system

Abstract

The system according to this embodiment aims to eliminate gender-based prejudice and bias. [Solution] The system according to the embodiment comprises an acquisition unit, an avatar generation unit, a reaction reflection unit, and a voice conversion unit. The acquisition unit acquires the user's appearance data. The avatar generation unit generates a gender-neutral avatar based on the appearance data acquired by the acquisition unit. The reaction reflection unit reflects the user's reactions in real time on the avatar generated by the avatar generation unit. The voice conversion unit converts the user's responses into AI voice and provides responses on their behalf.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, it is difficult to completely eliminate gender-based prejudice and bias, and there is room for improvement.

[0005] The system according to the embodiment aims to eliminate gender-based prejudice and bias.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an acquisition unit, an avatar generation unit, a reaction reflection unit, and a voice conversion unit. The acquisition unit acquires the user's appearance data. The avatar generation unit generates a gender-neutral avatar based on the appearance data acquired by the acquisition unit. The reaction reflection unit reflects the user's reactions in real time on the avatar generated by the avatar generation unit. The voice conversion unit converts the user's responses into AI voice and provides responses on their behalf. [Effects of the Invention]

[0007] The system according to this embodiment can eliminate gender-based prejudice and bias. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The EqualMeet system according to an embodiment of the present invention is a system that provides an online interview environment that completely eliminates gender bias. This system eliminates gender bias by generating a gender-neutral avatar based on the user's appearance data and reflecting the user's reactions (such as changes in facial expressions and tone of voice) in real time. It also provides an agent service that converts the user's answers into AI voice and answers on their behalf. As a result, interviewers can conduct interviews in the same way as conventional interviews, while eliminating gender bias. For example, the EqualMeet system generates a gender-neutral avatar based on the user's appearance data. This avatar hides the user's appearance and reflects the user's reactions during the interview in real time. Next, the EqualMeet system provides an agent service that converts the user's answers into AI voice and answers on their behalf. As a result, interviewers can conduct interviews without gender bias. This service has benefits for both companies and users. Companies can increase the transparency of the selection process and build a gender-neutral environment, which can lead to an increase in the number of job applicants. Users can undergo interviews with peace of mind, free from gender bias, and expect selection based solely on their abilities and inner qualities. The EqualMeet system aims to create a future where everyone can undergo interviews with confidence, by being standardized as an option during interviews. The market size, including the interview-related market and the DX promotion-related market, is estimated at approximately 1.45 trillion yen. Even with the increase in agent services using AI-generated tools, the final decision rests with humans, and a fundamental change in the system is necessary to reduce bias. The EqualMeet system, by using generated AI, can change the framework that was previously impossible, realizing completely bias-free, fair, and safe interviews. In this way, the EqualMeet system can eliminate gender bias and provide fair and safe interviews.

[0029] The EqualMeet system according to this embodiment comprises an acquisition unit, an avatar generation unit, a reaction reflection unit, and a voice conversion unit. The acquisition unit acquires the user's appearance data. The acquisition unit can, for example, acquire an image of the user's face using a camera. The acquisition unit can also acquire an image of the user's entire body. Furthermore, the acquisition unit can acquire the user's movement data. For example, the acquisition unit can take an image of the user's face using a camera and extract facial features using image processing technology. The acquisition unit can also take an image of the entire body and extract features of posture and body shape. The acquisition unit can also acquire movement data and extract features of movement. The avatar generation unit generates a gender-neutral avatar based on the appearance data acquired by the acquisition unit. The avatar generation unit can, for example, use a generation AI to generate a gender-neutral avatar based on the user's facial features. Furthermore, the avatar generation unit can generate a gender-neutral avatar based on the features of the entire body. Furthermore, the avatar generation unit can generate a gender-neutral avatar based on the features of movement. For example, the avatar generation unit inputs the user's facial features into the generation AI and generates an avatar with a neutral face. The avatar generation unit can also input full-body features and generate an avatar with a neutral body type. The avatar generation unit can also input movement features and generate an avatar that performs neutral movements. The reaction reflection unit reflects the user's reactions in real time onto the avatar generated by the avatar generation unit. The reaction reflection unit can, for example, use facial recognition technology to detect changes in the user's facial expressions and reflect them in the avatar. The reaction reflection unit can also use voice analysis technology to detect changes in the user's voice tone and reflect them in the avatar. Furthermore, the reaction reflection unit can use motion recognition technology to detect changes in the user's movements and reflect them in the avatar. For example, the reaction reflection unit can use facial recognition technology to detect the user's smile or surprised expression and reflect it in the avatar. The reaction reflection unit can also use voice analysis technology to detect changes in the tone and volume of the user's voice and reflect them in the avatar. The reaction reflection unit can also use motion recognition technology to detect changes in the user's hand movements and posture, and reflect them in the avatar.The voice conversion unit converts the user's answers into AI voice and provides answers on their behalf. The voice conversion unit can, for example, use speech recognition technology to convert the user's answers into text data. The voice conversion unit can also use speech synthesis technology to convert the text data into AI voice. Furthermore, the voice conversion unit can reflect the user's emotions during the voice conversion process. For example, the voice conversion unit can use speech recognition technology to convert the user's answers into text data, and then use speech synthesis technology to convert the text data into a gender-neutral AI voice. The voice conversion unit can also adjust the tone and volume of the voice to reflect the user's emotions. As a result, the EqualMeet system according to this embodiment can eliminate gender bias and provide a fair and safe interview.

[0030] The data acquisition unit acquires user appearance data. For example, the acquisition unit can acquire images of the user's face using a camera. It can also acquire images of the user's entire body. Furthermore, the acquisition unit can acquire user movement data. Specifically, the acquisition unit uses a high-resolution camera to capture images of the user's face from multiple angles and uses image processing technology to extract facial features in detail. This includes the position and shape of the eyes, nose, and mouth, as well as skin color and texture. When acquiring full-body images, the unit captures the user standing and walking, and extracts features of their posture and body shape. This provides data such as the user's height, weight, and body proportions. For acquiring movement data, motion capture technology can be used in addition to cameras. For example, sensors can detect the movements of the user's hands, arms, and legs, and the characteristics of the movements can be recorded in detail. This allows for accurate understanding of the user's walking patterns, gestures, and changes in posture. The acquisition unit collects this data in real time and transmits it to a central database. The data is encrypted and strictly managed to protect privacy. Furthermore, the data acquisition unit can adjust the frequency and accuracy of data collection, enabling flexible responses to specific situations and conditions. For example, data can be collected at a high frequency at the start of an interview, allowing for real-time monitoring of changes in the user's tension and stress levels. This allows the data acquisition unit to collect data efficiently and effectively, improving the overall system performance.

[0031] The avatar generation unit generates a gender-neutral avatar based on the appearance data acquired by the acquisition unit. For example, the avatar generation unit uses a generation AI to generate a gender-neutral avatar based on the user's facial features. Specifically, the generation AI receives the user's facial features as input data and adjusts the shape of the face and the placement of parts to generate a gender-neutral avatar. This includes algorithms for making the shapes of the eyes, nose, and mouth gender-neutral. The avatar generation unit can also generate a gender-neutral avatar based on the user's overall body features. The generation AI analyzes the user's body shape data and adjusts the body's proportions and posture to generate a gender-neutral, gender-neutral physique. Furthermore, the avatar generation unit can generate a gender-neutral avatar based on its movement characteristics. The generation AI analyzes the user's movement data and adjusts the smoothness of the movements and the naturalness of the gestures to generate gender-neutral, gender-neutral movements. For example, the avatar generation unit inputs the user's facial features into the generation AI to generate a gender-neutral avatar. The generating AI analyzes facial features and adjusts the shapes of the eyes, nose, and mouth to be androgynous. The avatar generation unit can also take full-body features as input and generate an androgynous avatar. The generating AI analyzes body shape data and adjusts body proportions and posture to be androgynous. Furthermore, the avatar generation unit can take movement characteristics as input and generate an avatar that performs androgynous movements. The generating AI analyzes movement data and adjusts the smoothness of the movements and the naturalness of the gestures to be androgynous. As a result, the avatar generation unit can generate androgynous avatars based on the user's appearance data, providing a fair interview environment.

[0032] The reaction reflection unit reflects the user's reactions in real time onto the avatar generated by the avatar generation unit. For example, the reaction reflection unit uses facial recognition technology to detect changes in the user's facial expressions and reflects them on the avatar. Specifically, facial recognition technology analyzes the user's facial image to detect expressions such as smiles, surprise, and anger. This includes algorithms that analyze features such as eye and mouth movements and eyebrow positions. The reaction reflection unit reflects this facial expression data on the avatar in real time, so that the avatar changes according to the user's facial expressions. The reaction reflection unit can also use voice analysis technology to detect changes in the user's voice tone and reflect them on the avatar. Voice analysis technology analyzes the tone, volume, and rhythm of the user's voice to detect changes in emotion. The reaction reflection unit reflects this voice data on the avatar in real time, so that the avatar changes according to the user's voice tone. Furthermore, the reaction reflection unit can also use motion recognition technology to detect changes in the user's motions and reflect them on the avatar. Motion recognition technology analyzes the user's hand movements and changes in posture to detect gestures and changes in posture. The reaction reflection unit reflects this motion data onto the avatar in real time, causing the avatar to change in response to the user's actions. For example, the reaction reflection unit can use facial expression recognition technology to detect the user's smile or surprised expression and reflect it on the avatar. The reaction reflection unit can also use voice analysis technology to detect changes in the tone and volume of the user's voice and reflect them on the avatar. The reaction reflection unit can also use motion recognition technology to detect changes in the user's hand movements and posture and reflect them on the avatar. As a result, the reaction reflection unit can reflect the user's reactions onto the avatar in real time, enabling more natural and realistic communication.

[0033] The voice conversion unit converts the user's answers into AI voice and provides answers on their behalf. For example, the voice conversion unit uses speech recognition technology to convert the user's answers into text data. Specifically, speech recognition technology analyzes the user's voice and extracts the utterance as text data. This includes algorithms that analyze the waveform of the voice and recognize phonemes and words. Based on this text data, the voice conversion unit uses speech synthesis technology to convert the text data into AI voice. Speech synthesis technology receives text data as input and adjusts the tone, rhythm, and volume of the voice to generate natural speech. Furthermore, the voice conversion unit can also reflect the user's emotions during the voice conversion process. For example, the voice conversion unit uses speech recognition technology to convert the user's answers into text data, and then uses speech synthesis technology to convert the text data into a neutral AI voice. Speech synthesis technology adjusts the tone and volume of the voice to reflect the user's emotions. As a result, the AI ​​voice can generate natural speech that reflects the user's emotions. The voice conversion unit can also adjust the tone and volume of the voice to reflect the user's emotions. For example, if a user is excited, the voice tone can be raised and emphasis can be increased to reflect that excited emotion. Conversely, if a user is calm, the voice tone can be lowered and the rhythm slowed to reflect that calm emotion. In this way, the voice conversion unit can convert the user's responses into natural-sounding AI voice, providing a fair and reassuring interview.

