system

Abstract

The system according to this embodiment aims to improve the quality of communication through the correction and translation of natural language input. [Solution] The system according to the embodiment comprises a reception unit, a correction suggestion unit, a correction unit, a translation unit, and an output unit. The reception unit receives natural language input from the user. The correction suggestion unit makes correction suggestions for the input received by the reception unit. The correction unit corrects the input received by the reception unit according to the user's response to the correction suggestion from the correction suggestion unit. The translation unit translates the correction result from the correction unit into language. The output unit outputs the translation result from the translation unit in voice or text.

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 character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, the correction and translation of natural language input are not sufficiently performed, and there is room for improvement in improving the quality of communication.

[0005] The system according to the embodiment aims to improve the quality of communication through the correction and translation of natural language input.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a reception unit, a correction suggestion unit, a correction unit, a translation unit, and an output unit. The reception unit receives natural language input from the user. The correction suggestion unit makes correction suggestions for the input received by the reception unit. The correction unit corrects the input received by the reception unit according to the user's response to the correction suggestion from the correction suggestion unit. The translation unit translates the correction result from the correction unit into language. The output unit outputs the translation result from the translation unit in either audio or text format. [Effects of the Invention]

[0007] The system according to this embodiment can improve the quality of communication through the correction and translation of natural language input. [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 controls communication between multiple computers. Examples of communication standards applicable to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The communication support AI assistant according to an embodiment of the present invention is a system that provides translation and subtitle generation to overcome language barriers, provides feedback and suggestions to improve the quality of communication, and provides appropriate responses in social situations. The communication support AI assistant improves the quality of communication by receiving natural language input from the user, making correction suggestions, making corrections, translating, and outputting. For example, if the user inputs "Hello, what are your plans for today?", this input is received by the reception unit. Next, the reception unit makes correction suggestions for the input received. The correction suggestion unit detects grammatical and semantic errors and makes correction suggestions to the user. For example, for the input "Hello, what are your plans for today?", it makes a correction suggestion such as "Hello, what plans do you have for today?". When the user corrects the input according to the correction suggestion, the correction unit translates the correction result into a specific language. The translation unit translates the corrected input into, for example, English. For example, the input "Hello, what plans do you have for today?" is translated to "Hello, what plans do you have for today?". The translation result is output by the output unit in either voice or text. For example, the translated English text is output as speech. Furthermore, it can also accept natural language input from the user's conversation partner. The reception unit receives input from the conversation partner, and the translation unit translates that input. For example, if the conversation partner inputs "I have a meeting at 3 PM," it is translated as "I have a meeting at 3 PM." It also has an evaluation unit that assesses the conversation with the conversation partner, and a feedback unit that provides feedback on the evaluation results to the user. For example, it evaluates the flow and content of the conversation and provides feedback to the user such as "It would be good to ask more specific questions." Furthermore, the revision suggestion unit can make revision suggestions based on the user's context and an analysis of the conversation partner's emotions. For example, if the conversation partner is angry, it suggests a calmer expression.In this way, it is possible to provide translation and subtitle generation that overcome language barriers, feedback and suggestions to improve the quality of communication, and appropriate responses in social situations. As a result, the communication support AI assistant can improve the quality of communication by accepting the user's natural language input, making correction suggestions, correcting, translating, and outputting.

[0029] The communication support AI assistant according to the embodiment comprises a reception unit, a correction suggestion unit, a correction unit, a translation unit, and an output unit. The reception unit receives natural language input from the user. Natural language input from the user includes, but is not limited to, English, Japanese, and other languages. The reception unit can, for example, receive voice input or text input. The correction suggestion unit makes correction suggestions for the input received by the reception unit. The correction suggestion unit makes correction suggestions by, for example, grammatical correction, semantic correction, and style correction. The correction suggestion unit can, for example, detect grammatical errors and make correction suggestions to the user. The correction suggestion unit can also detect semantic errors and make correction suggestions to the user. The correction suggestion unit can, for example, detect grammatical errors using grammatical rules and syntactic analysis. Semantic errors can be detected by, for example, semantic analysis and contextual understanding. The correction unit corrects the input received by the reception unit according to the user's response to the correction suggestions from the correction suggestion unit. The correction unit, for example, reflects the correction results when the user corrects the input in response to correction suggestions. The translation unit translates the correction results from the correction unit into a specific language. The translation unit translates the correction results using, for example, machine translation. The translation unit can translate into, for example, English, Japanese, or other languages. The translation unit performs translation considering the handling of technical terms and translation accuracy. The output unit outputs the translation results from the translation unit in either speech or text. The output unit outputs the translation results in speech using, for example, speech synthesis technology. The output unit can also output the translation results in text using a text display method. As a result, the communication support AI assistant according to this embodiment can improve the quality of communication by receiving natural language input from the user, making correction suggestions, correcting, translating, and outputting.

[0030] The reception unit accepts natural language input from users. This natural language input includes, but is not limited to, English, Japanese, and other languages. The reception unit can also accept voice and text input. Specifically, in the case of voice input, the user speaks into a microphone, and the voice data is sent to the reception unit. The voice data is converted into text data using speech recognition technology. Speech recognition technology involves a process that extracts features from the speech waveform and maps them to phonemes and words. This ensures that the user's speech is accurately transcribed into text. In the case of text input, the user directly inputs text using a keyboard or touchscreen. The reception unit receives the entered text data as is and passes it on to the next processing step. Furthermore, the reception unit has an automatic input language detection function for multilingual support. For example, if a user inputs in English, the system automatically recognizes it as English and processes it appropriately. This eliminates the need for users to pre-configure language settings, allowing for natural input. The reception unit plays a role in improving the overall efficiency of the system by receiving user input quickly and accurately.

[0031] The Correction Proposal Department makes correction suggestions for input received by the Reception Department. The Correction Proposal Department makes correction suggestions using methods such as grammatical correction, semantic correction, and style correction. Specifically, it detects grammatical errors and makes correction suggestions to the user. Grammatical error detection uses grammatical rules and syntactic analysis. Grammatical rules are a set of rules that define the grammatical structure of a language, and syntactic analysis is the process of analyzing the input text and understanding its grammatical structure. For example, it can detect grammatical errors such as subject-verb agreement and tense agreement. Semantic errors are detected using semantic analysis and contextual understanding. Semantic analysis is the process of understanding the meaning of words and phrases and grasping the meaning of the entire sentence. Contextual understanding detects semantic errors by considering the context and surrounding relationships of the text. For example, it can detect the misuse of homonyms and the use of words that do not fit the context. Style correction involves making suggestions to improve the tone and style of the writing. For example, this includes suggestions to change to a more formal style or to make redundant expressions more concise. The correction suggestion unit presents these correction suggestions to the user and modifies the input based on the suggestion selected by the user. This allows the user to make their input more accurate and appropriate.

