impossible to feel the memory and presence of the deceased. [[ID=3�]]

[0005] The system according to the embodiment aims to generate a virtual human based on the data of the deceased and interact with the deceased in the metaverse space.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a data collection unit, a generation unit, and a dialogue unit. The data collection unit collects data such as appearance, voice, and episodes. The generation unit generates a 3D virtual human based on the data collected by the data collection unit. The dialogue unit interacts with the virtual human generated by the generation unit in a metaverse space. [Effects of the Invention]

[0007] The system according to this embodiment generates a virtual human based on the data of a deceased person and allows interaction with the deceased person in a metaverse space. [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 labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between multiple computers. Examples of communication standards applicable 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 generates a 3D virtual human from data recorded and acquired during the person's lifetime, and enables conversation with the deceased in a metaverse space after death. This system collects data such as appearance, voice, and episodes, generates a 3D virtual human, and can engage in dialogue in a metaverse space. For example, this system collects data on a person who will be deceased during their lifetime. This data includes appearance (facial expressions, skeletal structure, movement patterns, habits, etc.), voice (voice, speaking style, tone, catchphrases, etc.), and episodes (past events, hobbies, etc.). Next, a 3D virtual human is generated based on the collected data. The generated virtual human reproduces the appearance, voice, and speaking style of the deceased, enabling dialogue in a metaverse space. Furthermore, the acquired episodes are stored in a database, and an agent is constructed that speaks by referring to past events. This allows for a reunion with the deceased and enjoyment of conversation. For example, this system collects data on a person who will be deceased during their lifetime. At this time, appearance, voice, and episodes are recorded in detail through interviews and photography. For example, photographs and videos are taken from various angles to record facial expressions and movements. The system also records voice data, capturing the voice, speaking style, tone, and verbal tics. Furthermore, it collects anecdotes about past events and hobbies through interviews. Next, a 3D virtual human is generated based on the collected data. Specifically, 3DCG software is used for modeling, and UVs, textures, bones, weights, and materials are set. Lip-sync technology is used to link the voice and movement. In addition, speech synthesis technology is used to generate a voice that closely resembles the real person based on the collected voice data. The generated virtual human can then converse in the metaverse space. Specifically, a large-scale language model is fine-tuned to build a conversational generative AI chat. The quirks and characteristics acquired during the interviews are used to learn, and the deceased's basic information and anecdotes are stored in a database. This allows for natural conversation by referring to the database as needed. Finally, the user puts on a VR set and microphone, and can reunite with the virtual deceased in the metaverse space and enjoy a conversation.Based on the user's choices, the system references a database based on their relationship with the deceased and provides appropriate conversation. This allows users to heal grief and regret and share memories through reconnecting with the deceased. The system can recreate the appearance, voice, and speaking style of the deceased, enabling dialogue in a metaverse space.

[0029] The system according to this embodiment comprises a data collection unit, a generation unit, and a dialogue unit. The data collection unit collects data such as appearance, voice, and episodes. The data collection unit records appearance, voice, and episodes in detail, for example, through interviews or photography. For example, the data collection unit takes photos and videos from various angles and records facial expressions and movements. The data collection unit can also record voice data, recording voice, speaking style, tone, and catchphrases. The data collection unit can also collect episodes such as past events and hobbies through interviews. The generation unit generates a 3D virtual human based on the collected data. The generation unit performs modeling using 3DCG software, for example, and sets UVs, textures, bones, weights, and materials. The generation unit can also link voice and movement using lip-sync technology. The generation unit can also generate a voice that closely resembles the real person based on the collected voice data using speech synthesis technology. Some or all of the above-described processing in the generation unit may be performed using a generation AI, or it may be performed without using a generation AI. For example, the generation unit inputs collected data into a generation AI, which then generates a 3D virtual human. The dialogue unit engages in dialogue with the generated virtual human in a metaverse space. The dialogue unit can, for example, fine-tune a large-scale language model to build a conversational generation AI chat. The dialogue unit can also learn habits and characteristics acquired during interviews and store basic information and episodes of the deceased as a database. The dialogue unit can also engage in natural dialogue by referring to the database as needed. Some or all of the above-described processes in the dialogue unit may be performed using AI or not. For example, the dialogue unit can have the AI ​​perform a dialogue between the generated virtual human and the user. As a result, the system according to the embodiment can collect data such as appearance, voice, and episodes, generate a 3D virtual human, and engage in dialogue in a metaverse space.

[0030] The data collection unit collects data such as appearance, voice, and anecdotes. For example, the data collection unit meticulously records appearance, voice, and anecdotes through interviews and photography. Specifically, the data collection unit takes photos and videos of the subject from various angles, meticulously recording facial expressions and movements. This includes using high-resolution cameras and multiple cameras to acquire three-dimensional information about the subject. Furthermore, the data collection unit records audio data, meticulously documenting voice tone, speaking style, and verbal tics. This includes using high-quality microphones to acquire clear audio data. The data collection unit can also collect anecdotes about the subject's past events, hobbies, and special skills through interviews. Interviews should ideally be conducted in a relaxed environment to elicit natural speech and facial expressions from the subject. This allows the data collection unit to gain a detailed understanding of the subject's personality and characteristics. Furthermore, the data collection unit centrally manages the collected data, making it available for subsequent processing. For example, the collected data is stored in cloud storage, making it accessible to the generation and dialogue units. This allows the data collection unit to collect data efficiently and effectively, improving the overall system performance.

[0031] The generation unit generates a 3D virtual human based on collected data. For example, the generation unit uses 3DCG software to perform modeling and sets up UVs, textures, bones, weights, and materials. Specifically, it first creates the basic shape of the 3D model based on photographs or videos of the subject. Next, it performs UV mapping and applies textures. Textures are used to reproduce the texture of the subject's skin and the patterns of their clothing. Furthermore, bones are set to give the model movement. Bones represent the joints and skeleton of the model and are important for achieving natural movement. Weight setting associates the bones with the vertices of the model, so that the model deforms according to the movement of the bones. Material setting adjusts the texture and reflectivity of the model's surface to achieve a realistic appearance. The generation unit can also link voice and movement using lip-sync technology. Lip-sync technology controls the model's mouth movements based on audio data to reproduce natural speech. The generation unit can also generate a voice that closely resembles the real person based on collected audio data using speech synthesis technology. Speech synthesis technology learns the characteristics of the subject's voice and reproduces natural pronunciation and intonation. Some or all of the above-described processes in the generation unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the generation unit can input collected data into a generation AI and have the generation AI perform the generation of a 3D virtual human. The generation AI can learn from a vast dataset and generate highly accurate 3D models. This allows the generation unit to generate 3D virtual humans efficiently and with high accuracy, improving the overall performance of the system.

