system

Abstract

The system according to this embodiment aims to enable dialogue with the deceased and the sharing of memories, thereby providing a new form of grief care. [Solution] The system according to the embodiment comprises a learning unit, a generation unit, an answering unit, and a virtual participation unit. The learning unit learns the user's characteristics from the user's dialogue, diary, SNS data, etc. The generation unit creates a virtual avatar that reproduces the user's appearance, voice, and gestures based on the characteristics learned by the learning unit. The answering unit has the virtual avatar created by the generation unit generate answers based on the individual's values ​​to questions from family members. The virtual participation unit virtually participates in future family events and leaves messages based on the answers generated by the answering unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there is a problem that it is difficult to interact with the deceased or share memories, and it is not sufficient as a means of grief care.

[0005] The system according to the embodiment aims to enable interaction with the deceased and sharing of memories, and provide new grief care.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a learning unit, a generation unit, an answering unit, and a virtual participation unit. The learning unit learns the user's personal characteristics from the user's dialogue, diary, SNS data, etc. The generation unit creates a virtual avatar that reproduces the user's appearance, voice, and gestures based on the characteristics learned by the learning unit. The answering unit has the virtual avatar created by the generation unit generate answers based on the individual's values ​​to questions from family members. The virtual participation unit virtually participates in future family events and leaves messages based on the answers generated by the answering unit. [Effects of the Invention]

[0007] The system according to this embodiment can enable dialogue with the deceased and the sharing of memories, providing a new form of grief care. [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 manages communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The virtual avatar system according to an embodiment of the present invention is a system that uses a generating AI to learn the user's personality and create a virtual avatar that can communicate with family members even after death. This virtual avatar system enables the transmission of wills, sharing of memories, and virtual participation in future family events, providing a new form of grief care. Furthermore, the virtual avatar system contributes to self-understanding and strengthening family bonds through use during one's lifetime. For example, the generating AI in the virtual avatar system learns the individual's characteristics from the user's conversations, diaries, and SNS data. Next, the generating AI creates a virtual avatar that reproduces the user's appearance, voice, and gestures. This avatar generates answers based on the individual's values ​​to questions from family members and engages in interactive communication. The virtual avatar system also allows users to virtually participate in future family events such as weddings and the birth of grandchildren and leave messages. In addition, the virtual avatar system provides digital estate management support and grief care guidance. This system reduces the psychological burden on family members after death and enables end-of-life planning that more reliably reflects the deceased's wishes. This allows virtual avatar systems to learn the user's personality and create virtual avatars that can communicate with family members even after death.

[0029] The virtual avatar system according to this embodiment comprises a learning unit, a generation unit, a response unit, and a virtual participation unit. The learning unit learns the user's personal characteristics from the user's dialogue, diary, SNS data, etc. For example, the learning unit collects the user's daily dialogue, the contents recorded in their diary, and the data posted on SNS, and analyzes this data to learn the user's characteristics. The learning unit can learn the user's personality, hobbies, behavioral patterns, etc., using generational AI. For example, the learning unit extracts words and phrases that the user frequently uses and learns the user's characteristics based on them. The learning unit can also estimate the user's emotions and select learning data based on the estimated emotions. The generation unit creates a virtual avatar that reproduces the user's appearance, voice, and gestures based on the characteristics learned by the learning unit. For example, the generation unit analyzes the user's photos and videos and creates a 3D model based on them. The generation unit can synthesize the user's voice using generational AI to achieve natural dialogue. For example, the generation unit analyzes the tone and pitch of the user's voice and synthesizes a voice based on that. The generation unit can also apply algorithms to reproduce the user's gestures and speaking style. The response unit generates answers based on the user's personal values ​​to questions from family members using the virtual avatar created by the generation unit. For example, the response unit can analyze questions from family members and generate appropriate answers. The response unit can use generational AI to customize the content of answers based on the user's values ​​and beliefs. For example, the response unit can generate appropriate answers based on the user's religious beliefs. The response unit can also generate optimal answers considering the context of the family's questions. The virtual participation unit virtually participates in future family events and leaves messages based on the answers generated by the response unit. For example, the virtual participation unit can virtually participate in family events such as weddings or the birth of grandchildren and leave congratulatory messages. The virtual participation unit can use generational AI to estimate the user's emotions and adjust the method of virtual participation based on the estimated emotions. For example, if the virtual participation unit is happy, it will generate cheerful and energetic messages. The virtual participation unit can also customize the content of messages based on the details of the family event.As a result, the virtual avatar system according to this embodiment can learn the user's personality and create a virtual avatar that can communicate with family members even after death.

[0030] The learning unit learns individual characteristics from user conversations, diaries, and social media data. Specifically, it collects data such as the content of daily conversations, events recorded in diaries, and text, images, and videos posted on social media, and analyzes this data to learn user characteristics. The learning unit can learn the user's personality, hobbies, and behavioral patterns in detail using generative AI. For example, the learning unit extracts words and phrases that the user frequently uses and understands the user's linguistic characteristics based on that. It can also estimate emotions from the content of user posts and the tone of conversations, and select learning data based on changes in emotion. Furthermore, the learning unit can analyze the user's past behavioral history and interests to predict user behavioral patterns. For example, if a user tends to perform certain activities at certain times of the day, it can learn that pattern and predict future behavior. The learning unit can also analyze the user's relationships on social networks to understand what kind of people the user has and what kind of relationships they have. As a result, the learning unit can comprehensively learn the multifaceted characteristics of the user and provide the information necessary to generate a virtual avatar.

[0031] The generation unit creates a virtual avatar that reproduces the user's appearance, voice, and mannerisms based on features learned by the learning unit. Specifically, it analyzes the user's photos and videos and creates a 3D model based on them. The generation unit can synthesize the user's voice using generative AI to achieve natural dialogue. For example, the generation unit analyzes the tone, pitch, and rhythm of the user's voice and synthesizes the voice based on that. It also applies algorithms to reproduce the user's mannerisms and speaking style, realistically reproducing the user's movements and facial expressions. Furthermore, the generation unit also reproduces the user's physical characteristics such as clothing and hairstyle, creating a virtual avatar that reflects the user's personality. For example, it learns the style and color of clothing and hairstyles that the user prefers to wear and reflects them in the virtual avatar. The generation unit can also learn the user's movement and gesture characteristics and adjust the virtual avatar to move naturally. As a result, the generation unit can create a virtual avatar that faithfully reproduces the user's appearance, voice, and mannerisms, and achieve natural dialogue that reflects the user's personality.

[0032] The answering unit generates answers based on the user's values ​​to questions from family members using a virtual avatar created by the generation unit. Specifically, it analyzes questions from family members and generates appropriate answers. The answering unit can customize the content of answers based on the user's values ​​and beliefs using generational AI. For example, the answering unit can generate appropriate answers based on the user's religious beliefs and ethical values. It can also generate optimal answers by considering the context of the family member's question. For example, if a family member asks about a specific situation or event, it will understand the context and provide an appropriate answer. Furthermore, the answering unit can predict what kind of answer the user will give by referring to the user's past statements and actions, and generate an answer based on that. For example, it can learn what opinions the user has held on a particular topic in the past and generate an answer based on that. The answering unit can also estimate the feelings and intentions of family members and provide answers accordingly. In this way, the answering unit can provide answers that reflect the user's values ​​and beliefs through dialogue with family members, thereby facilitating smooth communication with family members.