[0032] The editing unit modifies the input received by the receiving unit according to the user's response to the editing suggestion unit. For example, if the user modifies the input in response to an editing suggestion, the editing unit reflects the result of that modification. Specifically, if the user accepts an editing suggestion, the editing unit applies the suggested content to the original input and generates the modified text. The editing unit can also handle cases where the user partially accepts the suggestion. For example, the user can choose to accept grammatical corrections but reject style corrections. The editing unit makes appropriate corrections based on the user's selection. The editing unit also has a function to retain the original input if the user rejects the editing suggestion. This allows the user to make corrections that align with their intentions. Furthermore, the editing unit has a function to save the correction history and allow it to be referenced later. This allows the user to review past corrections and make further corrections as needed. The editing unit plays a role in improving the quality of communication by accurately and efficiently correcting the user's input.

[0033] The translation unit translates the corrections made by the editing unit into a specific language. For example, the translation unit uses machine translation to translate the corrections. Specifically, it receives the corrected text as input and translates it into the specified language. The machine translation utilizes the latest translation technology using neural networks, enabling highly accurate translations. The translation unit can translate into English, Japanese, and other languages. The translation unit considers the handling of specialized terminology and translation accuracy. For example, in specialized fields such as medicine and law, accurate translation of specialized terminology is required. The translation unit achieves accurate translation of specialized terminology using specialized terminology dictionaries and field-specific translation models. Furthermore, the translation unit has the ability to understand the meaning of the entire sentence in order to perform contextual translations. This enables natural and fluent translations rather than literal word-for-word translations. In addition, the translation unit has the function to receive user feedback and continuously improve translation accuracy. This allows users to obtain high-quality translations that meet their needs. By quickly and accurately translating corrected texts, the translation unit plays a role in facilitating communication between different languages.

[0034] The output unit outputs the translation results from the translation unit in either audio or text format. For example, the output unit can output the translation results in audio format using speech synthesis technology. Specifically, it receives the translated text as input and generates natural-sounding speech using a speech synthesis engine. The speech synthesis engine can produce fluent speech by considering the pronunciation and intonation of the text. This allows the user to hear the translation results in audio format. The output unit can also output the translation results in text format using a text display method. For example, it can display the translation results on a display or screen, allowing the user to visually confirm them. Furthermore, the output unit can output both audio and text simultaneously, according to the user's preference. This allows the user to confirm the translation results using both audio and text. The output unit is designed to allow flexible selection of output methods, taking user convenience into consideration. For example, it includes functions to adjust the speed and volume of audio output, and to change the font size and color of the text display. This allows the user to customize the output method to their liking. By outputting translation results quickly and appropriately, the output unit plays a role in aiding user understanding and improving the quality of communication.

[0035] The reception unit can receive input from the user's conversation partner. For example, the reception unit can receive voice or text input from the conversation partner. The translation unit can translate the input from the conversation partner. For example, if the conversation partner inputs "I have a meeting at 3 PM", the translation unit will translate it as "I have a meeting at 3 PM". The output unit can output the translation result of the input from the conversation partner by the translation unit as voice or text. For example, the output unit can output the translated Japanese sentence as voice. The output unit can also display the translated Japanese sentence as text. In this way, by receiving input from the conversation partner, translating it, and outputting it, two-way communication can be supported. Some or all of the above processing in the reception unit may be performed using AI, for example, or without AI. For example, the reception unit can input voice input from the conversation partner into a generating AI and have the generating AI perform the conversion from voice data to text data.

[0036] The evaluation unit can evaluate the conversation with the other party. The evaluation unit evaluates, for example, the flow and content of the conversation. The evaluation unit evaluates based on criteria such as grammatical accuracy, semantic consistency, and fluency of the conversation. The feedback unit can provide feedback to the user based on the evaluation results from the evaluation unit. The feedback unit provides feedback to the user, for example, based on the flow and content of the conversation, such as "It would be good to ask more specific questions." In this way, the user's communication skills can be improved by evaluating the conversation and providing feedback. Some or all of the above processing in the evaluation unit may be performed using AI, for example, or without AI. For example, the evaluation unit can input the content of the conversation into a generating AI and have the generating AI perform the evaluation of the conversation.

[0037] The correction suggestion unit can detect grammatical and semantic errors in user input. For example, the correction suggestion unit can detect grammatical errors using grammatical rules and syntactic analysis. For example, the correction suggestion unit can detect semantic errors using semantic analysis and contextual understanding. By detecting grammatical and semantic errors, it can provide accurate correction suggestions. Some or all of the above-described processes in the correction suggestion unit may be performed using AI, for example, or without AI. For example, the correction suggestion unit can input user input into a generating AI and have the generating AI perform grammatical and semantic error detection.

[0038] The revision suggestion unit can make revision suggestions tailored to the user's situation. For example, the revision suggestion unit makes revision suggestions based on the user's intent, context, and usage scenario. For example, if the user is using it in a business setting, the revision suggestion unit will suggest formal expressions. Conversely, if the user is using it in a casual setting, the revision suggestion unit can also suggest relaxed expressions. This allows for more appropriate suggestions by making revision suggestions tailored to the user's situation. Some or all of the above processing in the revision suggestion unit may be performed using AI, for example, or without AI. For example, the revision suggestion unit can input data about the user's situation into a generating AI and have the generating AI execute revision suggestions tailored to the situation.

[0039] The revision suggestion unit can provide revision suggestions tailored to the user's language skills. For example, the revision suggestion unit can provide suggestions for beginners, intermediate learners, and advanced learners. For instance, it might suggest simpler expressions for beginners and more complex expressions for intermediate learners. It can also suggest more advanced expressions for advanced learners. This allows for improved learning effectiveness by providing revision suggestions that match the user's language skill level. Some or all of the above-described processes in the revision suggestion unit may be performed using AI, or not. For example, the revision suggestion unit can input the user's language skill data into a generating AI and have the generating AI execute revision suggestions tailored to the language skill.