[0034] The reaction reflection unit includes a detection unit that detects changes in facial expressions and tone of voice. The reaction reflection unit can detect changes in the user's facial expressions, for example, using facial recognition technology. For example, the reaction reflection unit can track facial feature points to detect smiles and surprised expressions. The reaction reflection unit can also detect changes in the user's tone of voice using voice analysis technology. For example, the reaction reflection unit can analyze changes in voice tone and volume to detect changes in emotion. Furthermore, the reaction reflection unit can detect changes in the user's movements using motion recognition technology. For example, the reaction reflection unit can analyze changes in hand movements and posture to detect reactions. This allows for a more accurate reflection of the user's reactions by detecting changes in facial expressions and tone of voice. Some or all of the above-described processes in the reaction reflection unit may be performed using AI or not. For example, the reaction reflection unit can input facial expression data detected using facial recognition technology into a generating AI, which can then analyze the changes in facial expressions and reflect them in the avatar.

[0035] The speech conversion unit comprises a recognition unit that uses speech recognition technology and a synthesis unit that uses speech synthesis technology. The speech conversion unit, for example, uses speech recognition technology to convert the user's response into text data. For example, the speech conversion unit can use deep learning-based speech recognition technology to convert the user's voice into text with high accuracy. The speech conversion unit can also use speech synthesis technology to convert the text data into AI voice. For example, the speech conversion unit can use text-to-speech (TTS) technology to generate natural-sounding voice. Furthermore, the speech conversion unit can also reflect the user's emotions during speech conversion. For example, the speech conversion unit can adjust the tone and volume of the voice to enrich emotional expression. As a result, by using speech recognition technology and speech synthesis technology, the user's response can be converted into AI voice and used as a proxy answer. Some or all of the above-described processes in the speech conversion unit may be performed using AI or not. For example, the speech conversion unit can input text data acquired using speech recognition technology into a generating AI, and the generating AI can analyze the text data to generate natural-sounding voice.

[0036] The acquisition unit analyzes the user's past appearance data and selects the optimal acquisition method. For example, the acquisition unit analyzes the user's past appearance data to determine the optimal timing for acquiring the most natural facial expression. For example, the acquisition unit can prioritize acquiring data from past data when the user is relaxed. The acquisition unit can also select the optimal method for acquiring facial expressions under specific circumstances from past data. For example, the acquisition unit can prioritize acquiring data from past data under specific lighting conditions or camera angles. By analyzing the user's past appearance data, the acquisition unit can select the optimal method for acquiring the most natural facial expression. Some or all of the above processing in the acquisition unit may be performed using AI or not. For example, the acquisition unit can input past appearance data into a generating AI, which can then analyze the data and select the optimal acquisition method.

[0037] The acquisition unit filters the appearance data based on the user's current lifestyle and areas of interest. For example, the acquisition unit can acquire appearance data in a relaxed environment based on the user's current lifestyle. For example, if the user is at home, the acquisition unit can acquire data in a relaxed state. The acquisition unit can also acquire appearance data while displaying content that is of interest to the user, based on the user's areas of interest. For example, the acquisition unit can acquire data while displaying videos or music that the user is interested in. Furthermore, the acquisition unit can acquire appearance data in an optimal environment based on the user's lifestyle and areas of interest. For example, the acquisition unit can select a place and time when the user can relax and acquire data. This allows for the acquisition of appearance data in an optimal environment by filtering based on the user's lifestyle and areas of interest. Some or all of the above processing in the acquisition unit may be performed using AI or not. For example, the acquisition unit can input data on the user's lifestyle and areas of interest into a generating AI, which can analyze the data and select the optimal acquisition method.

[0038] The acquisition unit prioritizes acquiring highly relevant data when acquiring appearance data, taking into account the user's geographical location information. For example, the acquisition unit acquires appearance data in an optimal environment based on the user's geographical location information. For example, if the user is in a specific region, the acquisition unit can prioritize acquiring appearance data related to that region. The acquisition unit can also prioritize acquiring highly relevant data by taking into account the user's geographical location information. For example, if the user is in a specific location, the acquisition unit can prioritize acquiring data related to that location. In this way, by prioritizing the acquisition of highly relevant data based on the user's geographical location information, appearance data can be acquired in an optimal environment. Some or all of the above processing in the acquisition unit may be performed using AI or not. For example, the acquisition unit can input the user's geographical location information into a generating AI, and the generating AI can analyze the data and prioritize the acquisition of highly relevant data.

[0039] The acquisition unit analyzes the user's social media activity and acquires relevant data when acquiring appearance data. For example, the acquisition unit analyzes the user's social media activity and selects the optimal timing to acquire the most natural facial expression. For example, the acquisition unit can analyze the user's posts, the number of likes, comments, etc., and acquire data while displaying interesting content. The acquisition unit can also analyze the user's social media activity and prioritize the acquisition of relevant data. For example, the acquisition unit can select the optimal method for acquiring facial expressions under specific circumstances from the user's social media activity. This allows the system to select the optimal timing to acquire the most natural facial expression by analyzing the user's social media activity. Some or all of the above processing in the acquisition unit may be performed using AI or not. For example, the acquisition unit can input data on the user's social media activity into a generating AI, which can analyze the data and prioritize the acquisition of relevant data.

[0040] The avatar generation unit adjusts the level of detail of the avatar based on the importance of the appearance data during avatar generation. For example, the avatar generation unit can generate a detailed avatar based on the importance of the appearance data. For example, the avatar generation unit can generate a sophisticated avatar based on detailed data of facial features and body shape. The avatar generation unit can also generate a simplified avatar based on the importance of the appearance data. For example, the avatar generation unit can generate a simplified avatar based on data of low importance. In this way, by adjusting the level of detail of the avatar based on the importance of the appearance data, the optimal avatar can be generated. Some or all of the above processing in the avatar generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the avatar generation unit can input appearance data into a generation AI, and the generation AI can analyze the importance of the data and adjust the level of detail of the avatar.

[0041] The avatar generation unit applies different generation algorithms depending on the user's category when generating avatars. For example, the avatar generation unit can apply the optimal generation algorithm depending on the user's category. For example, the avatar generation unit can apply different generation algorithms depending on categories such as age, gender, and occupation. The avatar generation unit can also apply different generation algorithms depending on the user's category. For example, the avatar generation unit can generate avatars by applying a specific algorithm to users belonging to a specific category. In this way, the optimal avatar can be generated by applying different generation algorithms depending on the user's category. Some or all of the above-described processes in the avatar generation unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the avatar generation unit can input user category data into a generation AI, and the generation AI can analyze the data and apply the optimal generation algorithm.

[0042] The avatar generation unit determines the priority of avatars based on the user's submission timing when generating avatars. For example, the avatar generation unit can generate the optimal avatar based on the user's submission timing. For example, the avatar generation unit can determine the priority of avatars based on the submission date and time or submission order. Alternatively, the avatar generation unit can also determine the priority of avatars based on the user's submission timing. For example, the avatar generation unit can prioritize generating avatars for users who submitted earlier. By determining the priority of avatars based on the user's submission timing, the optimal avatar can be generated. Some or all of the above-described processes in the avatar generation unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the avatar generation unit can input submission timing data into a generation AI, which can then analyze the data to determine the priority of avatars.

[0043] The avatar generation unit adjusts the order of avatars based on user relevance during avatar generation. For example, the avatar generation unit can generate the optimal avatar based on user relevance. For example, the avatar generation unit can adjust the order of avatars based on interest level and past usage history. The avatar generation unit can also adjust the order of avatars based on user relevance. For example, the avatar generation unit can prioritize generating avatars for highly relevant users. In this way, the optimal avatar can be generated by adjusting the order of avatars based on user relevance. Some or all of the above processing in the avatar generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the avatar generation unit can input user relevance data into a generation AI, and the generation AI can analyze the data and adjust the order of avatars.

[0044] The reaction reflection unit analyzes the user's past reaction data to select the optimal reflection method when reflecting reactions. For example, the reaction reflection unit can analyze the user's past reaction data and select the optimal method to reflect the most natural reaction. For example, the reaction reflection unit can select the optimal method to reflect a reaction under specific circumstances from past data. The reaction reflection unit can also select the optimal method to reflect specific facial expressions or actions from past data. For example, the reaction reflection unit can prioritize the reflection of specific facial expressions or actions from past data. In this way, by analyzing the user's past reaction data, the optimal method to reflect the most natural reaction can be selected. Some or all of the above processing in the reaction reflection unit may be performed using AI or not. For example, the reaction reflection unit can input past reaction data into a generating AI, which can analyze the data and select the optimal reflection method.

[0045] The reaction reflection unit customizes the means of reflection based on the user's current living situation when reflecting reactions. For example, the reaction reflection unit reflects the optimal reaction based on the user's current living situation. For example, if the user is at home, the reaction reflection unit can reflect a relaxed reaction. The reaction reflection unit can also reflect a customized reaction based on the user's living situation. For example, if the user is in a specific location, the reaction reflection unit can reflect a reaction appropriate for that location. In this way, the optimal reaction can be reflected by customizing the means of reflection based on the user's current living situation. Some or all of the above processing in the reaction reflection unit may be performed using AI or not. For example, the reaction reflection unit can input the user's living situation data into a generating AI, which can analyze the data and select the optimal reflection method.

[0046] The reaction reflection unit selects the optimal reflection method when reflecting reactions, taking into account the user's geographical location information. For example, the reaction reflection unit reflects the optimal reaction based on the user's geographical location information. For example, if the user is in a specific region, the reaction reflection unit can reflect a reaction related to that region. The reaction reflection unit can also reflect a customized reaction, taking into account the user's geographical location information. For example, if the user is in a specific location, the reaction reflection unit can reflect a reaction appropriate for that location. This allows for the reflection of more appropriate reactions by selecting the optimal reflection method based on the user's geographical location information. Some or all of the above processing in the reaction reflection unit may be performed using AI or not. For example, the reaction reflection unit can input the user's geographical location information into a generating AI, which can then analyze the data and select the optimal reflection method.

[0047] The reaction reflection unit analyzes the user's social media activity and proposes a method for reflecting reactions. For example, the reaction reflection unit analyzes the user's social media activity and proposes a method for reflecting the optimal reaction. For example, the reaction reflection unit can analyze the user's posts, the number of likes, comments, etc., and reflect reactions while displaying content that is of interest. The reaction reflection unit can also analyze the user's social media activity and reflect customized reactions. For example, the reaction reflection unit can select the optimal method for reflecting reactions under specific circumstances from the user's social media activity. In this way, by analyzing the user's social media activity, it can propose a method for reflecting the optimal reaction. Some or all of the above processing in the reaction reflection unit may be performed using AI or not. For example, the reaction reflection unit can input data on the user's social media activity into a generating AI, which can analyze the data and select the optimal reflection method.

[0048] The speech conversion unit analyzes the user's past response data to select the optimal conversion method during speech conversion. For example, the speech conversion unit analyzes the user's past response data to select the optimal method for the most natural speech conversion. For example, the speech conversion unit can select the optimal method for speech conversion under specific circumstances from past data. The speech conversion unit can also select the optimal method for reflecting specific tones and emphasis from past data. For example, the speech conversion unit can prioritize reflecting specific tones and emphasis from past data. This allows the optimal method for the most natural speech conversion to be selected by analyzing the user's past response data. Some or all of the above processing in the speech conversion unit may be performed using AI or not. For example, the speech conversion unit can input past response data into a generating AI, which can then analyze the data and select the optimal conversion method.