[0033] The virtual participant unit virtually participates in future family events and leaves messages based on responses generated by the response unit. Specifically, it can virtually participate in family events such as weddings and the birth of grandchildren and leave congratulatory messages. The virtual participant unit uses generation AI to estimate the user's emotions and adjust its virtual participation method based on those emotions. For example, if the virtual participant unit is happy, it will generate a cheerful and energetic message. It can also customize the content of the message based on the details of the family event. For example, at a wedding, it will generate a message that includes words of congratulations to the bride and groom and memories shared by the user in the past. Furthermore, the virtual participant unit can reproduce the user's voice and gestures, providing an experience as if the virtual avatar is actually participating in the event. For example, it can read messages aloud in the user's voice or the virtual avatar can smile and wave. The virtual participant unit can also analyze family reactions in real time and generate additional messages accordingly. In this way, the virtual participant unit can virtually participate in family events and deepen family bonds through messages that reflect the user's emotions and personality.

[0034] The support department can provide digital legacy management support and grief care guidance. For example, the support department can provide support for managing a user's digital legacy. The support department can manage backups of user account information and data, making them accessible to family members after the user's death. The support department can also provide grief care guidance, helping families cope with their grief. For example, the support department can refer users to counseling or support groups. By providing digital legacy management support and grief care guidance, the psychological burden on families after a user's death can be reduced.

[0035] The learning unit can analyze the user's past dialogue history and select the optimal learning algorithm. For example, the learning unit can extract words and phrases that the user frequently uses and adjust the learning algorithm based on them. The learning unit can also analyze the user's dialogue patterns and select an algorithm to reproduce natural dialogue. Furthermore, the learning unit can detect changes in emotion from the user's dialogue history and select an algorithm that corresponds to it. In this way, the optimal learning algorithm can be selected by analyzing the user's dialogue history. Some or all of the above processes in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input the user's dialogue history data into a generating AI and have the generating AI perform the selection of the optimal learning algorithm.

[0036] The learning unit can customize learning content based on the user's lifestyle and hobbies during the learning process. For example, the learning unit prioritizes learning data related to the user's daily routines and hobbies. The learning unit can also learn information about the user's favorite music and movies and incorporate it into the dialogue. Furthermore, the learning unit can learn data about the user's eating habits and exercise habits to provide health advice. This allows for more personalized learning by customizing learning content based on the user's lifestyle and hobbies. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input data about the user's lifestyle and hobbies into a generating AI and have the generating AI perform the customization of learning content.

[0037] The learning unit can prioritize learning highly relevant data while considering the user's geographical location. For example, the learning unit can prioritize learning information about the area where the user lives, enabling localized conversations. The learning unit can also learn data about places the user frequently visits and provide relevant topics. Furthermore, the learning unit can learn information about the user's travel destinations and share travel advice and memories. This allows for more personalized learning by prioritizing highly relevant data while considering the user's geographical location. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input the user's geographical location data into a generating AI and have the generating AI select highly relevant data.

[0038] The learning unit can analyze a user's social media activity and learn relevant data during the learning process. For example, the learning unit can analyze photos and comments posted by the user to learn personal characteristics. The learning unit can also learn information about accounts that the user follows and groups that the user participates in, and provide relevant topics. Furthermore, the learning unit can analyze the user's social media interaction patterns and reproduce natural conversations. In this way, relevant data can be learned by analyzing the user's social media activity. Some or all of the above processing in the learning unit may be performed using AI, for example, or not using AI. For example, the learning unit can input the user's social media activity data into a generating AI and have the generating AI select relevant data.

[0039] The generation unit can update the avatar based on changes in the user's appearance and voice during generation. For example, if the user changes their hairstyle, the generation unit will update the avatar's appearance to reflect that change. The generation unit can also adjust the avatar's voice to match changes in the user's voice tone or pitch. Furthermore, if the user's body shape changes, the generation unit can update the avatar's appearance to reflect that change. This allows for more accurate reproduction by updating the avatar based on changes in the user's appearance and voice. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input data on changes in the user's appearance and voice into a generation AI and have the generation AI perform the avatar update.

[0040] The generation unit can apply algorithms to accurately reproduce the user's gestures and speaking style during generation. For example, the generation unit can learn the gestures the user frequently uses and reflect them in the avatar. The generation unit can also learn the rhythm and tempo of the user's speech and reproduce natural dialogue. Furthermore, the generation unit can learn the user's unique facial expressions and movements and reflect them in the avatar. This allows for more natural dialogue by accurately reproducing the user's gestures and speaking style. Some or all of the above-described processes in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input user gesture and speaking style characteristic data into a generation AI and have the generation AI perform the avatar reproduction.

[0041] The generation unit can optimize the appearance of the avatar by referencing the user's past photos and videos during generation. For example, the generation unit can analyze the user's past photos to more accurately reproduce the avatar's appearance. The generation unit can also refer to the user's videos and reflect their movements and facial expressions in the avatar. Furthermore, the generation unit can extract specific features from the user's past photos and videos and reflect them in the avatar. This allows for a more accurate reproduction of the avatar's appearance by referencing the user's past photos and videos. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the user's past photo and video data into a generation AI and have the generation AI perform the optimization of the avatar's appearance.

[0042] The generation unit can improve the avatar during generation by incorporating feedback from the user's family and friends. For example, the generation unit can adjust the avatar's appearance and voice based on feedback from family and friends. The generation unit can also improve the avatar's movements and expressions by incorporating the opinions of family and friends. Furthermore, the generation unit can adjust the avatar's dialogue content by incorporating feedback from family and friends. This improves the accuracy of the avatar by incorporating feedback from the user's family and friends. Some or all of the above processes in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input feedback data from family and friends into a generation AI and have the generation AI perform improvements to the avatar.

[0043] The response unit can customize the content of responses based on the user's values ​​and beliefs when generating them. For example, the response unit can generate appropriate responses based on the user's religious beliefs. The response unit can also adjust the content of responses based on the user's ethics and morals. Furthermore, the response unit can customize the content of responses based on the user's political beliefs. This allows for the generation of more personalized responses by customizing the content of responses based on the user's values ​​and beliefs. Some or all of the above processing in the response unit may be performed using AI, for example, or without AI. For example, the response unit can input the user's values ​​and beliefs data into a generating AI and have the generating AI perform the customization of the response content.

[0044] The answering unit can generate the most appropriate answer by considering the context of the family's question during the answer generation process. For example, the answering unit can understand the background and intent of the family's question and generate an appropriate answer. The answering unit can also refer to the family's past question history to generate a consistent answer. Furthermore, the answering unit can consider the context of the family's question and generate an answer with an appropriate tone and expression. This allows for the generation of more appropriate answers by considering the context of the family's question. Some or all of the above processing in the answering unit may be performed using AI, for example, or not. For example, the answering unit can input contextual data of the family's question into a generation AI and have the generation AI perform the generation of the most appropriate answer.

[0045] The answering unit can improve the accuracy of its answers by referring to the family's past question history when generating answers. For example, the answering unit can refer to questions and answers that the family has asked in the past to generate consistent answers. The answering unit can also analyze the family's past question history and generate answers that include relevant information. Furthermore, the answering unit can extract specific patterns from the family's question history and generate answers based on them. This improves the accuracy of answers by referring to the family's past question history. Some or all of the above processing in the answering unit may be performed using AI, for example, or not using AI. For example, the answering unit can input the family's past question history data into a generation AI and have the generation AI perform the task of improving the accuracy of the answers.