[0040] The training unit can provide training to improve communication skills with conversation partners. For example, the training unit can improve users' communication skills through role-playing and feedback sessions. For example, the training unit can simulate actual conversations with conversation partners and provide feedback based on the results. The training unit can also provide training to help users learn appropriate responses in specific situations. Thus, by providing a training unit, users' communication skills can be improved. Some or all of the above processes in the training unit may be performed using AI, for example, or without AI. For example, the training unit can input user training data into a generating AI and have the generating AI provide the training.

[0041] The reception desk can analyze the user's past input history and select the optimal reception method. For example, the reception desk will prioritize accepting input methods that the user has frequently used in the past (such as voice or text). The reception desk 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 desk can automatically complete similar inputs by referring to content that the user has entered in the past. In this way, by analyzing past input history, the reception desk can provide the user with the most suitable reception method. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk can input the user's past input history data into a generating AI and have the generating AI select the optimal reception method.

[0042] The reception unit can filter input based on the user's current situation and areas of interest. For example, the reception unit can accept only highly relevant input based on the user's current situation. It can also prioritize input on specific topics based on the user's areas of interest. Furthermore, the reception unit can filter out unnecessary input based on the user's current situation and areas of interest. This allows for the priority acceptance of highly relevant input by filtering 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 data about the user's current situation and areas of interest into a generating AI and have the generating AI perform the filtering.

[0043] The reception unit can prioritize accepting inputs that are highly relevant, taking into account the user's geographical location information. For example, if the user is in a specific region, the reception unit can prioritize accepting inputs related to that region. Furthermore, if the user is traveling, the reception unit can prioritize accepting inputs related to their travel destination. Additionally, if the user is at home, the reception unit can prioritize accepting inputs related to their home. This allows for the prioritization of highly relevant inputs by considering the user's geographical location information. Some or all of the above processing in the reception unit may be performed using AI, for example, or without AI. For example, the reception unit can input the user's geographical location data into a generating AI and have the generating AI prioritize accepting highly relevant inputs.

[0044] The reception unit can analyze the user's social media activity when receiving input and accept relevant input. For example, the reception unit can prioritize accepting relevant input based on information the user has shared on social media. The reception unit can also analyze the user's social media activity history and suggest relevant input. Furthermore, the reception unit can accept relevant input based on the accounts the user follows on social media. This allows for the priority acceptance of 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, for example, or not using AI. For example, the reception unit can input the user's social media activity data into a generating AI and have the generating AI perform the acceptance of relevant input.

[0045] The correction suggestion unit can adjust the level of detail of its suggestions based on the importance of the input when making correction suggestions. For example, the correction suggestion unit can make detailed correction suggestions for important inputs. It can also make concise correction suggestions for less important inputs. Furthermore, the correction suggestion unit can make rapid correction suggestions for urgent inputs. This allows for detailed correction suggestions to be made for important inputs by adjusting the level of detail of the suggestions based on the importance of the input. Some or all of the above processing in the correction suggestion unit may be performed using AI, for example, or without AI. For example, the correction suggestion unit can input input importance data into a generating AI and have the generating AI adjust the level of detail of the suggestions based on importance.

[0046] The correction suggestion unit can apply different suggestion algorithms depending on the input category when making correction suggestions. For example, the correction suggestion unit can make formal correction suggestions for business-related inputs. It can also make relaxed correction suggestions for casual inputs. Furthermore, for technical inputs, the correction suggestion unit can make correction suggestions that include technical terms. By applying different suggestion algorithms depending on the input category, more appropriate correction suggestions can be made. Some or all of the above processing in the correction suggestion unit may be performed using AI, for example, or without AI. For example, the correction suggestion unit can input the input category data into a generating AI and have the generating AI execute the application of a suggestion algorithm according to the category.

[0047] The revision proposal unit can determine the order of revision proposals based on the submission timing of the inputs. For example, the revision proposal unit can prioritize revision proposals for inputs with high urgency. It can also quickly submit revision proposals for inputs with approaching submission deadlines. Furthermore, it can provide detailed revision proposals for inputs with distant submission deadlines. This allows for quick revision proposals for high-urgency inputs by determining the order of proposals based on the input submission timings. Some or all of the above processing in the revision proposal unit may be performed using AI, for example, or without AI. For example, the revision proposal unit can input input submission timing data into a generating AI and have the generating AI determine the order of proposals based on the submission timings.

[0048] The revision proposal unit can determine the order of proposals based on the relevance of the inputs when proposing revisions. For example, the revision proposal unit can prioritize revision proposals for highly relevant inputs. It can also postpone revision proposals for less relevant inputs. Furthermore, the revision proposal unit can provide detailed revision proposals for highly relevant inputs. In this way, by determining the order of proposals based on the relevance of the inputs, revision proposals can be prioritized for highly relevant inputs. Some or all of the above processing in the revision proposal unit may be performed using AI, for example, or without AI. For example, the revision proposal unit can input relevance data of the inputs into a generating AI and have the generating AI perform the determination of the order of proposals based on relevance.

[0049] The correction unit can analyze the user's past input history to select an appropriate correction method during the correction process. For example, the correction unit may prioritize suggesting correction methods previously used by the user. Furthermore, the correction unit can predict the optimal correction method based on the user's past input history. In addition, the correction unit can suggest similar correction methods by referencing content previously corrected by the user. This allows the correction unit to provide the optimal correction method by analyzing the user's past input history. Some or all of the above-described processes in the correction unit may be performed using AI, or without AI. For example, the correction unit can input the user's past input history data into a generating AI and have the generating AI select an appropriate correction method.

[0050] The correction unit can customize the correction method based on the user's current situation during the correction process. For example, the correction unit can suggest the optimal correction method based on the user's current situation. The correction unit can also determine the priority of corrections based on the user's current situation. Furthermore, the correction unit can adjust the level of detail of the corrections based on the user's current situation. This allows for more appropriate corrections by customizing the correction method based on the user's current situation. Some or all of the above processes in the correction unit may be performed using AI, for example, or without AI. For example, the correction unit can input the user's current situation data into a generating AI and have the generating AI perform a customization of the correction method based on the situation.

[0051] The correction unit can select an appropriate correction method when making corrections, taking into account the user's geographical location information. For example, if the user is in a specific region, the correction unit can suggest a correction method related to that region. Furthermore, if the user is traveling, the correction unit can suggest a correction method related to their travel destination. Additionally, if the user is at home, the correction unit can suggest a correction method related to their home. This allows the correction unit to provide the optimal correction method by considering the user's geographical location information. Some or all of the above processing in the correction unit may be performed using AI, for example, or without AI. For example, the correction unit can input the user's geographical location data into a generating AI and have the generating AI select an appropriate correction method.