[0032] The dialogue unit interacts with the generated virtual human in a metaverse space. For example, the dialogue unit fine-tunes a large-scale language model to build a conversational generative AI chat. Specifically, the dialogue unit learns the habits and characteristics of the subject based on collected data. This includes learning the subject's way of speaking, facial expressions, gestures, and other characteristics. The dialogue unit can also store basic information and anecdotes about the deceased as a database. The database includes information such as the subject's background, hobbies, and special skills. The dialogue unit can conduct natural conversations by referring to the database as needed. For example, if the user asks a question about a specific anecdote, the dialogue unit will refer to the database and generate an appropriate answer. Some or all of the above processing in the dialogue unit may be performed using AI or not. For example, the dialogue unit can have AI perform conversations between the generated virtual human and the user. The AI ​​uses natural language processing technology to analyze the user's statements and generate appropriate responses. This allows the dialogue unit to achieve natural and realistic conversations and provide a high level of user satisfaction. Furthermore, the dialogue unit can collect user feedback and continuously improve the accuracy and effectiveness of the dialogue content. For example, it can revise the content and expression of the dialogue based on user feedback to achieve a more natural and engaging conversation. In addition, the dialogue unit can interact with users using multiple communication methods. For example, it can provide users with diverse dialogue options by using not only dialogue within the metaverse space but also voice calls and text chat. This allows the dialogue unit to provide users with a flexible and high-quality dialogue experience and improve the overall performance of the system.

[0033] The generation unit can perform modeling using 3DCG software and set UVs, textures, bones, weights, and materials. For example, the generation unit can perform detailed modeling of a virtual human using 3DCG software. The generation unit can perform UV mapping and set textures. The generation unit can also place bones and adjust weights. The generation unit can set materials and adjust the texture of the virtual human. In this way, the generation unit can perform detailed modeling of a virtual human using 3DCG software. Some or all of the above processes in the generation unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the generation unit can input 3DCG software into a generation AI and have the generation AI execute each step of the modeling process.

[0034] The generation unit can link voice and movement using lip-sync technology. For example, the generation unit analyzes voice data using a voice analysis algorithm. The generation unit can model mouth movements and link them with voice data. The generation unit can also adjust the synchronization of voice and movement to achieve natural lip-sync. In this way, the generation unit can generate a virtual human with linked voice and movement using lip-sync technology. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input voice data into a generation AI and have the generation AI perform lip-sync generation.

[0035] The generation unit can generate a voice that closely resembles the original person's voice based on collected voice data using speech synthesis technology. The generation unit can generate voice data using, for example, text-to-speech (TTS) technology. The generation unit can also generate a voice that closely resembles the original person's voice based on collected voice data using voice cloning technology. The generation unit can also adjust the tone and manner of speaking to generate a natural-sounding voice. In this way, the generation unit can generate a voice that closely resembles the original person's voice using speech synthesis technology. Some or all of the above-described processes in the generation unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the generation unit can input voice data into a generation AI and have the generation AI perform the voice generation.

[0036] The dialogue unit can fine-tune a large-scale language model and build a conversational generative AI chat. The dialogue unit can perform fine-tuning and adapt to specific dialogue scenarios. The dialogue unit can also adjust the flow of dialogue and the timing of responses to achieve natural dialogue. Thus, the dialogue unit can build a conversational generative AI chat by fine-tuning a large-scale language model. Some or all of the above processing in the dialogue unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the dialogue unit can input a large-scale language model into a generative AI and leave the fine-tuning to the generative AI.

[0037] The dialogue unit can learn habits and characteristics acquired during interviews and store basic information and anecdotes about the deceased in a database. For example, the dialogue unit can learn habits and characteristics such as speech patterns, gestures, and facial expressions acquired during interviews. The dialogue unit can store basic information and anecdotes about the deceased in a database and refer to it as needed. The dialogue unit can also engage in natural conversation while referring to the database. In this way, the dialogue unit can store basic information and anecdotes about the deceased in a database by learning habits and characteristics acquired during interviews. Some or all of the above processing in the dialogue unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the dialogue unit can input data acquired during interviews into a generative AI and have the generative AI perform the construction of the database.

[0038] The dialogue unit can engage in natural conversations by referring to a database as needed. For example, the dialogue unit can refer to appropriate episodes and information from the database according to the flow of the conversation. The dialogue unit can generate natural responses based on the information stored in the database. The dialogue unit can also provide appropriate information according to the context of the conversation. In this way, the dialogue unit can engage in natural conversations by referring to a database as needed. Some or all of the above processing in the dialogue unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the dialogue unit can input the context of the conversation into a generative AI and have the generative AI perform the referencing of appropriate information and the generation of responses.

[0039] The data collection unit can analyze the user's past behavioral history and select the optimal data collection method. For example, the data collection unit can create scenarios for collecting natural movements based on activities the user has frequently performed in the past. The data collection unit can collect voice data using devices the user has preferred to use in the past. The data collection unit can also analyze the user's past behavioral patterns and select the optimal collection time. In this way, the data collection unit can select the optimal data collection method by analyzing the user's past behavioral history. Some or all of the above processing in the data collection unit may be performed using generative AI, or not. For example, the data collection unit can input the user's behavioral history data into a generative AI and have the generative AI select the optimal data collection method.

[0040] The data collection unit can filter data based on the user's current lifestyle and areas of interest during data collection. For example, the data collection unit can prioritize collecting episodes related to topics the user is currently interested in. The data collection unit can adjust the types of data collected according to the user's lifestyle. The data collection unit can also select the content of episodes to collect based on the user's areas of interest. This allows the data collection unit to collect highly relevant data by filtering based on the user's current lifestyle and areas of interest. Some or all of the above processing in the data collection unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the data collection unit can input data on the user's lifestyle and areas of interest into a generative AI and leave the filtering to the generative AI.

[0041] The data collection unit can prioritize the collection of highly relevant data by considering the user's geographical location information during data collection. For example, when a user is in a specific location, the data collection unit can collect episodes related to that location. Based on the user's place of residence, the data collection unit can prioritize the collection of region-related data. If a user is traveling, the data collection unit can also collect episodes related to their travel destination. In this way, the data collection unit can prioritize the collection of highly relevant data by considering the user's geographical location information. Some or all of the above processing in the data collection unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the data collection unit can input the user's geographical location information into a generative AI and have the generative AI perform the collection of highly relevant data.

[0042] The data collection unit can analyze a user's social media activity and collect relevant data during data collection. For example, the data collection unit can collect relevant episodes based on the content a user frequently posts on social media. The data collection unit can analyze a user's social media friendships and collect episodes related to their friends. The data collection unit can also collect data on topics of interest based on a user's social media activity history. In this way, the data collection unit can collect relevant data by analyzing a user's social media activity. Some or all of the above processing in the data collection unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the data collection unit can input the user's social media activity data into a generative AI and have the generative AI perform the collection of relevant data.

