System

Abstract

To provide a system according to an embodiment that generates an avatar utilizing an individual life log, and causes the avatar to continuously learn.SOLUTION: A system according to an embodiment comprises: a collection unit; an analysis unit; a generation unit; and a learning unit. The collection unit is configured to collect a life log. The analysis unit is configured to analyze the life log collected by the collection unit. The generation unit is configured to generate an avatar on the basis of a result analyzed by the analysis unit. The learning unit is configured to cause the avatar generated by the generation unit to continuously learn through a conversation with a user.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

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

[0003] [Patent Document 1] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technology does not adequately utilize an individual's life log to generate an avatar and have it continuously learn, so there is room for improvement.

[0005] The system according to the embodiment aims to generate an avatar by utilizing an individual's life log and have it learn continuously. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, an analysis unit, a generation unit, and a learning unit. The collection unit collects life logs. The analysis unit analyzes the life logs collected by the collection unit. The generation unit generates an avatar based on the results of the analysis by the analysis unit. The learning unit allows the avatar generated by the generation unit to continue learning through conversation with the user. Effect of the Invention

[0007] The system according to the embodiment can generate an avatar by utilizing an individual's life log and have it learn continuously. [Brief description of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

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

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

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

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

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

[0014] In the following embodiments, a communication I / F (Interface) with a code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 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." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

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

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

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

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

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

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

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

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

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

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

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

[0028] (Example 1) The system according to the embodiment of the present invention is a system that generates an "AI-generated avatar" by using life logs such as photos, videos, audio, statements, personality, customs, tastes, and relationships of family members and the user as training data. In this system, the user can converse with the avatar, and the avatar continues to learn through the conversation. This allows the user or a loved one to continue to exist in society semi-permanently even after the death of the user. This avatar can be implemented in a robot or output as a digital avatar. For example, the user inputs the life log of the user and his / her family into the system. The life log includes photos, videos, audio, statements, personality, customs, tastes, and relationships. These data are analyzed by AI, and the characteristics and behavioral patterns of the target person are extracted. Next, the AI ​​generates an avatar based on the extracted characteristics and behavioral patterns. This avatar can mimic the personality and behavior of the target person and can have a natural conversation with the user. For example, when the user asks, "What's the weather like today?", the avatar responds, "It's sunny today. It's perfect for going outside." Furthermore, the avatar continues to learn through conversation with the user. By incorporating new information and the user's reactions, the avatar becomes closer to the target person. For example, if the user says, "I saw a movie recently," the avatar will show interest and ask, "What kind of movie did you see?" and continue the conversation. This avatar can be implemented in a robot. For example, by installing the avatar in a household robot, the user can live their daily life while interacting with the robot. It can also be output as a digital avatar, and the user can enjoy conversations with the avatar through a smartphone or tablet. This system makes it possible to continue to exist in society semi-permanently even after the death of a loved one or oneself. For example, even after a family member passes away, you can continue to share family memories by continuing to talk to that person's avatar. Also, by creating your own avatar, you can pass on your experiences and knowledge to future generations. This allows the AI-based avatar system to generate avatars based on the user's life log and continue learning through conversations with the user.

[0029] The AI ​​avatar system according to the embodiment includes a collection unit, an analysis unit, a generation unit, and a learning unit. The collection unit collects a life log. The life log includes, for example, photos, videos, voices, remarks, personalities, habits, tastes, and human relationships, but is not limited to such examples. The collection unit, for example, collects photos and videos provided by the user in a digital format. The collection unit can also collect voice data using a microphone. Furthermore, the collection unit can also collect the user's remarks and conversation content as text data. For example, the collection unit collects data from a smartphone or tablet that the user uses on a daily basis. The analysis unit analyzes the life log collected by the collection unit. For example, the analysis unit analyzes the collected data using AI to extract the characteristics and behavioral patterns of the subject. For example, the analysis unit performs facial recognition of the subject from photos and videos using image analysis technology. Furthermore, the analysis unit can also extract the characteristics of the subject's voice from the voice data using voice analysis technology. Furthermore, the analysis unit can also analyze the subject's remarks from the text data using natural language processing technology. For example, the analysis unit clusters the collected data using AI and identifies the behavioral pattern of the subject. The generation unit generates an alter-ego based on the results of the analysis by the analysis unit. For example, the generation unit generates an alter-ego that imitates the characteristics and behavioral patterns of the subject using AI. For example, the generation unit imitates the content of the subject's remarks using a text generation AI (e.g., LLM). The generation unit can also reproduce the face and expressions of the subject using an image generation AI. Furthermore, the generation unit can also reproduce the voice of the subject using a voice generation AI. For example, the generation unit learns the characteristics of the subject using AI and generates the actions and remarks of the alter-ego. The learning unit allows the alter-ego generated by the generation unit to continue learning through conversation with the user. For example, the learning unit uses AI to analyze the content of the conversation with the user and incorporates new information and reactions. For example, the learning unit records questions and remarks made by the user to the alter-ego and updates the alter-ego's knowledge base. The learning unit can also analyze the user's reactions and improve the responses of the alter-ego. Furthermore, the learning unit can learn the behavioral patterns of the avatar through conversation with the user, thereby realizing more natural dialogue.For example, the learning unit uses AI to cluster the contents of a conversation with a user and optimize the response pattern of the avatar. This allows the AI ​​avatar system according to the embodiment to generate an avatar based on the user's life log and continue learning through conversations with the user.

[0030] The collection unit collects a life log. The life log includes, but is not limited to, for example, photos, videos, voices, remarks, personality, habits, tastes, and human relationships. The collection unit, for example, collects photos and videos provided by the user in a digital format. Specifically, the collection unit collects photos and videos taken by the user on a daily basis through cloud storage or a dedicated application, and manages these data in a centralized manner. The collection unit can also collect voice data using a microphone. For example, the voice uttered by the user through a smartphone or smart speaker is collected in real time and stored in a voice database. Furthermore, the collection unit can also collect the user's remarks and conversation contents as text data. For example, the communication performed by the user through a chat app or email is collected in text format and stored in a database for analysis using natural language processing technology. When collecting these data, the collection unit introduces encryption technology and access control to protect the user's privacy and ensures the safety of the data. For example, the collected data is end-to-end encrypted so that only systems and users who have received specific authentication can access it. This enables the collection unit to efficiently collect a wide range of life log data from a variety of devices and platforms, improving data quality across the system while protecting user privacy.

[0031] The analysis unit analyzes the life log collected by the collection unit. The analysis unit, for example, uses AI to analyze the collected data and extracts the characteristics and behavioral patterns of the subject. Specifically, the analysis unit uses image analysis technology to recognize the subject's face from photos and videos. For example, a face recognition algorithm using deep learning is applied to extract the facial features of the subject and compare them with existing face data in the database. The analysis unit can also extract the characteristics of the subject's voice from the voice data using voice analysis technology. For example, a spectrum analysis of the voice waveform is performed to extract features such as the pitch, tone, and speaking speed of the voice, and a profile of the subject's voice is created. Furthermore, the analysis unit can analyze the content of the subject's remarks from text data using natural language processing technology. For example, topic modeling and emotion analysis are performed to identify the subject's remarks and emotional state. The analysis unit combines these technologies to comprehensively analyze the subject's behavioral patterns, preferences, and personality characteristics. For example, the analysis unit uses AI to cluster the collected data and identify the subject's behavioral patterns. This allows the analysis unit to analyze the collected life log data from multiple angles and create a detailed profile of the subject. Furthermore, the analysis unit can update the analysis results in real time to reflect the subject's latest actions and status. This allows the analysis unit to always provide highly accurate analysis based on the latest information, improving the reliability and usefulness of the entire system.

[0032] The generation unit generates the avatar based on the results of the analysis by the analysis unit. The generation unit generates the avatar that imitates the characteristics and behavioral patterns of the target person using, for example, AI. Specifically, it imitates the content of the target person's speech using a text generation AI (for example, LLM). For example, it uses an LLM that has learned the target person's past speech data to generate content that the target person is likely to actually say. The generation unit can also reproduce the target person's face and facial expression using an image generation AI. For example, it uses a GAN (generative artificial network) to learn the facial features of the target person and generate a realistic facial image and facial expression. Furthermore, the generation unit can also reproduce the target person's voice using a voice generation AI. For example, it uses a voice synthesis technology to learn the characteristics of the target person's voice and generate a natural voice. The generation unit combines these technologies to learn the characteristics of the target person and generate the actions and statements of the avatar. For example, it uses an AI to learn the characteristics of the target person and generate the actions and statements of the avatar. The generation unit can also adjust the actions and statements of the generated avatar in real time so that the generated avatar can communicate naturally through dialogue with the user. This enables the generation unit to generate an avatar that faithfully reproduces the characteristics and behavioral patterns of the target person, thereby realizing natural dialogue with the user.

[0033] The learning unit continues to learn through the conversation between the avatar generated by the generation unit and the user. For example, the learning unit uses AI to analyze the content of the conversation with the user and incorporates new information and reactions. Specifically, the learning unit records the questions and remarks made by the user to the avatar and updates the avatar's knowledge base. For example, if the user begins to have a new hobby or interest, the information is added to the avatar's knowledge base and the information is used in the next conversation. The learning unit can also analyze the user's reaction and improve the avatar's response. For example, if the user reacts favorably to a certain response, the response pattern is strengthened, and conversely, if the user reacts negatively, the response pattern is modified. Furthermore, the learning unit can learn the behavioral patterns of the avatar through conversation with the user and realize more natural conversation. For example, the AI ​​is used to cluster the content of the conversation with the user and optimize the avatar's response pattern. The learning unit continuously performs these learning processes and always keeps the avatar's knowledge and response patterns up to date. This allows the learning unit to improve the performance of the avatar through conversation with the user and realize more natural and effective communication. Furthermore, the learning unit can collect feedback from the user and continuously improve the avatar's responses and actions. For example, a function is provided for the user to evaluate the avatar's responses, and the avatar's responses are adjusted based on the evaluation results. This allows the learning unit to provide a high-quality avatar that meets the user's needs and expectations, improving the user experience.