[0049] The voice conversion unit customizes the conversion method based on the user's current living situation during voice conversion. For example, the voice conversion unit performs optimal voice conversion based on the user's current living situation. For example, if the user is at home, the voice conversion unit can perform voice conversion in a relaxed state. The voice conversion unit can also perform customized voice conversion based on the user's living situation. For example, if the user is in a specific location, the voice conversion unit can perform voice conversion appropriate for that location. In this way, optimal voice conversion can be achieved by customizing the conversion method based on the user's current living situation. Some or all of the above processing in the voice conversion unit may be performed using AI or not. For example, the voice conversion unit can input the user's living situation data into a generating AI, and the generating AI can analyze the data and select the optimal conversion method.

[0050] The speech conversion unit selects the optimal conversion method when converting speech, taking into account the user's geographical location information. For example, the speech conversion unit performs optimal speech conversion based on the user's geographical location information. For example, if the user is in a specific region, the speech conversion unit can perform speech conversion relevant to that region. The speech conversion unit can also perform customized speech conversion, taking into account the user's geographical location information. For example, if the user is in a specific location, the speech conversion unit can perform speech conversion appropriate for that location. This allows for more appropriate speech conversion by selecting the optimal conversion method based on the user's geographical location information. Some or all of the above processing in the speech conversion unit may be performed using AI, or it may be performed without AI. For example, the speech conversion unit can input the user's geographical location information into a generating AI, which can then analyze the data and select the optimal conversion method.

[0051] The speech conversion unit analyzes the user's social media activity during speech conversion and proposes a conversion method. For example, the speech conversion unit analyzes the user's social media activity and proposes a method for performing optimal speech conversion. For example, the speech conversion unit can analyze the user's posts, the number of likes, comments, etc., and perform speech conversion while displaying interesting content. The speech conversion unit can also analyze the user's social media activity and perform customized speech conversion. For example, the speech conversion unit can select the optimal method for performing speech conversion under specific circumstances from the user's social media activity. In this way, by analyzing the user's social media activity, it can propose a method for performing optimal speech conversion. Some or all of the above processing in the speech conversion unit may be performed using AI or not. For example, the speech conversion unit can input data on the user's social media activity into a generating AI, which can analyze the data and select the optimal conversion method.

[0052] The detection unit analyzes the user's past facial expressions and voice tone data to select the optimal detection method during detection. For example, the detection unit analyzes the user's past facial expressions and voice tone data to select the optimal method for detecting the most natural changes. For example, the detection unit can select the optimal method for detecting changes in facial expressions and voice tone under specific circumstances from past data. The detection unit can also select the optimal method for reflecting specific tones and intensities from past data. For example, the detection unit can prioritize reflecting specific tones and intensities from past data. This allows the detection unit to select the optimal method for detecting the most natural changes by analyzing the user's past facial expressions and voice tone data. Some or all of the above processing in the detection unit may be performed using AI or not. For example, the detection unit can input past facial expressions and voice tone data into a generating AI, which can then analyze the data and select the optimal detection method.

[0053] The detection unit selects the optimal detection method when detecting a user, taking into account the user's geographical location information. For example, the detection unit can detect optimal changes in facial expressions and tone of voice based on the user's geographical location information. For example, if the user is in a specific region, the detection unit can detect changes in facial expressions and tone of voice related to that region. The detection unit can also select a customized detection method, taking into account the user's geographical location information. For example, if the user is in a specific location, the detection unit can detect changes in facial expressions and tone of voice appropriate for that location. By selecting the optimal detection method based on the user's geographical location information, more appropriate changes in facial expressions and tone of voice can be detected. Some or all of the above processing in the detection unit may be performed using AI or not. For example, the detection unit can input the user's geographical location information into a generating AI, which can then analyze the data and select the optimal detection method.

[0054] The recognition unit analyzes the user's past voice data to select the optimal recognition method during speech recognition. For example, the recognition unit can analyze the user's past voice data and select the optimal method for the most natural speech recognition. For example, the recognition unit can select the optimal method for speech recognition under specific circumstances from past data. The recognition unit can also select the optimal method for reflecting specific tones and intensity from past data. For example, the recognition unit can prioritize reflecting specific tones and intensity from past data. In this way, by analyzing the user's past voice data, the optimal method for the most natural speech recognition can be selected. Some or all of the above processing in the recognition unit may be performed using AI or not. For example, the recognition unit can input past voice data into a generating AI, and the generating AI can analyze the data and select the optimal recognition method.

[0055] The recognition unit selects the optimal recognition method during speech recognition, taking into account the user's geographical location information. For example, the recognition unit performs optimal speech recognition based on the user's geographical location information. For example, if the user is in a specific region, the recognition unit can perform speech recognition relevant to that region. The recognition unit can also perform customized speech recognition, taking into account the user's geographical location information. For example, if the user is in a specific location, the recognition unit can perform speech recognition appropriate for that location. This allows for more appropriate speech recognition by selecting the optimal recognition method based on the user's geographical location information. Some or all of the above processing in the recognition unit may be performed using AI, or it may be performed without AI. For example, the recognition unit can input the user's geographical location information into a generating AI, which can then analyze the data and select the optimal recognition method.

[0056] The synthesis unit analyzes the user's past voice data to select the optimal synthesis method during speech synthesis. For example, the synthesis unit can analyze the user's past voice data and select the optimal method for producing the most natural speech synthesis. For example, the synthesis unit can select the optimal method for producing speech synthesis under specific circumstances from past data. The synthesis unit can also select the optimal method for reflecting specific tones and intensity from past data. For example, the synthesis unit can prioritize reflecting specific tones and intensity from past data. This allows the synthesis unit to select the optimal method for producing the most natural speech synthesis by analyzing the user's past voice data. Some or all of the above processing in the synthesis unit may be performed using AI or not. For example, the synthesis unit can input past voice data into a generation AI, which can then analyze the data and select the optimal synthesis method.

[0057] The synthesis unit selects the optimal synthesis method when synthesizing speech, taking into account the user's geographical location information. For example, the synthesis unit performs optimal speech synthesis based on the user's geographical location information. For example, if the user is in a specific region, the synthesis unit can perform speech synthesis relevant to that region. The synthesis unit can also perform customized speech synthesis, taking into account the user's geographical location information. For example, if the user is in a specific location, the synthesis unit can perform speech synthesis appropriate for that location. This allows for more appropriate speech synthesis by selecting the optimal synthesis method based on the user's geographical location information. Some or all of the above processing in the synthesis unit may be performed using AI, or it may be performed without AI. For example, the synthesis unit can input the user's geographical location information into a generating AI, which can then analyze the data and select the optimal synthesis method.

[0058] The synthesis unit analyzes the user's social media activity during speech synthesis and proposes a synthesis method. For example, the synthesis unit analyzes the user's social media activity and proposes a method for performing optimal speech synthesis. For example, the synthesis unit can analyze the user's posts, the number of likes, comments, etc., and perform speech synthesis while displaying interesting content. The synthesis unit can also analyze the user's social media activity and perform customized speech synthesis. For example, the synthesis unit can select the optimal method for performing speech synthesis under specific circumstances from the user's social media activity. In this way, by analyzing the user's social media activity, it can propose a method for performing optimal speech synthesis. Some or all of the above processing in the synthesis unit may be performed using AI or not. For example, the synthesis unit can input data on the user's social media activity into a generating AI, which can analyze the data and select the optimal synthesis method.

[0059] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0060] The data acquisition unit can customize how appearance data is acquired based on the user's hobbies and interests. For example, if the user owns items related to a particular hobby, the data acquisition unit can acquire appearance data that includes those items. The data acquisition unit can also prioritize acquiring data from locations that the user is interested in. Furthermore, the data acquisition unit can guide the user to adopt specific poses and facial expressions based on their hobbies and interests. By customizing the data acquisition method based on the user's hobbies and interests, more natural and individualized data can be acquired.

[0061] The avatar generation unit can adjust the appearance of the avatar according to the user's occupation and role. For example, if the user is a business person, the avatar generation unit can generate an avatar wearing a suit. It can also generate an avatar in casual clothing if the user is engaged in a creative profession. Furthermore, the avatar generation unit can equip the avatar with specific accessories and tools depending on the user's role. This allows for the generation of a more appropriate avatar by adjusting its appearance according to the user's occupation and role.

[0062] The reaction reflection unit can adjust how reactions are reflected based on the user's cultural background. For example, if the user belongs to a particular cultural sphere, the reaction reflection unit can reflect gestures and facial expressions specific to that culture. Furthermore, the reaction reflection unit can emphasize certain reactions based on the user's cultural background. In addition, the reaction reflection unit can adjust the timing and intensity of reactions according to the user's cultural background. By adjusting how reactions are reflected based on the user's cultural background, it is possible to reflect more natural and appropriate reactions.

[0063] The speech conversion unit can adjust its speech conversion method based on the user's language skills. For example, if the user speaks multiple languages, the speech conversion unit can perform speech conversion according to each language. Furthermore, the speech conversion unit can reflect specific accents and intonations based on the user's language skills. In addition, the speech conversion unit can adjust the speed and clarity of the speech according to the user's language skills. By adjusting the speech conversion method based on the user's language skills, it is possible to achieve more natural and easily understandable speech conversion.

[0064] The acquisition unit can adjust the method of acquiring appearance data based on the user's health condition. For example, if the user is tired, the acquisition unit can prioritize acquiring data from a relaxed state. The acquisition unit can also adjust specific lighting conditions and camera angles based on the user's health condition. Furthermore, the acquisition unit can adjust the frequency and timing of data acquisition according to the user's health condition. This allows for the acquisition of more natural and healthy-looking data by adjusting the method of acquiring appearance data based on the user's health condition.

[0065] The following briefly describes the processing flow for example form 1.

[0066] Step 1: The acquisition unit acquires the user's appearance data. The acquisition unit can, for example, use a camera to acquire images of the user's face and entire body, and can also acquire motion data. The acquisition unit uses image processing technology to extract facial features, posture, body shape features, and motion features. Step 2: The avatar generation unit generates a gender-neutral avatar based on the appearance data acquired by the acquisition unit. The avatar generation unit uses a generation AI to generate a gender-neutral avatar based on the user's facial features, full body features, and movement characteristics. Step 3: The reaction reflection unit reflects the user's reactions in real time onto the avatar generated by the avatar generation unit. The reaction reflection unit uses facial expression recognition technology, voice analysis technology, and motion recognition technology to detect changes in the user's facial expressions, tone of voice, and movements, and reflects them on the avatar. Step 4: The voice conversion unit converts the user's response into AI voice and provides a proxy response. The voice conversion unit uses speech recognition technology to convert the user's response into text data, and then uses speech synthesis technology to convert the text data into AI voice. The voice conversion unit can also adjust the tone and volume of the voice to reflect the user's emotions.

[0067] (Example of form 2) The EqualMeet system according to an embodiment of the present invention is a system that provides an online interview environment that completely eliminates gender bias. This system eliminates gender bias by generating a gender-neutral avatar based on the user's appearance data and reflecting the user's reactions (such as changes in facial expressions and tone of voice) in real time. It also provides an agent service that converts the user's answers into AI voice and answers on their behalf. As a result, interviewers can conduct interviews in the same way as conventional interviews, while eliminating gender bias. For example, the EqualMeet system generates a gender-neutral avatar based on the user's appearance data. This avatar hides the user's appearance and reflects the user's reactions during the interview in real time. Next, the EqualMeet system provides an agent service that converts the user's answers into AI voice and answers on their behalf. As a result, interviewers can conduct interviews without gender bias. This service has benefits for both companies and users. Companies can increase the transparency of the selection process and build a gender-neutral environment, which can lead to an increase in the number of job applicants. Users can undergo interviews with peace of mind, free from gender bias, and expect selection based solely on their abilities and inner qualities. The EqualMeet system aims to create a future where everyone can undergo interviews with confidence, by being standardized as an option during interviews. The market size, including the interview-related market and the DX promotion-related market, is estimated at approximately 1.45 trillion yen. Even with the increase in agent services using AI-generated tools, the final decision rests with humans, and a fundamental change in the system is necessary to reduce bias. The EqualMeet system, by using generated AI, can change the framework that was previously impossible, realizing completely bias-free, fair, and safe interviews. In this way, the EqualMeet system can eliminate gender bias and provide fair and safe interviews.