[0043] The generation unit can adjust the accuracy of the generation based on the level of detail of the collected data during generation. For example, if detailed data is collected, the generation unit will generate a highly accurate virtual human. If the data is insufficient, the generation unit can use supplementary data to improve the accuracy of the generation. The generation unit can also adjust the facial expressions and movements of the virtual human being generated according to the level of detail of the data. In this way, the generation unit can generate a more accurate virtual human by adjusting the accuracy of the generation based on the level of detail of the collected data. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input the collected data into a generation AI and have the generation AI perform the adjustment of the accuracy of the generation.

[0044] The generation unit can apply different generation algorithms depending on the category of the virtual human during generation. For example, the generation unit can apply an algorithm that produces friendly expressions and movements to a virtual human intended for family. For a virtual human intended for friends, it can apply an algorithm that produces casual expressions and movements. For a virtual human intended for business, it can apply an algorithm that produces formal expressions and movements. In this way, the generation unit can generate more appropriate virtual humans by applying different generation algorithms depending on the category of the virtual human. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input virtual human category data into a generation AI and have the generation AI execute the application of the generation algorithm.

[0045] The generation unit can determine the generation priority based on the submission timing of the collected data during generation. For example, the generation unit can prioritize generating the latest virtual human based on recently collected data. The generation unit can also generate past virtual humans based on older data. The generation unit can also adjust the generation priority according to the submission timing. This allows the generation unit to generate virtual humans based on the latest data by determining the generation priority based on the submission timing of the collected data. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input the submission timing of the collected data into the generation AI and have the generation AI perform the priority determination.

[0046] The generation unit can adjust the generation order based on the relevance of the collected data during generation. For example, the generation unit can preferentially generate virtual humans based on highly relevant data. The generation unit can also postpone the generation of virtual humans based on less relevant data. The generation unit can also adjust the generation order according to the relevance of the data. In this way, the generation unit can generate virtual humans based on highly relevant data by adjusting the generation order based on the relevance of the collected data. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input the relevance of the collected data into the generation AI and have the generation AI perform the adjustment of the generation order.

[0047] The dialogue unit can adjust the level of detail in a dialogue based on the importance of the virtual human being. For example, the dialogue unit can provide detailed information in dialogues with important virtual humans, and concise information in dialogues with less important virtual humans. The dialogue unit can also adjust the level of detail in a dialogue according to importance. This allows the dialogue unit to prioritize more important dialogues by adjusting the level of detail based on the importance of the virtual human being. Some or all of the above processing in the dialogue unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the dialogue unit can input virtual human importance data into a generative AI and have the generative AI perform the adjustment of the level of detail in the dialogue.

[0048] The dialogue unit can apply different dialogue algorithms depending on the category of the virtual human during a conversation. For example, the dialogue unit can apply a friendly dialogue algorithm to a virtual human intended for family. For a virtual human intended for friends, it can apply a casual dialogue algorithm. For a virtual human intended for business, it can also apply a formal dialogue algorithm. In this way, the dialogue unit can conduct more appropriate conversations by applying different dialogue algorithms depending on the category of the virtual human. Some or all of the above processing in the dialogue unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the dialogue unit can input virtual human category data into a generative AI and have the generative AI perform the application of dialogue algorithms.

[0049] The dialogue unit can determine the priority of dialogues based on the submission date of the virtual humans during a dialogue. For example, the dialogue unit may prioritize dialogues with recently generated virtual humans. The dialogue unit may postpone dialogues with older virtual humans. The dialogue unit can also adjust the dialogue priority according to the submission date. This allows the dialogue unit to prioritize dialogues with the most recent virtual humans by determining the dialogue priority based on the submission date of the virtual humans. Some or all of the above processing in the dialogue unit may be performed using a generative AI, or not. For example, the dialogue unit can input virtual human submission date data into a generative AI and have the generative AI perform the task of determining the dialogue priority.

[0050] The dialogue unit can adjust the order of conversations based on the relevance of the virtual humans during a conversation. For example, the dialogue unit can prioritize conversations with highly relevant virtual humans. The dialogue unit can postpone conversations with less relevant virtual humans. The dialogue unit can also adjust the order of conversations according to relevance. In this way, the dialogue unit can prioritize more relevant conversations by adjusting the order of conversations based on the relevance of the virtual humans. Some or all of the above processing in the dialogue unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the dialogue unit can input virtual human relevance data into a generative AI and have the generative AI perform the adjustment of the order of conversations.

[0051] The dialogue unit can adjust the order of conversations based on the relevance of the virtual humans during a conversation. For example, the dialogue unit can prioritize conversations with highly relevant virtual humans. The dialogue unit can postpone conversations with less relevant virtual humans. The dialogue unit can also adjust the order of conversations according to relevance. In this way, the dialogue unit can prioritize more relevant conversations by adjusting the order of conversations based on the relevance of the virtual humans. Some or all of the above processing in the dialogue unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the dialogue unit can input virtual human relevance data into a generative AI and have the generative AI perform the adjustment of the order of conversations.

[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 data collection unit can analyze the user's past behavioral history and select the optimal data collection method. For example, it can create scenarios for collecting natural movements based on activities the user frequently performed in the past. It can also collect voice data using devices the user has preferred to use in the past. It can also analyze the user's past behavioral patterns and select the optimal collection time. In this way, the data collection unit can select the optimal data collection method by analyzing the user's past behavioral history.

[0054] The data collection unit can filter data based on the user's current lifestyle and areas of interest during the data collection process. For example, it can prioritize collecting episodes related to topics the user is currently interested in. It can also adjust the types of data collected according to the user's lifestyle. It can even select the content of episodes to collect based on the user's areas of interest. As a result, the data collection unit can collect highly relevant data by filtering based on the user's current lifestyle and areas of interest.

[0055] The generation unit can adjust the accuracy of the generation based on the level of detail of the collected data during the generation process. For example, if detailed data is collected, a highly accurate virtual human can be generated. If the data is insufficient, supplementary data can be used to improve the accuracy of the generation. The facial expressions and movements of the generated virtual human can also be adjusted according to the level of detail of the data. In this way, the generation unit can generate a more accurate virtual human by adjusting the accuracy of the generation based on the level of detail of the collected data.

[0056] The generation unit can apply different generation algorithms depending on the category of the virtual human during generation. For example, an algorithm that produces friendly facial expressions and movements can be applied to a virtual human for family use. An algorithm that produces casual facial expressions and movements can be applied to a virtual human for friends use. An algorithm that produces formal facial expressions and movements can also be applied to a virtual human for business use. In this way, the generation unit can generate more appropriate virtual humans by applying different generation algorithms depending on the category of the virtual human.

[0057] The dialogue unit can adjust the level of detail in a conversation based on the importance of the virtual human being. For example, it can provide detailed information in conversations with important virtual humans, and concise information in conversations with less important virtual humans. It can also adjust the level of detail in a conversation according to importance. This allows the dialogue unit to prioritize more important conversations by adjusting the level of detail in a conversation based on the importance of the virtual human being.

[0058] The following briefly describes the processing flow for example form 1.