[0052] The correction unit can analyze the user's social media activity and propose correction methods during the correction process. For example, the correction unit can propose relevant correction measures based on information shared by the user on social media. The correction unit can also analyze the user's social media activity history and propose relevant correction measures. Furthermore, the correction unit can propose relevant correction measures based on the accounts the user follows on social media. In this way, relevant correction measures can be provided by analyzing the user's social media activity. Some or all of the above processing in the correction unit may be performed using AI, for example, or without AI. For example, the correction unit can input the user's social media activity data into a generating AI and have the generating AI execute the proposal of correction methods.

[0053] The translation unit can adjust the level of detail of the translation based on the importance of the input during translation. For example, the translation unit will provide a detailed translation for important inputs. It can also provide a concise translation for less important inputs. Furthermore, the translation unit can provide a rapid translation for urgent inputs. This allows for detailed translations of important inputs by adjusting the level of detail based on the importance of the input. Some or all of the above processing in the translation unit may be performed using AI, for example, or without AI. For example, the translation unit can input input importance data into a generating AI and have the generating AI adjust the level of detail of the translation based on importance.

[0054] The translation unit can apply different translation algorithms depending on the input category during translation. For example, the translation unit can perform formal translations for business-related inputs, and relaxed translations for casual inputs. Furthermore, it can perform translations that include technical terms for technical inputs. By applying different translation algorithms depending on the input category, more appropriate translations can be achieved. Some or all of the above processing in the translation unit may be performed using AI, for example, or not. For example, the translation unit can input input category data into a generating AI and have the generating AI apply a translation algorithm appropriate to the category.

[0055] The translation unit can determine the order of translations based on the submission date of the inputs during the translation process. For example, the translation unit can prioritize translating urgent inputs. It can also quickly translate inputs with upcoming submission dates. Furthermore, it can perform detailed translations on inputs with later submission dates. This allows for quick translation of urgent inputs by determining the order of translations based on the submission date. Some or all of the above processes in the translation unit may be performed using AI, for example, or not. For example, the translation unit can input input submission date data into a generating AI and have the generating AI determine the order of translations based on the submission date.

[0056] The translation unit can determine the order of translations based on the relevance of the inputs during translation. For example, the translation unit will prioritize translating highly relevant inputs. It can also postpone translating less relevant inputs. Furthermore, the translation unit can perform detailed translations for highly relevant inputs. This allows for prioritizing the translation of highly relevant inputs by determining the order of translations based on their relevance. Some or all of the above processing in the translation unit may be performed using AI, for example, or without AI. For example, the translation unit can input relevance data of the inputs into a generating AI and have the generating AI perform the determination of the translation order based on relevance.

[0057] The output unit can analyze the user's past output history and select an appropriate output method at the time of output. For example, the output unit may preferentially suggest output methods that the user has used in the past. The output unit can also predict the optimal output method from the user's past output history. Furthermore, the output unit can suggest similar output methods by referring to content that the user has output in the past. In this way, the optimal output method can be provided by analyzing the user's past output history. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can input the user's past output history data into a generating AI and have the generating AI select an appropriate output method.

[0058] The output unit can customize the output method based on the user's current situation at the time of output. For example, the output unit can suggest the optimal output method based on the user's current situation. The output unit can also determine the output priority based on the user's current situation. Furthermore, the output unit can adjust the level of detail of the output based on the user's current situation. This allows for more appropriate output by customizing the output method based on the user's current situation. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can input the user's current situation data into a generating AI and have the generating AI perform the customization of the output method based on the situation.

[0059] The output unit can select an appropriate output method when outputting data, taking into account the user's geographical location information. For example, if the user is in a specific region, the output unit can suggest an output method related to that region. Furthermore, if the user is traveling, the output unit can suggest an output method related to their travel destination. Additionally, if the user is at home, the output unit can suggest an output method related to their home. This allows the system to provide the optimal output method by considering the user's geographical location information. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can input the user's geographical location data into a generating AI and have the generating AI select an appropriate output method.

[0060] The output unit can analyze the user's social media activity and propose output methods at the time of output. For example, the output unit can propose relevant output methods based on information shared by the user on social media. The output unit can also analyze the user's social media activity history and propose relevant output methods. Furthermore, the output unit can propose relevant output methods based on accounts followed by the user on social media. In this way, relevant output methods can be provided by analyzing the user's social media activity. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can input the user's social media activity data into a generating AI and have the generating AI execute the proposal of output methods.

[0061] The evaluation unit can improve the accuracy of its evaluation by considering the interrelationships of the dialogue during the evaluation process. For example, the evaluation unit can analyze the flow of the dialogue and perform an evaluation while considering the interrelationships. It can also analyze the content of the dialogue and perform an evaluation while considering the interrelationships. Furthermore, the evaluation unit can analyze the statements of the dialogue participants and perform an evaluation while considering the interrelationships. In this way, the accuracy of the evaluation can be improved by considering the interrelationships of the dialogue. Some or all of the above processing in the evaluation unit may be performed using AI, for example, or without using AI. For example, the evaluation unit can input dialogue interrelationship data into a generating AI and have the generating AI perform an improvement in the accuracy of the evaluation based on the interrelationships.

[0062] The evaluation unit can perform evaluations while considering information about the dialogue participants. For example, the evaluation unit can perform evaluations while considering the age of the dialogue participants. It can also perform evaluations while considering the occupation of the dialogue participants. Furthermore, the evaluation unit can perform evaluations while considering the interests of the dialogue participants. This makes it possible to perform more appropriate evaluations by considering the attribute information of the dialogue participants. Some or all of the above processing in the evaluation unit may be performed using AI, for example, or without using AI. For example, the evaluation unit can input attribute information data of the dialogue participants into a generating AI and have the generating AI perform an evaluation based on the attribute information.

[0063] The evaluation unit can perform evaluations based on the geographical distribution of dialogues. For example, if the dialogue participants are in different regions, the evaluation unit can perform evaluations considering the characteristics of those regions. Furthermore, if the dialogue participants are in the same region, the evaluation unit can perform evaluations considering the characteristics of that region. In addition, if the dialogue participants are concentrated in a particular region, the evaluation unit can perform evaluations considering the characteristics of that region. This allows for more appropriate evaluations by considering the geographical distribution of dialogues. Some or all of the above processing in the evaluation unit may be performed using AI, for example, or without AI. For example, the evaluation unit can input the geographical distribution data of dialogues into a generating AI and have the generating AI perform evaluations based on the geographical distribution.