[0068] The EqualMeet system according to this embodiment comprises an acquisition unit, an avatar generation unit, a reaction reflection unit, and a voice conversion unit. The acquisition unit acquires the user's appearance data. The acquisition unit can, for example, acquire an image of the user's face using a camera. The acquisition unit can also acquire an image of the user's entire body. Furthermore, the acquisition unit can acquire the user's movement data. For example, the acquisition unit can take an image of the user's face using a camera and extract facial features using image processing technology. The acquisition unit can also take an image of the entire body and extract features of posture and body shape. The acquisition unit can also acquire movement data and extract features of movement. The avatar generation unit generates a gender-neutral avatar based on the appearance data acquired by the acquisition unit. The avatar generation unit can, for example, use a generation AI to generate a gender-neutral avatar based on the user's facial features. Furthermore, the avatar generation unit can generate a gender-neutral avatar based on the features of the entire body. Furthermore, the avatar generation unit can generate a gender-neutral avatar based on the features of movement. For example, the avatar generation unit inputs the user's facial features into the generation AI and generates an avatar with a neutral face. The avatar generation unit can also input full-body features and generate an avatar with a neutral body type. The avatar generation unit can also input movement features and generate an avatar that performs neutral movements. The reaction reflection unit reflects the user's reactions in real time onto the avatar generated by the avatar generation unit. The reaction reflection unit can, for example, use facial recognition technology to detect changes in the user's facial expressions and reflect them in the avatar. The reaction reflection unit can also use voice analysis technology to detect changes in the user's voice tone and reflect them in the avatar. Furthermore, the reaction reflection unit can use motion recognition technology to detect changes in the user's movements and reflect them in the avatar. For example, the reaction reflection unit can use facial recognition technology to detect the user's smile or surprised expression and reflect it in the avatar. The reaction reflection unit can also use voice analysis technology to detect changes in the tone and volume of the user's voice and reflect them in the avatar. The reaction reflection unit can also use motion recognition technology to detect changes in the user's hand movements and posture, and reflect them in the avatar.The voice conversion unit converts the user's answers into AI voice and provides answers on their behalf. The voice conversion unit can, for example, use speech recognition technology to convert the user's answers into text data. The voice conversion unit can also use speech synthesis technology to convert the text data into AI voice. Furthermore, the voice conversion unit can reflect the user's emotions during the voice conversion process. For example, the voice conversion unit can use speech recognition technology to convert the user's answers into text data, and then use speech synthesis technology to convert the text data into a gender-neutral AI voice. The voice conversion unit can also adjust the tone and volume of the voice to reflect the user's emotions. As a result, the EqualMeet system according to this embodiment can eliminate gender bias and provide a fair and safe interview.

[0069] The data acquisition unit acquires user appearance data. For example, the acquisition unit can acquire images of the user's face using a camera. It can also acquire images of the user's entire body. Furthermore, the acquisition unit can acquire user movement data. Specifically, the acquisition unit uses a high-resolution camera to capture images of the user's face from multiple angles and uses image processing technology to extract facial features in detail. This includes the position and shape of the eyes, nose, and mouth, as well as skin color and texture. When acquiring full-body images, the unit captures the user standing and walking, and extracts features of their posture and body shape. This provides data such as the user's height, weight, and body proportions. For acquiring movement data, motion capture technology can be used in addition to cameras. For example, sensors can detect the movements of the user's hands, arms, and legs, and the characteristics of the movements can be recorded in detail. This allows for accurate understanding of the user's walking patterns, gestures, and changes in posture. The acquisition unit collects this data in real time and transmits it to a central database. The data is encrypted and strictly managed to protect privacy. Furthermore, the data acquisition unit can adjust the frequency and accuracy of data collection, enabling flexible responses to specific situations and conditions. For example, data can be collected at a high frequency at the start of an interview, allowing for real-time monitoring of changes in the user's tension and stress levels. This allows the data acquisition unit to collect data efficiently and effectively, improving the overall system performance.

[0070] The avatar generation unit generates a gender-neutral avatar based on the appearance data acquired by the acquisition unit. For example, the avatar generation unit uses a generation AI to generate a gender-neutral avatar based on the user's facial features. Specifically, the generation AI receives the user's facial features as input data and adjusts the shape of the face and the placement of parts to generate a gender-neutral avatar. This includes algorithms for making the shapes of the eyes, nose, and mouth gender-neutral. The avatar generation unit can also generate a gender-neutral avatar based on the user's overall body features. The generation AI analyzes the user's body shape data and adjusts the body's proportions and posture to generate a gender-neutral, gender-neutral physique. Furthermore, the avatar generation unit can generate a gender-neutral avatar based on its movement characteristics. The generation AI analyzes the user's movement data and adjusts the smoothness of the movements and the naturalness of the gestures to generate gender-neutral, gender-neutral movements. For example, the avatar generation unit inputs the user's facial features into the generation AI to generate a gender-neutral avatar. The generating AI analyzes facial features and adjusts the shapes of the eyes, nose, and mouth to be androgynous. The avatar generation unit can also take full-body features as input and generate an androgynous avatar. The generating AI analyzes body shape data and adjusts body proportions and posture to be androgynous. Furthermore, the avatar generation unit can take movement characteristics as input and generate an avatar that performs androgynous movements. The generating AI analyzes movement data and adjusts the smoothness of the movements and the naturalness of the gestures to be androgynous. As a result, the avatar generation unit can generate androgynous avatars based on the user's appearance data, providing a fair interview environment.

[0071] The reaction reflection unit reflects the user's reactions in real time onto the avatar generated by the avatar generation unit. For example, the reaction reflection unit uses facial recognition technology to detect changes in the user's facial expressions and reflects them on the avatar. Specifically, facial recognition technology analyzes the user's facial image to detect expressions such as smiles, surprise, and anger. This includes algorithms that analyze features such as eye and mouth movements and eyebrow positions. The reaction reflection unit reflects this facial expression data on the avatar in real time, so that the avatar changes according to the user's facial expressions. The reaction reflection unit can also use voice analysis technology to detect changes in the user's voice tone and reflect them on the avatar. Voice analysis technology analyzes the tone, volume, and rhythm of the user's voice to detect changes in emotion. The reaction reflection unit reflects this voice data on the avatar in real time, so that the avatar changes according to the user's voice tone. Furthermore, the reaction reflection unit can also use motion recognition technology to detect changes in the user's motions and reflect them on the avatar. Motion recognition technology analyzes the user's hand movements and changes in posture to detect gestures and changes in posture. The reaction reflection unit reflects this motion data onto the avatar in real time, causing the avatar to change in response to the user's actions. For example, the reaction reflection unit can use facial expression recognition technology to detect the user's smile or surprised expression and reflect it on the avatar. The reaction reflection unit can also use voice analysis technology to detect changes in the tone and volume of the user's voice and reflect them on the avatar. The reaction reflection unit can also use motion recognition technology to detect changes in the user's hand movements and posture and reflect them on the avatar. As a result, the reaction reflection unit can reflect the user's reactions onto the avatar in real time, enabling more natural and realistic communication.

[0072] The voice conversion unit converts the user's answers into AI voice and provides answers on their behalf. For example, the voice conversion unit uses speech recognition technology to convert the user's answers into text data. Specifically, speech recognition technology analyzes the user's voice and extracts the utterance as text data. This includes algorithms that analyze the waveform of the voice and recognize phonemes and words. Based on this text data, the voice conversion unit uses speech synthesis technology to convert the text data into AI voice. Speech synthesis technology receives text data as input and adjusts the tone, rhythm, and volume of the voice to generate natural speech. Furthermore, the voice conversion unit can also reflect the user's emotions during the voice conversion process. For example, the voice conversion unit uses speech recognition technology to convert the user's answers into text data, and then uses speech synthesis technology to convert the text data into a neutral AI voice. Speech synthesis technology adjusts the tone and volume of the voice to reflect the user's emotions. As a result, the AI ​​voice can generate natural speech that reflects the user's emotions. The voice conversion unit can also adjust the tone and volume of the voice to reflect the user's emotions. For example, if a user is excited, the voice tone can be raised and emphasis can be increased to reflect that excited emotion. Conversely, if a user is calm, the voice tone can be lowered and the rhythm slowed to reflect that calm emotion. In this way, the voice conversion unit can convert the user's responses into natural-sounding AI voice, providing a fair and reassuring interview.

[0073] The reaction reflection unit includes a detection unit that detects changes in facial expressions and tone of voice. The reaction reflection unit can detect changes in the user's facial expressions, for example, using facial recognition technology. For example, the reaction reflection unit can track facial feature points to detect smiles and surprised expressions. The reaction reflection unit can also detect changes in the user's tone of voice using voice analysis technology. For example, the reaction reflection unit can analyze changes in voice tone and volume to detect changes in emotion. Furthermore, the reaction reflection unit can detect changes in the user's movements using motion recognition technology. For example, the reaction reflection unit can analyze changes in hand movements and posture to detect reactions. This allows for a more accurate reflection of the user's reactions by detecting changes in facial expressions and tone of voice. Some or all of the above-described processes in the reaction reflection unit may be performed using AI or not. For example, the reaction reflection unit can input facial expression data detected using facial recognition technology into a generating AI, which can then analyze the changes in facial expressions and reflect them in the avatar.

[0074] The speech conversion unit comprises a recognition unit that uses speech recognition technology and a synthesis unit that uses speech synthesis technology. The speech conversion unit, for example, uses speech recognition technology to convert the user's response into text data. For example, the speech conversion unit can use deep learning-based speech recognition technology to convert the user's voice into text with high accuracy. The speech conversion unit can also use speech synthesis technology to convert the text data into AI voice. For example, the speech conversion unit can use text-to-speech (TTS) technology to generate natural-sounding voice. Furthermore, the speech conversion unit can also reflect the user's emotions during speech conversion. For example, the speech conversion unit can adjust the tone and volume of the voice to enrich emotional expression. As a result, by using speech recognition technology and speech synthesis technology, the user's response can be converted into AI voice and used as a proxy answer. Some or all of the above-described processes in the speech conversion unit may be performed using AI or not. For example, the speech conversion unit can input text data acquired using speech recognition technology into a generating AI, and the generating AI can analyze the text data to generate natural-sounding voice.