[0059] Step 1: The data collection unit collects data such as appearance, voice, and anecdotes. For example, it records appearance, voice, and anecdotes in detail through interviews and photography. It takes photos and videos from various angles to record facial expressions and movements. It can also record audio data to capture voice, speaking style, tone, and verbal tics. Through interviews, it can also collect anecdotes about past events and hobbies. Step 2: The generation unit generates a 3D virtual human based on the collected data. For example, it uses 3DCG software to perform modeling and sets up UVs, textures, bones, weights, and materials. Lip-sync technology can be used to link voice and movement. Speech synthesis technology can also be used to generate a voice that closely resembles the real person based on the collected voice data. Alternatively, a generation AI can be used to input the collected data into the generation AI and have the generation AI perform the generation of the 3D virtual human. Step 3: The dialogue unit interacts with the generated virtual human in the metaverse space. For example, it fine-tunes a large-scale language model to build a conversational AI chat. It can also learn habits and characteristics acquired during interviews and store basic information and episodes of the deceased as a database. It can also perform natural dialogue by referring to the database as needed. The AI ​​can also perform dialogue between the generated virtual human and the user.

[0060] (Example of form 2) The system according to an embodiment of the present invention is a system that generates a 3D virtual human from data recorded and acquired during the person's lifetime, and enables conversation with the deceased in a metaverse space after death. This system collects data such as appearance, voice, and episodes, generates a 3D virtual human, and can engage in dialogue in a metaverse space. For example, this system collects data on a person who will be deceased during their lifetime. This data includes appearance (facial expressions, skeletal structure, movement patterns, habits, etc.), voice (voice, speaking style, tone, catchphrases, etc.), and episodes (past events, hobbies, etc.). Next, a 3D virtual human is generated based on the collected data. The generated virtual human reproduces the appearance, voice, and speaking style of the deceased, enabling dialogue in a metaverse space. Furthermore, the acquired episodes are stored in a database, and an agent is constructed that speaks by referring to past events. This allows for a reunion with the deceased and enjoyment of conversation. For example, this system collects data on a person who will be deceased during their lifetime. At this time, appearance, voice, and episodes are recorded in detail through interviews and photography. For example, photographs and videos are taken from various angles to record facial expressions and movements. The system also records voice data, capturing the voice, speaking style, tone, and verbal tics. Furthermore, it collects anecdotes about past events and hobbies through interviews. Next, a 3D virtual human is generated based on the collected data. Specifically, 3DCG software is used for modeling, and UVs, textures, bones, weights, and materials are set. Lip-sync technology is used to link the voice and movement. In addition, speech synthesis technology is used to generate a voice that closely resembles the real person based on the collected voice data. The generated virtual human can then converse in the metaverse space. Specifically, a large-scale language model is fine-tuned to build a conversational generative AI chat. The quirks and characteristics acquired during the interviews are used to learn, and the deceased's basic information and anecdotes are stored in a database. This allows for natural conversation by referring to the database as needed. Finally, the user puts on a VR set and microphone, and can reunite with the virtual deceased in the metaverse space and enjoy a conversation.Based on the user's choices, the system references a database based on their relationship with the deceased and provides appropriate conversation. This allows users to heal grief and regret and share memories through reconnecting with the deceased. The system can recreate the appearance, voice, and speaking style of the deceased, enabling dialogue in a metaverse space.

[0061] The system according to this embodiment comprises a data collection unit, a generation unit, and a dialogue unit. The data collection unit collects data such as appearance, voice, and episodes. The data collection unit records appearance, voice, and episodes in detail, for example, through interviews or photography. For example, the data collection unit takes photos and videos from various angles and records facial expressions and movements. The data collection unit can also record voice data, recording voice, speaking style, tone, and catchphrases. The data collection unit can also collect episodes such as past events and hobbies through interviews. The generation unit generates a 3D virtual human based on the collected data. The generation unit performs modeling using 3DCG software, for example, and sets UVs, textures, bones, weights, and materials. The generation unit can also link voice and movement using lip-sync technology. The generation unit can also generate a voice that closely resembles the real person based on the collected voice data using speech synthesis technology. Some or all of the above-described processing in the generation unit may be performed using a generation AI, or it may be performed without using a generation AI. For example, the generation unit inputs collected data into a generation AI, which then generates a 3D virtual human. The dialogue unit engages in dialogue with the generated virtual human in a metaverse space. The dialogue unit can, for example, fine-tune a large-scale language model to build a conversational generation AI chat. The dialogue unit can also learn habits and characteristics acquired during interviews and store basic information and episodes of the deceased as a database. The dialogue unit can also engage in natural dialogue by referring to the database as needed. Some or all of the above-described processes in the dialogue unit may be performed using AI or not. For example, the dialogue unit can have the AI ​​perform a dialogue between the generated virtual human and the user. As a result, the system according to the embodiment can collect data such as appearance, voice, and episodes, generate a 3D virtual human, and engage in dialogue in a metaverse space.

[0062] The data collection unit collects data such as appearance, voice, and anecdotes. For example, the data collection unit meticulously records appearance, voice, and anecdotes through interviews and photography. Specifically, the data collection unit takes photos and videos of the subject from various angles, meticulously recording facial expressions and movements. This includes using high-resolution cameras and multiple cameras to acquire three-dimensional information about the subject. Furthermore, the data collection unit records audio data, meticulously documenting voice tone, speaking style, and verbal tics. This includes using high-quality microphones to acquire clear audio data. The data collection unit can also collect anecdotes about the subject's past events, hobbies, and special skills through interviews. Interviews should ideally be conducted in a relaxed environment to elicit natural speech and facial expressions from the subject. This allows the data collection unit to gain a detailed understanding of the subject's personality and characteristics. Furthermore, the data collection unit centrally manages the collected data, making it available for subsequent processing. For example, the collected data is stored in cloud storage, making it accessible to the generation and dialogue units. This allows the data collection unit to collect data efficiently and effectively, improving the overall system performance.

[0063] The generation unit generates a 3D virtual human based on collected data. For example, the generation unit uses 3DCG software to perform modeling and sets up UVs, textures, bones, weights, and materials. Specifically, it first creates the basic shape of the 3D model based on photographs or videos of the subject. Next, it performs UV mapping and applies textures. Textures are used to reproduce the texture of the subject's skin and the patterns of their clothing. Furthermore, bones are set to give the model movement. Bones represent the joints and skeleton of the model and are important for achieving natural movement. Weight setting associates the bones with the vertices of the model, so that the model deforms according to the movement of the bones. Material setting adjusts the texture and reflectivity of the model's surface to achieve a realistic appearance. The generation unit can also link voice and movement using lip-sync technology. Lip-sync technology controls the model's mouth movements based on audio data to reproduce natural speech. The generation unit can also generate a voice that closely resembles the real person based on collected audio data using speech synthesis technology. Speech synthesis technology learns the characteristics of the subject's voice and reproduces natural pronunciation and intonation. Some or all of the above-described processes in the generation unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the generation unit can input collected data into a generation AI and have the generation AI perform the generation of a 3D virtual human. The generation AI can learn from a vast dataset and generate highly accurate 3D models. This allows the generation unit to generate 3D virtual humans efficiently and with high accuracy, improving the overall performance of the system.