[0064] The evaluation unit can improve the accuracy of its evaluation by referencing relevant literature related to the dialogue during the evaluation process. For example, the evaluation unit can perform its evaluation by referring to literature related to the content of the dialogue. It can also perform its evaluation by referring to literature related to the theme of the dialogue. Furthermore, the evaluation unit can perform its evaluation by referring to literature related to the statements made by the dialogue participants. In this way, the accuracy of the evaluation can be improved by referring to relevant literature related to the dialogue. Some or all of the above processing in the evaluation unit may be performed using AI, for example, or without using AI. For example, the evaluation unit can input dialogue-related literature data into a generating AI and have the generating AI perform an improvement in the accuracy of the evaluation based on the relevant literature.

[0065] The feedback unit can adjust the level of detail of the feedback based on the importance of the dialogue. For example, the feedback unit provides detailed feedback for important dialogues. It can also provide concise feedback for less important dialogues. Furthermore, the feedback unit can provide rapid feedback for urgent dialogues. This allows for detailed feedback on important dialogues by adjusting the level of detail based on the importance of the dialogue. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input dialogue importance data into a generating AI and have the generating AI adjust the level of detail of the feedback based on importance.

[0066] The feedback unit can apply a feedback algorithm according to the category of the dialogue during the feedback process. For example, the feedback unit can provide formal feedback for business-related dialogues, and relaxed feedback for casual dialogues. Furthermore, it can provide feedback that includes technical jargon for technical dialogues. By applying different feedback algorithms depending on the dialogue category, more appropriate feedback becomes possible. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input dialogue category data into a generating AI and have the generating AI apply a feedback algorithm according to the category.

[0067] The feedback unit can determine the order of feedback based on the submission date of the dialogues. For example, the feedback unit can prioritize feedback for dialogues with high urgency. It can also provide rapid feedback for dialogues with upcoming submission dates. Furthermore, it can provide detailed feedback for dialogues with later submission dates. By determining the order of feedback based on the submission date of the dialogues, it is possible to provide rapid feedback for dialogues with high urgency. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input dialogue submission date data into a generating AI and have the generating AI determine the order of feedback based on the submission date.

[0068] The feedback unit can determine the order of feedback based on the relevance of the dialogues during the feedback process. For example, the feedback unit can prioritize feedback for highly relevant dialogues. It can also postpone feedback for less relevant dialogues. Furthermore, the feedback unit can provide detailed feedback for highly relevant dialogues. In this way, by determining the order of feedback based on the relevance of the dialogues, feedback can be prioritized for highly relevant dialogues. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input dialogue relevance data into a generating AI and have the generating AI determine the order of feedback based on relevance.

[0069] The training unit can analyze the user's past training history during training to select an appropriate training method. For example, the training unit can prioritize suggesting training methods the user has used in the past. The training unit can also predict the optimal training method based on the user's past training history. Furthermore, the training unit can suggest similar training methods by referring to the content the user has trained on in the past. In this way, by analyzing the user's past training history, the optimal training method can be provided. Some or all of the above processing in the training unit may be performed using AI, for example, or without AI. For example, the training unit can input the user's past training history data into a generating AI and have the generating AI select an appropriate training method.

[0070] The training unit can customize the training method based on the user's current situation during training. For example, the training unit can suggest the optimal training method based on the user's current situation. The training unit can also determine the priority of training based on the user's current situation. Furthermore, the training unit can adjust the level of detail of the training based on the user's current situation. This allows for more appropriate training by customizing the training method based on the user's current situation. Some or all of the above processes in the training unit may be performed using AI, for example, or without AI. For example, the training unit can input the user's current situation data into a generating AI and have the generating AI perform the customization of the training method based on the situation.

[0071] The training unit can select an appropriate training method during training, taking into account the user's geographical location. For example, if the user is in a specific region, the training unit can suggest a training method relevant to that region. Furthermore, if the user is traveling, the training unit can suggest a training method relevant to their travel destination. Additionally, if the user is at home, the training unit can suggest a training method relevant to their home. This allows the system to provide the optimal training method by considering the user's geographical location. Some or all of the above processing in the training unit may be performed using AI, or without AI. For example, the training unit can input the user's geographical location data into a generating AI and have the generating AI select an appropriate training method.

[0072] The training unit can analyze a user's social media activity during training and propose training methods. For example, the training unit can propose relevant training methods based on information shared by the user on social media. The training unit can also analyze a user's social media activity history and propose relevant training methods. Furthermore, the training unit can propose relevant training methods based on the accounts the user follows on social media. In this way, relevant training methods can be provided by analyzing the user's social media activity. Some or all of the above processing in the training unit may be performed using AI, for example, or without AI. For example, the training unit can input the user's social media activity data into a generating AI and have the generating AI execute the proposal of training methods.

[0073] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0074] The AI ​​communication assistant analyzes the user's past conversation history and can predict the next statement based on the flow and content of the conversation. For example, if the user previously typed "Hello, what are your plans for today?", the AI ​​can predict "I have a meeting this afternoon" as the next statement. Similarly, if the user previously typed "Good work, how is the progress?", the AI ​​can predict "It's going smoothly" as the next statement. Furthermore, if the user previously typed "Good morning, what's the weather like today?", the AI ​​can predict "It's sunny" as the next statement. In this way, by analyzing the user's past conversation history, the AI ​​can predict the next statement and support smoother conversations.

[0075] AI communication assistants can customize the content of conversations by considering the profile information of the person the user is talking to. For example, if the person is a business partner, they can use formal language. If the person is a friend, they can use casual language. Furthermore, if the person is an expert, they can use language that includes technical terms. In this way, by considering the profile information of the person being spoken to, they can provide more appropriate conversation content.

[0076] The AI ​​communication assistant can analyze the past statements of the person the user is talking to and predict the flow of the conversation. For example, if the person previously said, "Hello, what are your plans for today?", it can predict the next statement to be, "I have a meeting this afternoon." Similarly, if the person previously said, "Good work today, how is the progress?", it can predict the next statement to be, "It's going smoothly." Furthermore, if the person previously said, "Good morning, what's the weather like today?", it can predict the next statement to be, "It's sunny." In this way, by analyzing the past statements of the person the user is talking to, it can predict the next statement and support smoother conversations.