[0046] The response unit can adjust the content of responses based on the family's interests and hobbies when generating them. For example, the response unit can generate responses that include information related to the family's interests. The response unit can also generate interesting responses based on the family's hobbies. Furthermore, the response unit can refer to data on the family's interests and hobbies to generate appropriate responses. This allows for the generation of more appropriate responses by adjusting the content of responses based on the family's interests and hobbies. Some or all of the above processing in the response unit may be performed using AI, for example, or without AI. For example, the response unit can input data on the family's interests and hobbies into a generation AI and have the generation AI perform the adjustment of the response content.

[0047] The virtual participant can customize the message content based on the details of the family event when participating virtually. For example, in the case of a wedding, the virtual participant can generate a message that includes congratulations and reminiscences. In the case of the birth of a grandchild, the virtual participant can also generate a message that includes words of encouragement and hopes for the future. Furthermore, in the case of a family member's birthday, the virtual participant can generate a message that includes individual memories and words of gratitude. This allows for the generation of more appropriate messages by customizing the message content based on the details of the family event. Some or all of the above processing in the virtual participant may be performed using AI, for example, or not. For example, the virtual participant can input detailed family event data into a generating AI and have the generating AI perform the customization of the message content.

[0048] The virtual participant can generate the most appropriate message by referencing the user's past statements and actions during virtual participation. For example, the virtual participant can generate relevant messages based on what the user has said in the past. The virtual participant can also refer to the user's past actions and generate messages based on those actions. Furthermore, the virtual participant can generate messages aligned with a specific theme from the user's past statements and actions. This allows for the generation of more appropriate messages by referencing the user's past statements and actions. Some or all of the above processing in the virtual participant may be performed using AI, for example, or without AI. For example, the virtual participant can input the user's past statements and actions data into a generating AI and have the generating AI generate the most appropriate message.

[0049] The virtual participant unit can generate highly relevant messages when a family member is virtually participating, taking into account their geographical location. For example, if a family member is in a specific location, the virtual participant unit can generate a message related to that location. If a family member is traveling, the virtual participant unit can also generate a message related to their travel destination. Furthermore, if a family member is participating in a specific event, the virtual participant unit can generate a message related to that event. By considering the family member's geographical location, more appropriate messages are generated. Some or all of the above processing in the virtual participant unit may be performed using AI, for example, or without AI. For example, the virtual participant unit can input the family's geographical location data into a generating AI and have the generating AI perform the generation of highly relevant messages.

[0050] The virtual participant unit can analyze the family's social media activity and generate relevant messages during virtual participation. For example, the virtual participant unit generates messages based on what the family has shared on social media. The virtual participant unit can also analyze the family's social media activity and generate relevant messages. Furthermore, the virtual participant unit can analyze the family's social media interaction patterns and generate messages based on them. Thus, relevant messages are generated by analyzing the family's social media activity. Some or all of the above processing in the virtual participant unit may be performed using AI, for example, or without AI. For example, the virtual participant unit can input family social media activity data into a generating AI and have the generating AI perform the generation of relevant messages.

[0051] The support unit can provide optimal support by referring to the user's past behavior history when providing support. For example, the support unit can refer to the support the user has received in the past and provide similar support. The support unit can also analyze the user's past behavior history and provide optimal support. Furthermore, the support unit can refer to the user's past behavior patterns and provide support based on them. In this way, optimal support is provided by referring to the user's past behavior history. Some or all of the above processes in the support unit may be performed using AI, for example, or without AI. For example, the support unit can input the user's past behavior history data into a generating AI and have the generating AI perform the task of providing optimal support.

[0052] The support unit can provide optimal support by considering the user's geographical location when providing support. For example, if the user is in a specific location, the support unit can provide support related to that location. If the user is traveling, the support unit can also provide support related to the travel destination. Furthermore, if the user is participating in a specific event, the support unit can provide support related to that event. In this way, optimal support is provided by considering the user's geographical location. Some or all of the above processing in the support unit may be performed using AI, for example, or not using AI. For example, the support unit can input the user's geographical location data into a generating AI and have the generating AI perform the task of providing optimal support.

[0053] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0054] A virtual avatar system can also monitor a user's health and provide health advice. For example, the learning unit collects and analyzes the user's health data (e.g., heart rate, sleep patterns, exercise level, etc.). Next, the generation unit creates an avatar that reflects the user's health based on the analysis results. For example, if the user is tired, the avatar can display a tired expression. Furthermore, the response unit provides appropriate health advice based on the user's health status. For example, if the user is stressed, it can suggest ways to relax. In this way, the virtual avatar system can also contribute to the user's health management.

[0055] A virtual avatar system can also provide customized entertainment content based on the user's hobbies and interests. For example, the learning unit collects and analyzes data on the user's hobbies and interests. Then, the generation unit creates entertainment content that matches the user's hobbies and interests based on the analysis results. For example, if the user likes movies, the avatar can provide the latest movie information. Furthermore, the response unit suggests customized entertainment content based on the user's hobbies and interests. For example, if the user likes music, it can recommend new music albums. In this way, the virtual avatar system can enhance the user's entertainment experience.

[0056] Virtual avatar systems can also support user learning. For example, the learning unit collects and analyzes data on the user's learning history and learning style. Then, the generation unit creates learning content tailored to the user's learning style based on the analysis results. For example, if the user is a visual learner, the avatar can provide visual learning materials. Furthermore, the response unit provides appropriate learning advice based on the user's learning progress. For example, if the user is struggling with a particular subject, it can suggest effective learning methods. In this way, virtual avatar systems can also contribute to supporting user learning.

[0057] Virtual avatar systems can also provide career support to users. For example, the learning unit collects and analyzes data on the user's career history and skills. Then, the generation unit provides advice tailored to the user's career goals based on the analysis results. For instance, if a user wants to try a new job, the avatar can suggest the necessary skills and qualifications. Furthermore, the response unit provides appropriate career advice based on the user's career progress. For example, if a user is aiming for promotion, it can suggest an effective career plan. In this way, virtual avatar systems can also contribute to supporting users' careers.

[0058] A virtual avatar system can also support users' travel planning. For example, the learning unit collects and analyzes data on the user's travel history and interests. Then, the generation unit creates a travel plan tailored to the user's interests based on the analysis results. For instance, if the user likes nature, the avatar can suggest travel destinations rich in nature. Furthermore, the response unit provides appropriate travel advice based on the user's travel plan. For example, if the user is traveling to a specific region, the avatar can suggest tourist spots and recommended activities in that region. In this way, the virtual avatar system can also contribute to the user's travel planning.

[0059] A virtual avatar system can also support users' financial management. For example, the learning unit collects and analyzes data on the user's income and expenses. Then, the generation unit creates an avatar that reflects the user's financial situation based on the analysis results. For example, if the user is aiming to save money, the avatar can provide saving advice. Furthermore, the response unit provides appropriate financial management advice based on the user's financial situation. For example, if the user is considering investing, it can provide information on risks and returns. In this way, the virtual avatar system can also contribute to the user's financial management.

[0060] The following briefly describes the processing flow for example form 1.