[0034] The collection unit can collect data on photos, videos, voices, remarks, personalities, habits, tastes, and human relationships. The collection unit, for example, collects photos and videos provided by the user in a digital format. For example, the collection unit uploads photos and videos taken with a smartphone or digital camera to cloud storage. The collection unit can also collect voice data using a microphone. For example, the collection unit collects voice data using a microphone of a smartphone or tablet that the user uses daily. Furthermore, the collection unit can also collect the user's remarks and conversation contents as text data. For example, the collection unit collects the contents of a messaging app or email that the user uses daily as text data. This allows a more detailed life log to be obtained by collecting various data. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can automatically classify photos and videos provided by the user using AI and store them in a database.

[0035] The analysis unit can analyze the collected data and extract the characteristics and behavioral patterns of the subject. The analysis unit can analyze the collected data using, for example, AI and extract the characteristics and behavioral patterns of the subject. For example, the analysis unit can use image analysis technology to recognize the face of the subject from a photo or video. For example, the analysis unit can use a face recognition algorithm to identify the face of a person appearing in a photo or video and extract its features. The analysis unit can also use voice analysis technology to extract the characteristics of the subject's voice from the voice data. For example, the analysis unit can use a voice recognition algorithm to analyze the tone and pitch of the subject's voice from the voice data and extract its features. Furthermore, the analysis unit can also analyze the contents of the subject's remarks from text data using natural language processing technology. For example, the analysis unit can use a text analysis algorithm to analyze the intention and emotions of the subject's remarks from the text data and extract their features. As a result, the characteristics and behavioral patterns of the subject can be clarified by analyzing the data. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can automatically analyze the collected data using AI and extract the characteristics and behavioral patterns of the subjects.

[0036] The generation unit can generate an alter ego based on the analysis result. The generation unit generates an alter ego that imitates the characteristics and behavioral patterns of the subject using, for example, AI. For example, the generation unit imitates the content of the subject's speech using a text generation AI (for example, LLM). For example, the generation unit can learn the subject's past speech data and generate natural dialogue. The generation unit can also reproduce the subject's face and facial expression using an image generation AI. For example, the generation unit can generate a realistic digital avatar based on the subject's photo data. Furthermore, the generation unit can also reproduce the subject's voice using a voice generation AI. For example, the generation unit can generate a natural voice based on the subject's voice data. This makes it possible to create an alter ego that is close to the subject by generating an alter ego based on the analysis result. Part or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can automatically process the analysis result using AI to generate an alter ego.

[0037] The learning unit can incorporate new information or reactions through conversations with the user. The learning unit, for example, uses AI to analyze the contents of the conversation with the user and incorporates new information and reactions. For example, the learning unit records questions and remarks made by the user to the avatar and updates the avatar's knowledge base. For example, when the user says, "I saw a movie recently," the avatar shows interest by asking, "What kind of movie did you see?" and continues the conversation. The learning unit can also analyze the user's reactions and improve the avatar's responses. For example, if the user shows a positive reaction to the avatar's response, the learning unit strengthens the response pattern. Furthermore, the learning unit can learn the avatar's behavioral patterns through conversations with the user and realize more natural dialogue. For example, the learning unit learns words and phrases that the user uses on a daily basis and reflects them in the avatar's responses. As a result, the avatar becomes closer to the target person by continuing to learn through conversations with the user. Some or all of the above-mentioned processing in the learning unit may be performed, for example, using AI, or may be performed without using AI. For example, the learning unit can automatically analyze the content of conversations with users using AI and incorporate new information and responses.

[0038] The generation unit can implement the alter ego in the robot. The generation unit implements the alter ego generated using, for example, AI in the robot. For example, the generation unit equips a domestic robot with an alter ego and provides a function of interacting with a user. For example, the generation unit can reproduce the voice of the alter ego using a voice synthesis system of the robot. The generation unit can also reproduce the action of the alter ego using a motion control system of the robot. For example, the generation unit controls the joints and motors of the robot to reproduce the gestures and facial expressions of the alter ego. Furthermore, the generation unit can detect the user's movements and facial expressions using the robot's sensor system and reflect them in the response of the alter ego. For example, the generation unit analyzes the user's facial expressions and tone of voice using the robot's camera and microphone, and adjusts the response of the alter ego. As a result, by implementing the alter ego in the robot, physical interaction becomes possible. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can automatically generate the actions and responses of the alter ego using AI and implement them in the robot.

[0039] The generation unit can output the alter ego as a digital avatar. The generation unit outputs the alter ego generated using, for example, AI as a digital avatar. For example, the generation unit can display the alter ego as a digital avatar through an application on a smartphone or tablet. For example, the generation unit generates the facial and body movements of the digital avatar in real time to provide a function of interacting with a user. The generation unit can also generate the voice of the digital avatar to realize a conversation with a user. For example, the generation unit uses a voice synthesis technology to generate the voice of the alter ego in real time and respond to the user. Furthermore, the generation unit can generate facial expressions and gestures of the digital avatar to make the conversation with the user more natural. For example, the generation unit uses a facial expression recognition technology to generate facial expressions of the digital avatar according to the user's facial expression. As a result, the alter ego is output as a digital avatar, making it possible to have a conversation on a digital device. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can use AI to automatically generate movements and responses for a digital avatar and output them to a digital device.

[0040] The collection unit can analyze the user's past life log collection history and select a collection method. The collection unit can analyze the user's past life log collection history using, for example, AI, and select an optimal collection method. For example, the collection unit prioritizes collection of data types that the user has frequently collected in the past. For example, if the user has collected many photos in the past, the collection unit prioritizes collection of photos. The collection unit can also concentrate collection in a specific time period from the user's past collection history. For example, if the user has collected a lot of data in a specific time period in the past, the collection unit concentrates collection in that time period. Furthermore, the collection unit can analyze the user's past collection pattern and determine an optimal collection frequency. For example, if the user has collected data at a certain frequency in the past, the collection unit collects data based on that frequency. In this way, the optimal collection method can be selected by analyzing the past collection history. Part or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can automatically analyze the user's past collection history using AI and select an optimal collection method.

[0041] The collection unit can perform filtering based on the user's current living situation and areas of interest when collecting a life log. The collection unit performs filtering based on the user's current living situation and areas of interest when collecting a life log, for example, using AI. For example, when the user is traveling, the collection unit preferentially collects photos and videos related to the trip. For example, the collection unit analyzes the user's location information and collects photos and videos taken at the travel destination. In addition, when the user starts a new hobby, the collection unit can also collect data related to the hobby. For example, the collection unit analyzes the user's social media activity and collects posts and photos related to the new hobby. Furthermore, when the user is working on a specific project, the collection unit can also collect remarks and voices related to the project. For example, the collection unit analyzes the content of the user's conversation and collects remarks and voices related to the project. In this way, highly relevant data can be collected by filtering data based on the user's living situation and areas of interest. A part or all of the above-mentioned processing in the collection unit may be performed using AI, for example, or may be performed without using AI. For example, the collection unit can use AI to analyze a user's living situation and areas of interest in real time and filter the collected data.

[0042] The collection unit can preferentially collect highly relevant data in consideration of the geographical location information of the user when collecting a life log. The collection unit, for example, uses AI to preferentially collect highly relevant data in consideration of the geographical location information of the user when collecting a life log. For example, when the user is in a specific location, the collection unit collects photos and videos related to the location. For example, the collection unit analyzes the GPS data of the user, and when it is determined that the user is in a specific location, it starts collecting photos and videos related to the location. In addition, when the user is traveling, the collection unit can also collect data based on geographical information of the travel destination. For example, the collection unit analyzes the user's location information and collects photos and videos taken at the travel destination. Furthermore, when the user is participating in a specific event, the collection unit can also collect data related to the event. For example, the collection unit analyzes the user's location information, and when it is determined that the user is participating in a specific event, it starts collecting photos and videos related to the event. In this way, highly relevant data can be collected by considering the geographical location information of the user. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can use AI to analyze a user's geographic location information in real time and automatically select collected data.

[0043] The collection unit can analyze the user's social media activities and collect related data when collecting the life log. The collection unit can use, for example, AI to analyze the user's social media activities and collect related data when collecting the life log. For example, the collection unit collects photos and videos shared by the user on social media. For example, the collection unit analyzes the user's social media account and automatically collects the shared photos and videos. The collection unit can also collect the content of the user's comments on social media. For example, the collection unit analyzes the user's posts and collects the comments as text data. Furthermore, the collection unit can also collect data related to topics in which the user showed interest on social media. For example, the collection unit analyzes the user's "likes" and comments and collects data related to the topics in which the user showed interest. In this way, the user's social media activities can be analyzed to collect related data. Part or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can analyze the user's social media activities in real time using AI and automatically collect related data.

[0044] The analysis unit can adjust the level of detail of the analysis based on the importance of the life log during the analysis. The analysis unit adjusts the level of detail of the analysis based on the importance of the life log during the analysis, for example, using AI. For example, the analysis unit analyzes data related to important events in detail. For example, when a user participates in a specific event, the analysis unit analyzes data related to the event in detail. The analysis unit can also briefly analyze data related to daily events. For example, the analysis unit briefly analyzes data related to the user's daily behavior. Furthermore, the analysis unit can also analyze data in detail in which the user has shown particular interest. For example, when a user has shown interest in a specific topic, the analysis unit analyzes data related to the topic in detail. As a result, important data can be analyzed in detail by adjusting the level of detail of the analysis based on the importance of the life log. Part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can automatically evaluate the importance of the life log using AI and adjust the level of detail of the analysis.

[0045] The analysis unit can apply different analysis algorithms depending on the category of the life log during analysis. The analysis unit can apply different analysis algorithms depending on the category of the life log during analysis, for example, using AI. For example, the analysis unit applies an image analysis algorithm to photos and videos. For example, the analysis unit uses image recognition technology to identify people and objects appearing in photos and videos and analyze their features. The analysis unit can also apply a voice analysis algorithm to voice data. For example, the analysis unit uses voice recognition technology to analyze the features of the speaker's voice and the contents of the remarks from the voice data. Furthermore, the analysis unit can apply a natural language processing algorithm to the remarks and text data. For example, the analysis unit uses text analysis technology to analyze the speaker's intentions and emotions from the remarks and text data. This allows for more appropriate analysis results to be provided by applying different analysis algorithms depending on the category of the life log. Part or all of the above-mentioned processing in the analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the analysis unit can automatically classify the category of the life log using AI and apply an appropriate analysis algorithm.