[0077] AI communication assistants can customize the content of conversations by considering the cultural background of the person the user is talking to. For example, if the person is familiar with Japanese culture, the assistant will use expressions based on Japanese customs and etiquette. Similarly, if the person is familiar with American culture, the assistant can use expressions based on American customs and etiquette. Furthermore, if the person is familiar with French culture, the assistant can use expressions based on French customs and etiquette. This allows the assistant to provide more appropriate conversation content by considering the cultural background of the person they are talking to.

[0078] The AI ​​communication assistant can select conversation topics by considering the interests of the person the user is talking to. For example, if the person is interested in sports, it can select topics related to sports. Similarly, if the person is interested in music, it can select topics related to music. Furthermore, if the person is interested in travel, it can select topics related to travel. This allows the AI ​​to provide more appropriate conversation topics by considering the interests of the person it is talking to.

[0079] AI communication assistants can adjust the content of conversations by considering the language skills of the person the user is talking to. For example, if the person is a beginner, they will use simple expressions. If the person is an intermediate speaker, they can use slightly more complex expressions. Furthermore, if the person is an advanced speaker, they can use more advanced expressions. In this way, by considering the language skills of the person being spoken to, they can provide more appropriate conversation content.

[0080] The AI ​​communication assistant can analyze past feedback from the user's conversation partner and suggest ways to improve the conversation. For example, if the conversation partner previously commented that they wanted more specific questions, the AI ​​assistant will suggest more specific questions in the next conversation. Similarly, if the conversation partner previously commented that they wanted a more relaxed tone, the AI ​​assistant can suggest a more relaxed tone in the next conversation. Furthermore, if the conversation partner previously commented that they wanted a quicker response, the AI ​​assistant can suggest a quicker response in the next conversation. In this way, by analyzing past feedback from the conversation partner, the AI ​​assistant can suggest ways to improve the conversation and support better communication.

[0081] The following briefly describes the processing flow for example form 1.

[0082] Step 1: The reception desk accepts natural language input from the user. This natural language input may include, but is not limited to, English, Japanese, or other languages. The reception desk may also accept voice input or text input, for example. Step 2: The correction suggestion unit makes correction suggestions for the input received by the reception unit. The correction suggestion unit makes correction suggestions using methods such as grammatical correction, semantic correction, and style correction. For example, the correction suggestion unit can detect grammatical errors and make correction suggestions to the user. The correction suggestion unit can also detect semantic errors and make correction suggestions to the user. For example, the correction suggestion unit can detect grammatical errors using grammatical rules and syntactic analysis. Semantic errors can be detected using methods such as semantic analysis and contextual understanding. Step 3: The correction unit corrects the input received by the reception unit according to the user's response to the correction proposal from the correction proposal unit. For example, if the user corrects the input in response to the correction proposal, the correction unit reflects the result of that correction. Step 4: The translation unit translates the corrections made by the editing unit into a specific language. The translation unit may use machine translation to translate the corrections. The translation unit may translate into English, Japanese, or other languages. The translation unit takes into account the handling of technical terms and translation accuracy. Step 5: The output unit outputs the translation result from the translation unit in either audio or text. The output unit can output the translation result in audio, for example, using speech synthesis technology. Alternatively, the output unit can output the translation result in text using a text display method.

[0083] (Example of form 2) The communication support AI assistant according to an embodiment of the present invention is a system that provides translation and subtitle generation to overcome language barriers, provides feedback and suggestions to improve the quality of communication, and provides appropriate responses in social situations. The communication support AI assistant improves the quality of communication by receiving natural language input from the user, making correction suggestions, making corrections, translating, and outputting. For example, if the user inputs "Hello, what are your plans for today?", this input is received by the reception unit. Next, the reception unit makes correction suggestions for the input received. The correction suggestion unit detects grammatical and semantic errors and makes correction suggestions to the user. For example, for the input "Hello, what are your plans for today?", it makes a correction suggestion such as "Hello, what plans do you have for today?". When the user corrects the input according to the correction suggestion, the correction unit translates the correction result into a specific language. The translation unit translates the corrected input into, for example, English. For example, the input "Hello, what plans do you have for today?" is translated to "Hello, what plans do you have for today?". The translation result is output by the output unit in either voice or text. For example, the translated English text is output as speech. Furthermore, it can also accept natural language input from the user's conversation partner. The reception unit receives input from the conversation partner, and the translation unit translates that input. For example, if the conversation partner inputs "I have a meeting at 3 PM," it is translated as "I have a meeting at 3 PM." It also has an evaluation unit that assesses the conversation with the conversation partner, and a feedback unit that provides feedback on the evaluation results to the user. For example, it evaluates the flow and content of the conversation and provides feedback to the user such as "It would be good to ask more specific questions." Furthermore, the revision suggestion unit can make revision suggestions based on the user's context and an analysis of the conversation partner's emotions. For example, if the conversation partner is angry, it suggests a calmer expression.In this way, it is possible to provide translation and subtitle generation that overcome language barriers, feedback and suggestions to improve the quality of communication, and appropriate responses in social situations. As a result, the communication support AI assistant can improve the quality of communication by accepting the user's natural language input, making correction suggestions, correcting, translating, and outputting.

[0084] The communication support AI assistant according to the embodiment comprises a reception unit, a correction suggestion unit, a correction unit, a translation unit, and an output unit. The reception unit receives natural language input from the user. Natural language input from the user includes, but is not limited to, English, Japanese, and other languages. The reception unit can, for example, receive voice input or text input. The correction suggestion unit makes correction suggestions for the input received by the reception unit. The correction suggestion unit makes correction suggestions by, for example, grammatical correction, semantic correction, and style correction. The correction suggestion unit can, for example, detect grammatical errors and make correction suggestions to the user. The correction suggestion unit can also detect semantic errors and make correction suggestions to the user. The correction suggestion unit can, for example, detect grammatical errors using grammatical rules and syntactic analysis. Semantic errors can be detected by, for example, semantic analysis and contextual understanding. The correction unit corrects the input received by the reception unit according to the user's response to the correction suggestions from the correction suggestion unit. The correction unit, for example, reflects the correction results when the user corrects the input in response to correction suggestions. The translation unit translates the correction results from the correction unit into a specific language. The translation unit translates the correction results using, for example, machine translation. The translation unit can translate into, for example, English, Japanese, or other languages. The translation unit performs translation considering the handling of technical terms and translation accuracy. The output unit outputs the translation results from the translation unit in either speech or text. The output unit outputs the translation results in speech using, for example, speech synthesis technology. The output unit can also output the translation results in text using a text display method. As a result, the communication support AI assistant according to this embodiment can improve the quality of communication by receiving natural language input from the user, making correction suggestions, correcting, translating, and outputting.