[0061] Step 1: The learning unit learns individual characteristics from user conversations, diaries, and social media data. For example, it collects conversations that users have on a daily basis, entries in diaries, and data posted on social media, and analyzes this data to learn user characteristics. The learning unit can use generative AI to learn the user's personality, hobbies, and behavioral patterns. It extracts words and phrases that users frequently use and learns user characteristics based on them. It can also estimate the user's emotions and select learning data based on those estimated emotions. Step 2: The generation unit creates a virtual avatar that reproduces the user's appearance, voice, and mannerisms based on the features learned by the learning unit. For example, it analyzes the user's photos or videos and creates a 3D model based on them. The generation unit can use generative AI to synthesize the user's voice and achieve natural dialogue. It analyzes the tone and pitch of the user's voice and synthesizes the voice based on that. It can also apply algorithms to reproduce the user's mannerisms and speaking style characteristics. Step 3: The answering unit uses the virtual avatar created by the generation unit to generate answers to questions from family members based on the user's personal values. For example, it analyzes questions from family members and generates appropriate answers. The answering unit can use generation AI to customize the content of answers based on the user's values ​​and beliefs. It can generate appropriate answers based on the user's religious beliefs. It can also generate optimal answers by considering the context of the family's questions. Step 4: The virtual participant unit virtually participates in future family events and leaves messages based on the responses generated by the response unit. For example, it can virtually participate in family events such as weddings or the birth of grandchildren and leave congratulatory messages. The virtual participant unit can use generation AI to estimate the user's emotions and adjust its virtual participation method based on the estimated emotions. If the user is happy, it will generate a cheerful and energetic message. It can also customize the message content based on the details of the family event.

[0062] (Example of form 2) The virtual avatar system according to an embodiment of the present invention is a system that uses a generating AI to learn the user's personality and create a virtual avatar that can communicate with family members even after death. This virtual avatar system enables the transmission of wills, sharing of memories, and virtual participation in future family events, providing a new form of grief care. Furthermore, the virtual avatar system contributes to self-understanding and strengthening family bonds through use during one's lifetime. For example, the generating AI in the virtual avatar system learns the individual's characteristics from the user's conversations, diaries, and SNS data. Next, the generating AI creates a virtual avatar that reproduces the user's appearance, voice, and gestures. This avatar generates answers based on the individual's values ​​to questions from family members and engages in interactive communication. The virtual avatar system also allows users to virtually participate in future family events such as weddings and the birth of grandchildren and leave messages. In addition, the virtual avatar system provides digital estate management support and grief care guidance. This system reduces the psychological burden on family members after death and enables end-of-life planning that more reliably reflects the deceased's wishes. This allows virtual avatar systems to learn the user's personality and create virtual avatars that can communicate with family members even after death.

[0063] The virtual avatar system according to this embodiment comprises a learning unit, a generation unit, a response unit, and a virtual participation unit. The learning unit learns the user's personal characteristics from the user's dialogue, diary, SNS data, etc. For example, the learning unit collects the user's daily dialogue, the contents recorded in their diary, and the data posted on SNS, and analyzes this data to learn the user's characteristics. The learning unit can learn the user's personality, hobbies, behavioral patterns, etc., using generational AI. For example, the learning unit extracts words and phrases that the user frequently uses and learns the user's characteristics based on them. The learning unit can also estimate the user's emotions and select learning data based on the estimated emotions. The generation unit creates a virtual avatar that reproduces the user's appearance, voice, and gestures based on the characteristics learned by the learning unit. For example, the generation unit analyzes the user's photos and videos and creates a 3D model based on them. The generation unit can synthesize the user's voice using generational AI to achieve natural dialogue. For example, the generation unit analyzes the tone and pitch of the user's voice and synthesizes a voice based on that. The generation unit can also apply algorithms to reproduce the user's gestures and speaking style. The response unit generates answers based on the user's personal values ​​to questions from family members using the virtual avatar created by the generation unit. For example, the response unit can analyze questions from family members and generate appropriate answers. The response unit can use generational AI to customize the content of answers based on the user's values ​​and beliefs. For example, the response unit can generate appropriate answers based on the user's religious beliefs. The response unit can also generate optimal answers considering the context of the family's questions. The virtual participation unit virtually participates in future family events and leaves messages based on the answers generated by the response unit. For example, the virtual participation unit can virtually participate in family events such as weddings or the birth of grandchildren and leave congratulatory messages. The virtual participation unit can use generational AI to estimate the user's emotions and adjust the method of virtual participation based on the estimated emotions. For example, if the virtual participation unit is happy, it will generate cheerful and energetic messages. The virtual participation unit can also customize the content of messages based on the details of the family event.As a result, the virtual avatar system according to this embodiment can learn the user's personality and create a virtual avatar that can communicate with family members even after death.

[0064] The learning unit learns individual characteristics from user conversations, diaries, and social media data. Specifically, it collects data such as the content of daily conversations, events recorded in diaries, and text, images, and videos posted on social media, and analyzes this data to learn user characteristics. The learning unit can learn the user's personality, hobbies, and behavioral patterns in detail using generative AI. For example, the learning unit extracts words and phrases that the user frequently uses and understands the user's linguistic characteristics based on that. It can also estimate emotions from the content of user posts and the tone of conversations, and select learning data based on changes in emotion. Furthermore, the learning unit can analyze the user's past behavioral history and interests to predict user behavioral patterns. For example, if a user tends to perform certain activities at certain times of the day, it can learn that pattern and predict future behavior. The learning unit can also analyze the user's relationships on social networks to understand what kind of people the user has and what kind of relationships they have. As a result, the learning unit can comprehensively learn the multifaceted characteristics of the user and provide the information necessary to generate a virtual avatar.

[0065] The generation unit creates a virtual avatar that reproduces the user's appearance, voice, and mannerisms based on features learned by the learning unit. Specifically, it analyzes the user's photos and videos and creates a 3D model based on them. The generation unit can synthesize the user's voice using generative AI to achieve natural dialogue. For example, the generation unit analyzes the tone, pitch, and rhythm of the user's voice and synthesizes the voice based on that. It also applies algorithms to reproduce the user's mannerisms and speaking style, realistically reproducing the user's movements and facial expressions. Furthermore, the generation unit also reproduces the user's physical characteristics such as clothing and hairstyle, creating a virtual avatar that reflects the user's personality. For example, it learns the style and color of clothing and hairstyles that the user prefers to wear and reflects them in the virtual avatar. The generation unit can also learn the user's movement and gesture characteristics and adjust the virtual avatar to move naturally. As a result, the generation unit can create a virtual avatar that faithfully reproduces the user's appearance, voice, and mannerisms, and achieve natural dialogue that reflects the user's personality.

[0066] The answering unit generates answers based on the user's values ​​to questions from family members using a virtual avatar created by the generation unit. Specifically, it analyzes questions from family members and generates appropriate answers. The answering unit can customize the content of answers based on the user's values ​​and beliefs using generational AI. For example, the answering unit can generate appropriate answers based on the user's religious beliefs and ethical values. It can also generate optimal answers by considering the context of the family member's question. For example, if a family member asks about a specific situation or event, it will understand the context and provide an appropriate answer. Furthermore, the answering unit can predict what kind of answer the user will give by referring to the user's past statements and actions, and generate an answer based on that. For example, it can learn what opinions the user has held on a particular topic in the past and generate an answer based on that. The answering unit can also estimate the feelings and intentions of family members and provide answers accordingly. In this way, the answering unit can provide answers that reflect the user's values ​​and beliefs through dialogue with family members, thereby facilitating smooth communication with family members.

[0067] The virtual participant unit virtually participates in future family events and leaves messages based on responses generated by the response unit. Specifically, it can virtually participate in family events such as weddings and the birth of grandchildren and leave congratulatory messages. The virtual participant unit uses generation AI to estimate the user's emotions and adjust its virtual participation method based on those emotions. For example, if the virtual participant unit is happy, it will generate a cheerful and energetic message. It can also customize the content of the message based on the details of the family event. For example, at a wedding, it will generate a message that includes words of congratulations to the bride and groom and memories shared by the user in the past. Furthermore, the virtual participant unit can reproduce the user's voice and gestures, providing an experience as if the virtual avatar is actually participating in the event. For example, it can read messages aloud in the user's voice or the virtual avatar can smile and wave. The virtual participant unit can also analyze family reactions in real time and generate additional messages accordingly. In this way, the virtual participant unit can virtually participate in family events and deepen family bonds through messages that reflect the user's emotions and personality.