[0046] The analysis unit can determine the priority of the analysis based on the collection time of the life log during the analysis. The analysis unit determines the priority of the analysis based on the collection time of the life log during the analysis, for example, using AI. For example, the analysis unit preferentially analyzes recently collected data. For example, the analysis unit preferentially analyzes photos and videos recently taken by the user. The analysis unit can also preferentially analyze data related to a specific event. For example, if the user participates in a specific event, the analysis unit preferentially analyzes data related to the event. Furthermore, the analysis unit can also preferentially analyze data in which the user has shown particular interest. For example, if the user has shown interest in a specific topic, the analysis unit preferentially analyzes data related to the topic. In this way, by determining the priority of the analysis based on the collection time of the life log, the latest data can be preferentially analyzed. Part or all of the above-mentioned processing in the analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the analysis unit can automatically evaluate the collection time of the life log using AI and determine the priority of the analysis.

[0047] The analysis unit can adjust the order of analysis based on the relevance of the life log during analysis. The analysis unit adjusts the order of analysis based on the relevance of the life log during analysis, for example, using AI. For example, the analysis unit prioritizes analysis of highly relevant data. For example, when a user shows interest in a specific topic, the analysis unit prioritizes analysis of data related to the topic. The analysis unit can also postpone data with low relevance. For example, the analysis unit postpones data in which the user shows little interest. Furthermore, the analysis unit can also prioritize analysis of data in which the user shows particular interest. For example, the analysis unit prioritizes analysis of data that the user frequently accesses. As a result, by adjusting the order of analysis based on the relevance of the life log, highly relevant data can be prioritized for analysis. Part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can automatically evaluate the relevance of the life log using AI and adjust the order of analysis.

[0048] The generation unit can adjust the level of detail of the generation based on the importance of the analysis result when generating the avatar. The generation unit adjusts the level of detail of the generation based on the importance of the analysis result when generating the avatar, for example, using AI. For example, the generation unit reflects data related to important events in detail. For example, if the user participates in a specific event, the generation unit reflects data related to the event in detail. The generation unit can also briefly reflect data related to daily events. For example, the generation unit briefly reflects data related to the user's daily actions. Furthermore, the generation unit can also reflect data in detail in which the user has shown particular interest. For example, if the user has shown interest in a specific topic, the generation unit reflects data related to the topic in detail. Thereby, important data can be reflected in detail by adjusting the level of detail of the generation based on the importance of the analysis result. Part or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can automatically evaluate the importance of the analysis result using AI and adjust the level of detail of the generation.

[0049] The generation unit can apply different generation algorithms according to the category of the analysis result when generating the avatar. The generation unit applies different generation algorithms according to the category of the analysis result when generating the avatar, for example, using AI. For example, the generation unit applies an image generation algorithm to photos and videos. For example, the generation unit uses image recognition technology to identify people and objects appearing in photos and videos, analyzes their features, and applies an image generation algorithm. The generation unit can also apply a voice generation algorithm to voice data. For example, the generation unit uses voice recognition technology to analyze the features of the speaker's voice and the contents of the remarks from the voice data, and applies a voice generation algorithm. Furthermore, the generation unit can also apply a natural language generation algorithm to the remarks and text data. For example, the generation unit uses text analysis technology to analyze the speaker's intentions and emotions from the remarks and text data, and applies a natural language generation algorithm. This allows a more appropriate avatar to be generated by applying different generation algorithms according to the category of the analysis result. A part or all of the above-mentioned processing in the generation unit may be performed using AI, for example, or may be performed without using AI. For example, the generation unit can use AI to automatically classify categories of analysis results and apply appropriate generation algorithms.

[0050] The generation unit can determine the priority of generation based on the time when the analysis result was collected when the avatar was generated. The generation unit determines the priority of generation based on the time when the analysis result was collected when the avatar was generated, for example, using AI. For example, the generation unit preferentially reflects recently collected data. For example, the generation unit preferentially reflects photos and videos recently taken by the user. The generation unit can also preferentially reflect data related to a specific event. For example, if the user participates in a specific event, the generation unit preferentially reflects data related to the event. Furthermore, the generation unit can also preferentially reflect data in which the user showed a particular interest. For example, if the user shows an interest in a specific topic, the generation unit preferentially reflects data related to the topic. In this way, by determining the priority of generation based on the time when the analysis result was collected, the latest data can be preferentially reflected. Part or all of the above-mentioned processing in the generation unit may be performed using AI, for example, or may be performed without using AI. For example, the generation unit can automatically evaluate the time when the analysis result was collected using AI and determine the priority of generation.

[0051] The generation unit can adjust the order of generation based on the relevance of the analysis result when generating the avatar. The generation unit adjusts the order of generation based on the relevance of the analysis result when generating the avatar, for example, using AI. For example, the generation unit preferentially reflects highly relevant data. For example, if the user shows interest in a specific topic, the generation unit preferentially reflects data related to the topic. The generation unit can also postpone data with low relevance. For example, the generation unit postpones data in which the user shows little interest. Furthermore, the generation unit can also preferentially reflect data in which the user shows particular interest. For example, the generation unit preferentially reflects data that the user frequently accesses. Thereby, by adjusting the order of generation based on the relevance of the analysis result, highly relevant data can be preferentially reflected. Part or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can automatically evaluate the relevance of the analysis result using AI and adjust the order of generation.

[0052] The learning unit can optimize the learning algorithm by referring to past learning data during learning. The learning unit optimizes the learning algorithm by referring to past learning data, for example, using AI during learning. For example, the learning unit selects an optimal learning algorithm based on past learning data. For example, the learning unit analyzes past learning data, extracts an effective learning pattern, and selects a learning algorithm based on the pattern. The learning unit can also extract an effective learning pattern from the past learning data. For example, the learning unit clusters the past learning data and identifies an effective learning pattern. Furthermore, the learning unit can analyze the past learning data and improve the learning algorithm. For example, the learning unit adjusts parameters of the learning algorithm based on the past learning data to improve the accuracy of learning. As a result, the learning algorithm can be optimized by referring to the past learning data. A part or all of the above-mentioned processing in the learning unit may be performed using AI, for example, or may be performed without using AI. For example, the learning unit can automatically analyze past learning data using AI to optimize the learning algorithm.

[0053] The learning unit can adjust the level of detail of the learning based on the user's reaction during learning. The learning unit adjusts the level of detail of the learning based on the user's reaction during learning, for example, using AI. For example, the learning unit performs detailed learning when the user reacts actively. For example, the learning unit performs detailed learning when it is determined that the user is reacting actively by analyzing the user's facial expression and tone of voice. In addition, the learning unit can also perform brief learning when the user does not react. For example, the learning unit performs brief learning when it is determined that the user's reaction is poor. Furthermore, the learning unit can also adjust the progress speed of the learning according to the user's reaction. For example, the learning unit speeds up the progress speed of the learning when the user shows interest. As a result, more effective learning can be performed by adjusting the level of detail of the learning according to the user's reaction. Part or all of the above-mentioned processing in the learning unit may be performed using AI, for example, or may be performed without using AI. For example, the learning unit can analyze the user's reaction in real time using AI and automatically adjust the level of detail of the learning.

[0054] The learning unit can weight the learning data based on the user's conversation history during learning. The learning unit weights the learning data based on the user's conversation history during learning, for example, using AI. For example, the learning unit weights words and phrases frequently used by the user. For example, the learning unit analyzes the user's conversation history and weights frequently used words and phrases highly. The learning unit can also weight based on how often the user talks about a specific topic. For example, if the user talks frequently about a specific topic, the learning unit weights data related to the topic highly. Furthermore, the learning unit can weight important information from the user's conversation history. For example, the learning unit weights information in which the user has shown particular interest highly. As a result, more effective learning can be performed by weighting the learning data based on the user's conversation history. Part or all of the above-mentioned processing in the learning unit may be performed using AI, for example, or may be performed without using AI. For example, the learning unit can automatically analyze the user's conversation history using AI and weight the learning data.

[0055] The learning unit can determine the priority of learning based on the user's living situation when learning. The learning unit determines the priority of learning based on the user's living situation when learning, for example, using AI. For example, when the user starts a new hobby, the learning unit prioritizes learning related to the hobby. For example, the learning unit analyzes the user's social media activity and performs learning based on posts and photos related to the new hobby. In addition, when the user is working on a specific project, the learning unit can also prioritize learning related to the project. For example, the learning unit analyzes the content of the user's conversation and performs learning based on remarks and voices related to the project. Furthermore, the learning unit can adjust the priority of learning according to the user's living situation. For example, when the user is at work, the learning unit prioritizes work-related learning. As a result, more effective learning can be performed by determining the priority of learning based on the user's living situation. Part or all of the above-mentioned processing in the learning unit may be performed using AI, for example, or may be performed without using AI. For example, the learning unit can analyze the user's living situation in real time using AI and automatically determine the priority of learning.

[0056] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0057] The collection unit can collect biometric information of the user and monitor the health condition. For example, the collection unit can measure the user's heart rate and blood pressure with a sensor and collect data. The collection unit can also track the user's sleep pattern and evaluate the quality of sleep. Furthermore, the collection unit can record the user's amount of exercise and grasp the user's daily activity level. This makes it possible to monitor the user's health condition in real time and issue an alert if necessary.

[0058] The analysis unit can analyze the user's health data and predict health risks. For example, the analysis unit can analyze heart rate and blood pressure data to detect abnormal patterns. The analysis unit can also analyze sleep data to identify signs of sleep disorders. Furthermore, the analysis unit can analyze exercise data to evaluate the risk of insufficient or excessive exercise. This allows the user's health risks to be discovered early and appropriate measures to be taken.

[0059] The generating unit can generate personalized health advice based on the user's health data. For example, the generating unit can provide appropriate exercise and diet advice based on the user's heart rate and blood pressure data. The generating unit can also provide advice for improving sleep quality based on the sleep data. Furthermore, the generating unit can customize the user's exercise plan based on the exercise data. This allows the user to receive specific advice according to their own health condition.

[0060] The learning unit can learn changes in health condition based on the user's health data and improve prediction accuracy. For example, the learning unit can learn past heart rate and blood pressure data and predict future health risks. The learning unit can also learn sleep data and predict changes in sleep patterns. Furthermore, the learning unit can learn exercise data and predict changes in exercise habits. This makes it possible to detect changes in the user's health condition early and take appropriate measures.

[0061] The collection unit can analyze the user's social media activity and collect related health data. For example, the collection unit collects photos of exercise and meals shared by the user on social media. The collection unit can also collect health-related comments made by the user on social media. Furthermore, the collection unit can collect data related to health topics in which the user has shown interest on social media. In this way, by analyzing the user's social media activity, related health data can be collected and a more detailed health condition can be understood.