[0085] The reception unit accepts natural language input from users. This natural language input includes, but is not limited to, English, Japanese, and other languages. The reception unit can also accept voice and text input. Specifically, in the case of voice input, the user speaks into a microphone, and the voice data is sent to the reception unit. The voice data is converted into text data using speech recognition technology. Speech recognition technology involves a process that extracts features from the speech waveform and maps them to phonemes and words. This ensures that the user's speech is accurately transcribed into text. In the case of text input, the user directly inputs text using a keyboard or touchscreen. The reception unit receives the entered text data as is and passes it on to the next processing step. Furthermore, the reception unit has an automatic input language detection function for multilingual support. For example, if a user inputs in English, the system automatically recognizes it as English and processes it appropriately. This eliminates the need for users to pre-configure language settings, allowing for natural input. The reception unit plays a role in improving the overall efficiency of the system by receiving user input quickly and accurately.

[0086] The Correction Proposal Department makes correction suggestions for input received by the Reception Department. The Correction Proposal Department makes correction suggestions using methods such as grammatical correction, semantic correction, and style correction. Specifically, it detects grammatical errors and makes correction suggestions to the user. Grammatical error detection uses grammatical rules and syntactic analysis. Grammatical rules are a set of rules that define the grammatical structure of a language, and syntactic analysis is the process of analyzing the input text and understanding its grammatical structure. For example, it can detect grammatical errors such as subject-verb agreement and tense agreement. Semantic errors are detected using semantic analysis and contextual understanding. Semantic analysis is the process of understanding the meaning of words and phrases and grasping the meaning of the entire sentence. Contextual understanding detects semantic errors by considering the context and surrounding relationships of the text. For example, it can detect the misuse of homonyms and the use of words that do not fit the context. Style correction involves making suggestions to improve the tone and style of the writing. For example, this includes suggestions to change to a more formal style or to make redundant expressions more concise. The correction suggestion unit presents these correction suggestions to the user and modifies the input based on the suggestion selected by the user. This allows the user to make their input more accurate and appropriate.

[0087] The editing unit modifies the input received by the receiving unit according to the user's response to the editing suggestion unit. For example, if the user modifies the input in response to an editing suggestion, the editing unit reflects the result of that modification. Specifically, if the user accepts an editing suggestion, the editing unit applies the suggested content to the original input and generates the modified text. The editing unit can also handle cases where the user partially accepts the suggestion. For example, the user can choose to accept grammatical corrections but reject style corrections. The editing unit makes appropriate corrections based on the user's selection. The editing unit also has a function to retain the original input if the user rejects the editing suggestion. This allows the user to make corrections that align with their intentions. Furthermore, the editing unit has a function to save the correction history and allow it to be referenced later. This allows the user to review past corrections and make further corrections as needed. The editing unit plays a role in improving the quality of communication by accurately and efficiently correcting the user's input.

[0088] The translation unit translates the corrections made by the editing unit into a specific language. For example, the translation unit uses machine translation to translate the corrections. Specifically, it receives the corrected text as input and translates it into the specified language. The machine translation utilizes the latest translation technology using neural networks, enabling highly accurate translations. The translation unit can translate into English, Japanese, and other languages. The translation unit considers the handling of specialized terminology and translation accuracy. For example, in specialized fields such as medicine and law, accurate translation of specialized terminology is required. The translation unit achieves accurate translation of specialized terminology using specialized terminology dictionaries and field-specific translation models. Furthermore, the translation unit has the ability to understand the meaning of the entire sentence in order to perform contextual translations. This enables natural and fluent translations rather than literal word-for-word translations. In addition, the translation unit has the function to receive user feedback and continuously improve translation accuracy. This allows users to obtain high-quality translations that meet their needs. By quickly and accurately translating corrected texts, the translation unit plays a role in facilitating communication between different languages.

[0089] The output unit outputs the translation results from the translation unit in either audio or text format. For example, the output unit can output the translation results in audio format using speech synthesis technology. Specifically, it receives the translated text as input and generates natural-sounding speech using a speech synthesis engine. The speech synthesis engine can produce fluent speech by considering the pronunciation and intonation of the text. This allows the user to hear the translation results in audio format. The output unit can also output the translation results in text format using a text display method. For example, it can display the translation results on a display or screen, allowing the user to visually confirm them. Furthermore, the output unit can output both audio and text simultaneously, according to the user's preference. This allows the user to confirm the translation results using both audio and text. The output unit is designed to allow flexible selection of output methods, taking user convenience into consideration. For example, it includes functions to adjust the speed and volume of audio output, and to change the font size and color of the text display. This allows the user to customize the output method to their liking. By outputting translation results quickly and appropriately, the output unit plays a role in aiding user understanding and improving the quality of communication.

[0090] The reception unit can receive input from the user's conversation partner. For example, the reception unit can receive voice or text input from the conversation partner. The translation unit can translate the input from the conversation partner. For example, if the conversation partner inputs "I have a meeting at 3 PM", the translation unit will translate it as "I have a meeting at 3 PM". The output unit can output the translation result of the input from the conversation partner by the translation unit as voice or text. For example, the output unit can output the translated Japanese sentence as voice. The output unit can also display the translated Japanese sentence as text. In this way, by receiving input from the conversation partner, translating it, and outputting it, two-way communication can be supported. Some or all of the above processing in the reception unit may be performed using AI, for example, or without AI. For example, the reception unit can input voice input from the conversation partner into a generating AI and have the generating AI perform the conversion from voice data to text data.

[0091] The evaluation unit can evaluate the conversation with the other party. The evaluation unit evaluates, for example, the flow and content of the conversation. The evaluation unit evaluates based on criteria such as grammatical accuracy, semantic consistency, and fluency of the conversation. The feedback unit can provide feedback to the user based on the evaluation results from the evaluation unit. The feedback unit provides feedback to the user, for example, based on the flow and content of the conversation, such as "It would be good to ask more specific questions." In this way, the user's communication skills can be improved by evaluating the conversation and providing feedback. Some or all of the above processing in the evaluation unit may be performed using AI, for example, or without AI. For example, the evaluation unit can input the content of the conversation into a generating AI and have the generating AI perform the evaluation of the conversation.