[0075] The acquisition unit estimates the user's emotions and adjusts the timing of appearance data acquisition based on the estimated user emotions. The acquisition unit estimates the user's emotions using, for example, facial recognition technology. For example, the acquisition unit can analyze changes in the user's facial expressions and estimate whether they are relaxed or tense. The acquisition unit can also estimate the user's emotions using voice analysis technology. For example, the acquisition unit can analyze changes in the tone and volume of the user's voice and estimate changes in emotion. Furthermore, the acquisition unit can analyze the user's biometric data using biometric technology and estimate emotions. For example, the acquisition unit can analyze heart rate and skin electrical activity and estimate the user's emotional state. By adjusting the timing of appearance data acquisition based on the user's emotions, more natural facial expression data can be obtained. Emotion estimation is achieved using an emotion estimation function with an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the acquisition unit may be performed using AI or not. For example, the acquisition unit can input facial expression data acquired using facial expression recognition technology into a generating AI, which can then analyze changes in facial expression to estimate emotions and adjust the acquisition timing.

[0076] The acquisition unit analyzes the user's past appearance data and selects the optimal acquisition method. For example, the acquisition unit analyzes the user's past appearance data to determine the optimal timing for acquiring the most natural facial expression. For example, the acquisition unit can prioritize acquiring data from past data when the user is relaxed. The acquisition unit can also select the optimal method for acquiring facial expressions under specific circumstances from past data. For example, the acquisition unit can prioritize acquiring data from past data under specific lighting conditions or camera angles. By analyzing the user's past appearance data, the acquisition unit can select the optimal method for acquiring the most natural facial expression. Some or all of the above processing in the acquisition unit may be performed using AI or not. For example, the acquisition unit can input past appearance data into a generating AI, which can then analyze the data and select the optimal acquisition method.

[0077] The acquisition unit filters the appearance data based on the user's current lifestyle and areas of interest. For example, the acquisition unit can acquire appearance data in a relaxed environment based on the user's current lifestyle. For example, if the user is at home, the acquisition unit can acquire data in a relaxed state. The acquisition unit can also acquire appearance data while displaying content that is of interest to the user, based on the user's areas of interest. For example, the acquisition unit can acquire data while displaying videos or music that the user is interested in. Furthermore, the acquisition unit can acquire appearance data in an optimal environment based on the user's lifestyle and areas of interest. For example, the acquisition unit can select a place and time when the user can relax and acquire data. This allows for the acquisition of appearance data in an optimal environment by filtering based on the user's lifestyle and areas of interest. Some or all of the above processing in the acquisition unit may be performed using AI or not. For example, the acquisition unit can input data on the user's lifestyle and areas of interest into a generating AI, which can analyze the data and select the optimal acquisition method.

[0078] The acquisition unit estimates the user's emotions and determines the priority of appearance data to acquire based on the estimated user emotions. The acquisition unit estimates the user's emotions using, for example, facial recognition technology. For example, the acquisition unit can analyze changes in the user's facial expressions and estimate whether they are relaxed or tense. The acquisition unit can also estimate the user's emotions using voice analysis technology. For example, the acquisition unit can analyze changes in the tone and volume of the user's voice and estimate changes in emotion. Furthermore, the acquisition unit can analyze the user's biometric data using biometric technology and estimate emotions. For example, the acquisition unit can analyze heart rate and skin electrical activity and estimate the user's emotional state. By prioritizing appearance data based on the user's emotions, more appropriate data can be acquired preferentially. Emotion estimation is achieved using an emotion estimation function with an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the acquisition unit may be performed using AI or not. For example, the acquisition unit can input facial expression data acquired using facial expression recognition technology into a generating AI, which can then analyze changes in facial expression to estimate emotions and determine the priority of data to acquire.

[0079] The acquisition unit prioritizes acquiring highly relevant data when acquiring appearance data, taking into account the user's geographical location information. For example, the acquisition unit acquires appearance data in an optimal environment based on the user's geographical location information. For example, if the user is in a specific region, the acquisition unit can prioritize acquiring appearance data related to that region. The acquisition unit can also prioritize acquiring highly relevant data by taking into account the user's geographical location information. For example, if the user is in a specific location, the acquisition unit can prioritize acquiring data related to that location. In this way, by prioritizing the acquisition of highly relevant data based on the user's geographical location information, appearance data can be acquired in an optimal environment. Some or all of the above processing in the acquisition unit may be performed using AI or not. For example, the acquisition unit can input the user's geographical location information into a generating AI, and the generating AI can analyze the data and prioritize the acquisition of highly relevant data.

[0080] The acquisition unit analyzes the user's social media activity and acquires relevant data when acquiring appearance data. For example, the acquisition unit analyzes the user's social media activity and selects the optimal timing to acquire the most natural facial expression. For example, the acquisition unit can analyze the user's posts, the number of likes, comments, etc., and acquire data while displaying interesting content. The acquisition unit can also analyze the user's social media activity and prioritize the acquisition of relevant data. For example, the acquisition unit can select the optimal method for acquiring facial expressions under specific circumstances from the user's social media activity. This allows the system to select the optimal timing to acquire the most natural facial expression by analyzing the user's social media activity. Some or all of the above processing in the acquisition unit may be performed using AI or not. For example, the acquisition unit can input data on the user's social media activity into a generating AI, which can analyze the data and prioritize the acquisition of relevant data.

[0081] The avatar generation unit estimates the user's emotions and adjusts the avatar's representation based on the estimated emotions. For example, the avatar generation unit can estimate the user's emotions using facial recognition technology. For instance, it can analyze changes in the user's facial expressions to estimate whether they are relaxed or tense. It can also estimate the user's emotions using voice analysis technology. For example, it can analyze changes in the tone and volume of the user's voice to estimate changes in emotion. Furthermore, the avatar generation unit can analyze the user's biometric data using biometric technology to estimate emotions. For example, it can analyze heart rate and skin electrical activity to estimate the user's emotional state. This allows for the generation of more natural avatars by adjusting the avatar's representation based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the avatar generation unit may be performed using AI or not. For example, the avatar generation unit can input facial expression data acquired using facial expression recognition technology into a generation AI, which can analyze changes in facial expression to estimate emotions and adjust the avatar's representation.

[0082] The avatar generation unit adjusts the level of detail of the avatar based on the importance of the appearance data during avatar generation. For example, the avatar generation unit can generate a detailed avatar based on the importance of the appearance data. For example, the avatar generation unit can generate a sophisticated avatar based on detailed data of facial features and body shape. The avatar generation unit can also generate a simplified avatar based on the importance of the appearance data. For example, the avatar generation unit can generate a simplified avatar based on data of low importance. In this way, by adjusting the level of detail of the avatar based on the importance of the appearance data, the optimal avatar can be generated. Some or all of the above processing in the avatar generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the avatar generation unit can input appearance data into a generation AI, and the generation AI can analyze the importance of the data and adjust the level of detail of the avatar.

[0083] The avatar generation unit applies different generation algorithms depending on the user's category when generating avatars. For example, the avatar generation unit can apply the optimal generation algorithm depending on the user's category. For example, the avatar generation unit can apply different generation algorithms depending on categories such as age, gender, and occupation. The avatar generation unit can also apply different generation algorithms depending on the user's category. For example, the avatar generation unit can generate avatars by applying a specific algorithm to users belonging to a specific category. In this way, the optimal avatar can be generated by applying different generation algorithms depending on the user's category. Some or all of the above-described processes in the avatar generation unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the avatar generation unit can input user category data into a generation AI, and the generation AI can analyze the data and apply the optimal generation algorithm.

[0084] The avatar generation unit estimates the user's emotions and adjusts the avatar's appearance based on the estimated emotions. For example, the avatar generation unit can estimate the user's emotions using facial recognition technology. For instance, it can analyze changes in the user's facial expressions to estimate whether they are relaxed or tense. It can also estimate the user's emotions using voice analysis technology. For example, it can analyze changes in the tone and volume of the user's voice to estimate changes in emotion. Furthermore, the avatar generation unit can analyze the user's biometric data using biometric technology to estimate emotions. For example, it can analyze heart rate and skin electrical activity to estimate the user's emotional state. This allows for the creation of more natural-looking avatars by adjusting their appearance based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the avatar generation unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the avatar generation unit can input facial expression data acquired using facial expression recognition technology into a generation AI, which can then analyze the changes in facial expression to estimate emotions and adjust the appearance of the avatar.

[0085] The avatar generation unit determines the priority of avatars based on the user's submission timing when generating avatars. For example, the avatar generation unit can generate the optimal avatar based on the user's submission timing. For example, the avatar generation unit can determine the priority of avatars based on the submission date and time or submission order. Alternatively, the avatar generation unit can also determine the priority of avatars based on the user's submission timing. For example, the avatar generation unit can prioritize generating avatars for users who submitted earlier. By determining the priority of avatars based on the user's submission timing, the optimal avatar can be generated. Some or all of the above-described processes in the avatar generation unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the avatar generation unit can input submission timing data into a generation AI, which can then analyze the data to determine the priority of avatars.

[0086] The avatar generation unit adjusts the order of avatars based on user relevance during avatar generation. For example, the avatar generation unit can generate the optimal avatar based on user relevance. For example, the avatar generation unit can adjust the order of avatars based on interest level and past usage history. The avatar generation unit can also adjust the order of avatars based on user relevance. For example, the avatar generation unit can prioritize generating avatars for highly relevant users. In this way, the optimal avatar can be generated by adjusting the order of avatars based on user relevance. Some or all of the above processing in the avatar generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the avatar generation unit can input user relevance data into a generation AI, and the generation AI can analyze the data and adjust the order of avatars.

[0087] The reaction reflection unit estimates the user's emotions and adjusts the method of reflecting reactions based on the estimated emotions. For example, the reaction reflection unit can estimate the user's emotions using facial recognition technology. For instance, it can analyze changes in the user's facial expressions to estimate whether they are relaxed or tense. The reaction reflection unit can also estimate the user's emotions using voice analysis technology. For example, it can analyze changes in the tone and volume of the user's voice to estimate changes in emotion. Furthermore, the reaction reflection unit can analyze the user's biometric data using biometric technology to estimate emotions. For example, it can analyze heart rate and skin electrical activity to estimate the user's emotional state. This allows for more natural reactions to be reflected by adjusting the method of reflecting reactions based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the reaction reflection unit may be performed using AI or not. For example, the reaction reflection unit can input facial expression data acquired using facial expression recognition technology into a generating AI, which can analyze the changes in facial expression to estimate emotions and adjust the method of reflecting reactions.

[0088] The reaction reflection unit analyzes the user's past reaction data to select the optimal reflection method when reflecting reactions. For example, the reaction reflection unit can analyze the user's past reaction data and select the optimal method to reflect the most natural reaction. For example, the reaction reflection unit can select the optimal method to reflect a reaction under specific circumstances from past data. The reaction reflection unit can also select the optimal method to reflect specific facial expressions or actions from past data. For example, the reaction reflection unit can prioritize the reflection of specific facial expressions or actions from past data. In this way, by analyzing the user's past reaction data, the optimal method to reflect the most natural reaction can be selected. Some or all of the above processing in the reaction reflection unit may be performed using AI or not. For example, the reaction reflection unit can input past reaction data into a generating AI, which can analyze the data and select the optimal reflection method.

[0089] The reaction reflection unit customizes the means of reflection based on the user's current living situation when reflecting reactions. For example, the reaction reflection unit reflects the optimal reaction based on the user's current living situation. For example, if the user is at home, the reaction reflection unit can reflect a relaxed reaction. The reaction reflection unit can also reflect a customized reaction based on the user's living situation. For example, if the user is in a specific location, the reaction reflection unit can reflect a reaction appropriate for that location. In this way, the optimal reaction can be reflected by customizing the means of reflection based on the user's current living situation. Some or all of the above processing in the reaction reflection unit may be performed using AI or not. For example, the reaction reflection unit can input the user's living situation data into a generating AI, which can analyze the data and select the optimal reflection method.