[0062] The analysis unit can perform personalized health risk prediction based on the user's health data. For example, the analysis unit can analyze the user's heart rate and blood pressure data to predict individual health risks. The analysis unit can also analyze sleep data to predict the user's specific risk of sleep disorders. Furthermore, the analysis unit can analyze exercise data to predict health risks based on the user's exercise habits. This allows the user's individual health risks to be discovered early and appropriate measures to be taken.

[0063] The process flow of the first embodiment will be briefly described below.

[0064] Step 1: The collection unit collects a life log. The life log includes photos, videos, audio, statements, personality, habits, tastes, and human relationships. The collection unit can collect photos and videos provided by the user in digital format and can also collect audio data using a microphone. It can also collect the user's statements and conversation content as text data. For example, the collection unit collects data from a smartphone or tablet that the user uses on a daily basis. Step 2: The analysis unit analyzes the life logs collected by the collection unit. The analysis unit uses AI to analyze the collected data and extracts the characteristics and behavioral patterns of the subject. For example, image analysis technology can be used to recognize the subject's face from photos and videos, and audio analysis technology can be used to extract the characteristics of the subject's voice from audio data. In addition, natural language processing technology can be used to analyze the content of the subject's statements from text data. The analysis unit uses AI to cluster the collected data and identify the subject's behavioral patterns. Step 3: The generation unit generates an avatar based on the results of the analysis by the analysis unit. The generation unit uses AI to generate an avatar that mimics the characteristics and behavioral patterns of the target person. For example, it can use a text generation AI (e.g., LLM) to mimic the content of the target person's speech, and an image generation AI to reproduce the target person's face and expressions. In addition, it can use a voice generation AI to reproduce the target person's voice. The generation unit uses AI to learn the characteristics of the target person and generate the avatar's actions and speech. Step 4: The learning unit continues to learn through conversations between the avatar generated by the generation unit and the user. The learning unit uses AI to analyze the content of the conversation with the user and incorporates new information and reactions. For example, it records questions and comments made by the user to the avatar and updates the avatar's knowledge base. It can also analyze the user's reactions and improve the avatar's responses. Furthermore, it can learn the avatar's behavioral patterns through conversations with the user and achieve more natural dialogue. The learning unit uses AI to cluster the content of the conversation with the user and optimize the avatar's response patterns.

[0065] (Example 2) The system according to the embodiment of the present invention is a system that generates an "AI-generated avatar" by using life logs such as photos, videos, audio, statements, personality, customs, tastes, and relationships of family members and the user as training data. In this system, the user can converse with the avatar, and the avatar continues to learn through the conversation. This allows the user or a loved one to continue to exist in society semi-permanently even after the death of the user. This avatar can be implemented in a robot or output as a digital avatar. For example, the user inputs the life log of the user and his / her family into the system. The life log includes photos, videos, audio, statements, personality, customs, tastes, and relationships. These data are analyzed by AI, and the characteristics and behavioral patterns of the target person are extracted. Next, the AI ​​generates an avatar based on the extracted characteristics and behavioral patterns. This avatar can mimic the personality and behavior of the target person and can have a natural conversation with the user. For example, when the user asks, "What's the weather like today?", the avatar responds, "It's sunny today. It's perfect for going outside." Furthermore, the avatar continues to learn through conversation with the user. By incorporating new information and the user's reactions, the avatar becomes closer to the target person. For example, if the user says, "I saw a movie recently," the avatar will show interest and ask, "What kind of movie did you see?" and continue the conversation. This avatar can be implemented in a robot. For example, by installing the avatar in a household robot, the user can live their daily life while interacting with the robot. It can also be output as a digital avatar, and the user can enjoy conversations with the avatar through a smartphone or tablet. This system makes it possible to continue to exist in society semi-permanently even after the death of a loved one or oneself. For example, even after a family member passes away, you can continue to share family memories by continuing to talk to that person's avatar. Also, by creating your own avatar, you can pass on your experiences and knowledge to future generations. This allows the AI-based avatar system to generate avatars based on the user's life log and continue learning through conversations with the user.

[0066] The AI ​​avatar system according to the embodiment includes a collection unit, an analysis unit, a generation unit, and a learning unit. The collection unit collects a life log. The life log includes, for example, photos, videos, voices, remarks, personalities, habits, tastes, and human relationships, but is not limited to such examples. The collection unit, for example, collects photos and videos provided by the user in a digital format. The collection unit can also collect voice data using a microphone. Furthermore, the collection unit can also collect the user's remarks and conversation content as text data. For example, the collection unit collects data from a smartphone or tablet that the user uses on a daily basis. The analysis unit analyzes the life log collected by the collection unit. For example, the analysis unit analyzes the collected data using AI to extract the characteristics and behavioral patterns of the subject. For example, the analysis unit performs facial recognition of the subject from photos and videos using image analysis technology. Furthermore, the analysis unit can also extract the characteristics of the subject's voice from the voice data using voice analysis technology. Furthermore, the analysis unit can also analyze the subject's remarks from the text data using natural language processing technology. For example, the analysis unit clusters the collected data using AI and identifies the behavioral pattern of the subject. The generation unit generates an alter-ego based on the results of the analysis by the analysis unit. For example, the generation unit generates an alter-ego that imitates the characteristics and behavioral patterns of the subject using AI. For example, the generation unit imitates the content of the subject's remarks using a text generation AI (e.g., LLM). The generation unit can also reproduce the face and expressions of the subject using an image generation AI. Furthermore, the generation unit can also reproduce the voice of the subject using a voice generation AI. For example, the generation unit learns the characteristics of the subject using AI and generates the actions and remarks of the alter-ego. The learning unit allows the alter-ego generated by the generation unit to continue learning through conversation with the user. For example, the learning unit uses AI to analyze the content of the conversation with the user and incorporates new information and reactions. For example, the learning unit records questions and remarks made by the user to the alter-ego and updates the alter-ego's knowledge base. The learning unit can also analyze the user's reactions and improve the responses of the alter-ego. Furthermore, the learning unit can learn the behavioral patterns of the avatar through conversation with the user, thereby realizing more natural dialogue.For example, the learning unit uses AI to cluster the contents of a conversation with a user and optimize the response pattern of the avatar. This allows the AI ​​avatar system according to the embodiment to generate an avatar based on the user's life log and continue learning through conversations with the user.

[0067] The collection unit collects a life log. The life log includes, but is not limited to, for example, photos, videos, voices, remarks, personality, habits, tastes, and human relationships. The collection unit, for example, collects photos and videos provided by the user in a digital format. Specifically, the collection unit collects photos and videos taken by the user on a daily basis through cloud storage or a dedicated application, and manages these data in a centralized manner. The collection unit can also collect voice data using a microphone. For example, the voice uttered by the user through a smartphone or smart speaker is collected in real time and stored in a voice database. Furthermore, the collection unit can also collect the user's remarks and conversation contents as text data. For example, the communication performed by the user through a chat app or email is collected in text format and stored in a database for analysis using natural language processing technology. When collecting these data, the collection unit introduces encryption technology and access control to protect the user's privacy and ensures the safety of the data. For example, the collected data is end-to-end encrypted so that only systems and users who have received specific authentication can access it. This enables the collection unit to efficiently collect a wide range of life log data from a variety of devices and platforms, improving data quality across the system while protecting user privacy.

[0068] The analysis unit analyzes the life log collected by the collection unit. The analysis unit, for example, uses AI to analyze the collected data and extracts the characteristics and behavioral patterns of the subject. Specifically, the analysis unit uses image analysis technology to recognize the subject's face from photos and videos. For example, a face recognition algorithm using deep learning is applied to extract the facial features of the subject and compare them with existing face data in the database. The analysis unit can also extract the characteristics of the subject's voice from the voice data using voice analysis technology. For example, a spectrum analysis of the voice waveform is performed to extract features such as the pitch, tone, and speaking speed of the voice, and a profile of the subject's voice is created. Furthermore, the analysis unit can analyze the content of the subject's remarks from text data using natural language processing technology. For example, topic modeling and emotion analysis are performed to identify the subject's remarks and emotional state. The analysis unit combines these technologies to comprehensively analyze the subject's behavioral patterns, preferences, and personality characteristics. For example, the analysis unit uses AI to cluster the collected data and identify the subject's behavioral patterns. This allows the analysis unit to analyze the collected life log data from multiple angles and create a detailed profile of the subject. Furthermore, the analysis unit can update the analysis results in real time to reflect the subject's latest actions and status. This allows the analysis unit to always provide highly accurate analysis based on the latest information, improving the reliability and usefulness of the entire system.

[0069] The generation unit generates the avatar based on the results of the analysis by the analysis unit. The generation unit generates the avatar that imitates the characteristics and behavioral patterns of the target person using, for example, AI. Specifically, it imitates the content of the target person's speech using a text generation AI (for example, LLM). For example, it uses an LLM that has learned the target person's past speech data to generate content that the target person is likely to actually say. The generation unit can also reproduce the target person's face and facial expression using an image generation AI. For example, it uses a GAN (generative artificial network) to learn the facial features of the target person and generate a realistic facial image and facial expression. Furthermore, the generation unit can also reproduce the target person's voice using a voice generation AI. For example, it uses a voice synthesis technology to learn the characteristics of the target person's voice and generate a natural voice. The generation unit combines these technologies to learn the characteristics of the target person and generate the actions and statements of the avatar. For example, it uses an AI to learn the characteristics of the target person and generate the actions and statements of the avatar. The generation unit can also adjust the actions and statements of the generated avatar in real time so that the generated avatar can communicate naturally through dialogue with the user. This enables the generation unit to generate an avatar that faithfully reproduces the characteristics and behavioral patterns of the target person, thereby realizing natural dialogue with the user.

