system

Abstract

The system according to this embodiment aims to provide a multidimensional means of communication for people who are unable to speak. [Solution] The system according to the embodiment comprises a reception unit, a speech synthesis unit, a visual information sharing unit, and an emotion recognition unit. The reception unit receives text input. The speech synthesis unit converts the text received by the reception unit into speech. The visual information sharing unit shares visual information using a camera. The emotion recognition unit analyzes the camera image acquired by the visual information sharing unit and recognizes emotions.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes 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 conventional technology, there is a problem that sufficient multi-dimensional communication means for integrating people who cannot speak into society and economy have not been provided.

[0005] The system according to the embodiment aims to provide multi-dimensional communication means for people who cannot speak.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a reception unit, a speech synthesis unit, a visual information sharing unit, and an emotion recognition unit. The reception unit receives text input. The speech synthesis unit converts the text received by the reception unit into speech. The visual information sharing unit shares visual information using a camera. The emotion recognition unit analyzes the camera images acquired by the visual information sharing unit and recognizes emotions. [Effects of the Invention]

[0007] The system according to this embodiment can provide a multidimensional means of communication for people who are unable to speak. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The SocialVoice system according to an embodiment of the present invention is a comprehensive support platform for the social and economic integration of people who are unable to speak. The SocialVoice system utilizes text input, speech synthesis, visual information, and emotion recognition to provide multidimensional communication. Furthermore, it is equipped with remote work support functions, real-time translation, user-specific customization functions, and wellness monitoring. For example, when a user inputs text, the generating AI converts that text into natural speech. This allows people who are unable to speak to communicate by voice. Next, visual information can be shared using a camera. For example, a user can share what they are seeing through the camera with others. Furthermore, the generating AI analyzes the camera footage and recognizes the user's emotions. This enables appropriate responses according to the user's emotions. Remote work support functions are also included, providing the necessary support for people who are unable to speak when working remotely. For example, the generating AI analyzes the user's input and generates appropriate replies, improving the efficiency of remote work. In addition, the real-time translation function allows for smooth communication with people who speak different languages. User-specific customization functions are also extensive, with the generating AI analyzing the user's behavior and providing optimal settings. This allows users to use the platform in an environment that is best suited to them. Furthermore, it features a wellness monitoring function, where generating AI analyzes health data to detect abnormalities early. This also supports users' health management. In this way, the SocialVoice system is a comprehensive platform that provides multidimensional communication to people who cannot speak, supporting social and economic integration.

[0029] The SocialVoice system according to this embodiment comprises a reception unit, a speech synthesis unit, a visual information sharing unit, and an emotion recognition unit. The reception unit receives text input. The reception unit can receive text by methods such as keyboard input, voice input, or handwriting input. The speech synthesis unit converts the text received by the reception unit into speech. The speech synthesis unit generates natural speech using, for example, a generation AI. The generation AI can convert text into speech using a text generation AI (e.g., LLM). The visual information sharing unit shares visual information using a camera. The visual information sharing unit can share, for example, what a user is seeing through the camera with other people. The visual information sharing unit can share visual information based on the type of camera and the scope of the information to be shared. The emotion recognition unit analyzes the camera footage acquired by the visual information sharing unit and recognizes emotions. The emotion recognition unit analyzes the camera footage using, for example, a generation AI and recognizes the user's emotions. The generation AI can recognize emotions using facial expression recognition technology or speech analysis technology. This allows the SocialVoice system to provide multidimensional communication to people who are unable to speak, and to support social and economic integration.

[0030] The reception unit accepts text input. The reception unit can accept text via methods such as keyboard input, voice input, and handwriting input. Specifically, with keyboard input, the user enters text using a physical or virtual keyboard. With voice input, the user's speech is converted to text using speech recognition technology via a microphone. With handwriting input, characters handwritten with a stylus pen or finger on a tablet or smartphone touchscreen are recognized and converted to text. These input methods are designed to be selectable according to the user's convenience and situation. Furthermore, the reception unit can process the entered text in real time and quickly pass it to the speech synthesis unit and emotion recognition unit. For example, with voice input, partial text can be generated before the user finishes speaking and immediately sent to the speech synthesis unit, minimizing delays. The reception unit also has a function to automatically detect and correct errors in the entered text. For example, by correcting misrecognized words in voice input based on context, more accurate text can be generated. This allows the reception unit to support diverse input methods and generate text that accurately reflects the user's intent.

[0031] The speech synthesis unit converts text received by the reception unit into speech. The speech synthesis unit generates natural-sounding speech, for example, using a generative AI. The generative AI can convert text into speech using a text generation AI (e.g., LLM). Specifically, the generative AI analyzes the input text, understands the grammar and context, and generates speech with appropriate intonation and emotion. For example, if a user inputs "hello," the generative AI analyzes the text, generates an appropriate speech waveform, and pronounces "hello" in a natural voice. The generative AI can also customize the voice's gender, age, accent, etc., according to the user's preferences. For example, it can generate speech based on a voice profile selected by the user, such as a young woman's voice or an older man's voice. Furthermore, the speech synthesis unit has high-speed processing capabilities to output the generated speech in real time. This allows for smooth communication, as the text entered by the user is immediately output as speech. The speech synthesis unit regularly updates the generative AI's training data and incorporates the latest language models and speech synthesis technologies to consistently provide high-quality speech. This allows the speech synthesis unit to provide users with natural and easy-to-understand speech, thereby facilitating smoother communication.

[0032] The visual information sharing unit shares visual information using a camera. For example, the visual information sharing unit can share what a user is seeing through the camera with others. Specifically, a user can use a camera on a smartphone, tablet, or PC to capture video in real time and share that video with other users. The visual information sharing unit can share visual information based on the type of camera and the scope of the information to be shared. For example, a wide-angle camera can be used to share a wide-angle video, or a zoom function can be used to show a specific object in detail. In addition, the visual information sharing unit can provide optimal video quality according to the network environment and device performance by adjusting the video resolution and frame rate. Furthermore, the visual information sharing unit also has a function to add annotations to the video in real time. For example, a user can draw text or shapes on the camera video to supplement visual information for other users. In this way, the visual information sharing unit can share what a user is seeing with others and facilitate visual communication. The visual information sharing unit can also ensure privacy and security by encrypting and transmitting video data. In this way, the visual information sharing unit can share visual information safely and effectively and support communication between users.

[0033] The emotion recognition unit analyzes camera footage acquired by the visual information sharing unit to recognize emotions. For example, the emotion recognition unit uses generative AI to analyze camera footage and recognize the user's emotions. Specifically, the generative AI can recognize emotions using facial expression recognition technology and voice analysis technology. For example, it can analyze the user's facial expressions from camera footage to identify emotions such as smiles, anger, and sadness. It can also use voice analysis technology to analyze the tone, pitch, and rhythm of the user's voice and estimate emotions. The generative AI integrates this information to recognize the user's emotional state with high accuracy. Furthermore, the emotion recognition unit can utilize past data and the user's behavior history to analyze changes and trends in emotions. For example, it can grasp emotional fluctuations in specific situations or time periods and predict the user's emotional patterns. In addition, the emotion recognition unit can provide appropriate feedback and actions based on the recognized emotions. For example, if the user is feeling stressed, it can play relaxing music or display encouraging messages. In this way, the emotion recognition unit can grasp the user's emotional state in real time and provide psychological support to the user by taking appropriate action. The emotion recognition unit can consistently achieve highly accurate emotion recognition by regularly updating the training data of the generative AI and incorporating the latest emotion recognition technologies.

[0034] The Remote Work Support Department provides remote work support functions. For example, the Remote Work Support Department can provide functions such as video conferencing, file sharing, and task management. The Remote Work Support Department can analyze user input using generative AI and generate appropriate responses. This allows for the provision of necessary support for people who are unable to speak when working remotely. Some or all of the above-described processes in the Remote Work Support Department may be performed using AI or not. For example, the Remote Work Support Department can input user input data into a generative AI and have the generative AI generate appropriate responses.

[0035] The translation unit provides real-time translation functionality. The translation unit can perform translations in real time based, for example, on the translation algorithm used and the corresponding languages. The translation unit can translate text using generative AI. The generative AI can translate between different languages ​​in real time using, for example, text generation AI (e.g., LLM). This enables smooth communication between people who speak different languages. Some or all of the above-described processes in the translation unit may be performed using or without the generative AI. For example, the translation unit can input text data into the generative AI and leave the translation to the generative AI.

[0036] The customization section provides user-specific customization features. For example, the customization section can perform customizations such as changing the user interface, adding or removing features. The customization section can analyze user behavior using generative AI and provide optimal settings. For example, the generative AI can learn from the user's past behavior data and propose optimal customizations. This allows users to utilize the platform in an environment best suited to them. Some or all of the above-described processes in the customization section may be performed using generative AI, or they may be performed without it. For example, the customization section can input user behavior data into the generative AI and have the generative AI propose optimal settings.

[0037] The wellness monitoring unit provides wellness monitoring functions. For example, the wellness monitoring unit can monitor the user's health status based on methods for collecting and analyzing health data. The wellness monitoring unit can analyze health data using generative AI to detect abnormalities early. For example, the generative AI can analyze data such as the user's heart rate, blood pressure, and activity level to detect abnormalities. This supports the user's health management. Some or all of the above-described processes in the wellness monitoring unit may be performed using generative AI, or they may be performed without generative AI. For example, the wellness monitoring unit can input the user's health data into the generative AI and have the generative AI perform abnormality detection.

[0038] The reception desk can analyze the user's past input history and select the optimal input method. For example, the reception desk can prioritize suggesting input methods (such as voice or text) that the user has frequently used in the past. Furthermore, the reception desk can predict and suggest input methods to be used during specific time periods based on the user's past input history. In addition, the reception desk can suggest relevant input methods based on the content the user has previously entered. This improves input efficiency by providing the optimal input method based on the user's past input history. Some or all of the above processing in the reception desk may be performed using AI, or not. For example, the reception desk can input the user's input history data into a generating AI and have the generating AI select the optimal input method.