[0090] The reaction reflection unit estimates the user's emotions and determines the priority of reactions based on the estimated emotions. For example, the reaction reflection unit can estimate the user's emotions using facial recognition technology. For instance, it can analyze changes in the user's facial expressions to estimate whether they are relaxed or tense. The reaction reflection unit can also estimate the user's emotions using voice analysis technology. For example, it can analyze changes in the tone and volume of the user's voice to estimate changes in emotion. Furthermore, the reaction reflection unit can analyze the user's biometric data using biometric technology to estimate emotions. For example, it can analyze heart rate and skin electrical activity to estimate the user's emotional state. This allows for the prioritization of reactions based on the user's emotions, thereby prioritizing and reflecting more appropriate reactions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the reaction reflection unit may be performed using AI or not. For example, the reaction reflection unit can input facial expression data acquired using facial expression recognition technology into a generating AI, which can then analyze the changes in facial expression to estimate emotions and determine the priority of reactions.

[0091] The reaction reflection unit selects the optimal reflection method when reflecting reactions, taking into account the user's geographical location information. For example, the reaction reflection unit reflects the optimal reaction based on the user's geographical location information. For example, if the user is in a specific region, the reaction reflection unit can reflect a reaction related to that region. The reaction reflection unit can also reflect a customized reaction, taking into account the user's geographical location information. For example, if the user is in a specific location, the reaction reflection unit can reflect a reaction appropriate for that location. This allows for the reflection of more appropriate reactions by selecting the optimal reflection method based on the user's geographical location information. Some or all of the above processing in the reaction reflection unit may be performed using AI or not. For example, the reaction reflection unit can input the user's geographical location information into a generating AI, which can then analyze the data and select the optimal reflection method.

[0092] The reaction reflection unit analyzes the user's social media activity and proposes a method for reflecting reactions. For example, the reaction reflection unit analyzes the user's social media activity and proposes a method for reflecting the optimal reaction. For example, the reaction reflection unit can analyze the user's posts, the number of likes, comments, etc., and reflect reactions while displaying content that is of interest. The reaction reflection unit can also analyze the user's social media activity and reflect customized reactions. For example, the reaction reflection unit can select the optimal method for reflecting reactions under specific circumstances from the user's social media activity. In this way, by analyzing the user's social media activity, it can propose a method for reflecting the optimal reaction. Some or all of the above processing in the reaction reflection unit may be performed using AI or not. For example, the reaction reflection unit can input data on the user's social media activity into a generating AI, which can analyze the data and select the optimal reflection method.

[0093] The speech conversion unit estimates the user's emotions and adjusts the speech conversion method based on the estimated emotions. For example, the speech conversion unit can estimate the user's emotions using facial recognition technology. For instance, it can analyze changes in the user's facial expressions to estimate whether they are relaxed or tense. The speech conversion unit can also estimate the user's emotions using speech analysis technology. For example, it can analyze changes in the tone and volume of the user's voice to estimate changes in emotion. Furthermore, the speech conversion unit can analyze the user's biometric data using biometric technology to estimate emotions. For example, it can analyze heart rate and skin electrical activity to estimate the user's emotional state. This allows for more natural speech conversion by adjusting the speech conversion method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the speech conversion unit may be performed using AI or not. For example, the speech conversion unit can input facial expression data acquired using facial expression recognition technology into a generating AI, which can then analyze the changes in facial expression to estimate emotions and adjust the speech conversion method.

[0094] The speech conversion unit analyzes the user's past response data to select the optimal conversion method during speech conversion. For example, the speech conversion unit analyzes the user's past response data to select the optimal method for the most natural speech conversion. For example, the speech conversion unit can select the optimal method for speech conversion under specific circumstances from past data. The speech conversion unit can also select the optimal method for reflecting specific tones and emphasis from past data. For example, the speech conversion unit can prioritize reflecting specific tones and emphasis from past data. This allows the optimal method for the most natural speech conversion to be selected by analyzing the user's past response data. Some or all of the above processing in the speech conversion unit may be performed using AI or not. For example, the speech conversion unit can input past response data into a generating AI, which can then analyze the data and select the optimal conversion method.

[0095] The voice conversion unit customizes the conversion method based on the user's current living situation during voice conversion. For example, the voice conversion unit performs optimal voice conversion based on the user's current living situation. For example, if the user is at home, the voice conversion unit can perform voice conversion in a relaxed state. The voice conversion unit can also perform customized voice conversion based on the user's living situation. For example, if the user is in a specific location, the voice conversion unit can perform voice conversion appropriate for that location. In this way, optimal voice conversion can be achieved by customizing the conversion method based on the user's current living situation. Some or all of the above processing in the voice conversion unit may be performed using AI or not. For example, the voice conversion unit can input the user's living situation data into a generating AI, and the generating AI can analyze the data and select the optimal conversion method.

[0096] The speech conversion unit estimates the user's emotions and determines the priority of speech conversion based on the estimated emotions. For example, the speech conversion unit can estimate the user's emotions using facial recognition technology. For instance, it can analyze changes in the user's facial expressions to estimate whether they are relaxed or tense. The speech conversion unit can also estimate the user's emotions using speech analysis technology. For example, it can analyze changes in the tone and volume of the user's voice to estimate changes in emotion. Furthermore, the speech conversion unit can analyze the user's biometric data using biometric technology to estimate emotions. For example, it can analyze heart rate and skin electrical activity to estimate the user's emotional state. This allows for prioritizing speech conversion based on the user's emotions, enabling more appropriate speech conversion to be prioritized. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the speech conversion unit may be performed using AI or not. For example, the speech conversion unit can input facial expression data acquired using facial expression recognition technology into a generating AI, which can then analyze changes in facial expression to estimate emotions and determine the priority of speech conversion.

[0097] The speech conversion unit selects the optimal conversion method when converting speech, taking into account the user's geographical location information. For example, the speech conversion unit performs optimal speech conversion based on the user's geographical location information. For example, if the user is in a specific region, the speech conversion unit can perform speech conversion relevant to that region. The speech conversion unit can also perform customized speech conversion, taking into account the user's geographical location information. For example, if the user is in a specific location, the speech conversion unit can perform speech conversion appropriate for that location. This allows for more appropriate speech conversion by selecting the optimal conversion method based on the user's geographical location information. Some or all of the above processing in the speech conversion unit may be performed using AI, or it may be performed without AI. For example, the speech conversion unit can input the user's geographical location information into a generating AI, which can then analyze the data and select the optimal conversion method.

[0098] The speech conversion unit analyzes the user's social media activity during speech conversion and proposes a conversion method. For example, the speech conversion unit analyzes the user's social media activity and proposes a method for performing optimal speech conversion. For example, the speech conversion unit can analyze the user's posts, the number of likes, comments, etc., and perform speech conversion while displaying interesting content. The speech conversion unit can also analyze the user's social media activity and perform customized speech conversion. For example, the speech conversion unit can select the optimal method for performing speech conversion under specific circumstances from the user's social media activity. In this way, by analyzing the user's social media activity, it can propose a method for performing optimal speech conversion. Some or all of the above processing in the speech conversion unit may be performed using AI or not. For example, the speech conversion unit can input data on the user's social media activity into a generating AI, which can analyze the data and select the optimal conversion method.

[0099] The detection unit estimates the user's emotions and adjusts the method for detecting changes in facial expressions and tone of voice based on the estimated emotions. For example, the detection unit can estimate the user's emotions using facial recognition technology. For instance, it can analyze changes in the user's facial expressions to estimate whether they are relaxed or tense. The detection unit can also estimate the user's emotions using voice analysis technology. For example, it can analyze changes in the tone and volume of the user's voice to estimate changes in emotion. Furthermore, the detection unit can analyze the user's biometric data using biometric technology to estimate emotions. For example, it can analyze heart rate and skin electrical activity to estimate the user's emotional state. This allows for a more accurate reflection of the user's reactions by adjusting the method for detecting changes in facial expressions and tone of voice based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the detection unit may be performed using AI or not. For example, the detection unit can input facial expression data acquired using facial expression recognition technology into a generating AI, which can then analyze changes in facial expression to estimate emotions and adjust the method for detecting changes in facial expression and tone of voice.

[0100] The detection unit analyzes the user's past facial expressions and voice tone data to select the optimal detection method during detection. For example, the detection unit analyzes the user's past facial expressions and voice tone data to select the optimal method for detecting the most natural changes. For example, the detection unit can select the optimal method for detecting changes in facial expressions and voice tone under specific circumstances from past data. The detection unit can also select the optimal method for reflecting specific tones and intensities from past data. For example, the detection unit can prioritize reflecting specific tones and intensities from past data. This allows the detection unit to select the optimal method for detecting the most natural changes by analyzing the user's past facial expressions and voice tone data. Some or all of the above processing in the detection unit may be performed using AI or not. For example, the detection unit can input past facial expressions and voice tone data into a generating AI, which can then analyze the data and select the optimal detection method.

[0101] The detection unit estimates the user's emotions and determines the priority of changes in facial expressions and tone of voice based on the estimated emotions. For example, the detection unit can estimate the user's emotions using facial recognition technology. For instance, it can analyze changes in the user's facial expressions to estimate whether they are relaxed or tense. The detection unit can also estimate the user's emotions using voice analysis technology. For example, it can analyze changes in the tone and volume of the user's voice to estimate changes in emotion. Furthermore, the detection unit can analyze the user's biometric data using biometric technology to estimate emotions. For example, it can analyze heart rate and skin electrical activity to estimate the user's emotional state. This allows for the prioritization of changes in facial expressions and tone of voice based on the user's emotions, enabling the detection of more appropriate changes. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the detection unit may be performed using AI or not. For example, the detection unit can input facial expression data acquired using facial expression recognition technology into a generating AI, which can analyze changes in facial expression to estimate emotions and determine the priority of changes in facial expression and tone of voice.

[0102] The detection unit selects the optimal detection method when detecting a user, taking into account the user's geographical location information. For example, the detection unit can detect optimal changes in facial expressions and tone of voice based on the user's geographical location information. For example, if the user is in a specific region, the detection unit can detect changes in facial expressions and tone of voice related to that region. The detection unit can also select a customized detection method, taking into account the user's geographical location information. For example, if the user is in a specific location, the detection unit can detect changes in facial expressions and tone of voice appropriate for that location. By selecting the optimal detection method based on the user's geographical location information, more appropriate changes in facial expressions and tone of voice can be detected. Some or all of the above processing in the detection unit may be performed using AI or not. For example, the detection unit can input the user's geographical location information into a generating AI, which can then analyze the data and select the optimal detection method.

[0103] The recognition unit estimates the user's emotions and adjusts the speech recognition method based on the estimated emotions. For example, the recognition unit can estimate the user's emotions using facial expression recognition technology. For instance, it can analyze changes in the user's facial expressions to estimate whether they are relaxed or tense. The recognition unit can also estimate the user's emotions using speech analysis technology. For example, it can analyze changes in the tone and volume of the user's voice to estimate changes in emotion. Furthermore, the recognition unit can analyze the user's biometric data using biometric technology to estimate emotions. For example, it can analyze heart rate and skin electrical activity to estimate the user's emotional state. This allows for more accurate speech recognition by adjusting the speech recognition method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the recognition unit may be performed using AI or not. For example, the recognition unit can input facial expression data acquired using facial expression recognition technology into a generating AI, which can then analyze the changes in facial expression to estimate emotions and adjust the speech recognition method.