[0070] The learning unit continues to learn through the conversation between the avatar generated by the generation unit and the user. For example, the learning unit uses AI to analyze the content of the conversation with the user and incorporates new information and reactions. Specifically, the learning unit records the questions and remarks made by the user to the avatar and updates the avatar's knowledge base. For example, if the user begins to have a new hobby or interest, the information is added to the avatar's knowledge base and the information is used in the next conversation. The learning unit can also analyze the user's reaction and improve the avatar's response. For example, if the user reacts favorably to a certain response, the response pattern is strengthened, and conversely, if the user reacts negatively, the response pattern is modified. Furthermore, the learning unit can learn the behavioral patterns of the avatar through conversation with the user and realize more natural conversation. For example, the AI ​​is used to cluster the content of the conversation with the user and optimize the avatar's response pattern. The learning unit continuously performs these learning processes and always keeps the avatar's knowledge and response patterns up to date. This allows the learning unit to improve the performance of the avatar through conversation with the user and realize more natural and effective communication. Furthermore, the learning unit can collect feedback from the user and continuously improve the avatar's responses and actions. For example, a function is provided for the user to evaluate the avatar's responses, and the avatar's responses are adjusted based on the evaluation results. This allows the learning unit to provide a high-quality avatar that meets the user's needs and expectations, improving the user experience.

[0071] The collection unit can collect data on photos, videos, voices, remarks, personalities, habits, tastes, and human relationships. The collection unit, for example, collects photos and videos provided by the user in a digital format. For example, the collection unit uploads photos and videos taken with a smartphone or digital camera to cloud storage. The collection unit can also collect voice data using a microphone. For example, the collection unit collects voice data using a microphone of a smartphone or tablet that the user uses daily. Furthermore, the collection unit can also collect the user's remarks and conversation contents as text data. For example, the collection unit collects the contents of a messaging app or email that the user uses daily as text data. This allows a more detailed life log to be obtained by collecting various data. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can automatically classify photos and videos provided by the user using AI and store them in a database.

[0072] The analysis unit can analyze the collected data and extract the characteristics and behavioral patterns of the subject. The analysis unit can analyze the collected data using, for example, AI and extract the characteristics and behavioral patterns of the subject. For example, the analysis unit can use image analysis technology to recognize the face of the subject from a photo or video. For example, the analysis unit can use a face recognition algorithm to identify the face of a person appearing in a photo or video and extract its features. The analysis unit can also use voice analysis technology to extract the characteristics of the subject's voice from the voice data. For example, the analysis unit can use a voice recognition algorithm to analyze the tone and pitch of the subject's voice from the voice data and extract its features. Furthermore, the analysis unit can also analyze the contents of the subject's remarks from text data using natural language processing technology. For example, the analysis unit can use a text analysis algorithm to analyze the intention and emotions of the subject's remarks from the text data and extract their features. As a result, the characteristics and behavioral patterns of the subject can be clarified by analyzing the data. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can automatically analyze the collected data using AI and extract the characteristics and behavioral patterns of the subjects.

[0073] The generation unit can generate an alter ego based on the analysis result. The generation unit generates an alter ego that imitates the characteristics and behavioral patterns of the subject using, for example, AI. For example, the generation unit imitates the content of the subject's speech using a text generation AI (for example, LLM). For example, the generation unit can learn the subject's past speech data and generate natural dialogue. The generation unit can also reproduce the subject's face and facial expression using an image generation AI. For example, the generation unit can generate a realistic digital avatar based on the subject's photo data. Furthermore, the generation unit can also reproduce the subject's voice using a voice generation AI. For example, the generation unit can generate a natural voice based on the subject's voice data. This makes it possible to create an alter ego that is close to the subject by generating an alter ego based on the analysis result. Part or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can automatically process the analysis result using AI to generate an alter ego.

[0074] The learning unit can incorporate new information or reactions through conversations with the user. The learning unit, for example, uses AI to analyze the contents of the conversation with the user and incorporates new information and reactions. For example, the learning unit records questions and remarks made by the user to the avatar and updates the avatar's knowledge base. For example, when the user says, "I saw a movie recently," the avatar shows interest by asking, "What kind of movie did you see?" and continues the conversation. The learning unit can also analyze the user's reactions and improve the avatar's responses. For example, if the user shows a positive reaction to the avatar's response, the learning unit strengthens the response pattern. Furthermore, the learning unit can learn the avatar's behavioral patterns through conversations with the user and realize more natural dialogue. For example, the learning unit learns words and phrases that the user uses on a daily basis and reflects them in the avatar's responses. As a result, the avatar becomes closer to the target person by continuing to learn through conversations with the user. Some or all of the above-mentioned processing in the learning unit may be performed, for example, using AI, or may be performed without using AI. For example, the learning unit can automatically analyze the content of conversations with users using AI and incorporate new information and responses.

[0075] The generation unit can implement the alter ego in the robot. The generation unit implements the alter ego generated using, for example, AI in the robot. For example, the generation unit equips a domestic robot with an alter ego and provides a function of interacting with a user. For example, the generation unit can reproduce the voice of the alter ego using a voice synthesis system of the robot. The generation unit can also reproduce the action of the alter ego using a motion control system of the robot. For example, the generation unit controls the joints and motors of the robot to reproduce the gestures and facial expressions of the alter ego. Furthermore, the generation unit can detect the user's movements and facial expressions using the robot's sensor system and reflect them in the response of the alter ego. For example, the generation unit analyzes the user's facial expressions and tone of voice using the robot's camera and microphone, and adjusts the response of the alter ego. As a result, by implementing the alter ego in the robot, physical interaction becomes possible. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can automatically generate the actions and responses of the alter ego using AI and implement them in the robot.

[0076] The generation unit can output the alter ego as a digital avatar. The generation unit outputs the alter ego generated using, for example, AI as a digital avatar. For example, the generation unit can display the alter ego as a digital avatar through an application on a smartphone or tablet. For example, the generation unit generates the facial and body movements of the digital avatar in real time to provide a function of interacting with a user. The generation unit can also generate the voice of the digital avatar to realize a conversation with a user. For example, the generation unit uses a voice synthesis technology to generate the voice of the alter ego in real time and respond to the user. Furthermore, the generation unit can generate facial expressions and gestures of the digital avatar to make the conversation with the user more natural. For example, the generation unit uses a facial expression recognition technology to generate facial expressions of the digital avatar according to the user's facial expression. As a result, the alter ego is output as a digital avatar, making it possible to have a conversation on a digital device. A part or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can use AI to automatically generate movements and responses for a digital avatar and output them to a digital device.

[0077] The collection unit can estimate the user's emotions and adjust the timing of collecting the life log based on the estimated user's emotions. The collection unit, for example, uses AI to estimate the user's emotions and adjusts the timing of collecting the life log based on the estimated emotions. For example, the collection unit collects photos and videos when the user is relaxed. For example, the collection unit analyzes the user's facial expressions with a camera and starts collecting photos and videos when it determines that the user is relaxed. The collection unit can also refrain from collecting voices and remarks when the user is stressed. For example, the collection unit analyzes the tone and speed of the user's voice and suspends the collection of voices and remarks when it determines that the user is stressed. Furthermore, the collection unit can also collect data on the user's personality and preferences when the user is emotionally stable. For example, the collection unit measures the user's heart rate and electrodermal activity with a sensor and starts collecting data on the user's personality and preferences when it determines that the user is emotionally stable. This allows more appropriate data to be collected by adjusting the collection timing according to the user's emotions. The estimation of emotions is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can analyze the user's emotions in real time using AI and automatically adjust the collection timing.

[0078] The collection unit can analyze the user's past life log collection history and select a collection method. The collection unit can analyze the user's past life log collection history using, for example, AI, and select an optimal collection method. For example, the collection unit prioritizes collection of data types that the user has frequently collected in the past. For example, if the user has collected many photos in the past, the collection unit prioritizes collection of photos. The collection unit can also concentrate collection in a specific time period from the user's past collection history. For example, if the user has collected a lot of data in a specific time period in the past, the collection unit concentrates collection in that time period. Furthermore, the collection unit can analyze the user's past collection pattern and determine an optimal collection frequency. For example, if the user has collected data at a certain frequency in the past, the collection unit collects data based on that frequency. In this way, the optimal collection method can be selected by analyzing the past collection history. Part or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can automatically analyze the user's past collection history using AI and select an optimal collection method.

[0079] The collection unit can perform filtering based on the user's current living situation and areas of interest when collecting a life log. The collection unit performs filtering based on the user's current living situation and areas of interest when collecting a life log, for example, using AI. For example, when the user is traveling, the collection unit preferentially collects photos and videos related to the trip. For example, the collection unit analyzes the user's location information and collects photos and videos taken at the travel destination. In addition, when the user starts a new hobby, the collection unit can also collect data related to the hobby. For example, the collection unit analyzes the user's social media activity and collects posts and photos related to the new hobby. Furthermore, when the user is working on a specific project, the collection unit can also collect remarks and voices related to the project. For example, the collection unit analyzes the content of the user's conversation and collects remarks and voices related to the project. In this way, highly relevant data can be collected by filtering data based on the user's living situation and areas of interest. Part or all of the above-mentioned processing in the collection unit may be performed using AI, for example, or may be performed without using AI. For example, the collection unit can use AI to analyze a user's living situation and areas of interest in real time and filter the collected data.

[0080] The collection unit can estimate the user's emotions and determine the priority of the life logs to be collected based on the estimated user's emotions. The collection unit, for example, uses AI to estimate the user's emotions and determines the priority of the life logs to be collected based on the estimated emotions. For example, the collection unit preferentially collects positive photos and videos when the user is in a happy mood. For example, the collection unit analyzes the user's facial expression with a camera, and starts collecting positive photos and videos when it determines that the user is in a happy mood. In addition, the collection unit can also preferentially collect voices and statements related to emotions when the user is in a sad mood. For example, the collection unit analyzes the tone and speed of the user's voice, and starts collecting voices and statements related to emotions when it determines that the user is in a sad mood. Furthermore, the collection unit can also preferentially collect data related to interesting events when the user is excited. For example, the collection unit measures the user's heart rate and electrodermal activity with a sensor, and starts collecting data related to interesting events when it determines that the user is excited. In this way, important data can be preferentially collected by determining the priority of the life logs to be collected according to the user's emotions. The estimation of emotions is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can analyze the user's emotions in real time using AI and automatically determine the priority of the life logs to be collected.

[0081] The collection unit can preferentially collect highly relevant data in consideration of the geographical location information of the user when collecting a life log. The collection unit, for example, uses AI to preferentially collect highly relevant data in consideration of the geographical location information of the user when collecting a life log. For example, when the user is in a specific location, the collection unit collects photos and videos related to the location. For example, the collection unit analyzes the GPS data of the user, and when it is determined that the user is in a specific location, it starts collecting photos and videos related to the location. In addition, when the user is traveling, the collection unit can also collect data based on geographical information of the travel destination. For example, the collection unit analyzes the user's location information and collects photos and videos taken at the travel destination. Furthermore, when the user is participating in a specific event, the collection unit can also collect data related to the event. For example, the collection unit analyzes the user's location information, and when it is determined that the user is participating in a specific event, it starts collecting photos and videos related to the event. In this way, highly relevant data can be collected by considering the geographical location information of the user. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can use AI to analyze a user's geographic location information in real time and automatically select collected data.