[0039] The reception unit can filter text input based on the user's current situation and areas of interest. For example, the reception unit can automatically filter relevant keywords based on the user's current situation. It can also filter input based on the user's areas of interest, prioritizing the display of highly relevant information. Furthermore, the reception unit can suggest appropriate input content considering the user's current activity. This allows for the provision of appropriate input content based on the user's current situation and areas of interest. Some or all of the above processing in the reception unit may be performed using AI or not. For example, the reception unit can input the user's current situation data and areas of interest data into a generating AI and leave the filtering to the generating AI.

[0040] The reception unit can prioritize accepting highly relevant inputs when a user is entering text, taking into account their geographical location. For example, if the user is in a specific location, the reception unit will prioritize input related to that location. The reception unit can also automatically suggest relevant keywords based on the user's current location. Furthermore, the reception unit can filter appropriate input content based on the user's geographical location. This improves input accuracy by prioritizing the acceptance of highly relevant inputs based on the user's geographical location. Some or all of the above processing in the reception unit may be performed using AI or not. For example, the reception unit can input the user's geographical location data into a generating AI and have the generating AI suggest highly relevant inputs.

[0041] The reception unit can analyze the user's social media activity when text is entered and accept relevant input. For example, the reception unit can automatically suggest relevant keywords based on the user's social media activity. The reception unit can also filter appropriate input content based on the user's past posts. Furthermore, the reception unit can analyze the user's social media activity and prioritize input of highly relevant information. In this way, by analyzing the user's social media activity, it can provide highly relevant input. Some or all of the above processing in the reception unit may be performed using AI or not. For example, the reception unit can input the user's social media activity data into a generating AI and have the generating AI suggest relevant inputs.

[0042] The speech synthesis unit can adjust the level of detail in the speech based on the importance of the text during speech synthesis. For example, if the text is of high importance, the speech synthesis unit will generate speech that includes detailed explanations. Conversely, if the text is of low importance, the speech synthesis unit can also generate concise speech. Furthermore, the speech synthesis unit can adjust the tone and speed of the speech according to the importance of the text. This allows for the provision of appropriate information by adjusting the level of detail in the speech according to the importance of the text. Some or all of the above processing in the speech synthesis unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the speech synthesis unit can input text importance data into a generation AI and have the generation AI perform the adjustment of the level of detail in the speech.

[0043] The speech synthesis unit can apply different speech synthesis algorithms depending on the category of the text during speech synthesis. For example, in the case of news articles, the speech synthesis unit can generate speech in a formal tone. It can also generate speech in a casual tone for entertainment articles. Furthermore, in the case of technical articles, the speech synthesis unit can generate speech that accurately pronounces technical terms. This allows for the provision of appropriate speech depending on the category of the text. Some or all of the above processing in the speech synthesis unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the speech synthesis unit can input text category data into a generation AI and cause the generation AI to apply an appropriate speech synthesis algorithm.

[0044] The speech synthesis unit can determine the priority of speech based on the submission date of the text during speech synthesis. For example, in the case of urgent text, the speech synthesis unit will generate speech immediately. The speech synthesis unit can also prioritize the generation of speech for text with an approaching submission deadline. Furthermore, the speech synthesis unit can postpone the generation of speech for text with ample time before the submission deadline. By determining the priority of speech based on the submission date of the text, the speech synthesis unit can provide speech in an appropriate order. Some or all of the above processing in the speech synthesis unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the speech synthesis unit can input text submission date data into a generation AI and have the generation AI perform the determination of speech priority.

[0045] The speech synthesis unit can adjust the order of speech based on the relevance of the text during speech synthesis. For example, the speech synthesis unit can prioritize the speech synthesis of highly relevant text. It can also postpone the speech synthesis of less relevant text. Furthermore, the speech synthesis unit can dynamically adjust the order of speech according to the relevance of the text. This allows information to be provided in an appropriate order by adjusting the order of speech based on the relevance of the text. Some or all of the above processing in the speech synthesis unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the speech synthesis unit can input text relevance data into a generation AI and have the generation AI perform the adjustment of the speech order.

[0046] The visual information sharing unit can adjust the level of detail shared based on the importance of the camera footage when sharing visual information. For example, if the footage is of high importance, the visual information sharing unit will share footage containing detailed information. Conversely, if the footage is of low importance, the visual information sharing unit can also share footage containing concise information. Furthermore, the visual information sharing unit can dynamically adjust the level of detail shared according to the importance of the footage. This allows for appropriate information sharing by adjusting the level of detail shared according to the importance of the camera footage. Some or all of the above processing in the visual information sharing unit may be performed using AI or not. For example, the visual information sharing unit can input camera footage importance data into a generating AI and have the generating AI perform the adjustment of the level of detail shared.

[0047] The visual information sharing unit can apply different sharing algorithms depending on the category of the video when sharing visual information. For example, in the case of news footage, the visual information sharing unit can share it in a formal tone. In the case of entertainment footage, the visual information sharing unit can also share it in a casual tone. Furthermore, in the case of technical footage, the visual information sharing unit can share footage that accurately explains technical terms. This allows for the provision of appropriate information sharing according to the category of the video. Some or all of the above processing in the visual information sharing unit may be performed using AI or not. For example, the visual information sharing unit can input video category data into a generating AI and have the generating AI execute the application of an appropriate sharing algorithm.

[0048] The visual information sharing unit can prioritize sharing highly relevant videos by considering the user's geographical location information when sharing visual information. For example, if the user is in a specific location, the visual information sharing unit will prioritize sharing videos related to that location. The visual information sharing unit can also automatically suggest relevant videos based on the user's current location. Furthermore, the visual information sharing unit can filter appropriate videos based on the user's geographical location information. This allows for appropriate information sharing by prioritizing the sharing of highly relevant videos based on the user's geographical location information. Some or all of the above processing in the visual information sharing unit may be performed using AI or not. For example, the visual information sharing unit can input the user's geographical location information data into a generating AI and have the generating AI suggest highly relevant videos.

[0049] The visual information sharing unit can analyze the user's social media activity and share relevant videos when sharing visual information. For example, the visual information sharing unit can automatically suggest relevant videos based on the user's social media activity. The visual information sharing unit can also filter appropriate videos based on the user's past posts. Furthermore, the visual information sharing unit can analyze the user's social media activity and prioritize sharing highly relevant videos. This allows the system to provide highly relevant videos by analyzing the user's social media activity. Some or all of the above processing in the visual information sharing unit may be performed using AI or not. For example, the visual information sharing unit can input the user's social media activity data into a generating AI and have the generating AI suggest relevant videos.

[0050] The emotion recognition unit can adjust the level of detail of its recognition based on the importance of the camera footage during emotion recognition. For example, the emotion recognition unit performs detailed emotion recognition for high-importance footage. It can also perform simplified emotion recognition for low-importance footage. Furthermore, the emotion recognition unit can dynamically adjust the level of detail of its recognition according to the importance of the footage. This allows for appropriate emotion recognition by adjusting the level of detail according to the importance of the camera footage. Some or all of the above processing in the emotion recognition unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the emotion recognition unit can input camera footage importance data into a generative AI and have the generative AI perform the adjustment of the level of detail of its recognition.

[0051] The emotion recognition unit can apply different recognition algorithms depending on the category of the video during emotion recognition. For example, in the case of news footage, the emotion recognition unit can perform emotion recognition in a formal tone. In the case of entertainment footage, the emotion recognition unit can also perform emotion recognition in a casual tone. Furthermore, in the case of technical footage, the emotion recognition unit can apply an algorithm that accurately recognizes technical terms. This allows for appropriate emotion recognition depending on the category of the video. Some or all of the above processing in the emotion recognition unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the emotion recognition unit can input video category data into a generative AI and cause the generative AI to execute the application of an appropriate recognition algorithm.

[0052] The emotion recognition unit can prioritize recognizing highly relevant emotions by considering the user's geographical location information during emotion recognition. For example, if the user is in a specific location, the emotion recognition unit will prioritize recognizing emotions associated with that location. The emotion recognition unit can also automatically suggest relevant emotions based on the user's current location. Furthermore, the emotion recognition unit can filter appropriate emotions based on the user's geographical location information. This allows for appropriate emotion recognition by prioritizing the recognition of highly relevant emotions based on the user's geographical location information. Some or all of the above processing in the emotion recognition unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the emotion recognition unit can input the user's geographical location information data into a generative AI and have the generative AI perform the recognition of highly relevant emotions.

[0053] The emotion recognition unit can analyze the user's social media activity and recognize relevant emotions during emotion recognition. For example, the emotion recognition unit can automatically suggest relevant emotions based on the user's social media activity. The emotion recognition unit can also filter appropriate emotions based on the user's past posts. Furthermore, the emotion recognition unit can analyze the user's social media activity and prioritize the recognition of highly relevant emotions. This allows the unit to provide highly relevant emotions by analyzing the user's social media activity. Some or all of the above processing in the emotion recognition unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the emotion recognition unit can input the user's social media activity data into a generative AI and have the generative AI perform the recognition of relevant emotions.

[0054] The Remote Work Support Department can provide the optimal support method when assisting remote workers by referring to the user's past work history. For example, the Remote Work Support Department can propose the optimal support method based on the user's past work. It can also propose efficient work methods based on the user's past work history. Furthermore, the Remote Work Support Department can analyze the user's past work history and provide the most effective support method. This improves the accuracy of support by providing the optimal support method based on the user's past work history. Some or all of the above processes in the Remote Work Support Department may be performed using AI or not. For example, the Remote Work Support Department can input the user's work history data into a generating AI and have the generating AI propose the optimal support method.

[0055] The Remote Work Support Department can provide optimal support methods when assisting with remote work, taking into account the user's device information. For example, if the user is using a smartphone, the Remote Work Support Department can provide support methods adapted to the screen size. Furthermore, if the user is using a tablet, the Remote Work Support Department can provide support methods optimized for larger screens. Additionally, if the user is using a smartwatch, the Remote Work Support Department can provide concise and highly visible support methods. This improves the accuracy of support by providing optimal support methods based on the user's device information. Some or all of the above processing in the Remote Work Support Department may be performed using AI, or not. For example, the Remote Work Support Department can input user device information data into a generating AI and have the generating AI propose optimal support methods.