[0104] The recognition unit analyzes the user's past voice data to select the optimal recognition method during speech recognition. For example, the recognition unit can analyze the user's past voice data and select the optimal method for the most natural speech recognition. For example, the recognition unit can select the optimal method for speech recognition under specific circumstances from past data. The recognition unit can also select the optimal method for reflecting specific tones and intensity from past data. For example, the recognition unit can prioritize reflecting specific tones and intensity from past data. In this way, by analyzing the user's past voice data, the optimal method for the most natural speech recognition can be selected. Some or all of the above processing in the recognition unit may be performed using AI or not. For example, the recognition unit can input past voice data into a generating AI, and the generating AI can analyze the data and select the optimal recognition method.

[0105] The recognition unit estimates the user's emotions and determines the priority of speech recognition based on the estimated emotions. For example, the recognition unit can estimate the user's emotions using facial recognition technology. For instance, it can analyze changes in the user's facial expressions to estimate whether they are relaxed or tense. The recognition unit can also estimate the user's emotions using speech analysis technology. For example, it can analyze changes in the tone and volume of the user's voice to estimate changes in emotion. Furthermore, the recognition unit can analyze the user's biometric data using biometric technology to estimate emotions. For example, it can analyze heart rate and skin electrical activity to estimate the user's emotional state. This allows for more appropriate speech recognition to be prioritized based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the recognition unit may be performed using AI or not. For example, the recognition unit can input facial expression data acquired using facial expression recognition technology into a generating AI, which can then analyze changes in facial expression to estimate emotions and determine the priority for speech recognition.

[0106] The recognition unit selects the optimal recognition method during speech recognition, taking into account the user's geographical location information. For example, the recognition unit performs optimal speech recognition based on the user's geographical location information. For example, if the user is in a specific region, the recognition unit can perform speech recognition relevant to that region. The recognition unit can also perform customized speech recognition, taking into account the user's geographical location information. For example, if the user is in a specific location, the recognition unit can perform speech recognition appropriate for that location. This allows for more appropriate speech recognition by selecting the optimal recognition method based on the user's geographical location information. Some or all of the above processing in the recognition unit may be performed using AI, or it may be performed without AI. For example, the recognition unit can input the user's geographical location information into a generating AI, which can then analyze the data and select the optimal recognition method.

[0107] The synthesis unit estimates the user's emotions and adjusts the speech synthesis method based on the estimated emotions. For example, the synthesis unit can estimate the user's emotions using facial recognition technology. For instance, it can analyze changes in the user's facial expressions to estimate whether they are relaxed or tense. The synthesis unit can also estimate the user's emotions using speech analysis technology. For example, it can analyze changes in the tone and volume of the user's voice to estimate changes in emotion. Furthermore, the synthesis unit can analyze the user's biometric data using biometric technology to estimate emotions. For example, it can analyze heart rate and skin electrical activity to estimate the user's emotional state. This allows for more natural speech synthesis by adjusting the speech synthesis method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the synthesis unit may be performed using AI or not. For example, the synthesis unit can input facial expression data acquired using facial expression recognition technology into a generating AI, which can then analyze the changes in facial expression to estimate emotions and adjust the speech synthesis method.

[0108] The synthesis unit analyzes the user's past voice data to select the optimal synthesis method during speech synthesis. For example, the synthesis unit can analyze the user's past voice data and select the optimal method for producing the most natural speech synthesis. For example, the synthesis unit can select the optimal method for producing speech synthesis under specific circumstances from past data. The synthesis unit can also select the optimal method for reflecting specific tones and intensity from past data. For example, the synthesis unit can prioritize reflecting specific tones and intensity from past data. This allows the synthesis unit to select the optimal method for producing the most natural speech synthesis by analyzing the user's past voice data. Some or all of the above processing in the synthesis unit may be performed using AI or not. For example, the synthesis unit can input past voice data into a generation AI, which can then analyze the data and select the optimal synthesis method.

[0109] The synthesis unit estimates the user's emotions and determines the priority of speech synthesis based on the estimated emotions. The synthesis unit estimates the user's emotions using, for example, facial recognition technology. For instance, it can analyze changes in the user's facial expressions to estimate whether they are relaxed or tense. The synthesis unit can also estimate the user's emotions using speech analysis technology. For example, it can analyze changes in the tone and volume of the user's voice to estimate changes in emotion. Furthermore, the synthesis unit can analyze the user's biometric data using biometric technology to estimate emotions. For example, it can analyze heart rate and skin electrical activity to estimate the user's emotional state. This allows for prioritizing speech synthesis based on the user's emotions, enabling more appropriate speech synthesis to be prioritized. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the synthesis unit may be performed using AI or not. For example, the synthesis unit can input facial expression data acquired using facial expression recognition technology into a generating AI, which can then analyze changes in facial expression to estimate emotions and determine the priority for speech synthesis.

[0110] The synthesis unit selects the optimal synthesis method when synthesizing speech, taking into account the user's geographical location information. For example, the synthesis unit performs optimal speech synthesis based on the user's geographical location information. For example, if the user is in a specific region, the synthesis unit can perform speech synthesis relevant to that region. The synthesis unit can also perform customized speech synthesis, taking into account the user's geographical location information. For example, if the user is in a specific location, the synthesis unit can perform speech synthesis appropriate for that location. This allows for more appropriate speech synthesis by selecting the optimal synthesis method based on the user's geographical location information. Some or all of the above processing in the synthesis unit may be performed using AI, or it may be performed without AI. For example, the synthesis unit can input the user's geographical location information into a generating AI, which can then analyze the data and select the optimal synthesis method.

[0111] The synthesis unit analyzes the user's social media activity during speech synthesis and proposes a synthesis method. For example, the synthesis unit analyzes the user's social media activity and proposes a method for performing optimal speech synthesis. For example, the synthesis unit can analyze the user's posts, the number of likes, comments, etc., and perform speech synthesis while displaying interesting content. The synthesis unit can also analyze the user's social media activity and perform customized speech synthesis. For example, the synthesis unit can select the optimal method for performing speech synthesis under specific circumstances from the user's social media activity. In this way, by analyzing the user's social media activity, it can propose a method for performing optimal speech synthesis. Some or all of the above processing in the synthesis unit may be performed using AI or not. For example, the synthesis unit can input data on the user's social media activity into a generating AI, which can analyze the data and select the optimal synthesis method.

[0112] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0113] The data acquisition unit can customize how appearance data is acquired based on the user's hobbies and interests. For example, if the user owns items related to a particular hobby, the data acquisition unit can acquire appearance data that includes those items. The data acquisition unit can also prioritize acquiring data from locations that the user is interested in. Furthermore, the data acquisition unit can guide the user to adopt specific poses and facial expressions based on their hobbies and interests. By customizing the data acquisition method based on the user's hobbies and interests, more natural and individualized data can be acquired.

[0114] The avatar generation unit can adjust the appearance of the avatar according to the user's occupation and role. For example, if the user is a business person, the avatar generation unit can generate an avatar wearing a suit. It can also generate an avatar in casual clothing if the user is engaged in a creative profession. Furthermore, the avatar generation unit can equip the avatar with specific accessories and tools depending on the user's role. This allows for the generation of a more appropriate avatar by adjusting its appearance according to the user's occupation and role.

[0115] The reaction reflection unit can adjust how reactions are reflected based on the user's cultural background. For example, if the user belongs to a particular cultural sphere, the reaction reflection unit can reflect gestures and facial expressions specific to that culture. Furthermore, the reaction reflection unit can emphasize certain reactions based on the user's cultural background. In addition, the reaction reflection unit can adjust the timing and intensity of reactions according to the user's cultural background. By adjusting how reactions are reflected based on the user's cultural background, it is possible to reflect more natural and appropriate reactions.

[0116] The speech conversion unit can adjust its speech conversion method based on the user's language skills. For example, if the user speaks multiple languages, the speech conversion unit can perform speech conversion according to each language. Furthermore, the speech conversion unit can reflect specific accents and intonations based on the user's language skills. In addition, the speech conversion unit can adjust the speed and clarity of the speech according to the user's language skills. By adjusting the speech conversion method based on the user's language skills, it is possible to achieve more natural and easily understandable speech conversion.

[0117] The acquisition unit can adjust the method of acquiring appearance data based on the user's health condition. For example, if the user is tired, the acquisition unit can prioritize acquiring data from a relaxed state. The acquisition unit can also adjust specific lighting conditions and camera angles based on the user's health condition. Furthermore, the acquisition unit can adjust the frequency and timing of data acquisition according to the user's health condition. This allows for the acquisition of more natural and healthy-looking data by adjusting the method of acquiring appearance data based on the user's health condition.

[0118] The acquisition unit can estimate the user's emotions and adjust the method of acquiring appearance data based on the estimated user emotions. For example, if the acquisition unit is relaxed, it can prioritize acquiring data from that state. If the user is tense, it can create a relaxing environment before acquiring data. Furthermore, the acquisition unit can adjust specific lighting conditions and camera angles according to the user's emotions. By adjusting the method of acquiring appearance data based on the user's emotions, it is possible to acquire more natural and emotionally relevant data.

[0119] The avatar generation unit can estimate the user's emotions and adjust the avatar's facial expressions based on those emotions. For example, if the user is relaxed, the avatar generation unit can generate an avatar with a relaxed expression. Similarly, if the user is tense, the avatar generation unit can generate an avatar with a tense expression. Furthermore, the avatar generation unit can reflect changes in the avatar's facial expressions in real time according to the user's emotions. This allows for the generation of more natural and emotionally accurate avatars by adjusting the avatar's facial expressions based on the user's emotions.

[0120] The reaction reflection unit can estimate the user's emotions and adjust the intensity of the reaction based on those emotions. For example, if the user is relaxed, the reaction reflection unit can reflect a gentle reaction. Conversely, if the user is excited, the reaction reflection unit can reflect a strong reaction. Furthermore, the reaction reflection unit can adjust the timing and duration of the reaction according to the user's emotions. By adjusting the intensity of the reaction based on the user's emotions, it is possible to reflect a more natural and emotionally appropriate reaction.

[0121] The voice conversion unit can estimate the user's emotions and adjust the tone and volume of the voice based on those estimates. For example, if the user is relaxed, the voice conversion unit can generate a calm tone of voice. Conversely, if the user is excited, the voice conversion unit can generate a strong tone of voice. Furthermore, the voice conversion unit can also adjust the speed and intonation of the voice according to the user's emotions. By adjusting the tone and volume of the voice based on the user's emotions, it is possible to perform more natural and emotionally appropriate voice conversion.

[0122] The detection unit can estimate the user's emotions and adjust the method of detecting changes in facial expressions and tone of voice based on the estimated emotions. For example, if the user is relaxed, the detection unit can prioritize detecting changes in facial expressions and tone of voice in that state. It can also detect changes in facial expressions and tone of voice in a tense state if the user is nervous. Furthermore, the detection unit can emphasize specific changes in facial expressions and tone of voice depending on the user's emotions. By adjusting the method of detecting changes in facial expressions and tone of voice based on the user's emotions, it is possible to more accurately reflect the user's reactions.

[0123] The following briefly describes the processing flow for example form 2.