[0064] The dialogue unit interacts with the generated virtual human in a metaverse space. For example, the dialogue unit fine-tunes a large-scale language model to build a conversational generative AI chat. Specifically, the dialogue unit learns the habits and characteristics of the subject based on collected data. This includes learning the subject's way of speaking, facial expressions, gestures, and other characteristics. The dialogue unit can also store basic information and anecdotes about the deceased as a database. The database includes information such as the subject's background, hobbies, and special skills. The dialogue unit can conduct natural conversations by referring to the database as needed. For example, if the user asks a question about a specific anecdote, the dialogue unit will refer to the database and generate an appropriate answer. Some or all of the above processing in the dialogue unit may be performed using AI or not. For example, the dialogue unit can have AI perform conversations between the generated virtual human and the user. The AI ​​uses natural language processing technology to analyze the user's statements and generate appropriate responses. This allows the dialogue unit to achieve natural and realistic conversations and provide a high level of user satisfaction. Furthermore, the dialogue unit can collect user feedback and continuously improve the accuracy and effectiveness of the dialogue content. For example, it can revise the content and expression of the dialogue based on user feedback to achieve a more natural and engaging conversation. In addition, the dialogue unit can interact with users using multiple communication methods. For example, it can provide users with diverse dialogue options by using not only dialogue within the metaverse space but also voice calls and text chat. This allows the dialogue unit to provide users with a flexible and high-quality dialogue experience and improve the overall performance of the system.

[0065] The generation unit can perform modeling using 3DCG software and set UVs, textures, bones, weights, and materials. For example, the generation unit can perform detailed modeling of a virtual human using 3DCG software. The generation unit can perform UV mapping and set textures. The generation unit can also place bones and adjust weights. The generation unit can set materials and adjust the texture of the virtual human. In this way, the generation unit can perform detailed modeling of a virtual human using 3DCG software. Some or all of the above processes in the generation unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the generation unit can input 3DCG software into a generation AI and have the generation AI execute each step of the modeling process.

[0066] The generation unit can link voice and movement using lip-sync technology. For example, the generation unit analyzes voice data using a voice analysis algorithm. The generation unit can model mouth movements and link them with voice data. The generation unit can also adjust the synchronization of voice and movement to achieve natural lip-sync. In this way, the generation unit can generate a virtual human with linked voice and movement using lip-sync technology. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input voice data into a generation AI and have the generation AI perform lip-sync generation.

[0067] The generation unit can generate a voice that closely resembles the original person's voice based on collected voice data using speech synthesis technology. The generation unit can generate voice data using, for example, text-to-speech (TTS) technology. The generation unit can also generate a voice that closely resembles the original person's voice based on collected voice data using voice cloning technology. The generation unit can also adjust the tone and manner of speaking to generate a natural-sounding voice. In this way, the generation unit can generate a voice that closely resembles the original person's voice using speech synthesis technology. Some or all of the above-described processes in the generation unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the generation unit can input voice data into a generation AI and have the generation AI perform the voice generation.

[0068] The dialogue unit can fine-tune a large-scale language model and build a conversational generative AI chat. The dialogue unit can perform fine-tuning and adapt to specific dialogue scenarios. The dialogue unit can also adjust the flow of dialogue and the timing of responses to achieve natural dialogue. Thus, the dialogue unit can build a conversational generative AI chat by fine-tuning a large-scale language model. Some or all of the above processing in the dialogue unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the dialogue unit can input a large-scale language model into a generative AI and leave the fine-tuning to the generative AI.

[0069] The dialogue unit can learn habits and characteristics acquired during interviews and store basic information and anecdotes about the deceased in a database. For example, the dialogue unit can learn habits and characteristics such as speech patterns, gestures, and facial expressions acquired during interviews. The dialogue unit can store basic information and anecdotes about the deceased in a database and refer to it as needed. The dialogue unit can also engage in natural conversation while referring to the database. In this way, the dialogue unit can store basic information and anecdotes about the deceased in a database by learning habits and characteristics acquired during interviews. Some or all of the above processing in the dialogue unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the dialogue unit can input data acquired during interviews into a generative AI and have the generative AI perform the construction of the database.

[0070] The dialogue unit can engage in natural conversations by referring to a database as needed. For example, the dialogue unit can refer to appropriate episodes and information from the database according to the flow of the conversation. The dialogue unit can generate natural responses based on the information stored in the database. The dialogue unit can also provide appropriate information according to the context of the conversation. In this way, the dialogue unit can engage in natural conversations by referring to a database as needed. Some or all of the above processing in the dialogue unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the dialogue unit can input the context of the conversation into a generative AI and have the generative AI perform the referencing of appropriate information and the generation of responses.

[0071] The data collection unit can estimate the user's emotions and adjust the timing of data collection based on the estimated emotions. For example, the data collection unit can conduct interviews when the user is relaxed and collect natural facial expressions and voices. If the user is emotional, the data collection unit can temporarily suspend data collection and resume it when the user has calmed down. If the user is tired, the data collection unit can conduct short collection sessions and collect additional data at a later date. In this way, the data collection unit can collect more natural data by adjusting the timing of data collection based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using or without a generative AI. For example, the data collection unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation and adjustment of data collection timing.

[0072] The data collection unit can analyze the user's past behavioral history and select the optimal data collection method. For example, the data collection unit can create scenarios for collecting natural movements based on activities the user has frequently performed in the past. The data collection unit can collect voice data using devices the user has preferred to use in the past. The data collection unit can also analyze the user's past behavioral patterns and select the optimal collection time. In this way, the data collection unit can select the optimal data collection method by analyzing the user's past behavioral history. Some or all of the above processing in the data collection unit may be performed using generative AI, or not. For example, the data collection unit can input the user's behavioral history data into a generative AI and have the generative AI select the optimal data collection method.

[0073] The data collection unit can filter data based on the user's current lifestyle and areas of interest during data collection. For example, the data collection unit can prioritize collecting episodes related to topics the user is currently interested in. The data collection unit can adjust the types of data collected according to the user's lifestyle. The data collection unit can also select the content of episodes to collect based on the user's areas of interest. This allows the data collection unit to collect highly relevant data by filtering based on the user's current lifestyle and areas of interest. Some or all of the above processing in the data collection unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the data collection unit can input data on the user's lifestyle and areas of interest into a generative AI and leave the filtering to the generative AI.

[0074] The data collection unit can estimate the user's emotions and determine the priority of data to collect based on the estimated user emotions. For example, when the user is emotional, the data collection unit can prioritize collecting episodes related to those emotions. When the user is relaxed, the data collection unit can conduct detailed interviews and collect deeper episodes. When the user is busy, the data collection unit can also prioritize data that can be collected in a short amount of time. In this way, the data collection unit can prioritize the collection of more important data by determining the priority of data to collect based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using or without a generative AI. For example, the data collection unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation and data prioritization.