[0056] The translation unit can adjust the level of detail in the translation based on the importance of the text. For example, the translation unit will provide a detailed translation for high-importance text, and a concise translation for low-importance text. Furthermore, the translation unit can dynamically adjust the level of detail in the translation according to the importance of the text. This allows for the provision of appropriate information by adjusting the level of detail in the translation according to the importance of the text. Some or all of the above processing in the translation unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the translation unit can input text importance data into a generative AI and have the generative AI perform the adjustment of the level of detail in the translation.

[0057] The translation unit can apply different translation algorithms depending on the category of the text during translation. For example, the unit can translate news articles in a formal tone, while translating entertainment articles in a more casual tone. Furthermore, for technical articles, it can apply an algorithm that accurately translates specialized terminology. This allows the unit to provide appropriate translations according to the text category. Some or all of the above processes in the translation unit may be performed using or without a generative AI. For example, the translation unit can input text category data into a generative AI and have the generative AI apply the appropriate translation algorithm.

[0058] The translation department can prioritize translations based on the text submission date. For example, it can translate urgent texts immediately. It can also prioritize texts with approaching submission deadlines. Furthermore, it can postpone translations of texts with ample time before the submission deadline. This allows for translations to be provided in an appropriate order by prioritizing translations based on the text submission date. Some or all of the above processes in the translation department may be performed using or without a generative AI. For example, the translation department can input text submission date data into a generative AI and have the generative AI determine the translation priority.

[0059] The customization unit can provide the optimal customization method by referring to the user's past behavior history during customization. For example, the customization unit can propose the optimal customization method based on the user's past customizations. Furthermore, the customization unit can propose an efficient customization method based on the user's past behavior history. In addition, the customization unit can analyze the user's past behavior history and provide the most effective customization method. This improves the accuracy of customization by providing the optimal customization method based on the user's past behavior history. Some or all of the above-described processes in the customization unit may be performed using a generative AI, or they may be performed without a generative AI. For example, the customization unit can input user behavior history data into a generative AI and have the generative AI propose the optimal customization method.

[0060] The customization unit can provide the optimal customization method by considering the user's device information during the customization process. For example, if the user is using a smartphone, the customization unit can provide a customization method that matches the screen size. Furthermore, if the user is using a tablet, the customization unit can provide a customization method optimized for a larger screen. Additionally, if the user is using a smartwatch, the customization unit can provide a concise and highly visible customization method. This improves the accuracy of customization by providing the optimal customization method based on the user's device information. Some or all of the above-described processes in the customization unit may be performed using a generative AI, or they may be performed without a generative AI. For example, the customization unit can input user device information data into a generative AI and have the generative AI propose the optimal customization method.

[0061] The wellness monitoring unit can provide the optimal monitoring method by referring to the user's past health data during wellness monitoring. For example, the wellness monitoring unit can propose the optimal monitoring method based on the user's past health data. It can also propose an efficient monitoring method based on the user's past health history. Furthermore, the wellness monitoring unit can analyze the user's past health data and provide the most effective monitoring method. This improves the accuracy of monitoring by providing the optimal monitoring method based on the user's past health data. Some or all of the above processing in the wellness monitoring unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the wellness monitoring unit can input the user's health data into a generative AI and have the generative AI propose the optimal monitoring method.

[0062] The wellness monitoring unit can provide an optimal monitoring method during wellness monitoring, taking into account the user's device information. For example, if the user is using a smartphone, the wellness monitoring unit can provide a monitoring method adapted to the screen size. Furthermore, if the user is using a tablet, the wellness monitoring unit can provide a monitoring method optimized for a larger screen. Additionally, if the user is using a smartwatch, the wellness monitoring unit can provide a simple and highly visible monitoring method. This improves monitoring accuracy by providing an optimal monitoring method based on the user's device information. Some or all of the above-described processes in the wellness monitoring unit may be performed using or without a generative AI. For example, the wellness monitoring unit can input user device information data into a generative AI and have the generative AI propose an optimal monitoring method.

[0063] The wellness monitoring unit can analyze the user's current health status in real time during wellness monitoring and detect abnormalities early. For example, the wellness monitoring unit can monitor the user's heart rate and blood pressure in real time and detect abnormalities. It can also analyze the user's activity level in real time and detect abnormal patterns early. Furthermore, the wellness monitoring unit can analyze the user's sleep data in real time and detect abnormal sleep patterns. In this way, abnormalities can be detected early by analyzing the user's current health status in real time. Some or all of the above processing in the wellness monitoring unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the wellness monitoring unit can input the user's health data into a generative AI and have the generative AI perform abnormality detection.

[0064] The wellness monitoring unit can analyze the user's dietary data and evaluate their health status during wellness monitoring. For example, the wellness monitoring unit can evaluate nutritional balance based on the user's dietary data. It can also analyze the user's dietary history and suggest healthy eating patterns. Furthermore, the wellness monitoring unit can analyze the user's dietary data in real time and evaluate their health status. In this way, the health status can be evaluated by analyzing the user's dietary data. Some or all of the above processing in the wellness monitoring unit may be performed using or without a generative AI. For example, the wellness monitoring unit can input the user's dietary data into a generative AI and have the generative AI perform the health status evaluation.

[0065] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0066] The SocialVoice system may also include a reception unit that analyzes the user's past input history and selects the optimal input method. For example, it can prioritize suggesting input methods (voice, text, etc.) that the user has frequently used in the past. The reception unit can also predict and suggest input methods to be used during specific time periods based on the user's past input history. Furthermore, the reception unit can suggest relevant input methods based on the content the user has previously entered. This improves input efficiency by providing the optimal input method based on the user's past input history. Some or all of the above processing in the reception unit may be performed using AI or not. For example, the reception unit can input the user's input history data into a generating AI and have the generating AI select the optimal input method.

[0067] The SocialVoice system may further include a reception unit that prioritizes receiving highly relevant inputs by considering the user's geographical location. For example, if the user is in a specific location, information related to that location can be prioritized for input. The reception unit can also automatically suggest relevant keywords based on the user's current location. Furthermore, the reception unit can filter appropriate input content based on the user's geographical location. This improves the accuracy of input by prioritizing the acceptance of highly relevant inputs based on the user's geographical location. Some or all of the above processing in the reception unit may be performed using AI or not. For example, the reception unit can input the user's geographical location data into a generating AI and have the generating AI suggest highly relevant inputs.

[0068] The SocialVoice system may further include a reception unit that analyzes the user's social media activity and accepts relevant input. For example, it can automatically suggest relevant keywords from the user's social media activity. The reception unit can also filter appropriate input content based on the user's past posts. Furthermore, the reception unit can analyze the user's social media activity and prioritize input of highly relevant information. This allows the system to provide highly relevant input by analyzing the user's social media activity. Some or all of the above processing in the reception unit may be performed using AI or not. For example, the reception unit can input the user's social media activity data into a generating AI and have the generating AI suggest relevant inputs.

[0069] The SocialVoice system may further include a wellness monitoring unit that provides the optimal monitoring method by referring to the user's past health data. For example, it can propose the optimal monitoring method based on the user's past health data. The wellness monitoring unit can also propose an efficient monitoring method from the user's past health history. Furthermore, the wellness monitoring unit can analyze the user's past health data and provide the most effective monitoring method. This improves the accuracy of monitoring by providing the optimal monitoring method based on the user's past health data. Some or all of the above processing in the wellness monitoring unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the wellness monitoring unit can input the user's health data into a generative AI and have the generative AI propose the optimal monitoring method.

[0070] The SocialVoice system can also include a wellness monitoring unit that analyzes the user's current health status in real time and detects abnormalities early. For example, it can monitor the user's heart rate and blood pressure in real time and detect abnormalities. The wellness monitoring unit can also analyze the user's activity level in real time and detect abnormal patterns early. Furthermore, the wellness monitoring unit can analyze the user's sleep data in real time and detect abnormal sleep patterns. This allows for early detection of abnormalities by analyzing the user's current health status in real time. Some or all of the above-described processes in the wellness monitoring unit may be performed using or without a generative AI. For example, the wellness monitoring unit can input the user's health data into a generative AI and have the generative AI perform abnormality detection.

[0071] The following briefly describes the processing flow for example form 1.

[0072] Step 1: The reception desk accepts text input. The reception desk can accept text using methods such as keyboard input, voice input, or handwriting input. Step 2: The speech synthesis unit converts the text received by the reception unit into speech. The speech synthesis unit generates natural-sounding speech, for example, using a generation AI. The generation AI can convert text into speech using a text generation AI (e.g., LLM). Step 3: The visual information sharing unit shares visual information using the camera. For example, the visual information sharing unit can share what the user is seeing through the camera with other people. The visual information sharing unit can share visual information based on the type of camera and the scope of the information to be shared. Step 4: The emotion recognition unit analyzes the camera footage acquired by the visual information sharing unit and recognizes emotions. The emotion recognition unit analyzes the camera footage using, for example, a generative AI to recognize the user's emotions. The generative AI can recognize emotions using facial expression recognition technology or voice analysis technology.

[0073] (Example of form 2) The SocialVoice system according to an embodiment of the present invention is a comprehensive support platform for the social and economic integration of people who are unable to speak. The SocialVoice system utilizes text input, speech synthesis, visual information, and emotion recognition to provide multidimensional communication. Furthermore, it is equipped with remote work support functions, real-time translation, user-specific customization functions, and wellness monitoring. For example, when a user inputs text, the generating AI converts that text into natural speech. This allows people who are unable to speak to communicate by voice. Next, visual information can be shared using a camera. For example, a user can share what they are seeing through the camera with others. Furthermore, the generating AI analyzes the camera footage and recognizes the user's emotions. This enables appropriate responses according to the user's emotions. Remote work support functions are also included, providing the necessary support for people who are unable to speak when working remotely. For example, the generating AI analyzes the user's input and generates appropriate replies, improving the efficiency of remote work. In addition, the real-time translation function allows for smooth communication with people who speak different languages. User-specific customization functions are also extensive, with the generating AI analyzing the user's behavior and providing optimal settings. This allows users to use the platform in an environment that is best suited to them. Furthermore, it features a wellness monitoring function, where generating AI analyzes health data to detect abnormalities early. This also supports users' health management. In this way, the SocialVoice system is a comprehensive platform that provides multidimensional communication to people who cannot speak, supporting social and economic integration.