[0082] The collection unit can analyze the user's social media activities and collect related data when collecting the life log. The collection unit can use, for example, AI to analyze the user's social media activities and collect related data when collecting the life log. For example, the collection unit collects photos and videos shared by the user on social media. For example, the collection unit analyzes the user's social media account and automatically collects the shared photos and videos. The collection unit can also collect the content of the user's comments on social media. For example, the collection unit analyzes the user's posts and collects the comments as text data. Furthermore, the collection unit can also collect data related to topics in which the user showed interest on social media. For example, the collection unit analyzes the user's "likes" and comments and collects data related to the topics in which the user showed interest. In this way, the user's social media activities can be analyzed to collect related data. Part or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can analyze the user's social media activities in real time using AI and automatically collect related data.

[0083] The analysis unit can estimate the user's emotion and adjust the expression method of the analysis based on the estimated user's emotion. The analysis unit, for example, uses AI to estimate the user's emotion and adjusts the expression method of the analysis based on the estimated emotion. For example, the analysis unit provides detailed analysis results when the user is relaxed. For example, the analysis unit analyzes the user's facial expression with a camera and displays detailed analysis results when it is determined that the user is relaxed. The analysis unit can also provide concise analysis results when the user is stressed. For example, the analysis unit analyzes the tone and speed of the user's voice and displays concise analysis results when it is determined that the user is stressed. Furthermore, the analysis unit can also provide visually attractive analysis results when the user is excited. For example, the analysis unit measures the user's heart rate and electrodermal activity with a sensor and displays visually attractive graphs and charts when it is determined that the user is excited. This makes it possible to provide more appropriate analysis results by adjusting the expression method of the analysis according to the user's emotion. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit may analyze the user's emotions in real time using AI and automatically adjust the way the analysis is expressed.

[0084] The analysis unit can adjust the level of detail of the analysis based on the importance of the life log during the analysis. The analysis unit adjusts the level of detail of the analysis based on the importance of the life log during the analysis, for example, using AI. For example, the analysis unit analyzes data related to important events in detail. For example, when a user participates in a specific event, the analysis unit analyzes data related to the event in detail. The analysis unit can also briefly analyze data related to daily events. For example, the analysis unit briefly analyzes data related to the user's daily behavior. Furthermore, the analysis unit can also analyze data in detail in which the user has shown particular interest. For example, when a user has shown interest in a specific topic, the analysis unit analyzes data related to the topic in detail. As a result, important data can be analyzed in detail by adjusting the level of detail of the analysis based on the importance of the life log. Part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can automatically evaluate the importance of the life log using AI and adjust the level of detail of the analysis.

[0085] The analysis unit can apply different analysis algorithms depending on the category of the life log during analysis. The analysis unit can apply different analysis algorithms depending on the category of the life log during analysis, for example, using AI. For example, the analysis unit applies an image analysis algorithm to photos and videos. For example, the analysis unit uses image recognition technology to identify people and objects appearing in photos and videos and analyze their features. The analysis unit can also apply a voice analysis algorithm to voice data. For example, the analysis unit uses voice recognition technology to analyze the features of the speaker's voice and the contents of the remarks from the voice data. Furthermore, the analysis unit can apply a natural language processing algorithm to the remarks and text data. For example, the analysis unit uses text analysis technology to analyze the speaker's intentions and emotions from the remarks and text data. This allows for more appropriate analysis results to be provided by applying different analysis algorithms depending on the category of the life log. Part or all of the above-mentioned processing in the analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the analysis unit can automatically classify the category of the life log using AI and apply an appropriate analysis algorithm.

[0086] The analysis unit can estimate the user's emotions and adjust the length of the analysis based on the estimated user's emotions. The analysis unit, for example, uses AI to estimate the user's emotions and adjusts the length of the analysis based on the estimated emotions. For example, the analysis unit provides a short and to the point analysis result when the user is in a hurry. For example, the analysis unit analyzes the user's facial expression with a camera, and displays a short and to the point analysis result when it is determined that the user is in a hurry. The analysis unit can also provide a detailed analysis result when the user is relaxed. For example, the analysis unit analyzes the tone and speed of the user's voice, and displays a detailed analysis result when it is determined that the user is relaxed. Furthermore, the analysis unit can also provide a visually appealing analysis result when the user is excited. For example, the analysis unit measures the user's heart rate and electrodermal activity with a sensor, and displays a visually appealing graph or chart when it is determined that the user is excited. This allows the length of the analysis to be adjusted according to the user's emotions, thereby providing a more appropriate analysis result. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit may use AI to analyze the user's emotions in real time and automatically adjust the length of the analysis.

[0087] The analysis unit can determine the priority of the analysis based on the collection time of the life log during the analysis. The analysis unit determines the priority of the analysis based on the collection time of the life log during the analysis, for example, using AI. For example, the analysis unit preferentially analyzes recently collected data. For example, the analysis unit preferentially analyzes photos and videos recently taken by the user. The analysis unit can also preferentially analyze data related to a specific event. For example, if the user participates in a specific event, the analysis unit preferentially analyzes data related to the event. Furthermore, the analysis unit can also preferentially analyze data in which the user has shown particular interest. For example, if the user has shown interest in a specific topic, the analysis unit preferentially analyzes data related to the topic. In this way, by determining the priority of the analysis based on the collection time of the life log, the latest data can be preferentially analyzed. Part or all of the above-mentioned processing in the analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the analysis unit can automatically evaluate the collection time of the life log using AI and determine the priority of the analysis.

[0088] The analysis unit can adjust the order of analysis based on the relevance of the life log during analysis. The analysis unit adjusts the order of analysis based on the relevance of the life log during analysis, for example, using AI. For example, the analysis unit prioritizes analysis of highly relevant data. For example, when a user shows interest in a specific topic, the analysis unit prioritizes analysis of data related to the topic. The analysis unit can also postpone data with low relevance. For example, the analysis unit postpones data in which the user shows little interest. Furthermore, the analysis unit can also prioritize analysis of data in which the user shows particular interest. For example, the analysis unit prioritizes analysis of data that the user frequently accesses. As a result, by adjusting the order of analysis based on the relevance of the life log, highly relevant data can be prioritized for analysis. Part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can automatically evaluate the relevance of the life log using AI and adjust the order of analysis.

[0089] The generation unit can estimate the user's emotion and adjust the avatar generation method based on the estimated user's emotion. The generation unit, for example, uses AI to estimate the user's emotion and adjusts the avatar generation method based on the estimated emotion. For example, the generation unit generates a detailed avatar when the user is relaxed. For example, the generation unit analyzes the user's facial expression with a camera and generates a detailed avatar when it is determined that the user is relaxed. The generation unit can also generate a concise avatar when the user is stressed. For example, the generation unit analyzes the tone and speed of the user's voice and generates a concise avatar when it is determined that the user is stressed. Furthermore, the generation unit can also generate a visually attractive avatar when the user is excited. For example, the generation unit measures the user's heart rate and electrodermal activity with a sensor and generates a visually attractive avatar when it is determined that the user is excited. This allows a more appropriate avatar to be generated by adjusting the avatar generation method according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the generation unit may analyze the user's emotions in real time using AI and automatically adjust the method of generating the avatar.

[0090] The generation unit can adjust the level of detail of the generation based on the importance of the analysis result when generating the avatar. The generation unit adjusts the level of detail of the generation based on the importance of the analysis result when generating the avatar, for example, using AI. For example, the generation unit reflects data related to important events in detail. For example, if the user participates in a specific event, the generation unit reflects data related to the event in detail. The generation unit can also briefly reflect data related to daily events. For example, the generation unit briefly reflects data related to the user's daily actions. Furthermore, the generation unit can also reflect data in detail in which the user has shown particular interest. For example, if the user has shown interest in a specific topic, the generation unit reflects data related to the topic in detail. Thereby, important data can be reflected in detail by adjusting the level of detail of the generation based on the importance of the analysis result. Part or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can automatically evaluate the importance of the analysis result using AI and adjust the level of detail of the generation.

[0091] The generation unit can apply different generation algorithms according to the category of the analysis result when generating the avatar. The generation unit applies different generation algorithms according to the category of the analysis result when generating the avatar, for example, using AI. For example, the generation unit applies an image generation algorithm to photos and videos. For example, the generation unit uses image recognition technology to identify people and objects appearing in photos and videos, analyzes their features, and applies an image generation algorithm. The generation unit can also apply a voice generation algorithm to voice data. For example, the generation unit uses voice recognition technology to analyze the features of the speaker's voice and the contents of the remarks from the voice data, and applies a voice generation algorithm. Furthermore, the generation unit can also apply a natural language generation algorithm to the remarks and text data. For example, the generation unit uses text analysis technology to analyze the speaker's intentions and emotions from the remarks and text data, and applies a natural language generation algorithm. This allows a more appropriate avatar to be generated by applying different generation algorithms according to the category of the analysis result. A part or all of the above-mentioned processing in the generation unit may be performed using AI, for example, or may be performed without using AI. For example, the generation unit can use AI to automatically classify categories of analysis results and apply appropriate generation algorithms.

[0092] The generation unit can estimate the user's emotion and adjust the order of avatar generation based on the estimated user's emotion. The generation unit, for example, uses AI to estimate the user's emotion and adjusts the order of avatar generation based on the estimated emotion. For example, if the user is in a hurry, the generation unit prioritizes an avatar that can be generated in a short time. For example, if the generation unit analyzes the user's facial expression with a camera and determines that the user is in a hurry, it prioritizes an avatar that can be generated in a short time. In addition, the generation unit can also prioritize a detailed avatar if the user is relaxed. For example, the generation unit analyzes the tone and speed of the user's voice and prioritizes a detailed avatar if it determines that the user is relaxed. Furthermore, the generation unit can also prioritize a visually attractive avatar if the user is excited. For example, the generation unit measures the user's heart rate and electrodermal activity with a sensor and prioritizes a visually attractive avatar if it determines that the user is excited. This allows a more appropriate avatar to be generated by adjusting the order of avatar generation according to the user's emotion. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using AI, or may be performed without using AI. For example, the generation unit may analyze the user's emotions in real time using AI and automatically adjust the order in which the avatars are generated.