[0124] Step 1: The acquisition unit acquires the user's appearance data. The acquisition unit can, for example, use a camera to acquire images of the user's face and entire body, and can also acquire motion data. The acquisition unit uses image processing technology to extract facial features, posture, body shape features, and motion features. Step 2: The avatar generation unit generates a gender-neutral avatar based on the appearance data acquired by the acquisition unit. The avatar generation unit uses a generation AI to generate a gender-neutral avatar based on the user's facial features, full body features, and movement characteristics. Step 3: The reaction reflection unit reflects the user's reactions in real time onto the avatar generated by the avatar generation unit. The reaction reflection unit uses facial expression recognition technology, voice analysis technology, and motion recognition technology to detect changes in the user's facial expressions, tone of voice, and movements, and reflects them on the avatar. Step 4: The voice conversion unit converts the user's response into AI voice and provides a proxy response. The voice conversion unit uses speech recognition technology to convert the user's response into text data, and then uses speech synthesis technology to convert the text data into AI voice. The voice conversion unit can also adjust the tone and volume of the voice to reflect the user's emotions.

[0125] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0126] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0127] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0128] Each of the multiple elements described above, including the acquisition unit, avatar generation unit, reaction reflection unit, and voice conversion unit, is implemented in at least one of the smart device 14 and the data processing device 12. For example, the acquisition unit uses the camera 42 of the smart device 14 to acquire images of the user's face and entire body, and the specific processing unit 290 of the data processing device 12 extracts features using image processing technology. The avatar generation unit uses the specific processing unit 290 of the data processing device 12 to generate a neutral avatar using generation AI. The reaction reflection unit uses the control unit 46A of the smart device 14 to detect the user's reactions using facial recognition technology and voice analysis technology, and reflects them in the avatar. The voice conversion unit uses the specific processing unit 290 of the data processing device 12 to convert the user's responses into AI voice using voice recognition technology and voice synthesis technology. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0129] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0130] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0131] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0132] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0133] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0134] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0135] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0136] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0137] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0138] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0139] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0140] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0141] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0142] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0143] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0144] Each of the multiple elements described above, including the acquisition unit, avatar generation unit, reaction reflection unit, and voice conversion unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the acquisition unit uses the camera 42 of the smart glasses 214 to acquire images of the user's face and entire body, and the specific processing unit 290 of the data processing unit 12 extracts features using image processing technology. The avatar generation unit uses the specific processing unit 290 of the data processing unit 12 to generate a neutral avatar using generation AI. The reaction reflection unit uses the control unit 46A of the smart glasses 214 to detect the user's reactions using facial recognition technology and voice analysis technology and reflects them in the avatar. The voice conversion unit uses the specific processing unit 290 of the data processing unit 12 to convert the user's responses into AI voice using voice recognition technology and voice synthesis technology. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0145] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0146] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0147] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0148] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0149] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0150] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0151] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0152] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0153] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0154] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0155] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0156] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0157] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0158] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0159] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0160] Each of the multiple elements described above, including the acquisition unit, avatar generation unit, reaction reflection unit, and voice conversion unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the acquisition unit acquires images of the user's face and entire body using the camera 42 of the headset terminal 314 and extracts features using image processing technology by the specific processing unit 290 of the data processing unit 12. The avatar generation unit generates a neutral avatar using generation AI by the specific processing unit 290 of the data processing unit 12. The reaction reflection unit detects the user's reactions using facial recognition technology and voice analysis technology by the control unit 46A of the headset terminal 314 and reflects them in the avatar. The voice conversion unit converts the user's responses into AI voice using voice recognition technology and voice synthesis technology by the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0161] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0162] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0163] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0164] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0165] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0166] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0167] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0168] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0169] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0170] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0171] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0172] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0173] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0174] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0175] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0176] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0177] Each of the multiple elements described above, including the acquisition unit, avatar generation unit, reaction reflection unit, and voice conversion unit, is implemented in, for example, at least one of the robot 414 and the data processing unit 12. For example, the acquisition unit uses the camera 42 of the robot 414 to acquire images of the user's face and entire body, and the specific processing unit 290 of the data processing unit 12 extracts features using image processing technology. The avatar generation unit uses the specific processing unit 290 of the data processing unit 12 to generate a neutral avatar using a generation AI. The reaction reflection unit uses the control unit 46A of the robot 414 to detect the user's reactions using facial recognition technology and voice analysis technology, and reflects them in the avatar. The voice conversion unit uses the specific processing unit 290 of the data processing unit 12 to convert the user's responses into AI voice using voice recognition technology and voice synthesis technology. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0178] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0179] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0180] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0181] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0182] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0183] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0184] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0185] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0186] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0187] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0188] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0189] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0190] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0191] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0192] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0193] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0194] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0195] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0196] (Note 1) An acquisition unit that acquires user appearance data, An avatar generation unit generates a gender-neutral avatar based on the appearance data acquired by the acquisition unit, The avatar generated by the avatar generation unit is reflected in real time by the reaction reflection unit, It includes a voice conversion unit that converts the person's answer into AI voice and answers on their behalf. A system characterized by the following features. (Note 2) The reaction reflection unit is, It is equipped with a detection unit that detects changes in facial expressions and tone of voice. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned voice conversion unit is It comprises a recognition unit that uses speech recognition technology and a synthesis unit that uses speech synthesis technology. The system described in Appendix 1, characterized by the features described herein. (Note 4) The acquisition unit is, The system estimates the user's emotions and adjusts the timing of appearance data acquisition based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 5) The acquisition unit is, Analyze the user's past appearance data and select the optimal acquisition method. The system described in Appendix 1, characterized by the features described herein. (Note 6) The acquisition unit is, When acquiring appearance data, filtering is performed based on the user's current lifestyle and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 7) The acquisition unit is, The system estimates the user's emotions and determines the priority of appearance data to acquire based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The acquisition unit is, When acquiring appearance data, the system prioritizes acquiring highly relevant data by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 9) The acquisition unit is, When acquiring appearance data, the system analyzes the user's social media activity and retrieves relevant data. The system described in Appendix 1, characterized by the features described herein. (Note 10) The avatar generation unit is, It estimates the user's emotions and adjusts the avatar's representation based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The avatar generation unit is, When generating an avatar, the level of detail is adjusted based on the importance of the appearance data. The system described in Appendix 1, characterized by the features described herein. (Note 12) The avatar generation unit is, When generating avatars, different generation algorithms are applied depending on the user's category. The system described in Appendix 1, characterized by the features described herein. (Note 13) The avatar generation unit is, It estimates the user's emotions and adjusts the avatar's appearance based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The avatar generation unit is, When generating avatars, the system prioritizes avatars based on when the user submitted them. The system described in Appendix 1, characterized by the features described herein. (Note 15) The avatar generation unit is, When generating avatars, the order of avatars is adjusted based on user relevance. The system described in Appendix 1, characterized by the features described herein. (Note 16) The reaction reflection unit is, It estimates the user's emotions and adjusts how reactions are reflected based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The reaction reflection unit is, When reflecting reactions, the system analyzes the user's past reaction data to select the optimal method for reflecting them. The system described in Appendix 1, characterized by the features described herein. (Note 18) The reaction reflection unit is, When reflecting reactions, the method of reflection will be customized based on the user's current life situation. The system described in Appendix 1, characterized by the features described herein. (Note 19) The reaction reflection unit is, It estimates the user's emotions and determines the priority of reactions based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The reaction reflection unit is, When reflecting reactions, the system will select the optimal method of reflection, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 21) The reaction reflection unit is, When reflecting reactions, we analyze users' social media activity and suggest methods for reflecting those reactions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned voice conversion unit is It estimates the user's emotions and adjusts the speech conversion method based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned voice conversion unit is During speech conversion, the system analyzes the user's past response data to select the optimal conversion method. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned voice conversion unit is During voice conversion, the conversion method is customized based on the user's current living situation. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned voice conversion unit is It estimates the user's emotions and determines the priority of speech conversion based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned voice conversion unit is During speech conversion, the system selects the optimal conversion method by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned voice conversion unit is During voice conversion, the system analyzes the user's social media activity and suggests conversion methods. The system described in Appendix 1, characterized by the features described herein. (Note 28) The detection unit is We estimate the user's emotions and adjust the method for detecting changes in facial expressions and tone of voice based on the estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 29) The detection unit is During detection, the system analyzes the user's past facial expressions and voice tones to select the most suitable detection method. The system described in Appendix 2, characterized by the features described herein. (Note 30) The detection unit is It estimates the user's emotions and determines the priority of changes in facial expressions and tone of voice based on the estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 31) The detection unit is During detection, the optimal detection method is selected considering the user's geographical location information. The system described in Appendix 2, characterized by the features described herein. (Note 32) The aforementioned recognition unit, It estimates the user's emotions and adjusts the speech recognition method based on the estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 33) The aforementioned recognition unit, During speech recognition, the system analyzes the user's past voice data to select the optimal recognition method. The system described in Appendix 3, characterized by the features described herein. (Note 34) The aforementioned recognition unit, It estimates the user's emotions and determines the priority of speech recognition based on the estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 35) The aforementioned recognition unit, During speech recognition, the system selects the optimal recognition method by considering the user's geographical location. The system described in Appendix 3, characterized by the features described herein. (Note 36) The aforementioned synthesis section is The system estimates the user's emotions and adjusts the speech synthesis method based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 37) The aforementioned synthesis section is During speech synthesis, the system analyzes the user's past voice data to select the optimal synthesis method. The system described in Appendix 3, characterized by the features described herein. (Note 38) The aforementioned synthesis section is It estimates the user's emotions and determines the priority of speech synthesis based on the estimated user emotions. The system described in Appendix 3, characterized by the features described herein. (Note 39) The aforementioned synthesis section is During speech synthesis, the optimal synthesis method is selected by considering the user's geographical location information. The system described in Appendix 3, characterized by the features described herein. (Note 40) The aforementioned synthesis section is During speech synthesis, the system analyzes the user's social media activity and suggests synthesis methods. The system described in Appendix 3, characterized by the features described herein. [Explanation of symbols]

[0197] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. An acquisition unit that acquires user appearance data, An avatar generation unit generates a gender-neutral avatar based on the appearance data acquired by the acquisition unit, The avatar generated by the avatar generation unit is reflected in real time by the reaction reflection unit, It includes a voice conversion unit that converts the person's answer into AI voice and answers on their behalf. A system characterized by the following features.

2. The reaction reflection unit is, It is equipped with a detection unit that detects changes in facial expressions and tone of voice. The system according to feature 1.

3. The aforementioned voice conversion unit is It comprises a recognition unit that uses speech recognition technology and a synthesis unit that uses speech synthesis technology. The system according to feature 1.

4. The acquisition unit is, The system estimates the user's emotions and adjusts the timing of appearance data acquisition based on the estimated emotions. The system according to feature 1.

5. The acquisition unit is, Analyze the user's past appearance data and select the optimal acquisition method. The system according to feature 1.

6. The acquisition unit is, When acquiring appearance data, filtering is performed based on the user's current lifestyle and areas of interest. The system according to feature 1.

7. The acquisition unit is, The system estimates the user's emotions and determines the priority of appearance data to acquire based on the estimated user emotions. The system according to feature 1.

8. The acquisition unit is, When acquiring appearance data, the system prioritizes acquiring highly relevant data by considering the user's geographical location. The system according to feature 1.

9. The acquisition unit is, When acquiring appearance data, the system analyzes the user's social media activity and retrieves relevant data. The system according to feature 1.

Images