[0074] The SocialVoice system according to this embodiment comprises a reception unit, a speech synthesis unit, a visual information sharing unit, and an emotion recognition unit. The reception unit receives text input. The reception unit can receive text by methods such as keyboard input, voice input, or handwriting input. The speech synthesis unit converts the text received by the reception unit into speech. The speech synthesis unit generates natural speech using, for example, a generation AI. The generation AI can convert text into speech using a text generation AI (e.g., LLM). The visual information sharing unit shares visual information using a camera. The visual information sharing unit can share, for example, what a user is seeing through the camera with other people. The visual information sharing unit can share visual information based on the type of camera and the scope of the information to be shared. The emotion recognition unit analyzes the camera footage acquired by the visual information sharing unit and recognizes emotions. The emotion recognition unit analyzes the camera footage using, for example, a generation AI and recognizes the user's emotions. The generation AI can recognize emotions using facial expression recognition technology or speech analysis technology. This allows the SocialVoice system to provide multidimensional communication to people who are unable to speak, and to support social and economic integration.

[0075] The reception unit accepts text input. The reception unit can accept text via methods such as keyboard input, voice input, and handwriting input. Specifically, with keyboard input, the user enters text using a physical or virtual keyboard. With voice input, the user's speech is converted to text using speech recognition technology via a microphone. With handwriting input, characters handwritten with a stylus pen or finger on a tablet or smartphone touchscreen are recognized and converted to text. These input methods are designed to be selectable according to the user's convenience and situation. Furthermore, the reception unit can process the entered text in real time and quickly pass it to the speech synthesis unit and emotion recognition unit. For example, with voice input, partial text can be generated before the user finishes speaking and immediately sent to the speech synthesis unit, minimizing delays. The reception unit also has a function to automatically detect and correct errors in the entered text. For example, by correcting misrecognized words in voice input based on context, more accurate text can be generated. This allows the reception unit to support diverse input methods and generate text that accurately reflects the user's intent.

[0076] The speech synthesis unit converts text received by the reception unit into speech. The speech synthesis unit generates natural-sounding speech, for example, using a generative AI. The generative AI can convert text into speech using a text generation AI (e.g., LLM). Specifically, the generative AI analyzes the input text, understands the grammar and context, and generates speech with appropriate intonation and emotion. For example, if a user inputs "hello," the generative AI analyzes the text, generates an appropriate speech waveform, and pronounces "hello" in a natural voice. The generative AI can also customize the voice's gender, age, accent, etc., according to the user's preferences. For example, it can generate speech based on a voice profile selected by the user, such as a young woman's voice or an older man's voice. Furthermore, the speech synthesis unit has high-speed processing capabilities to output the generated speech in real time. This allows for smooth communication, as the text entered by the user is immediately output as speech. The speech synthesis unit regularly updates the generative AI's training data and incorporates the latest language models and speech synthesis technologies to consistently provide high-quality speech. This allows the speech synthesis unit to provide users with natural and easy-to-understand speech, thereby facilitating smoother communication.

[0077] The visual information sharing unit shares visual information using a camera. For example, the visual information sharing unit can share what a user is seeing through the camera with others. Specifically, a user can use a camera on a smartphone, tablet, or PC to capture video in real time and share that video with other users. The visual information sharing unit can share visual information based on the type of camera and the scope of the information to be shared. For example, a wide-angle camera can be used to share a wide-angle video, or a zoom function can be used to show a specific object in detail. In addition, the visual information sharing unit can provide optimal video quality according to the network environment and device performance by adjusting the video resolution and frame rate. Furthermore, the visual information sharing unit also has a function to add annotations to the video in real time. For example, a user can draw text or shapes on the camera video to supplement visual information for other users. In this way, the visual information sharing unit can share what a user is seeing with others and facilitate visual communication. The visual information sharing unit can also ensure privacy and security by encrypting and transmitting video data. In this way, the visual information sharing unit can share visual information safely and effectively and support communication between users.

[0078] The emotion recognition unit analyzes camera footage acquired by the visual information sharing unit to recognize emotions. For example, the emotion recognition unit uses generative AI to analyze camera footage and recognize the user's emotions. Specifically, the generative AI can recognize emotions using facial expression recognition technology and voice analysis technology. For example, it can analyze the user's facial expressions from camera footage to identify emotions such as smiles, anger, and sadness. It can also use voice analysis technology to analyze the tone, pitch, and rhythm of the user's voice and estimate emotions. The generative AI integrates this information to recognize the user's emotional state with high accuracy. Furthermore, the emotion recognition unit can utilize past data and the user's behavior history to analyze changes and trends in emotions. For example, it can grasp emotional fluctuations in specific situations or time periods and predict the user's emotional patterns. In addition, the emotion recognition unit can provide appropriate feedback and actions based on the recognized emotions. For example, if the user is feeling stressed, it can play relaxing music or display encouraging messages. In this way, the emotion recognition unit can grasp the user's emotional state in real time and provide psychological support to the user by taking appropriate action. The emotion recognition unit can consistently achieve highly accurate emotion recognition by regularly updating the training data of the generative AI and incorporating the latest emotion recognition technologies.

[0079] The Remote Work Support Department provides remote work support functions. For example, the Remote Work Support Department can provide functions such as video conferencing, file sharing, and task management. The Remote Work Support Department can analyze user input using generative AI and generate appropriate responses. This allows for the provision of necessary support for people who are unable to speak when working remotely. Some or all of the above-described processes in the Remote Work Support Department may be performed using AI or not. For example, the Remote Work Support Department can input user input data into a generative AI and have the generative AI generate appropriate responses.

[0080] The translation unit provides real-time translation functionality. The translation unit can perform translations in real time based, for example, on the translation algorithm used and the corresponding languages. The translation unit can translate text using generative AI. The generative AI can translate between different languages ​​in real time using, for example, text generation AI (e.g., LLM). This enables smooth communication between people who speak different languages. Some or all of the above-described processes in the translation unit may be performed using or without the generative AI. For example, the translation unit can input text data into the generative AI and leave the translation to the generative AI.

[0081] The customization section provides user-specific customization features. For example, the customization section can perform customizations such as changing the user interface, adding or removing features. The customization section can analyze user behavior using generative AI and provide optimal settings. For example, the generative AI can learn from the user's past behavior data and propose optimal customizations. This allows users to utilize the platform in an environment best suited to them. Some or all of the above-described processes in the customization section may be performed using generative AI, or they may be performed without it. For example, the customization section can input user behavior data into the generative AI and have the generative AI propose optimal settings.

[0082] The wellness monitoring unit provides wellness monitoring functions. For example, the wellness monitoring unit can monitor the user's health status based on methods for collecting and analyzing health data. The wellness monitoring unit can analyze health data using generative AI to detect abnormalities early. For example, the generative AI can analyze data such as the user's heart rate, blood pressure, and activity level to detect abnormalities. This supports the user's health management. Some or all of the above-described processes in the wellness monitoring unit may be performed using generative AI, or they may be performed without generative AI. For example, the wellness monitoring unit can input the user's health data into the generative AI and have the generative AI perform abnormality detection.

[0083] The reception unit can estimate the user's emotions and adjust the timing of text input acceptance based on the estimated emotions. For example, if the user is stressed, the reception unit can delay the input acceptance timing to provide time to relax. Conversely, if the user is relaxed, the reception unit can speed up the input acceptance timing to facilitate smooth operation. Furthermore, if the user is in a hurry, the reception unit can accept input immediately to enable a quick response. In this way, a more appropriate input environment can be provided by adjusting the timing of text input acceptance according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception unit may be performed using AI or not. For example, the reception unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0084] The reception desk can analyze the user's past input history and select the optimal input method. For example, the reception desk can prioritize suggesting input methods (such as voice or text) that the user has frequently used in the past. Furthermore, the reception desk can predict and suggest input methods to be used during specific time periods based on the user's past input history. In addition, the reception desk can suggest relevant input methods based on the content the user has previously entered. This improves input efficiency by providing the optimal input method based on the user's past input history. Some or all of the above processing in the reception desk may be performed using AI, or not. For example, the reception desk can input the user's input history data into a generating AI and have the generating AI select the optimal input method.

[0085] The reception unit can filter text input based on the user's current situation and areas of interest. For example, the reception unit can automatically filter relevant keywords based on the user's current situation. It can also filter input based on the user's areas of interest, prioritizing the display of highly relevant information. Furthermore, the reception unit can suggest appropriate input content considering the user's current activity. This allows for the provision of appropriate input content based on the user's current situation and areas of interest. Some or all of the above processing in the reception unit may be performed using AI or not. For example, the reception unit can input the user's current situation data and areas of interest data into a generating AI and leave the filtering to the generating AI.

[0086] The reception desk can estimate the user's emotions and determine the priority of the text to be entered based on the estimated emotions. For example, if the user is stressed, the reception desk may postpone less important text. Conversely, if the user is relaxed, the reception desk may prioritize the input of more important text. Furthermore, if the user is in a hurry, the reception desk may prioritize the input of most urgent text. This allows for a more appropriate input order by determining the priority of the text to be entered according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception desk may be performed using AI or not. For example, the reception desk can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0087] The reception unit can prioritize accepting highly relevant inputs when a user is entering text, taking into account their geographical location. For example, if the user is in a specific location, the reception unit will prioritize input related to that location. The reception unit can also automatically suggest relevant keywords based on the user's current location. Furthermore, the reception unit can filter appropriate input content based on the user's geographical location. This improves input accuracy by prioritizing the acceptance of highly relevant inputs based on the user's geographical location. Some or all of the above processing in the reception unit may be performed using AI or not. For example, the reception unit can input the user's geographical location data into a generating AI and have the generating AI suggest highly relevant inputs.