[0075] The data collection unit can prioritize the collection of highly relevant data by considering the user's geographical location information during data collection. For example, when a user is in a specific location, the data collection unit can collect episodes related to that location. Based on the user's place of residence, the data collection unit can prioritize the collection of region-related data. If a user is traveling, the data collection unit can also collect episodes related to their travel destination. In this way, the data collection unit can prioritize the collection of highly relevant data by considering the user's geographical location information. Some or all of the above processing in the data collection unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the data collection unit can input the user's geographical location information into a generative AI and have the generative AI perform the collection of highly relevant data.

[0076] The data collection unit can analyze a user's social media activity and collect relevant data during data collection. For example, the data collection unit can collect relevant episodes based on the content a user frequently posts on social media. The data collection unit can analyze a user's social media friendships and collect episodes related to their friends. The data collection unit can also collect data on topics of interest based on a user's social media activity history. In this way, the data collection unit can collect relevant data by analyzing a user's social media activity. Some or all of the above processing in the data collection unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the data collection unit can input the user's social media activity data into a generative AI and have the generative AI perform the collection of relevant data.

[0077] The generation unit can estimate the user's emotions and adjust the method of generating the virtual human based on the estimated user emotions. For example, if the user is relaxed, the generation unit can generate a virtual human with natural facial expressions and movements. If the user is emotional, the generation unit can generate a virtual human with facial expressions and movements that reflect those emotions. If the user is excited, the generation unit can also generate a virtual human with lively movements. In this way, the generation unit can generate more natural virtual humans by adjusting the method of generating the virtual human based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the generation unit may be performed using the generation AI or not. For example, the generation unit can input user emotion data into the generation AI and have the generation AI perform adjustments to the generation method based on the emotions.

[0078] The generation unit can adjust the accuracy of the generation based on the level of detail of the collected data during generation. For example, if detailed data is collected, the generation unit will generate a highly accurate virtual human. If the data is insufficient, the generation unit can use supplementary data to improve the accuracy of the generation. The generation unit can also adjust the facial expressions and movements of the virtual human being generated according to the level of detail of the data. In this way, the generation unit can generate a more accurate virtual human by adjusting the accuracy of the generation based on the level of detail of the collected data. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input the collected data into a generation AI and have the generation AI perform the adjustment of the accuracy of the generation.

[0079] The generation unit can apply different generation algorithms depending on the category of the virtual human during generation. For example, the generation unit can apply an algorithm that produces friendly expressions and movements to a virtual human intended for family. For a virtual human intended for friends, it can apply an algorithm that produces casual expressions and movements. For a virtual human intended for business, it can apply an algorithm that produces formal expressions and movements. In this way, the generation unit can generate more appropriate virtual humans by applying different generation algorithms depending on the category of the virtual human. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input virtual human category data into a generation AI and have the generation AI execute the application of the generation algorithm.

[0080] The generation unit can estimate the user's emotions and determine the priority of virtual humans to generate based on the estimated user emotions. For example, if the user is emotional, the generation unit will prioritize generating a virtual human that reflects those emotions. If the user is relaxed, the generation unit can prioritize generating a virtual human with natural facial expressions and movements. If the user is in a hurry, the generation unit can also prioritize generating a virtual human that can be generated quickly. In this way, the generation unit can prioritize generating more important virtual humans by determining the priority of virtual humans to generate based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the generation unit may be performed using or without a generation AI. For example, the generation unit can input user emotion data into a generation AI and have the generation AI perform emotion-based priority determination.

[0081] The generation unit can determine the generation priority based on the submission timing of the collected data during generation. For example, the generation unit can prioritize generating the latest virtual human based on recently collected data. The generation unit can also generate past virtual humans based on older data. The generation unit can also adjust the generation priority according to the submission timing. This allows the generation unit to generate virtual humans based on the latest data by determining the generation priority based on the submission timing of the collected data. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input the submission timing of the collected data into the generation AI and have the generation AI perform the priority determination.

[0082] The generation unit can adjust the generation order based on the relevance of the collected data during generation. For example, the generation unit can preferentially generate virtual humans based on highly relevant data. The generation unit can also postpone the generation of virtual humans based on less relevant data. The generation unit can also adjust the generation order according to the relevance of the data. In this way, the generation unit can generate virtual humans based on highly relevant data by adjusting the generation order based on the relevance of the collected data. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can input the relevance of the collected data into the generation AI and have the generation AI perform the adjustment of the generation order.

[0083] The dialogue unit can estimate the user's emotions and adjust the way it expresses the dialogue based on those emotions. For example, if the user is sad, the dialogue unit can speak in a gentle tone. If the user is happy, the dialogue unit can speak in a cheerful tone. If the user is angry, the dialogue unit can speak in a calm tone. In this way, the dialogue unit can provide more appropriate dialogue by adjusting the way it expresses the dialogue based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the dialogue unit may be performed using or without a generative AI. For example, the dialogue unit can input user emotion data into a generative AI and have the generative AI adjust the way it expresses the dialogue based on those emotions.

[0084] The dialogue unit can adjust the level of detail in a dialogue based on the importance of the virtual human being. For example, the dialogue unit can provide detailed information in dialogues with important virtual humans, and concise information in dialogues with less important virtual humans. The dialogue unit can also adjust the level of detail in a dialogue according to importance. This allows the dialogue unit to prioritize more important dialogues by adjusting the level of detail based on the importance of the virtual human being. Some or all of the above processing in the dialogue unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the dialogue unit can input virtual human importance data into a generative AI and have the generative AI perform the adjustment of the level of detail in the dialogue.

[0085] The dialogue unit can apply different dialogue algorithms depending on the category of the virtual human during a conversation. For example, the dialogue unit can apply a friendly dialogue algorithm to a virtual human intended for family. For a virtual human intended for friends, it can apply a casual dialogue algorithm. For a virtual human intended for business, it can also apply a formal dialogue algorithm. In this way, the dialogue unit can conduct more appropriate conversations by applying different dialogue algorithms depending on the category of the virtual human. Some or all of the above processing in the dialogue unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the dialogue unit can input virtual human category data into a generative AI and have the generative AI perform the application of dialogue algorithms.

[0086] The dialogue unit can estimate the user's emotions and adjust the length of the dialogue based on the estimated emotions. For example, if the user is emotional, the dialogue unit can conduct a short dialogue to calm them down. If the user is relaxed, the dialogue unit can conduct a longer dialogue to provide detailed information. If the user is in a hurry, the dialogue unit can also conduct a dialogue that quickly conveys the main points. In this way, the dialogue unit can conduct a more appropriate dialogue by adjusting the length of the dialogue based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the dialogue unit may be performed using or without a generative AI. For example, the dialogue unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of dialogue length based on emotions.