[0068] The support department can provide digital legacy management support and grief care guidance. For example, the support department can provide support for managing a user's digital legacy. The support department can manage backups of user account information and data, making them accessible to family members after the user's death. The support department can also provide grief care guidance, helping families cope with their grief. For example, the support department can refer users to counseling or support groups. By providing digital legacy management support and grief care guidance, the psychological burden on families after a user's death can be reduced.

[0069] The learning unit can estimate the user's emotions and select training data based on those estimated emotions. For example, if the user is sad, the learning unit will prioritize selecting positive diary entries or social media posts as training data. If the user is happy, the learning unit can also select data that includes past happy memories or success stories to reinforce that emotion. Furthermore, if the user is stressed, the learning unit can select relaxing data for training. This allows for more personalized learning by selecting training data based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The 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 learning unit may be performed using AI, or not. For example, the learning unit can input the user's emotion data into a generative AI and have the generative AI perform the selection of training data based on emotions.

[0070] The learning unit can analyze the user's past dialogue history and select the optimal learning algorithm. For example, the learning unit can extract words and phrases that the user frequently uses and adjust the learning algorithm based on them. The learning unit can also analyze the user's dialogue patterns and select an algorithm to reproduce natural dialogue. Furthermore, the learning unit can detect changes in emotion from the user's dialogue history and select an algorithm that corresponds to it. In this way, the optimal learning algorithm can be selected by analyzing the user's dialogue history. Some or all of the above processes in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input the user's dialogue history data into a generating AI and have the generating AI perform the selection of the optimal learning algorithm.

[0071] The learning unit can customize learning content based on the user's lifestyle and hobbies during the learning process. For example, the learning unit prioritizes learning data related to the user's daily routines and hobbies. The learning unit can also learn information about the user's favorite music and movies and incorporate it into the dialogue. Furthermore, the learning unit can learn data about the user's eating habits and exercise habits to provide health advice. This allows for more personalized learning by customizing learning content based on the user's lifestyle and hobbies. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input data about the user's lifestyle and hobbies into a generating AI and have the generating AI perform the customization of learning content.

[0072] The learning unit can estimate the user's emotions and adjust the learning frequency based on the estimated emotions. For example, if the user is stressed, the learning unit can reduce the learning frequency and increase the time the user can relax. If the user is relaxed, the learning unit can also increase the learning frequency and collect data more efficiently. Furthermore, if the user is busy, the learning unit can adjust the learning frequency to reduce the burden. This allows for more effective learning by adjusting the learning frequency 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 learning unit may be performed using AI or not using AI. For example, the learning unit can input user emotion data into a generative AI and have the generative AI adjust the learning frequency based on emotions.

[0073] The learning unit can prioritize learning highly relevant data while considering the user's geographical location. For example, the learning unit can prioritize learning information about the area where the user lives, enabling localized conversations. The learning unit can also learn data about places the user frequently visits and provide relevant topics. Furthermore, the learning unit can learn information about the user's travel destinations and share travel advice and memories. This allows for more personalized learning by prioritizing highly relevant data while considering the user's geographical location. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input the user's geographical location data into a generating AI and have the generating AI select highly relevant data.

[0074] The learning unit can analyze a user's social media activity and learn relevant data during the learning process. For example, the learning unit can analyze photos and comments posted by the user to learn personal characteristics. The learning unit can also learn information about accounts that the user follows and groups that the user participates in, and provide relevant topics. Furthermore, the learning unit can analyze the user's social media interaction patterns and reproduce natural conversations. In this way, relevant data can be learned by analyzing the user's social media activity. Some or all of the above processing in the learning unit may be performed using AI, for example, or not using AI. For example, the learning unit can input the user's social media activity data into a generating AI and have the generating AI select relevant data.

[0075] The generation unit can estimate the user's emotions and adjust the avatar's expression based on the estimated emotions. For example, if the user is sad, the generation unit can make the avatar's expression gentle and comforting. If the user is happy, the generation unit can also make the avatar's expression brighter and empathetic. Furthermore, if the user is angry, the generation unit can calm the avatar's expression and proceed with the conversation calmly. By adjusting the avatar's expression based on the user's emotions, a more natural conversation becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the user's emotion data into the generation AI and have the generation AI adjust the avatar's expression based on the emotion.

[0076] The generation unit can update the avatar based on changes in the user's appearance and voice during generation. For example, if the user changes their hairstyle, the generation unit will update the avatar's appearance to reflect that change. The generation unit can also adjust the avatar's voice to match changes in the user's voice tone or pitch. Furthermore, if the user's body shape changes, the generation unit can update the avatar's appearance to reflect that change. This allows for more accurate reproduction by updating the avatar based on changes in the user's appearance and voice. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input data on changes in the user's appearance and voice into a generation AI and have the generation AI perform the avatar update.

[0077] The generation unit can apply algorithms to accurately reproduce the user's gestures and speaking style during generation. For example, the generation unit can learn the gestures the user frequently uses and reflect them in the avatar. The generation unit can also learn the rhythm and tempo of the user's speech and reproduce natural dialogue. Furthermore, the generation unit can learn the user's unique facial expressions and movements and reflect them in the avatar. This allows for more natural dialogue by accurately reproducing the user's gestures and speaking style. Some or all of the above-described processes in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input user gesture and speaking style characteristic data into a generation AI and have the generation AI perform the avatar reproduction.

[0078] The generation unit can estimate the user's emotions and adjust the avatar's movements based on the estimated emotions. For example, if the user is relaxed, the generation unit will adjust the avatar's movements to be more relaxed. If the user is excited, the generation unit can make the avatar's movements more lively and energetic. If the user is tired, the generation unit can make the avatar's movements more subdued and calm. By adjusting the avatar's movements based on the user's emotions, a more natural dialogue becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The 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 generation unit may be performed using AI, for example, or not using AI. For example, the generation unit can input user emotion data into the generative AI and have the generative AI perform the adjustment of the avatar's movements based on the emotion.

[0079] The generation unit can optimize the appearance of the avatar by referencing the user's past photos and videos during generation. For example, the generation unit can analyze the user's past photos to more accurately reproduce the avatar's appearance. The generation unit can also refer to the user's videos and reflect their movements and facial expressions in the avatar. Furthermore, the generation unit can extract specific features from the user's past photos and videos and reflect them in the avatar. This allows for a more accurate reproduction of the avatar's appearance by referencing the user's past photos and videos. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the user's past photo and video data into a generation AI and have the generation AI perform the optimization of the avatar's appearance.

[0080] The generation unit can improve the avatar during generation by incorporating feedback from the user's family and friends. For example, the generation unit can adjust the avatar's appearance and voice based on feedback from family and friends. The generation unit can also improve the avatar's movements and expressions by incorporating the opinions of family and friends. Furthermore, the generation unit can adjust the avatar's dialogue content by incorporating feedback from family and friends. This improves the accuracy of the avatar by incorporating feedback from the user's family and friends. Some or all of the above processes in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input feedback data from family and friends into a generation AI and have the generation AI perform improvements to the avatar.

[0081] The response unit can estimate the user's emotions and adjust the way it expresses its response based on those emotions. For example, if the user is sad, the response unit can generate a comforting response with kind words. If the user is happy, the response unit can also generate an empathetic response that shares their joy. Furthermore, if the user is angry, the response unit can generate a response that calmly guides the conversation. By adjusting the way the response is expressed based on the user's emotions, a more appropriate response can be generated. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or a generative AI. The generative 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 response unit may be performed using AI, or not using AI. For example, the response unit can input user emotion data into a generative AI and have the generative AI adjust the way the response is expressed based on those emotions.