[0088] The reception unit can analyze the user's social media activity when text is entered and accept relevant input. For example, the reception unit can automatically suggest relevant keywords based on the user's social media activity. The reception unit can also filter appropriate input content based on the user's past posts. Furthermore, the reception unit can analyze the user's social media activity and prioritize input of highly relevant information. In this way, by analyzing the user's social media activity, it can provide highly relevant input. Some or all of the above processing in the reception unit may be performed using AI or not. For example, the reception unit can input the user's social media activity data into a generating AI and have the generating AI suggest relevant inputs.

[0089] The speech synthesis unit can estimate the user's emotions and adjust the tone and speed of the speech based on the estimated emotions. For example, if the user is relaxed, the speech synthesis unit can produce a calm tone and slow speech. If the user is in a hurry, the speech synthesis unit can also produce a fast and clear speech. Furthermore, if the user is excited, the speech synthesis unit can produce a lively tone. This allows for a more natural-sounding speech by adjusting the tone and speed according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the speech synthesis unit may be performed using or without a generative AI. For example, the speech synthesis unit can input user emotion data into a generative AI and have the generative AI adjust the tone and speed of the speech.

[0090] The speech synthesis unit can adjust the level of detail in the speech based on the importance of the text during speech synthesis. For example, if the text is of high importance, the speech synthesis unit will generate speech that includes detailed explanations. Conversely, if the text is of low importance, the speech synthesis unit can also generate concise speech. Furthermore, the speech synthesis unit can adjust the tone and speed of the speech according to the importance of the text. This allows for the provision of appropriate information by adjusting the level of detail in the speech according to the importance of the text. Some or all of the above processing in the speech synthesis unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the speech synthesis unit can input text importance data into a generation AI and have the generation AI perform the adjustment of the level of detail in the speech.

[0091] The speech synthesis unit can apply different speech synthesis algorithms depending on the category of the text during speech synthesis. For example, in the case of news articles, the speech synthesis unit can generate speech in a formal tone. It can also generate speech in a casual tone for entertainment articles. Furthermore, in the case of technical articles, the speech synthesis unit can generate speech that accurately pronounces technical terms. This allows for the provision of appropriate speech depending on the category of the text. Some or all of the above processing in the speech synthesis unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the speech synthesis unit can input text category data into a generation AI and cause the generation AI to apply an appropriate speech synthesis algorithm.

[0092] The speech synthesis unit can estimate the user's emotions and adjust the length of the speech based on the estimated emotions. For example, if the user is relaxed, the speech synthesis unit can generate a longer speech with detailed explanations. It can also generate a shorter, more concise speech if the user is in a hurry. Furthermore, if the user is excited, the speech synthesis unit can generate speech with visually stimulating effects. This allows for the provision of more appropriate speech by adjusting the length according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the speech synthesis unit may be performed using or without a generative AI. For example, the speech synthesis unit can input user emotion data into a generative AI and have the generative AI adjust the length of the speech.

[0093] The speech synthesis unit can determine the priority of speech based on the submission date of the text during speech synthesis. For example, in the case of urgent text, the speech synthesis unit will generate speech immediately. The speech synthesis unit can also prioritize the generation of speech for text with an approaching submission deadline. Furthermore, the speech synthesis unit can postpone the generation of speech for text with ample time before the submission deadline. By determining the priority of speech based on the submission date of the text, the speech synthesis unit can provide speech in an appropriate order. Some or all of the above processing in the speech synthesis unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the speech synthesis unit can input text submission date data into a generation AI and have the generation AI perform the determination of speech priority.

[0094] The speech synthesis unit can adjust the order of speech based on the relevance of the text during speech synthesis. For example, the speech synthesis unit can prioritize the speech synthesis of highly relevant text. It can also postpone the speech synthesis of less relevant text. Furthermore, the speech synthesis unit can dynamically adjust the order of speech according to the relevance of the text. This allows information to be provided in an appropriate order by adjusting the order of speech based on the relevance of the text. Some or all of the above processing in the speech synthesis unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the speech synthesis unit can input text relevance data into a generation AI and have the generation AI perform the adjustment of the speech order.

[0095] The visual information sharing unit can estimate the user's emotions and adjust the method of sharing visual information based on the estimated emotions. For example, if the user is relaxed, the visual information sharing unit can share detailed visual information. If the user is in a hurry, the visual information sharing unit can also share concise visual information. Furthermore, if the user is excited, the visual information sharing unit can share visually stimulating information. This allows for more appropriate information sharing by adjusting the method of sharing visual information according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the visual information sharing unit may be performed using AI or not. For example, the visual information sharing unit can input user emotion data into the generative AI and have the generative AI adjust the method of sharing visual information.

[0096] The visual information sharing unit can adjust the level of detail shared based on the importance of the camera footage when sharing visual information. For example, if the footage is of high importance, the visual information sharing unit will share footage containing detailed information. Conversely, if the footage is of low importance, the visual information sharing unit can also share footage containing concise information. Furthermore, the visual information sharing unit can dynamically adjust the level of detail shared according to the importance of the footage. This allows for appropriate information sharing by adjusting the level of detail shared according to the importance of the camera footage. Some or all of the above processing in the visual information sharing unit may be performed using AI or not. For example, the visual information sharing unit can input camera footage importance data into a generating AI and have the generating AI perform the adjustment of the level of detail shared.

[0097] The visual information sharing unit can apply different sharing algorithms depending on the category of the video when sharing visual information. For example, in the case of news footage, the visual information sharing unit can share it in a formal tone. In the case of entertainment footage, the visual information sharing unit can also share it in a casual tone. Furthermore, in the case of technical footage, the visual information sharing unit can share footage that accurately explains technical terms. This allows for the provision of appropriate information sharing according to the category of the video. Some or all of the above processing in the visual information sharing unit may be performed using AI or not. For example, the visual information sharing unit can input video category data into a generating AI and have the generating AI execute the application of an appropriate sharing algorithm.

[0098] The visual information sharing unit can estimate the user's emotions and determine the priority of visual information based on the estimated emotions. For example, if the user is stressed, the visual information sharing unit will postpone sharing less important visual information. Conversely, if the user is relaxed, the visual information sharing unit can prioritize sharing more important visual information. Furthermore, if the user is in a hurry, the visual information sharing unit can prioritize sharing highly urgent visual information. This allows for more appropriate information sharing by determining the priority of visual information according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the visual information sharing unit may be performed using AI or not. For example, the visual information sharing unit can input user emotion data into a generative AI and have the generative AI determine the priority of visual information.

[0099] The visual information sharing unit can prioritize sharing highly relevant videos by considering the user's geographical location information when sharing visual information. For example, if the user is in a specific location, the visual information sharing unit will prioritize sharing videos related to that location. The visual information sharing unit can also automatically suggest relevant videos based on the user's current location. Furthermore, the visual information sharing unit can filter appropriate videos based on the user's geographical location information. This allows for appropriate information sharing by prioritizing the sharing of highly relevant videos based on the user's geographical location information. Some or all of the above processing in the visual information sharing unit may be performed using AI or not. For example, the visual information sharing unit can input the user's geographical location information data into a generating AI and have the generating AI suggest highly relevant videos.

[0100] The visual information sharing unit can analyze the user's social media activity and share relevant videos when sharing visual information. For example, the visual information sharing unit can automatically suggest relevant videos based on the user's social media activity. The visual information sharing unit can also filter appropriate videos based on the user's past posts. Furthermore, the visual information sharing unit can analyze the user's social media activity and prioritize sharing highly relevant videos. This allows the system to provide highly relevant videos by analyzing the user's social media activity. Some or all of the above processing in the visual information sharing unit may be performed using AI or not. For example, the visual information sharing unit can input the user's social media activity data into a generating AI and have the generating AI suggest relevant videos.

[0101] The emotion recognition unit can estimate the user's emotions and adjust the accuracy of emotion recognition based on the estimated emotions. For example, the emotion recognition unit can increase the accuracy of emotion recognition when the user is relaxed. It can also lower the accuracy of emotion recognition to process quickly when the user is in a hurry. Furthermore, it can adjust the accuracy of emotion recognition to respond appropriately when the user is excited. In this way, by adjusting the accuracy of emotion recognition according to the user's emotions, it is possible to provide more appropriate emotion recognition. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the emotion recognition unit may be performed using the generative AI or not. For example, the emotion recognition unit can input the user's emotion data into the generative AI and have the generative AI perform the adjustment of the accuracy of emotion recognition.

[0102] The emotion recognition unit can adjust the level of detail of its recognition based on the importance of the camera footage during emotion recognition. For example, the emotion recognition unit performs detailed emotion recognition for high-importance footage. It can also perform simplified emotion recognition for low-importance footage. Furthermore, the emotion recognition unit can dynamically adjust the level of detail of its recognition according to the importance of the footage. This allows for appropriate emotion recognition by adjusting the level of detail according to the importance of the camera footage. Some or all of the above processing in the emotion recognition unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the emotion recognition unit can input camera footage importance data into a generative AI and have the generative AI perform the adjustment of the level of detail of its recognition.

[0103] The emotion recognition unit can apply different recognition algorithms depending on the category of the video during emotion recognition. For example, in the case of news footage, the emotion recognition unit can perform emotion recognition in a formal tone. In the case of entertainment footage, the emotion recognition unit can also perform emotion recognition in a casual tone. Furthermore, in the case of technical footage, the emotion recognition unit can apply an algorithm that accurately recognizes technical terms. This allows for appropriate emotion recognition depending on the category of the video. Some or all of the above processing in the emotion recognition unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the emotion recognition unit can input video category data into a generative AI and cause the generative AI to execute the application of an appropriate recognition algorithm.

[0104] The emotion recognition unit can estimate the user's emotions and determine the priority of emotion recognition based on the estimated emotions. For example, if the user is stressed, the emotion recognition unit will postpone the recognition of less important emotions. Conversely, if the user is relaxed, the emotion recognition unit can prioritize the recognition of more important emotions. Furthermore, if the user is in a hurry, the emotion recognition unit can prioritize the recognition of urgent emotions. In this way, by determining the priority of emotion recognition according to the user's emotions, more appropriate emotion recognition can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the emotion recognition unit may be performed using or without a generative AI. For example, the emotion recognition unit can input user emotion data into a generative AI and have the generative AI perform the determination of the priority of emotion recognition.