[0087] The dialogue unit can determine the priority of dialogues based on the submission date of the virtual humans during a dialogue. For example, the dialogue unit may prioritize dialogues with recently generated virtual humans. The dialogue unit may postpone dialogues with older virtual humans. The dialogue unit can also adjust the dialogue priority according to the submission date. This allows the dialogue unit to prioritize dialogues with the most recent virtual humans by determining the dialogue priority based on the submission date of the virtual humans. Some or all of the above processing in the dialogue unit may be performed using a generative AI, or not. For example, the dialogue unit can input virtual human submission date data into a generative AI and have the generative AI perform the task of determining the dialogue priority.

[0088] The dialogue unit can adjust the order of conversations based on the relevance of the virtual humans during a conversation. For example, the dialogue unit can prioritize conversations with highly relevant virtual humans. The dialogue unit can postpone conversations with less relevant virtual humans. The dialogue unit can also adjust the order of conversations according to relevance. In this way, the dialogue unit can prioritize more relevant conversations by adjusting the order of conversations based on the relevance of the virtual humans. Some or all of the above processing in the dialogue unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the dialogue unit can input virtual human relevance data into a generative AI and have the generative AI perform the adjustment of the order of conversations.

[0089] The dialogue unit can adjust the order of conversations based on the relevance of the virtual humans during a conversation. For example, the dialogue unit can prioritize conversations with highly relevant virtual humans. The dialogue unit can postpone conversations with less relevant virtual humans. The dialogue unit can also adjust the order of conversations according to relevance. In this way, the dialogue unit can prioritize more relevant conversations by adjusting the order of conversations based on the relevance of the virtual humans. Some or all of the above processing in the dialogue unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the dialogue unit can input virtual human relevance data into a generative AI and have the generative AI perform the adjustment of the order of conversations.

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

[0091] The data collection unit can estimate the user's emotions and adjust the timing of data collection based on those emotions. For example, it can conduct interviews when the user is relaxed and collect natural facial expressions and voices. If the user is emotional, data collection can be temporarily suspended and resumed when they have calmed down. If the user is tired, a short collection session can be conducted, with additional data collection at a later date. In this way, the data collection unit can collect more natural data by adjusting the timing of data collection based on the user's emotions.

[0092] The generation unit can estimate the user's emotions and adjust the virtual human generation method based on the estimated user emotions. For example, if the user is relaxed, it can generate a virtual human with natural facial expressions and movements. If the user is emotional, it can generate a virtual human with facial expressions and movements that reflect those emotions. If the user is excited, it can even generate a virtual human with lively movements. In this way, the generation unit can generate more natural virtual humans by adjusting the virtual human generation method based on the user's emotions.

[0093] 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 sad, it can speak in a gentle tone. If the user is happy, it can speak in a cheerful tone. If the user is angry, it can speak in a calm tone. In this way, the dialogue unit can provide more appropriate dialogue by adjusting its expression based on the user's emotions.

[0094] The dialogue unit can estimate the user's emotions and adjust the length of the conversation based on those emotions. For example, if the user is emotional, a short conversation can be used to calm them down. If the user is relaxed, a longer conversation can be used to provide more detailed information. If the user is in a hurry, a conversation that quickly conveys the main points can be used. In this way, the dialogue unit can provide more appropriate conversations by adjusting the length of the conversation based on the user's emotions.

[0095] The generation unit can estimate the user's emotions and determine the priority of virtual humans to generate based on those estimated emotions. For example, if the user is emotional, it can prioritize generating virtual humans that reflect those emotions. If the user is relaxed, it can prioritize generating virtual humans with natural expressions and movements. If the user is in a hurry, it can prioritize generating virtual humans that can be generated quickly. In this way, the generation unit can prioritize generating more important virtual humans by determining the priority of virtual humans to generate based on the user's emotions.

[0096] The data collection unit can analyze the user's past behavioral history and select the optimal data collection method. For example, it can create scenarios for collecting natural movements based on activities the user frequently performed in the past. It can also collect voice data using devices the user has preferred to use in the past. It can also analyze the user's past behavioral patterns and select the optimal collection time. In this way, the data collection unit can select the optimal data collection method by analyzing the user's past behavioral history.

[0097] The data collection unit can filter data based on the user's current lifestyle and areas of interest during the data collection process. For example, it can prioritize collecting episodes related to topics the user is currently interested in. It can also adjust the types of data collected according to the user's lifestyle. It can even select the content of episodes to collect based on the user's areas of interest. As a result, the data collection unit can collect highly relevant data by filtering based on the user's current lifestyle and areas of interest.

[0098] The generation unit can adjust the accuracy of the generation based on the level of detail of the collected data during the generation process. For example, if detailed data is collected, a highly accurate virtual human can be generated. If the data is insufficient, supplementary data can be used to improve the accuracy of the generation. The facial expressions and movements of the generated virtual human can also be adjusted according to the level of detail of the data. In this way, the generation unit can generate a more accurate virtual human by adjusting the accuracy of the generation based on the level of detail of the collected data.

[0099] The generation unit can apply different generation algorithms depending on the category of the virtual human during generation. For example, an algorithm that produces friendly facial expressions and movements can be applied to a virtual human for family use. An algorithm that produces casual facial expressions and movements can be applied to a virtual human for friends use. An algorithm that produces formal facial expressions and movements can also be applied to a virtual human for business use. In this way, the generation unit can generate more appropriate virtual humans by applying different generation algorithms depending on the category of the virtual human.

[0100] The dialogue unit can adjust the level of detail in a conversation based on the importance of the virtual human being. For example, it can provide detailed information in conversations with important virtual humans, and concise information in conversations with less important virtual humans. It can also adjust the level of detail in a conversation according to importance. This allows the dialogue unit to prioritize more important conversations by adjusting the level of detail in a conversation based on the importance of the virtual human being.

[0101] The following briefly describes the processing flow for example form 2.

[0102] Step 1: The data collection unit collects data such as appearance, voice, and anecdotes. For example, it records appearance, voice, and anecdotes in detail through interviews and photography. It takes photos and videos from various angles to record facial expressions and movements. It can also record audio data to capture voice, speaking style, tone, and verbal tics. Through interviews, it can also collect anecdotes about past events and hobbies. Step 2: The generation unit generates a 3D virtual human based on the collected data. For example, it uses 3DCG software to perform modeling and sets up UVs, textures, bones, weights, and materials. Lip-sync technology can be used to link voice and movement. Speech synthesis technology can also be used to generate a voice that closely resembles the real person based on the collected voice data. Alternatively, a generation AI can be used to input the collected data into the generation AI and have the generation AI perform the generation of the 3D virtual human. Step 3: The dialogue unit interacts with the generated virtual human in the metaverse space. For example, it fine-tunes a large-scale language model to build a conversational AI chat. It can also learn habits and characteristics acquired during interviews and store basic information and episodes of the deceased as a database. It can also perform natural dialogue by referring to the database as needed. The AI ​​can also perform dialogue between the generated virtual human and the user.