[0082] The response unit can customize the content of responses based on the user's values ​​and beliefs when generating them. For example, the response unit can generate appropriate responses based on the user's religious beliefs. The response unit can also adjust the content of responses based on the user's ethics and morals. Furthermore, the response unit can customize the content of responses based on the user's political beliefs. This allows for the generation of more personalized responses by customizing the content of responses based on the user's values ​​and beliefs. Some or all of the above processing in the response unit may be performed using AI, for example, or without AI. For example, the response unit can input the user's values ​​and beliefs data into a generating AI and have the generating AI perform the customization of the response content.

[0083] The answering unit can generate the most appropriate answer by considering the context of the family's question during the answer generation process. For example, the answering unit can understand the background and intent of the family's question and generate an appropriate answer. The answering unit can also refer to the family's past question history to generate a consistent answer. Furthermore, the answering unit can consider the context of the family's question and generate an answer with an appropriate tone and expression. This allows for the generation of more appropriate answers by considering the context of the family's question. Some or all of the above processing in the answering unit may be performed using AI, for example, or not. For example, the answering unit can input contextual data of the family's question into a generation AI and have the generation AI perform the generation of the most appropriate answer.

[0084] The response unit can estimate the user's emotions and adjust the length of the response based on the estimated emotions. For example, if the user is in a hurry, the response unit can generate a concise and to-the-point response. If the user is relaxed, the response unit can also generate a longer response that includes detailed explanations. Furthermore, if the user is excited, the response unit can generate a longer response that shares emotions. By adjusting the length of the response based on the user's emotions, a more appropriate response can be generated. 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 response unit may be performed using AI or not using AI. For example, the response unit can input user emotion data into a generative AI and have the generative AI adjust the length of the response based on the emotion.

[0085] The answering unit can improve the accuracy of its answers by referring to the family's past question history when generating answers. For example, the answering unit can refer to questions and answers that the family has asked in the past to generate consistent answers. The answering unit can also analyze the family's past question history and generate answers that include relevant information. Furthermore, the answering unit can extract specific patterns from the family's question history and generate answers based on them. This improves the accuracy of answers by referring to the family's past question history. Some or all of the above processing in the answering unit may be performed using AI, for example, or not using AI. For example, the answering unit can input the family's past question history data into a generation AI and have the generation AI perform the task of improving the accuracy of the answers.

[0086] The response unit can adjust the content of responses based on the family's interests and hobbies when generating them. For example, the response unit can generate responses that include information related to the family's interests. The response unit can also generate interesting responses based on the family's hobbies. Furthermore, the response unit can refer to data on the family's interests and hobbies to generate appropriate responses. This allows for the generation of more appropriate responses by adjusting the content of responses based on the family's interests and hobbies. Some or all of the above processing in the response unit may be performed using AI, for example, or without AI. For example, the response unit can input data on the family's interests and hobbies into a generation AI and have the generation AI perform the adjustment of the response content.

[0087] The virtual participant unit can estimate the user's emotions and adjust its virtual participation method based on the estimated emotions. For example, if the user is happy, the virtual participant unit can generate a cheerful and energetic message. If the user is sad, the virtual participant unit can also generate a comforting message. Furthermore, if the user is excited, the virtual participant unit can generate an energetic message. This allows for more appropriate virtual participation by adjusting the virtual participation method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The 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 virtual participant unit may be performed using AI, for example, or not using AI. For example, the virtual participant unit can input user emotion data into the generative AI and have the generative AI perform an adjustment of the virtual participation method based on the emotions.

[0088] The virtual participant can customize the message content based on the details of the family event when participating virtually. For example, in the case of a wedding, the virtual participant can generate a message that includes congratulations and reminiscences. In the case of the birth of a grandchild, the virtual participant can also generate a message that includes words of encouragement and hopes for the future. Furthermore, in the case of a family member's birthday, the virtual participant can generate a message that includes individual memories and words of gratitude. This allows for the generation of more appropriate messages by customizing the message content based on the details of the family event. Some or all of the above processing in the virtual participant may be performed using AI, for example, or not. For example, the virtual participant can input detailed family event data into a generating AI and have the generating AI perform the customization of the message content.

[0089] The virtual participant can generate the most appropriate message by referencing the user's past statements and actions during virtual participation. For example, the virtual participant can generate relevant messages based on what the user has said in the past. The virtual participant can also refer to the user's past actions and generate messages based on those actions. Furthermore, the virtual participant can generate messages aligned with a specific theme from the user's past statements and actions. This allows for the generation of more appropriate messages by referencing the user's past statements and actions. Some or all of the above processing in the virtual participant may be performed using AI, for example, or without AI. For example, the virtual participant can input the user's past statements and actions data into a generating AI and have the generating AI generate the most appropriate message.

[0090] The virtual participant unit can estimate the user's emotions and adjust the timing of virtual participation based on the estimated emotions. For example, if the user is relaxed, the virtual participant unit will send a message at an appropriate time. If the user is busy, the virtual participant unit can also adjust the timing of the message. Furthermore, if the user is in an emotional state, the virtual participant unit can send a message at an appropriate time. This allows for more appropriate virtual participation by adjusting the timing of virtual participation 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 virtual participant unit may be performed using AI or not using AI. For example, the virtual participant unit can input user emotion data into a generative AI and have the generative AI adjust the timing of virtual participation based on emotions.

[0091] The virtual participant unit can generate highly relevant messages when a family member is virtually participating, taking into account their geographical location. For example, if a family member is in a specific location, the virtual participant unit can generate a message related to that location. If a family member is traveling, the virtual participant unit can also generate a message related to their travel destination. Furthermore, if a family member is participating in a specific event, the virtual participant unit can generate a message related to that event. By considering the family member's geographical location, more appropriate messages are generated. Some or all of the above processing in the virtual participant unit may be performed using AI, for example, or without AI. For example, the virtual participant unit can input the family's geographical location data into a generating AI and have the generating AI perform the generation of highly relevant messages.

[0092] The virtual participant unit can analyze the family's social media activity and generate relevant messages during virtual participation. For example, the virtual participant unit generates messages based on what the family has shared on social media. The virtual participant unit can also analyze the family's social media activity and generate relevant messages. Furthermore, the virtual participant unit can analyze the family's social media interaction patterns and generate messages based on them. Thus, relevant messages are generated by analyzing the family's social media activity. Some or all of the above processing in the virtual participant unit may be performed using AI, for example, or without AI. For example, the virtual participant unit can input family social media activity data into a generating AI and have the generating AI perform the generation of relevant messages.

[0093] The support unit can estimate the user's emotions and adjust the support content based on the estimated emotions. For example, if the user is sad, the support unit can provide comforting support. If the user is happy, the support unit can also provide empathetic support that shares their joy. Furthermore, if the user is stressed, the support unit can provide support that helps them relax. By adjusting the support content based on the user's emotions, more appropriate support can be provided. 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 support unit may be performed using AI, for example, or not using AI. For example, the support unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of support content based on emotions.

[0094] The support unit can provide optimal support by referring to the user's past behavior history when providing support. For example, the support unit can refer to the support the user has received in the past and provide similar support. The support unit can also analyze the user's past behavior history and provide optimal support. Furthermore, the support unit can refer to the user's past behavior patterns and provide support based on them. In this way, optimal support is provided by referring to the user's past behavior history. Some or all of the above processes in the support unit may be performed using AI, for example, or without AI. For example, the support unit can input the user's past behavior history data into a generating AI and have the generating AI perform the task of providing optimal support.