[0105] The emotion recognition unit can prioritize recognizing highly relevant emotions by considering the user's geographical location information during emotion recognition. For example, if the user is in a specific location, the emotion recognition unit will prioritize recognizing emotions associated with that location. The emotion recognition unit can also automatically suggest relevant emotions based on the user's current location. Furthermore, the emotion recognition unit can filter appropriate emotions based on the user's geographical location information. This allows for appropriate emotion recognition by prioritizing the recognition of highly relevant emotions based on the user's geographical location information. Some or all of the above processing in the emotion recognition unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the emotion recognition unit can input the user's geographical location information data into a generative AI and have the generative AI perform the recognition of highly relevant emotions.

[0106] The emotion recognition unit can analyze the user's social media activity and recognize relevant emotions during emotion recognition. For example, the emotion recognition unit can automatically suggest relevant emotions based on the user's social media activity. The emotion recognition unit can also filter appropriate emotions based on the user's past posts. Furthermore, the emotion recognition unit can analyze the user's social media activity and prioritize the recognition of highly relevant emotions. This allows the unit to provide highly relevant emotions by analyzing the user's social media activity. Some or all of the above processing in the emotion recognition unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the emotion recognition unit can input the user's social media activity data into a generative AI and have the generative AI perform the recognition of relevant emotions.

[0107] The remote work support unit can estimate the user's emotions and adjust its remote work support methods based on those emotions. For example, if the user is feeling stressed, the remote work support unit can suggest a relaxing work environment. If the user is relaxed, the remote work support unit can also suggest efficient work methods. Furthermore, if the user is in a hurry, the remote work support unit can suggest work methods that allow for quick responses. By adjusting the remote work support methods according to the user's emotions, more appropriate support can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the remote work support unit may be performed using AI or not. For example, the remote work support unit can input user emotion data into a generative AI and have the generative AI adjust the remote work support methods.

[0108] The Remote Work Support Department can provide the optimal support method when assisting remote workers by referring to the user's past work history. For example, the Remote Work Support Department can propose the optimal support method based on the user's past work. It can also propose efficient work methods based on the user's past work history. Furthermore, the Remote Work Support Department can analyze the user's past work history and provide the most effective support method. This improves the accuracy of support by providing the optimal support method based on the user's past work history. Some or all of the above processes in the Remote Work Support Department may be performed using AI or not. For example, the Remote Work Support Department can input the user's work history data into a generating AI and have the generating AI propose the optimal support method.

[0109] The remote work support unit can estimate the user's emotions and determine the priority of remote work support based on the estimated emotions. For example, if the user is stressed, the remote work support unit may postpone less important tasks. Conversely, if the user is relaxed, the remote work support unit may prioritize assisting with more important tasks. Furthermore, if the user is in a hurry, the remote work support unit may prioritize assisting with urgent tasks. This allows for more appropriate support to be provided by determining the priority of remote work support according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the remote work support unit may be performed using AI or not. For example, the remote work support unit can input user emotion data into a generative AI and have the generative AI determine the priority of remote work support.

[0110] The Remote Work Support Department can provide optimal support methods when assisting with remote work, taking into account the user's device information. For example, if the user is using a smartphone, the Remote Work Support Department can provide support methods adapted to the screen size. Furthermore, if the user is using a tablet, the Remote Work Support Department can provide support methods optimized for larger screens. Additionally, if the user is using a smartwatch, the Remote Work Support Department can provide concise and highly visible support methods. This improves the accuracy of support by providing optimal support methods based on the user's device information. Some or all of the above processing in the Remote Work Support Department may be performed using AI, or not. For example, the Remote Work Support Department can input user device information data into a generating AI and have the generating AI propose optimal support methods.

[0111] The translation unit can estimate the user's emotions and adjust the translation's expression based on the estimated emotions. For example, if the user is relaxed, the translation unit will use calm language. If the user is in a hurry, the translation unit can use concise and clear language. Furthermore, if the user is excited, the translation unit can use lively language. By adjusting the translation's expression according to the user's emotions, a more appropriate translation can be provided. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the translation unit may be performed using or without a generative AI. For example, the translation unit can input user emotion data into a generative AI and have the generative AI adjust the translation's expression.

[0112] The translation unit can adjust the level of detail in the translation based on the importance of the text. For example, the translation unit will provide a detailed translation for high-importance text, and a concise translation for low-importance text. Furthermore, the translation unit can dynamically adjust the level of detail in the translation according to the importance of the text. This allows for the provision of appropriate information by adjusting the level of detail in the translation according to the importance of the text. Some or all of the above processing in the translation unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the translation unit can input text importance data into a generative AI and have the generative AI perform the adjustment of the level of detail in the translation.

[0113] The translation unit can apply different translation algorithms depending on the category of the text during translation. For example, the unit can translate news articles in a formal tone, while translating entertainment articles in a more casual tone. Furthermore, for technical articles, it can apply an algorithm that accurately translates specialized terminology. This allows the unit to provide appropriate translations according to the text category. Some or all of the above processes in the translation unit may be performed using or without a generative AI. For example, the translation unit can input text category data into a generative AI and have the generative AI apply the appropriate translation algorithm.

[0114] The translation unit can estimate the user's emotions and determine translation priorities based on those estimated emotions. For example, if the user is stressed, the translation unit may postpone less important translations. Conversely, if the user is relaxed, the translation unit may prioritize more important translations. Furthermore, if the user is in a hurry, the translation unit may prioritize urgent translations. This allows for more appropriate translations by prioritizing translations according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the translation unit may be performed using or without generative AI. For example, the translation unit can input user emotion data into a generative AI and have the generative AI determine translation priorities.

[0115] The translation department can prioritize translations based on the text submission date. For example, it can translate urgent texts immediately. It can also prioritize texts with approaching submission deadlines. Furthermore, it can postpone translations of texts with ample time before the submission deadline. This allows for translations to be provided in an appropriate order by prioritizing translations based on the text submission date. Some or all of the above processes in the translation department may be performed using or without a generative AI. For example, the translation department can input text submission date data into a generative AI and have the generative AI determine the translation priority.

[0116] The customization unit can estimate the user's emotions and adjust the customization method based on the estimated emotions. For example, if the user is relaxed, the customization unit can provide a gentle customization. It can also provide a rapid customization if the user is in a hurry. Furthermore, if the user is excited, the customization unit can provide a visually stimulating customization. In this way, by adjusting the customization method according to the user's emotions, a more appropriate customization can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the customization unit may be performed using or without a generative AI. For example, the customization unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of the customization method.

[0117] The customization unit can provide the optimal customization method by referring to the user's past behavior history during customization. For example, the customization unit can propose the optimal customization method based on the user's past customizations. Furthermore, the customization unit can propose an efficient customization method based on the user's past behavior history. In addition, the customization unit can analyze the user's past behavior history and provide the most effective customization method. This improves the accuracy of customization by providing the optimal customization method based on the user's past behavior history. Some or all of the above-described processes in the customization unit may be performed using a generative AI, or they may be performed without a generative AI. For example, the customization unit can input user behavior history data into a generative AI and have the generative AI propose the optimal customization method.

[0118] The customization unit can estimate the user's emotions and determine the priority of customizations based on those emotions. For example, if the user is stressed, the customization unit may postpone less important customizations. Conversely, if the user is relaxed, the customization unit may prioritize more important customizations. Furthermore, if the user is in a hurry, the customization unit may prioritize urgent customizations. This allows for more appropriate customizations to be provided by determining the priority of customizations according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, 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 customization unit may be performed using or without generative AI. For example, the customization unit can input user emotion data into a generative AI and have the generative AI determine the priority of customizations.

[0119] The customization unit can provide the optimal customization method by considering the user's device information during the customization process. For example, if the user is using a smartphone, the customization unit can provide a customization method that matches the screen size. Furthermore, if the user is using a tablet, the customization unit can provide a customization method optimized for a larger screen. Additionally, if the user is using a smartwatch, the customization unit can provide a concise and highly visible customization method. This improves the accuracy of customization by providing the optimal customization method based on the user's device information. Some or all of the above-described processes in the customization unit may be performed using a generative AI, or they may be performed without a generative AI. For example, the customization unit can input user device information data into a generative AI and have the generative AI propose the optimal customization method.

[0120] The wellness monitoring unit can estimate the user's emotions and adjust the wellness monitoring method based on the estimated emotions. For example, if the user is relaxed, the wellness monitoring unit can provide a gentle monitoring method. It can also provide a rapid monitoring method if the user is in a hurry. Furthermore, if the user is excited, the wellness monitoring unit can provide a visually stimulating monitoring method. This allows for more appropriate monitoring by adjusting the wellness monitoring method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, 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 wellness monitoring unit may be performed using or without a generative AI. For example, the wellness monitoring unit can input user emotion data into a generative AI and have the generative AI adjust the wellness monitoring method.

[0121] The wellness monitoring unit can provide the optimal monitoring method by referring to the user's past health data during wellness monitoring. For example, the wellness monitoring unit can propose the optimal monitoring method based on the user's past health data. It can also propose an efficient monitoring method based on the user's past health history. Furthermore, the wellness monitoring unit can analyze the user's past health data and provide the most effective monitoring method. This improves the accuracy of monitoring by providing the optimal monitoring method based on the user's past health data. Some or all of the above processing in the wellness monitoring unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the wellness monitoring unit can input the user's health data into a generative AI and have the generative AI propose the optimal monitoring method.

[0122] The wellness monitoring unit can estimate the user's emotions and determine the priority of wellness monitoring based on the estimated emotions. For example, if the user is stressed, the wellness monitoring unit may postpone low-priority monitoring. Conversely, if the user is relaxed, the wellness monitoring unit may prioritize high-priority monitoring. Furthermore, if the user is in a hurry, the wellness monitoring unit may prioritize high-urgency monitoring. This allows for more appropriate monitoring by determining the priority of wellness monitoring according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the wellness monitoring unit may be performed using or without generative AI. For example, the wellness monitoring unit can input user emotion data into a generative AI and have the generative AI determine the priority of wellness monitoring.