[0093] The generation unit can determine the priority of generation based on the time when the analysis result was collected when the avatar was generated. The generation unit determines the priority of generation based on the time when the analysis result was collected when the avatar was generated, for example, using AI. For example, the generation unit preferentially reflects recently collected data. For example, the generation unit preferentially reflects photos and videos recently taken by the user. The generation unit can also preferentially reflect data related to a specific event. For example, if the user participates in a specific event, the generation unit preferentially reflects data related to the event. Furthermore, the generation unit can also preferentially reflect data in which the user showed a particular interest. For example, if the user shows an interest in a specific topic, the generation unit preferentially reflects data related to the topic. In this way, by determining the priority of generation based on the time when the analysis result was collected, the latest data can be preferentially reflected. Part or all of the above-mentioned processing in the generation unit may be performed using AI, for example, or may be performed without using AI. For example, the generation unit can automatically evaluate the time when the analysis result was collected using AI and determine the priority of generation.

[0094] The generation unit can adjust the order of generation based on the relevance of the analysis result when generating the avatar. The generation unit adjusts the order of generation based on the relevance of the analysis result when generating the avatar, for example, using AI. For example, the generation unit preferentially reflects highly relevant data. For example, if the user shows interest in a specific topic, the generation unit preferentially reflects data related to the topic. The generation unit can also postpone data with low relevance. For example, the generation unit postpones data in which the user shows little interest. Furthermore, the generation unit can also preferentially reflect data in which the user shows particular interest. For example, the generation unit preferentially reflects data that the user frequently accesses. Thereby, by adjusting the order of generation based on the relevance of the analysis result, highly relevant data can be preferentially reflected. Part or all of the above-mentioned processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit can automatically evaluate the relevance of the analysis result using AI and adjust the order of generation.

[0095] The learning unit can estimate the user's emotions and select learning data based on the estimated user's emotions. The learning unit, for example, uses AI to estimate the user's emotions and selects learning data based on the estimated emotions. For example, the learning unit selects detailed learning data when the user is relaxed. For example, the learning unit analyzes the user's facial expression with a camera and selects detailed learning data when it is determined that the user is relaxed. The learning unit can also select concise learning data when the user is stressed. For example, the learning unit analyzes the tone and speed of the user's voice and selects concise learning data when it is determined that the user is stressed. Furthermore, the learning unit can also select visually attractive learning data when the user is excited. For example, the learning unit measures the user's heart rate and electrodermal activity with a sensor and selects visually attractive learning data when it is determined that the user is excited. This allows more appropriate learning to be performed by selecting learning data according to the user's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the learning unit may be performed, for example, using AI, or may be performed without using AI. For example, the learning unit may analyze the user's emotions in real time using AI and automatically select learning data.

[0096] The learning unit can optimize the learning algorithm by referring to past learning data during learning. The learning unit optimizes the learning algorithm by referring to past learning data, for example, using AI during learning. For example, the learning unit selects an optimal learning algorithm based on past learning data. For example, the learning unit analyzes past learning data, extracts an effective learning pattern, and selects a learning algorithm based on the pattern. The learning unit can also extract an effective learning pattern from the past learning data. For example, the learning unit clusters the past learning data and identifies an effective learning pattern. Furthermore, the learning unit can analyze the past learning data and improve the learning algorithm. For example, the learning unit adjusts parameters of the learning algorithm based on the past learning data to improve the accuracy of learning. As a result, the learning algorithm can be optimized by referring to the past learning data. A part or all of the above-mentioned processing in the learning unit may be performed using AI, for example, or may be performed without using AI. For example, the learning unit can automatically analyze past learning data using AI to optimize the learning algorithm.

[0097] The learning unit can adjust the level of detail of the learning based on the user's reaction during learning. The learning unit adjusts the level of detail of the learning based on the user's reaction during learning, for example, using AI. For example, the learning unit performs detailed learning when the user reacts actively. For example, the learning unit performs detailed learning when it is determined that the user is reacting actively by analyzing the user's facial expression and tone of voice. In addition, the learning unit can also perform brief learning when the user does not react. For example, the learning unit performs brief learning when it is determined that the user's reaction is poor. Furthermore, the learning unit can also adjust the progress speed of the learning according to the user's reaction. For example, the learning unit speeds up the progress speed of the learning when the user shows interest. As a result, more effective learning can be performed by adjusting the level of detail of the learning according to the user's reaction. Part or all of the above-mentioned processing in the learning unit may be performed using AI, for example, or may be performed without using AI. For example, the learning unit can analyze the user's reaction in real time using AI and automatically adjust the level of detail of the learning.

[0098] The learning unit can estimate the user's emotion and adjust the frequency of learning based on the estimated user's emotion. The learning unit, for example, estimates the user's emotion using AI and adjusts the frequency of learning based on the estimated emotion. For example, the learning unit frequently learns when the user is relaxed. For example, the learning unit analyzes the user's facial expression with a camera and frequently learns when it is determined that the user is relaxed. The learning unit can also reduce the frequency of learning when the user is stressed. For example, the learning unit analyzes the tone and speed of the user's voice and reduces the frequency of learning when it is determined that the user is stressed. Furthermore, the learning unit can also increase the frequency of learning when the user is excited. For example, the learning unit measures the user's heart rate and electrodermal activity with a sensor and increases the frequency of learning when it is determined that the user is excited. This allows more appropriate learning to be performed by adjusting the frequency of learning according to the user's emotion. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (for example, LLM) or a multimodal generation AI. A part or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can analyze the user's emotions in real time using AI and automatically adjust the frequency of learning.

[0099] The learning unit can weight the learning data based on the user's conversation history during learning. The learning unit weights the learning data based on the user's conversation history during learning, for example, using AI. For example, the learning unit weights words and phrases frequently used by the user. For example, the learning unit analyzes the user's conversation history and weights frequently used words and phrases highly. The learning unit can also weight based on how often the user talks about a specific topic. For example, if the user talks frequently about a specific topic, the learning unit weights data related to the topic highly. Furthermore, the learning unit can weight important information from the user's conversation history. For example, the learning unit weights information in which the user has shown particular interest highly. As a result, more effective learning can be performed by weighting the learning data based on the user's conversation history. Part or all of the above-mentioned processing in the learning unit may be performed using AI, for example, or may be performed without using AI. For example, the learning unit can automatically analyze the user's conversation history using AI and weight the learning data.

[0100] The learning unit can determine the priority of learning based on the user's living situation when learning. The learning unit determines the priority of learning based on the user's living situation when learning, for example, using AI. For example, when the user starts a new hobby, the learning unit prioritizes learning related to the hobby. For example, the learning unit analyzes the user's social media activity and performs learning based on posts and photos related to the new hobby. In addition, when the user is working on a specific project, the learning unit can also prioritize learning related to the project. For example, the learning unit analyzes the content of the user's conversation and performs learning based on remarks and voices related to the project. Furthermore, the learning unit can adjust the priority of learning according to the user's living situation. For example, when the user is at work, the learning unit prioritizes work-related learning. As a result, more effective learning can be performed by determining the priority of learning based on the user's living situation. Part or all of the above-mentioned processing in the learning unit may be performed using AI, for example, or may be performed without using AI. For example, the learning unit can analyze the user's living situation in real time using AI and automatically determine the priority of learning.

[0101] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0102] The collection unit can collect biometric information of the user and monitor the health condition. For example, the collection unit can measure the user's heart rate and blood pressure with a sensor and collect data. The collection unit can also track the user's sleep pattern and evaluate the quality of sleep. Furthermore, the collection unit can record the user's amount of exercise and grasp the user's daily activity level. This makes it possible to monitor the user's health condition in real time and issue an alert if necessary.

[0103] The analysis unit can analyze the user's health data and predict health risks. For example, the analysis unit can analyze heart rate and blood pressure data to detect abnormal patterns. The analysis unit can also analyze sleep data to identify signs of sleep disorders. Furthermore, the analysis unit can analyze exercise data to evaluate the risk of insufficient or excessive exercise. This allows the user's health risks to be discovered early and appropriate measures to be taken.

[0104] The generating unit can generate personalized health advice based on the user's health data. For example, the generating unit can provide appropriate exercise and diet advice based on the user's heart rate and blood pressure data. The generating unit can also provide advice for improving sleep quality based on the sleep data. Furthermore, the generating unit can customize the user's exercise plan based on the exercise data. This allows the user to receive specific advice according to their own health condition.

[0105] The learning unit can learn changes in health condition based on the user's health data and improve prediction accuracy. For example, the learning unit can learn past heart rate and blood pressure data and predict future health risks. The learning unit can also learn sleep data and predict changes in sleep patterns. Furthermore, the learning unit can learn exercise data and predict changes in exercise habits. This makes it possible to detect changes in the user's health condition early and take appropriate measures.

[0106] The collection unit can estimate the user's emotions and adjust the timing of collecting health data based on the estimated emotions. For example, the collection unit collects heart rate and blood pressure data when the user is relaxed. The collection unit can also refrain from collecting data when the user is feeling stressed. Furthermore, the collection unit can collect sleep data and exercise data when the user is emotionally stable. This allows data to be collected at an appropriate time according to the user's emotions, making it possible to grasp the user's health condition more accurately.

[0107] The analysis unit can estimate the user's emotion and adjust the analysis result of the health risk based on the estimated emotion. For example, the analysis unit can provide a detailed analysis result when the user is relaxed. The analysis unit can also provide a concise analysis result when the user is stressed. Furthermore, the analysis unit can provide a visually appealing analysis result when the user is excited. This allows the analysis result to be adjusted according to the user's emotion and more appropriate information to be provided.

[0108] The generating unit can estimate the user's emotion and adjust the content of the health advice based on the estimated emotion. For example, the generating unit can provide detailed health advice when the user is relaxed. The generating unit can also provide concise health advice when the user is stressed. Furthermore, the generating unit can provide visually appealing health advice when the user is excited. In this way, the content of the health advice can be adjusted according to the user's emotion, and more effective advice can be provided.

[0109] The learning unit can estimate the user's emotions and select learning data based on the estimated emotions. For example, the learning unit selects detailed learning data when the user is relaxed. The learning unit can also select concise learning data when the user is stressed. Furthermore, the learning unit can select visually appealing learning data when the user is excited. This allows the user to select learning data according to their emotions and perform more effective learning.