[0095] The support unit can estimate the user's emotions and determine the priority of support based on the estimated emotions. For example, if the user needs urgent support, the support unit will prioritize it. If the user is relaxed, the support unit can provide normal support. If the user is stressed, the support unit can also prioritize providing support that helps them relax. This allows for more appropriate support to be provided by prioritizing support 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 support unit may be performed using AI or not. For example, the support unit can input user emotion data into a generative AI and have the generative AI determine the priority of support based on emotions.

[0096] The support unit can provide optimal support by considering the user's geographical location when providing support. For example, if the user is in a specific location, the support unit can provide support related to that location. If the user is traveling, the support unit can also provide support related to the travel destination. Furthermore, if the user is participating in a specific event, the support unit can provide support related to that event. In this way, optimal support is provided by considering the user's geographical location. Some or all of the above processing in the support unit may be performed using AI, for example, or not using AI. For example, the support unit can input the user's geographical location data into a generating AI and have the generating AI perform the task of providing optimal support.

[0097] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0098] A virtual avatar system can also monitor a user's health and provide health advice. For example, the learning unit collects and analyzes the user's health data (e.g., heart rate, sleep patterns, exercise level, etc.). Next, the generation unit creates an avatar that reflects the user's health based on the analysis results. For example, if the user is tired, the avatar can display a tired expression. Furthermore, the response unit provides appropriate health advice based on the user's health status. For example, if the user is stressed, it can suggest ways to relax. In this way, the virtual avatar system can also contribute to the user's health management.

[0099] A virtual avatar system can also provide customized entertainment content based on the user's hobbies and interests. For example, the learning unit collects and analyzes data on the user's hobbies and interests. Then, the generation unit creates entertainment content that matches the user's hobbies and interests based on the analysis results. For example, if the user likes movies, the avatar can provide the latest movie information. Furthermore, the response unit suggests customized entertainment content based on the user's hobbies and interests. For example, if the user likes music, it can recommend new music albums. In this way, the virtual avatar system can enhance the user's entertainment experience.

[0100] A virtual avatar system can also estimate a user's emotions and support their stress management based on those estimates. For example, the learning unit collects and analyzes the user's emotional data. Then, the generation unit creates an avatar that reflects the user's emotional state based on the analysis results. For example, if the user is feeling stressed, the avatar can display a relaxed expression. Furthermore, the response unit suggests appropriate stress management methods based on the user's emotional state. For example, if the user is feeling tense, it can suggest deep breathing or meditation. In this way, the virtual avatar system can also contribute to the user's stress management.

[0101] Virtual avatar systems can also support user learning. For example, the learning unit collects and analyzes data on the user's learning history and learning style. Then, the generation unit creates learning content tailored to the user's learning style based on the analysis results. For example, if the user is a visual learner, the avatar can provide visual learning materials. Furthermore, the response unit provides appropriate learning advice based on the user's learning progress. For example, if the user is struggling with a particular subject, it can suggest effective learning methods. In this way, virtual avatar systems can also contribute to supporting user learning.

[0102] A virtual avatar system can also estimate a user's emotions and, based on those estimates, improve the user's motivation. For example, the learning unit collects and analyzes the user's emotional data. Next, the generation unit creates an avatar that reflects the user's emotional state based on the analysis results. For example, if the user is feeling down, the avatar can offer words of encouragement. Furthermore, the response unit suggests appropriate ways to improve motivation based on the user's emotional state. For example, if the user is discouraged, it can suggest goal setting or positive feedback. In this way, the virtual avatar system can also contribute to improving the user's motivation.

[0103] Virtual avatar systems can also provide career support to users. For example, the learning unit collects and analyzes data on the user's career history and skills. Then, the generation unit provides advice tailored to the user's career goals based on the analysis results. For instance, if a user wants to try a new job, the avatar can suggest the necessary skills and qualifications. Furthermore, the response unit provides appropriate career advice based on the user's career progress. For example, if a user is aiming for promotion, it can suggest an effective career plan. In this way, virtual avatar systems can also contribute to supporting users' careers.

[0104] A virtual avatar system can also estimate a user's emotions and, based on those emotions, support the user in improving their sleep. For example, the learning unit collects and analyzes the user's emotional data and sleep patterns. Next, the generation unit creates an avatar that reflects the user's emotional state based on the analysis results. For example, if the user is feeling anxious, the avatar can display a relaxed expression. Furthermore, the response unit suggests appropriate sleep improvement methods based on the user's emotional state. For example, if the user is having trouble sleeping, it can suggest relaxing music or meditation. In this way, the virtual avatar system can also contribute to improving the user's sleep.

[0105] A virtual avatar system can also support users' travel planning. For example, the learning unit collects and analyzes data on the user's travel history and interests. Then, the generation unit creates a travel plan tailored to the user's interests based on the analysis results. For instance, if the user likes nature, the avatar can suggest travel destinations rich in nature. Furthermore, the response unit provides appropriate travel advice based on the user's travel plan. For example, if the user is traveling to a specific region, the avatar can suggest tourist spots and recommended activities in that region. In this way, the virtual avatar system can also contribute to the user's travel planning.

[0106] A virtual avatar system can also estimate a user's emotions and support their interpersonal relationships based on those estimates. For example, the learning unit collects and analyzes the user's emotional data and interpersonal relationship data. Next, the generation unit creates an avatar that reflects the user's emotional state based on the analysis results. For example, if the user is feeling lonely, the avatar can offer empathetic words. Furthermore, the response unit provides appropriate interpersonal relationship advice based on the user's emotional state. For example, if the user is having trouble with friendships, the avatar can suggest effective communication methods. In this way, the virtual avatar system can also contribute to supporting the user's interpersonal relationships.

[0107] A virtual avatar system can also support users' financial management. For example, the learning unit collects and analyzes data on the user's income and expenses. Then, the generation unit creates an avatar that reflects the user's financial situation based on the analysis results. For example, if the user is aiming to save money, the avatar can provide saving advice. Furthermore, the response unit provides appropriate financial management advice based on the user's financial situation. For example, if the user is considering investing, it can provide information on risks and returns. In this way, the virtual avatar system can also contribute to the user's financial management.

[0108] The following briefly describes the processing flow for example form 2.

[0109] Step 1: The learning unit learns individual characteristics from user conversations, diaries, and social media data. For example, it collects conversations that users have on a daily basis, entries in diaries, and data posted on social media, and analyzes this data to learn user characteristics. The learning unit can use generative AI to learn the user's personality, hobbies, and behavioral patterns. It extracts words and phrases that users frequently use and learns user characteristics based on them. It can also estimate the user's emotions and select learning data based on those estimated emotions. Step 2: The generation unit creates a virtual avatar that reproduces the user's appearance, voice, and mannerisms based on the features learned by the learning unit. For example, it analyzes the user's photos or videos and creates a 3D model based on them. The generation unit can use generative AI to synthesize the user's voice and achieve natural dialogue. It analyzes the tone and pitch of the user's voice and synthesizes the voice based on that. It can also apply algorithms to reproduce the user's mannerisms and speaking style characteristics. Step 3: The answering unit uses the virtual avatar created by the generation unit to generate answers to questions from family members based on the user's personal values. For example, it analyzes questions from family members and generates appropriate answers. The answering unit can use generation AI to customize the content of answers based on the user's values ​​and beliefs. It can generate appropriate answers based on the user's religious beliefs. It can also generate optimal answers by considering the context of the family's questions. Step 4: The virtual participant unit virtually participates in future family events and leaves messages based on the responses generated by the response unit. For example, it can virtually participate in family events such as weddings or the birth of grandchildren and leave congratulatory messages. The virtual participant unit can use generation AI to estimate the user's emotions and adjust its virtual participation method based on the estimated emotions. If the user is happy, it will generate a cheerful and energetic message. It can also customize the message content based on the details of the family event.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] Each of the multiple elements described above, including the learning unit, generation unit, answering unit, virtual participation unit, and support unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the learning unit is implemented by the control unit 46A of the smart device 14 and collects and analyzes user conversations, diaries, SNS data, etc. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and creates a virtual avatar that reproduces the user's appearance, voice, and gestures. The answering unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates answers based on the individual's values ​​to questions from family members. The virtual participation unit is implemented by the control unit 46A of the smart device 14 and virtually participates in future family events and leaves messages. The support unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides digital legacy management support and grief care guidance. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0114] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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).