[0123] The wellness monitoring unit can provide an optimal monitoring method during wellness monitoring, taking into account the user's device information. For example, if the user is using a smartphone, the wellness monitoring unit can provide a monitoring method adapted to the screen size. Furthermore, if the user is using a tablet, the wellness monitoring unit can provide a monitoring method optimized for a larger screen. Additionally, if the user is using a smartwatch, the wellness monitoring unit can provide a simple and highly visible monitoring method. This improves monitoring accuracy by providing an optimal monitoring method based on the user's device information. Some or all of the above-described processes in the wellness monitoring unit may be performed using or without a generative AI. For example, the wellness monitoring unit can input user device information data into a generative AI and have the generative AI propose an optimal monitoring method.

[0124] The wellness monitoring unit can analyze the user's current health status in real time during wellness monitoring and detect abnormalities early. For example, the wellness monitoring unit can monitor the user's heart rate and blood pressure in real time and detect abnormalities. It can also analyze the user's activity level in real time and detect abnormal patterns early. Furthermore, the wellness monitoring unit can analyze the user's sleep data in real time and detect abnormal sleep patterns. In this way, abnormalities can be detected early by analyzing the user's current health status in real time. Some or all of the above processing in the wellness monitoring unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the wellness monitoring unit can input the user's health data into a generative AI and have the generative AI perform abnormality detection.

[0125] The wellness monitoring unit can analyze the user's dietary data and evaluate their health status during wellness monitoring. For example, the wellness monitoring unit can evaluate nutritional balance based on the user's dietary data. It can also analyze the user's dietary history and suggest healthy eating patterns. Furthermore, the wellness monitoring unit can analyze the user's dietary data in real time and evaluate their health status. In this way, the health status can be evaluated by analyzing the user's dietary data. Some or all of the above processing in the wellness monitoring unit may be performed using or without a generative AI. For example, the wellness monitoring unit can input the user's dietary data into a generative AI and have the generative AI perform the health status evaluation.

[0126] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0127] The SocialVoice system may further include a speech synthesis unit that estimates the user's emotions and adjusts the tone and speed of speech synthesis based on the estimated emotions. For example, if the user is relaxed, the speech synthesis unit can produce a slow voice in a calm tone. If the user is in a hurry, the speech synthesis unit can produce a clear voice at a fast speed. Furthermore, if the user is excited, the speech synthesis unit can produce a voice in an energetic tone. This allows for a more natural voice by adjusting the tone and speed of speech according to the user's emotions. Emotion estimation is achieved, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the speech synthesis unit may be performed using the generative AI or not. For example, the speech synthesis unit can input user emotion data into the generative AI and have the generative AI adjust the tone and speed of speech.

[0128] The SocialVoice system may also include a reception unit that analyzes the user's past input history and selects the optimal input method. For example, it can prioritize suggesting input methods (voice, text, etc.) that the user has frequently used in the past. The reception unit can also predict and suggest input methods to be used during specific time periods based on the user's past input history. Furthermore, the reception unit can suggest relevant input methods based on the content the user has previously entered. This improves input efficiency by providing the optimal input method based on the user's past input history. Some or all of the above processing in the reception unit may be performed using AI or not. For example, the reception unit can input the user's input history data into a generating AI and have the generating AI select the optimal input method.

[0129] The SocialVoice system may further include a remote work support unit that estimates the user's emotions and adjusts the remote work support methods based on the estimated emotions. For example, if the user is feeling stressed, the remote work support unit can suggest a relaxing work environment. If the user is relaxed, it can also suggest efficient work methods. Furthermore, if the user is in a hurry, it can suggest work methods that allow for quick response. This allows for more appropriate support to be provided by adjusting the remote work support methods according to the user's emotions. Emotion estimation is achieved, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the remote work support unit may be performed using AI or not. For example, the remote work support unit can input user emotion data into a generative AI and have the generative AI perform the adjustment of the remote work support methods.

[0130] The SocialVoice system may further include a reception unit that prioritizes receiving highly relevant inputs by considering the user's geographical location. For example, if the user is in a specific location, information related to that location can be prioritized for input. The reception unit can also automatically suggest relevant keywords based on the user's current location. Furthermore, the reception unit can filter appropriate input content based on the user's geographical location. This improves the accuracy of input by prioritizing the acceptance of highly relevant inputs based on the user's geographical location. Some or all of the above processing in the reception unit may be performed using AI or not. For example, the reception unit can input the user's geographical location data into a generating AI and have the generating AI suggest highly relevant inputs.

[0131] The SocialVoice system may further include a visual information sharing unit that estimates the user's emotions and adjusts the method of sharing visual information based on the estimated emotions. For example, if the user is relaxed, detailed visual information can be shared. If the user is in a hurry, concise visual information can be shared. Furthermore, if the user is excited, visually stimulating information can be shared. This allows for more appropriate information sharing by adjusting the method of sharing visual information according to the user's emotions. Emotion estimation is achieved, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the visual information sharing unit may be performed using AI or not. For example, the visual information sharing unit can input the user's emotion data into the generative AI and have the generative AI adjust the method of sharing visual information.

[0132] The SocialVoice system may further include a reception unit that analyzes the user's social media activity and accepts relevant input. For example, it can automatically suggest relevant keywords from the user's social media activity. The reception unit can also filter appropriate input content based on the user's past posts. Furthermore, the reception unit can analyze the user's social media activity and prioritize input of highly relevant information. This allows the system to provide highly relevant input by analyzing the user's social media activity. Some or all of the above processing in the reception unit may be performed using AI or not. For example, the reception unit can input the user's social media activity data into a generating AI and have the generating AI suggest relevant inputs.

[0133] The SocialVoice system may further include a customization unit that estimates the user's emotions and adjusts the customization method based on the estimated emotions. For example, if the user is relaxed, a gentle customization can be provided. If the user is in a hurry, a quick customization can be provided. Furthermore, if the user is excited, a visually stimulating customization can be provided. This allows for more appropriate customization by adjusting the customization method according to the user's emotions. Emotion estimation is achieved, for example, using an emotion engine or generative AI. Generative AI may be, 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 customization unit may be performed using or without a generative AI. For example, the customization unit can input the user's emotion data into a generative AI and have the generative AI perform the adjustment of the customization method.

[0134] The SocialVoice system may further include a wellness monitoring unit that provides the optimal monitoring method by referring to the user's past health data. For example, it can propose the optimal monitoring method based on the user's past health data. The wellness monitoring unit can also propose an efficient monitoring method from the user's past health history. Furthermore, the wellness monitoring unit can analyze the user's past health data and provide the most effective monitoring method. This improves the accuracy of monitoring by providing the optimal monitoring method based on the user's past health data. Some or all of the above processing in the wellness monitoring unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the wellness monitoring unit can input the user's health data into a generative AI and have the generative AI propose the optimal monitoring method.

[0135] The SocialVoice system may further include a translation unit that estimates the user's emotions and adjusts the translation's expression based on the estimated emotions. For example, if the user is relaxed, the translation can be done in a calm manner. If the user is in a hurry, the translation can be done in a concise and clear manner. Furthermore, if the user is excited, the translation can be done in a lively manner. This allows for more appropriate translations by adjusting the translation's expression according to the user's emotions. Emotion estimation can be achieved, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the translation unit may be performed using the generative AI or not. For example, the translation unit can input the user's emotion data into the generative AI and have the generative AI adjust the translation's expression.

[0136] The SocialVoice system can also include a wellness monitoring unit that analyzes the user's current health status in real time and detects abnormalities early. For example, it can monitor the user's heart rate and blood pressure in real time and detect abnormalities. The wellness monitoring unit can also analyze the user's activity level in real time and detect abnormal patterns early. Furthermore, the wellness monitoring unit can analyze the user's sleep data in real time and detect abnormal sleep patterns. This allows for early detection of abnormalities by analyzing the user's current health status in real time. Some or all of the above-described processes in the wellness monitoring unit may be performed using or without a generative AI. For example, the wellness monitoring unit can input the user's health data into a generative AI and have the generative AI perform abnormality detection.

[0137] The following briefly describes the processing flow for example form 2.

[0138] Step 1: The reception desk accepts text input. The reception desk can accept text using methods such as keyboard input, voice input, or handwriting input. Step 2: The speech synthesis unit converts the text received by the reception unit into speech. The speech synthesis unit generates natural-sounding speech, for example, using a generation AI. The generation AI can convert text into speech using a text generation AI (e.g., LLM). Step 3: The visual information sharing unit shares visual information using the camera. For example, the visual information sharing unit can share what the user is seeing through the camera with other people. The visual information sharing unit can share visual information based on the type of camera and the scope of the information to be shared. Step 4: The emotion recognition unit analyzes the camera footage acquired by the visual information sharing unit and recognizes emotions. The emotion recognition unit analyzes the camera footage using, for example, a generative AI to recognize the user's emotions. The generative AI can recognize emotions using facial expression recognition technology or voice analysis technology.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] Each of the multiple elements described above, including the reception unit, speech synthesis unit, visual information sharing unit, emotion recognition unit, remote work support unit, translation unit, customization unit, and wellness monitoring unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the reception unit is implemented by the reception device 38 of the smart device 14 and accepts text input. The speech synthesis unit is implemented by the specific processing unit 290 of the data processing unit 12 and converts text into speech. The visual information sharing unit shares visual information using the camera 42 of the smart device 14. The emotion recognition unit is implemented by the specific processing unit 290 of the data processing unit 12 and recognizes emotions by analyzing camera images. The remote work support unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides remote work support functions. The translation unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs real-time translation. The customization unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides user-specific customization functions. The wellness monitoring unit is implemented by the specific processing unit 290 of the data processing device 12, which analyzes health data and detects abnormalities. 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.

[0143] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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).

[0149] 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.

[0150] 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.

[0151] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

[0153] In 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.

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

[0155] The specific processing unit 290 transmits the result of the specific processing to the 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.