[0103] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating 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.

[0104] 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 text generation AI, image generation AI, and multimodal generation AI. 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 with 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 from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. 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 various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts 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.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0105] 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.

[0106] Each of the multiple elements described above, including the data acquisition unit, generation unit, and dialogue unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the data acquisition unit uses the camera 42 and microphone 38B of the smart device 14 to collect appearances, sounds, and episodes, and the control unit 46A records the data. The generation unit is implemented in the specific processing unit 290 of the data processing unit 12 and generates a 3D virtual human based on the collected data. The dialogue unit is implemented in the specific processing unit 290 of the data processing unit 12 and interacts with the generated virtual human in a metaverse space. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0107] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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).

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.).

[0119] 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.

[0120] 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. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. 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.

[0121] 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.

[0122] Each of the multiple elements described above, including the data acquisition unit, generation unit, and dialogue unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the data acquisition unit uses the camera 42 and microphone 238 of the smart glasses 214 to collect visual information, sound, and episodes, and the control unit 46A records the data. The generation unit is implemented in the specific processing unit 290 of the data processing unit 12 and generates a 3D virtual human based on the collected data. The dialogue unit is implemented in the specific processing unit 290 of the data processing unit 12 and interacts with the generated virtual human in a metaverse space. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0123] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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).

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.).

[0135] 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.

[0136] 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. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. 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.

[0137] 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.

[0138] Each of the multiple elements described above, including the data acquisition unit, generation unit, and dialogue unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the data acquisition unit uses the camera 42 and microphone 238 of the headset terminal 314 to collect visual information, audio, and episodes, and the control unit 46A records the data. The generation unit is implemented in the specific processing unit 290 of the data processing unit 12 and generates a 3D virtual human based on the collected data. The dialogue unit is implemented in the specific processing unit 290 of the data processing unit 12 and interacts with the generated virtual human in a metaverse space. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0139] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] The microphone 238 receives voice commands and other instructions from the user by receiving voice signals. 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.

[0144] 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).

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.).

[0152] 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.

[0153] 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. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. 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.

[0154] 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.

[0155] Each of the multiple elements described above, including the data acquisition unit, generation unit, and dialogue unit, is implemented in, for example, at least one of the robot 414 and the data processing unit 12. For example, the data acquisition unit uses the camera 42 and microphone 238 of the robot 414 to collect visual information, sounds, and episodes, and the control unit 46A records the data. The generation unit is implemented in, for example, the specific processing unit 290 of the data processing unit 12, and generates a 3D virtual human based on the collected data. The dialogue unit is implemented in, for example, the specific processing unit 290 of the data processing unit 12, and interacts with the generated virtual human in a metaverse space. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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."

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] (Note 1) The data collection unit collects data such as appearance, voice, and episodes, A generation unit generates a 3D virtual human based on the data collected by the aforementioned data collection unit, The system includes a dialogue unit that interacts with the virtual human generated by the generation unit in a metaverse space. A system characterized by the following features. (Note 2) The generating unit is Modeling is performed using 3DCG software, and UVs, textures, bones, weights, and materials are set up. The system described in Appendix 1, characterized by the features described herein. (Note 3) The generating unit is Use lip-sync technology to link voice and movement. The system described in Appendix 1, characterized by the features described herein. (Note 4) The generating unit is Using speech synthesis technology, a voice that closely resembles the person's voice is generated based on collected voice data. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned dialogue unit, We will fine-tune a large-scale language model and build an interactive generative AI chat. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned dialogue unit, The system learns habits and characteristics acquired during interviews, and stores basic information and anecdotes about the deceased in a database. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned dialogue unit, Engage in natural conversations while referencing the database as needed. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned data acquisition unit, We estimate the user's emotions and adjust the timing of data collection based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned data acquisition unit, Analyze the user's past behavior history and select the optimal data collection method. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned data acquisition unit, During data collection, filtering is performed based on the user's current lifestyle and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned data acquisition unit, It estimates the user's emotions and prioritizes the data to collect based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned data acquisition unit, When collecting data, the system prioritizes the collection of highly relevant data, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned data acquisition unit, During data collection, the system analyzes users' social media activity and collects relevant data. The system described in Appendix 1, characterized by the features described herein. (Note 14) The generating unit is It estimates the user's emotions and adjusts the method of generating virtual humans based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The generating unit is During generation, the accuracy of the generation is adjusted based on the level of detail of the collected data. The system described in Appendix 1, characterized by the features described herein. (Note 16) The generating unit is During generation, different generation algorithms are applied depending on the category of the virtual human. The system described in Appendix 1, characterized by the features described herein. (Note 17) The generating unit is It estimates the user's emotions and determines the priority of virtual human beings to generate based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The generating unit is During generation, the generation priority is determined based on when the collected data was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 19) The generating unit is During generation, the generation priority is determined based on when the collected data was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 20) The generating unit is During generation, the generation order is adjusted based on the relevance of the collected data. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned dialogue unit, It estimates the user's emotions and adjusts the way the dialogue is expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned dialogue unit, During conversations, adjust the level of detail based on the importance of the virtual human. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned dialogue unit, During interaction, different dialogue algorithms are applied depending on the category of the virtual human. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned dialogue unit, It estimates the user's emotions and adjusts the length of the conversation based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned dialogue unit, During the dialogue, the priority of the dialogue is determined based on when the virtual human was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned dialogue unit, During dialogue, the order of conversations is adjusted based on the relevance of the virtual human beings. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0175] 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 data collection unit that collects data such as appearance, voice, and episodes, A generation unit generates a 3D virtual human based on the data collected by the aforementioned data collection unit, The system includes a dialogue unit that interacts with the virtual human generated by the generation unit in a metaverse space. A system characterized by the following features.

2. The generating unit is Modeling is performed using 3DCG software, and UVs, textures, bones, weights, and materials are set up. The system according to feature 1.

3. The generating unit is Use lip-sync technology to link voice and movement. The system according to feature 1.

4. The generating unit is Using speech synthesis technology, a voice that closely resembles the person's voice is generated based on collected voice data. The system according to feature 1.

5. The aforementioned dialogue unit, We will fine-tune a large-scale language model and build an interactive generative AI chat. The system according to feature 1.

6. The aforementioned dialogue unit, The system learns habits and characteristics acquired during interviews, and stores basic information and anecdotes about the deceased in a database. The system according to feature 1.

7. The aforementioned dialogue unit, Engage in natural conversations while referencing the database as needed. The system according to feature 1.

8. The aforementioned data acquisition unit is We estimate the user's emotions and adjust the timing of data collection based on those estimated emotions. The system according to feature 1.

9. The aforementioned data acquisition unit is Analyze the user's past behavior history and select the optimal data collection method. The system according to feature 1.

10. The aforementioned data acquisition unit is During data collection, filtering is performed based on the user's current lifestyle and areas of interest. The system according to feature 1.

Images