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.).

[0126] 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.

[0127] 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.

[0128] 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.

[0129] Each of the multiple elements described above, including the learning unit, generation unit, answering unit, virtual participation unit, and support unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the learning unit is implemented by the control unit 46A of the smart glasses 214 and collects and analyzes the user's dialogue, diary, SNS data, etc. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and creates a virtual avatar that reproduces the user's appearance, voice, and gestures. The answering unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates answers based on the individual's values ​​to questions from family members. The virtual participation unit is implemented by the control unit 46A of the smart glasses 214 and virtually participates in future family events and leaves messages. The support unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides digital legacy management support and grief care guidance. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be changed in various ways.

[0130] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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).

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.).

[0142] 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.

[0143] 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.

[0144] 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.

[0145] Each of the multiple elements described above, including the learning unit, generation unit, answering unit, virtual participation unit, and support unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the learning unit is implemented by the control unit 46A of the headset terminal 314 and collects and analyzes user conversations, diaries, SNS data, etc. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and creates a virtual avatar that reproduces the user's appearance, voice, and gestures. The answering unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates answers based on the individual's values ​​to questions from family members. The virtual participation unit is implemented by the control unit 46A of the headset terminal 314 and allows the user to virtually participate in future family events and leave messages. The support unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides digital legacy management support and grief care guidance. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0146] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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).

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.).

[0159] 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.

[0160] 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.

[0161] 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.

[0162] Each of the multiple elements described above, including the learning unit, generation unit, answering unit, virtual participation unit, and support unit, is implemented in at least one of the following: the robot 414 and the data processing unit 12. For example, the learning unit is implemented by the control unit 46A of the robot 414 and collects and analyzes user dialogues, diaries, SNS data, etc. The generation unit is implemented by the specific processing unit 290 of the data processing unit 12 and creates a virtual avatar that reproduces the user's appearance, voice, and gestures. The answering unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates answers based on the individual's values ​​to questions from family members. The virtual participation unit is implemented by the control unit 46A of the robot 414 and virtually participates in future family events and leaves messages. The support unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides digital legacy management support and grief care guidance. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be changed in various ways.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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."

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] (Note 1) The learning unit learns individual characteristics from user conversations, diaries, and SNS data, A generation unit creates a virtual avatar that reproduces the user's appearance, voice, and gestures based on the features learned by the learning unit, The virtual avatar created by the generation unit generates an answer unit that generates answers based on the individual's values ​​in response to questions from family members, The system includes a virtual participation unit that virtually participates in future family events and leaves messages based on the answers generated by the aforementioned response unit. A system characterized by the following features. (Note 2) The department includes a support section that provides digital legacy management support and grief care guidance. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned learning unit, The system estimates the user's emotions and selects training data based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned learning unit, The system analyzes the user's past conversation history and selects the optimal learning algorithm. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned learning unit, During learning, the learning content is customized based on the user's lifestyle and hobbies. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned learning unit, It estimates the user's emotions and adjusts the learning frequency based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned learning unit, During training, the system prioritizes learning highly relevant data, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned learning unit, During training, the system analyzes users' social media activity and learns from relevant data. The system described in Appendix 1, characterized by the features described herein. (Note 9) The generating unit is It estimates the user's emotions and adjusts the avatar's representation based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The generating unit is During generation, the avatar is updated based on changes in the user's appearance and voice. The system described in Appendix 1, characterized by the features described herein. (Note 11) The generating unit is During generation, an algorithm is applied to accurately reproduce the user's gestures and speaking style. The system described in Appendix 1, characterized by the features described herein. (Note 12) The generating unit is It estimates the user's emotions and adjusts the avatar's behavior based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The generating unit is During generation, the avatar's appearance is optimized by referencing the user's past photos and videos. The system described in Appendix 1, characterized by the features described herein. (Note 14) The generating unit is During creation, the avatar is improved by incorporating feedback from the user's family and friends. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned response section is, It estimates the user's emotions and adjusts the way responses are expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned response section is, When generating responses, customize the content of the responses based on the user's values ​​and beliefs. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned response section is, When generating answers, the system considers the context of the family's questions to generate the most appropriate answers. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned response section is, It estimates the user's emotions and adjusts the length of the response based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned response section is, When generating answers, the system improves accuracy by referencing the family's past question history. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned response section is, When generating responses, adjust the content of the answers based on the family's interests and hobbies. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned virtual participant unit is It estimates the user's emotions and adjusts the virtual participation method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned virtual participant unit is When virtually attending, customize the message content based on the details of the family event. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned virtual participant unit is When a user virtually joins a meeting, the system generates the most appropriate message by referencing the user's past statements and actions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned virtual participant unit is It estimates the user's emotions and adjusts the timing of virtual participation based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned virtual participant unit is When virtual participants join, the system generates highly relevant messages by considering the geographical location of family members. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned virtual participant unit is During virtual participation, the system analyzes family members' social media activity and generates relevant messages. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned support unit is The system estimates the user's emotions and adjusts the support provided based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned support unit is When providing support, we refer to the user's past behavior history to provide the most appropriate support. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned support unit is The system estimates the user's emotions and determines support priorities based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned support unit is When providing support, we take the user's geographical location into consideration to provide the most suitable support. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0182] 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. The learning unit learns individual characteristics from user conversations, diaries, and SNS data, A generation unit creates a virtual avatar that reproduces the user's appearance, voice, and gestures based on the features learned by the aforementioned learning unit, The virtual avatar created by the generation unit generates an answer unit that generates answers based on the individual's values ​​in response to questions from family members, The system includes a virtual participation unit that virtually participates in future family events and leaves messages based on the answers generated by the aforementioned response unit. A system characterized by the following features.

2. The department includes a support section that provides digital legacy management support and grief care guidance. The system according to feature 1.

3. The aforementioned learning unit, The system estimates the user's emotions and selects training data based on those estimated emotions. The system according to feature 1.

4. The aforementioned learning unit, The system analyzes the user's past conversation history and selects the optimal learning algorithm. The system according to feature 1.

5. The aforementioned learning unit, During learning, the learning content is customized based on the user's lifestyle and hobbies. The system according to feature 1.

6. The aforementioned learning unit, It estimates the user's emotions and adjusts the learning frequency based on the estimated user emotions. The system according to feature 1.

7. The aforementioned learning unit, During training, the system prioritizes learning highly relevant data, taking into account the user's geographical location. The system according to feature 1.

8. The aforementioned learning unit, During training, the system analyzes users' social media activity and learns from relevant data. The system according to feature 1.

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

Images