[0156] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. 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.

[0157] 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.

[0158] Each of the multiple elements described above, including the reception unit, speech synthesis unit, visual information sharing unit, emotion recognition unit, remote work support unit, translation unit, customization unit, and wellness monitoring unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the reception unit is implemented by the microphone 238 of the smart glasses 214 and accepts voice input. The speech synthesis unit is implemented by the specific processing unit 290 of the data processing unit 12 and converts text into speech. The visual information sharing unit shares visual information using the camera 42 of the smart glasses 214. The emotion recognition unit is implemented by the specific processing unit 290 of the data processing unit 12 and recognizes emotions by analyzing camera images. The remote work support unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides remote work support functions. The translation unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs real-time translation. The customization unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides user-specific customization functions. The wellness monitoring unit is implemented by the specific processing unit 290 of the data processing device 12, which analyzes health data and detects abnormalities. 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.

[0159] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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).

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.).

[0171] 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.

[0172] 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.

[0173] 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.

[0174] Each of the multiple elements described above, including the reception unit, speech synthesis unit, visual information sharing unit, emotion recognition unit, remote work support unit, translation unit, customization unit, and wellness monitoring unit, is implemented by at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit is implemented by the microphone 238 of the headset terminal 314 and accepts voice input. The speech synthesis unit is implemented by the specific processing unit 290 of the data processing unit 12 and converts text into speech. The visual information sharing unit shares visual information using the camera 42 of the headset terminal 314. The emotion recognition unit is implemented by the specific processing unit 290 of the data processing unit 12 and recognizes emotions by analyzing camera images. The remote work support unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides remote work support functions. The translation unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs real-time translation. The customization unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides user-specific customization functions. The wellness monitoring unit is implemented by the specific processing unit 290 of the data processing device 12, which analyzes health data and detects abnormalities. 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.

[0175] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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).

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.).

[0188] 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.

[0189] 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.

[0190] 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.

[0191] Each of the multiple elements described above, including the reception unit, speech synthesis unit, visual information sharing unit, emotion recognition unit, remote work support unit, translation unit, customization unit, and wellness monitoring unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the reception unit is implemented by the microphone 238 of the robot 414 and receives voice input. The speech synthesis unit is implemented by the specific processing unit 290 of the data processing unit 12 and converts text into speech. The visual information sharing unit shares visual information using the camera 42 of the robot 414. The emotion recognition unit is implemented by the specific processing unit 290 of the data processing unit 12 and recognizes emotions by analyzing camera images. The remote work support unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides remote work support functions. The translation unit is implemented by the specific processing unit 290 of the data processing unit 12 and performs real-time translation. The customization unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides user-specific customization functions. The wellness monitoring unit is implemented by the specific processing unit 290 of the data processing device 12, which analyzes health data and detects abnormalities. 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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."

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] (Note 1) A reception area that accepts text input, A speech synthesis unit that converts text received by the reception unit into speech, A visual information sharing unit that shares visual information using a camera, The system includes an emotion recognition unit that analyzes camera images acquired by the aforementioned visual information sharing unit and recognizes emotions. A system characterized by the following features. (Note 2) The company has a remote work support department that provides remote work support functions. The system described in Appendix 1, characterized by the features described herein. (Note 3) It features a translation unit that provides real-time translation functionality. The system described in Appendix 1, characterized by the features described herein. (Note 4) It includes a customization section that provides customization features for each user. The system described in Appendix 1, characterized by the features described herein. (Note 5) It includes a wellness monitoring unit that provides wellness monitoring functionality. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned reception unit is The system estimates the user's emotions and adjusts the timing of text input acceptance based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned reception unit is Analyze the user's past input history and select the optimal input method. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned reception unit is When entering text, filtering is performed based on the user's current situation and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reception unit is It estimates the user's emotions and determines the priority of the text to be entered based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned reception unit is When users enter text, the system prioritizes accepting relevant input by considering their geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned reception unit is When a user enters text, the system analyzes their social media activity and accepts relevant input. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned speech synthesis unit, It estimates the user's emotions and adjusts the tone and speed of the voice based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned speech synthesis unit, During speech synthesis, adjust the level of detail in the speech based on the importance of the text. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned speech synthesis unit, When synthesizing speech, different speech synthesis algorithms are applied depending on the category of the text. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned speech synthesis unit, It estimates the user's emotions and adjusts the length of the audio based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned speech synthesis unit, During speech synthesis, the priority of speech is determined based on when the text was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned speech synthesis unit, During speech synthesis, the order of speech is adjusted based on the relevance of the text. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned visual information sharing unit is It estimates the user's emotions and adjusts how visual information is shared based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned visual information sharing unit is When sharing visual information, adjust the level of detail shared based on the importance of the camera footage. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned visual information sharing unit is When sharing visual information, different sharing algorithms are applied depending on the category of the video. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned visual information sharing unit is It estimates the user's emotions and prioritizes visual information based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned visual information sharing unit is When sharing visual information, the system prioritizes sharing highly relevant videos by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned visual information sharing unit is When sharing visual information, the system analyzes the user's social media activity and shares relevant videos. The system described in Appendix 1, characterized by the features described herein. (Note 24) The emotion recognition unit, It estimates the user's emotions and adjusts the accuracy of emotion recognition based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The emotion recognition unit, When recognizing emotions, the level of detail is adjusted based on the importance of the camera footage. The system described in Appendix 1, characterized by the features described herein. (Note 26) The emotion recognition unit, When recognizing emotions, different recognition algorithms are applied depending on the category of the video. The system described in Appendix 1, characterized by the features described herein. (Note 27) The emotion recognition unit, It estimates the user's emotions and determines the priority of emotion recognition based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The emotion recognition unit, When recognizing emotions, the system prioritizes recognizing emotions that are highly relevant, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 29) The emotion recognition unit, During emotion recognition, the system analyzes the user's social media activity and recognizes relevant emotions. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned Remote Work Support Department It estimates the user's emotions and adjusts the remote work support methods based on the estimated user emotions. The system described in Appendix 2, characterized by the features described herein. (Note 31) The aforementioned Remote Work Support Department When providing remote work support, we refer to the user's past work history to provide the most suitable support method. The system described in Appendix 2, characterized by the features described herein. (Note 32) The aforementioned Remote Work Support Department It estimates user emotions and prioritizes remote work support based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 33) The aforementioned Remote Work Support Department When providing remote work support, we offer the optimal support method by taking into account the user's device information. The system described in Appendix 2, characterized by the features described herein. (Note 34) The aforementioned translation department, It estimates the user's emotions and adjusts the translation's expression based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 35) The aforementioned translation department, During translation, adjust the level of detail based on the importance of the text. The system described in Appendix 3, characterized by the features described herein. (Note 36) The aforementioned translation department, During translation, different translation algorithms are applied depending on the text category. The system described in Appendix 3, characterized by the features described herein. (Note 37) The aforementioned translation department, It estimates the user's emotions and determines translation priorities based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 38) The aforementioned translation department, During the translation process, translation priorities are determined based on the submission date of the text. The system described in Appendix 3, characterized by the features described herein. (Note 39) The aforementioned customization unit is It estimates the user's emotions and adjusts the customization method based on the estimated user emotions. The system described in Appendix 4, characterized by the features described herein. (Note 40) The aforementioned customization unit is During customization, the system provides the optimal customization method by referring to the user's past behavior history. The system described in Appendix 4, characterized by the features described herein. (Note 41) The aforementioned customization unit is It estimates the user's emotions and determines the priority of customization based on those estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 42) The aforementioned customization unit is When customizing, we provide the optimal customization method while taking into account the user's device information. The system described in Appendix 4, characterized by the features described herein. (Note 43) The aforementioned wellness monitoring unit is The system estimates the user's emotions and adjusts the wellness monitoring method based on those estimated emotions. The system described in Appendix 5, characterized by the features described herein. (Note 44) The aforementioned wellness monitoring unit is During wellness monitoring, the system provides the optimal monitoring method by referencing the user's past health data. The system described in Appendix 5, characterized by the features described herein. (Note 45) The aforementioned wellness monitoring unit is It estimates the user's emotions and determines the priority of wellness monitoring based on the estimated user emotions. The system described in Appendix 5, characterized by the features described herein. (Note 46) The aforementioned wellness monitoring unit is During wellness monitoring, we provide the optimal monitoring method by taking into account the user's device information. The system described in Appendix 5, characterized by the features described herein. (Note 47) The aforementioned wellness monitoring unit is During wellness monitoring, the system analyzes the user's current health status in real time to detect abnormalities early. The system described in Appendix 5, characterized by the features described herein. (Note 48) The aforementioned wellness monitoring unit is During wellness monitoring, the system analyzes the user's dietary data to assess their health status. The system described in Appendix 5, characterized by the features described herein. [Explanation of Symbols]

[0211] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A reception area that accepts text input, A speech synthesis unit that converts text received by the reception unit into speech, A visual information sharing unit that shares visual information using a camera, The system includes an emotion recognition unit that analyzes camera images acquired by the aforementioned visual information sharing unit and recognizes emotions. A system characterized by the following features.

2. The company has a remote work support department that provides remote work support functions. The system according to feature 1.

3. It features a translation unit that provides real-time translation functionality. The system according to feature 1.

4. It includes a customization section that provides customization features for each user. The system according to feature 1.

5. It includes a wellness monitoring unit that provides wellness monitoring functionality. The system according to feature 1.

6. The aforementioned reception unit is The system estimates the user's emotions and adjusts the timing of text input acceptance based on those emotions. The system according to feature 1.

7. The aforementioned reception unit is Analyze the user's past input history and select the optimal input method. The system according to feature 1.

8. The aforementioned reception unit is When entering text, filtering is performed based on the user's current situation and areas of interest. The system according to feature 1.

9. The aforementioned reception unit is It estimates the user's emotions and determines the priority of the text to be entered based on the estimated user emotions. The system according to feature 1.

10. The aforementioned reception unit is When users enter text, the system prioritizes accepting relevant input by considering their geographical location. The system according to feature 1.

Images