[0110] The collection unit can analyze the user's social media activity and collect related health data. For example, the collection unit collects photos of exercise and meals shared by the user on social media. The collection unit can also collect health-related comments made by the user on social media. Furthermore, the collection unit can collect data related to health topics in which the user has shown interest on social media. In this way, by analyzing the user's social media activity, related health data can be collected and a more detailed health condition can be understood.

[0111] The analysis unit can perform personalized health risk prediction based on the user's health data. For example, the analysis unit can analyze the user's heart rate and blood pressure data to predict individual health risks. The analysis unit can also analyze sleep data to predict the user's specific risk of sleep disorders. Furthermore, the analysis unit can analyze exercise data to predict health risks based on the user's exercise habits. This allows the user's individual health risks to be discovered early and appropriate measures to be taken.

[0112] The process flow of the second embodiment will be briefly described below.

[0113] Step 1: The collection unit collects a life log. The life log includes photos, videos, audio, statements, personality, habits, tastes, and human relationships. The collection unit can collect photos and videos provided by the user in digital format and can also collect audio data using a microphone. It can also collect the user's statements and conversation content as text data. For example, the collection unit collects data from a smartphone or tablet that the user uses on a daily basis. Step 2: The analysis unit analyzes the life logs collected by the collection unit. The analysis unit uses AI to analyze the collected data and extracts the characteristics and behavioral patterns of the subject. For example, image analysis technology can be used to recognize the subject's face from photos and videos, and audio analysis technology can be used to extract the characteristics of the subject's voice from audio data. In addition, natural language processing technology can be used to analyze the content of the subject's statements from text data. The analysis unit uses AI to cluster the collected data and identify the subject's behavioral patterns. Step 3: The generation unit generates an avatar based on the results of the analysis by the analysis unit. The generation unit uses AI to generate an avatar that mimics the characteristics and behavioral patterns of the target person. For example, it can use a text generation AI (e.g., LLM) to mimic the content of the target person's speech, and an image generation AI to reproduce the target person's face and expressions. In addition, it can use a voice generation AI to reproduce the target person's voice. The generation unit uses AI to learn the characteristics of the target person and generate the avatar's actions and speech. Step 4: The learning unit continues to learn through conversations between the avatar generated by the generation unit and the user. The learning unit uses AI to analyze the content of the conversation with the user and incorporates new information and reactions. For example, it records questions and comments made by the user to the avatar and updates the avatar's knowledge base. It can also analyze the user's reactions and improve the avatar's responses. Furthermore, it can learn the avatar's behavioral patterns through conversations with the user and achieve more natural dialogue. The learning unit uses AI to cluster the content of the conversation with the user and optimize the avatar's response patterns.

[0114] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0115] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0116] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0117] Each of the multiple elements including the above-mentioned collection unit, analysis unit, generation unit, and learning unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit collects a life log using the camera 42 and microphone 38B of the smart device 14. The analysis unit analyzes the data collected by the specific processing unit 290 of the data processing device 12. The generation unit generates an alter ego by the specific processing unit 290 of the data processing device 12. The learning unit causes the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12 to learn the alter ego through a conversation with the user. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0118] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0119] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0120] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0121] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0122] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0123] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0124] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0125] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0126] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0127] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0128] In the smart glasses 214, the 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 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0129] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0130] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0131] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0132] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may be executed 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 required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0133] Each of the multiple elements including the above-mentioned collection unit, analysis unit, generation unit, and learning unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit collects a life log using the camera 42 and the microphone 238 of the smart glasses 214. The analysis unit analyzes the data collected by the specific processing unit 290 of the data processing device 12. The generation unit generates an alter ego by the specific processing unit 290 of the data processing device 12. The learning unit causes the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12 to learn the alter ego through a conversation with the user. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0134] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0135] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0136] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0137] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0138] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0139] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0140] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0141] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0142] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0143] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0144] In the headset type terminal 314, the 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 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0145] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0146] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0147] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0148] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0149] Each of the multiple elements including the above-mentioned collection unit, analysis unit, generation unit, and learning unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the collection unit collects a life log using the camera 42 and microphone 238 of the headset type terminal 314. The analysis unit analyzes the data collected by the specific processing unit 290 of the data processing device 12. The generation unit generates an avatar by the specific processing unit 290 of the data processing device 12. The learning unit causes the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12 to learn the avatar through a conversation with the user. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0150] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0151] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0152] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0153] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0154] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0155] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0156] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0157] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0158] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0159] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0160] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0161] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0162] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0163] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0164] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0165] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may be executed 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 required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0166] Each of the multiple elements including the above-mentioned collection unit, analysis unit, generation unit, and learning unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit collects a life log using the camera 42 and microphone 238 of the robot 414. The analysis unit analyzes the data collected by the specific processing unit 290 of the data processing device 12. The generation unit generates an avatar by the specific processing unit 290 of the data processing device 12. The learning unit causes the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12 to learn the avatar through a conversation with the user. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0167] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0168] FIG. 9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0169] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0170] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0171] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0172] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this 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 positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0173] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0174] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers, including computer 22.

[0175] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0176] In addition, 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 upon request from the data processing device 12.

[0177] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0178] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0179] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0180] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0181] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0182] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0183] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0184] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0185] (Appendix 1) A collection unit that collects life logs; an analysis unit that analyzes the life log collected by the collection unit; a generation unit that generates an alter-ego based on the result of the analysis by the analysis unit; A learning unit in which the avatar generated by the generation unit continues to learn through conversation with the user. A system characterized by: (Appendix 2) The collecting unit includes: Collecting data about your photos, videos, audio, statements, personality, habits, interests, and relationships 2. The system of claim 1, (Appendix 3) The analysis unit is Analyze the collected data and extract the characteristics and behavioral patterns of the subjects. 2. The system of claim 1, (Appendix 4) The generation unit is Generate an avatar based on the analysis results 2. The system of claim 1, (Appendix 5) The learning unit is Incorporate new information or responses through conversation with users 2. The system of claim 1, (Appendix 6) The generation unit is Implementing an avatar into a robot 2. The system of claim 1, (Appendix 7) The generation unit is Output your avatar as a digital avatar 2. The system of claim 1, (Appendix 8) The collecting unit includes: The system estimates the user's emotions and adjusts the timing of collecting life logs based on the estimated user emotions. 2. The system of claim 1, (Appendix 9) The collecting unit includes: Analyze the user's past life log collection history and select the collection method 2. The system of claim 1, (Appendix 10) The collecting unit includes: When collecting life logs, filtering is performed based on the user's current life situation and areas of interest. 2. The system of claim 1, (Appendix 11) The collecting unit includes: The user's emotions are estimated, and the priority of life logs to be collected is determined based on the estimated user's emotions. 2. The system of claim 1, (Appendix 12) The collecting unit includes: When collecting life logs, the system prioritizes the collection of relevant data by taking into account the user's geographic location information. 2. The system of claim 1, (Appendix 13) The collecting unit includes: When collecting life logs, analyze users' social media activities and collect related data. 2. The system of claim 1, (Appendix 14) The analysis unit is Infer user emotions and adjust the presentation of analytics based on the inferred user emotions 2. The system of claim 1, (Appendix 15) The analysis unit is During analysis, adjust the level of detail based on the importance of your life log 2. The system of claim 1, (Appendix 16) The analysis unit is During analysis, different analysis algorithms are applied depending on the category of the activity log. 2. The system of claim 1, (Appendix 17) The analysis unit is Infer user sentiment and adjust the length of the analysis based on the inferred user sentiment 2. The system of claim 1, (Appendix 18) The analysis unit is During analysis, prioritize analysis based on when the lifelog was collected 2. The system of claim 1, (Appendix 19) The analysis unit is During analysis, adjust the order of analysis based on the relevance of your lifelog 2. The system of claim 1, (Appendix 20) The generation unit is Estimate the user's emotions and adjust the method of generating the avatar based on the estimated user's emotions 2. The system of claim 1, (Appendix 21) The generation unit is When generating avatars, adjust the level of detail based on the importance of the analysis results. 2. The system of claim 1, (Appendix 22) The generation unit is When generating clones, different generation algorithms are applied depending on the category of the analysis result. 2. The system of claim 1, (Appendix 23) The generation unit is The user's emotions are estimated, and the order of avatar generation is adjusted based on the estimated user's emotions. 2. The system of claim 1, (Appendix 24) The generation unit is When generating clones, determine the priority of generation based on the time of collection of analysis results. 2. The system of claim 1, (Appendix 25) The generation unit is When generating clones, adjust the order of generation based on the relevance of the analysis results. 2. The system of claim 1, (Appendix 26) The learning unit is Estimate the user's emotions and select learning data based on the estimated user emotions. 2. The system of claim 1, (Appendix 27) The learning unit is During training, the learning algorithm is optimized by referencing past training data. 2. The system of claim 1, (Appendix 28) The learning unit is During learning, adjust the learning detail based on user responses 2. The system of claim 1, (Appendix 29) The learning unit is Infer user emotions and adjust the frequency of learning based on the estimated user emotions. 2. The system of claim 1, (Appendix 30) The learning unit is During training, the training data is weighted based on the user's conversation history. 2. The system of claim 1, (Appendix 31) The learning unit is Prioritize learning based on the user's life situation when studying 2. The system of claim 1, [Explanation of symbols]

[0186] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A collection unit that collects life logs; an analysis unit that analyzes the life log collected by the collection unit; a generation unit that generates an alter-ego based on the result of the analysis by the analysis unit; A learning unit in which the avatar generated by the generation unit continues to learn through conversation with the user. A system characterized by:

2. The collecting unit includes: Collecting data about your photos, videos, audio, statements, personality, habits, interests, and relationships 2. The system of claim 1 .

3. The analysis unit is Analyze the collected data and extract the characteristics and behavioral patterns of the subjects.

2. The system of claim 1 .

4. The learning unit is Incorporate new information or responses through conversation with users 2. The system of claim 1 .

5. The generation unit is Implementing an avatar into a robot 2. The system of claim 1 .

6. The generation unit is Output your avatar as a digital avatar 2. The system of claim 1 .

7. The collecting unit includes: The system estimates the user's emotions and adjusts the timing of collecting life logs based on the estimated user emotions.

2. The system of claim 1 .

Images