[0092] The correction suggestion unit can detect grammatical and semantic errors in user input. For example, the correction suggestion unit can detect grammatical errors using grammatical rules and syntactic analysis. For example, the correction suggestion unit can detect semantic errors using semantic analysis and contextual understanding. By detecting grammatical and semantic errors, it can provide accurate correction suggestions. Some or all of the above-described processes in the correction suggestion unit may be performed using AI, for example, or without AI. For example, the correction suggestion unit can input user input into a generating AI and have the generating AI perform grammatical and semantic error detection.

[0093] The revision suggestion unit can make revision suggestions tailored to the user's situation. For example, the revision suggestion unit makes revision suggestions based on the user's intent, context, and usage scenario. For example, if the user is using it in a business setting, the revision suggestion unit will suggest formal expressions. Conversely, if the user is using it in a casual setting, the revision suggestion unit can also suggest relaxed expressions. This allows for more appropriate suggestions by making revision suggestions tailored to the user's situation. Some or all of the above processing in the revision suggestion unit may be performed using AI, for example, or without AI. For example, the revision suggestion unit can input data about the user's situation into a generating AI and have the generating AI execute revision suggestions tailored to the situation.

[0094] The correction suggestion unit can analyze the emotions of the conversation partner and make correction suggestions based on those emotions. For example, the correction suggestion unit can analyze the emotions of the conversation partner using an emotion recognition algorithm. For example, if the conversation partner is angry, the correction suggestion unit can suggest calmer expressions. Also, if the conversation partner is happy, the correction suggestion unit can suggest more positive expressions. This enables more appropriate communication by making correction suggestions based on the emotions of the conversation partner. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the correction suggestion unit may be performed using AI, or not using AI. For example, the correction suggestion unit can input the conversation partner's emotion data into a generative AI and have the generative AI execute emotion-based correction suggestions.

[0095] The revision suggestion unit can provide revision suggestions tailored to the user's language skills. For example, the revision suggestion unit can provide suggestions for beginners, intermediate learners, and advanced learners. For instance, it might suggest simpler expressions for beginners and more complex expressions for intermediate learners. It can also suggest more advanced expressions for advanced learners. This allows for improved learning effectiveness by providing revision suggestions that match the user's language skill level. Some or all of the above-described processes in the revision suggestion unit may be performed using AI, or not. For example, the revision suggestion unit can input the user's language skill data into a generating AI and have the generating AI execute revision suggestions tailored to the language skill.

[0096] The training unit can provide training to improve communication skills with conversation partners. For example, the training unit can improve users' communication skills through role-playing and feedback sessions. For example, the training unit can simulate actual conversations with conversation partners and provide feedback based on the results. The training unit can also provide training to help users learn appropriate responses in specific situations. Thus, by providing a training unit, users' communication skills can be improved. Some or all of the above processes in the training unit may be performed using AI, for example, or without AI. For example, the training unit can input user training data into a generating AI and have the generating AI provide the training.

[0097] The reception unit can estimate the user's emotions and adjust the timing of input acceptance based on the estimated emotions. For example, if the user is stressed, the reception unit can temporarily delay input acceptance to give the user time to relax. Conversely, if the user is relaxed, the reception unit can accept input immediately to facilitate a smooth conversation. Furthermore, if the user is in a hurry, the reception unit can quickly accept input and immediately proceed to the next step. This allows for more appropriate timing of input acceptance by adjusting the timing of input acceptance based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception unit may be performed using AI or not. For example, the reception unit can input user emotion data into the generative AI and have the generative AI adjust the timing of input acceptance based on emotions.

[0098] The reception desk can analyze the user's past input history and select the optimal reception method. For example, the reception desk will prioritize accepting input methods that the user has frequently used in the past (such as voice or text). The reception desk 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 desk can automatically complete similar inputs by referring to content that the user has entered in the past. In this way, by analyzing past input history, the reception desk can provide the user with the most suitable reception method. Some or all of the above processing in the reception desk may be performed using AI, for example, or not using AI. For example, the reception desk can input the user's past input history data into a generating AI and have the generating AI select the optimal reception method.

[0099] The reception unit can filter input based on the user's current situation and areas of interest. For example, the reception unit can accept only highly relevant input based on the user's current situation. It can also prioritize input on specific topics based on the user's areas of interest. Furthermore, the reception unit can filter out unnecessary input based on the user's current situation and areas of interest. This allows for the priority acceptance of highly relevant input by filtering 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 data about the user's current situation and areas of interest into a generating AI and have the generating AI perform the filtering.

[0100] The reception unit can estimate the user's emotions and determine the priority of inputs to be received based on the estimated emotions. For example, if the user is stressed, the reception unit will prioritize important inputs. If the user is relaxed, the reception unit can also accept all inputs equally. Furthermore, if the user is in a hurry, the reception unit can prioritize urgent inputs. In this way, important inputs can be prioritized by determining the priority of inputs based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception unit may be performed using AI or not using AI. For example, the reception unit can input user emotion data into a generative AI and have the generative AI perform the determination of input priorities based on emotions.

[0101] The reception unit can prioritize accepting inputs that are highly relevant, taking into account the user's geographical location information. For example, if the user is in a specific region, the reception unit can prioritize accepting inputs related to that region. Furthermore, if the user is traveling, the reception unit can prioritize accepting inputs related to their travel destination. Additionally, if the user is at home, the reception unit can prioritize accepting inputs related to their home. This allows for the prioritization of highly relevant inputs by considering the user's geographical location information. Some or all of the above processing in the reception unit may be performed using AI, for example, or without AI. For example, the reception unit can input the user's geographical location data into a generating AI and have the generating AI prioritize accepting highly relevant inputs.

[0102] The reception unit can analyze the user's social media activity when receiving input and accept relevant input. For example, the reception unit can prioritize accepting relevant input based on information the user has shared on social media. The reception unit can also analyze the user's social media activity history and suggest relevant input. Furthermore, the reception unit can accept relevant input based on the accounts the user follows on social media. This allows for the priority acceptance of 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, for example, or not using AI. For example, the reception unit can input the user's social media activity data into a generating AI and have the generating AI perform the acceptance of relevant input.

[0103] The revision suggestion unit can estimate the user's emotions and adjust the expression of the revision suggestion based on the estimated emotions. For example, if the user is stressed, the revision suggestion unit will make revision suggestions in a calm manner. If the user is relaxed, the revision suggestion unit can also make detailed revision suggestions. Furthermore, if the user is in a hurry, the revision suggestion unit can make concise revision suggestions. By adjusting the expression of revision suggestions based on the user's emotions, more appropriate revision suggestions become possible. 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 revision suggestion unit may be performed using AI or not using AI. For example, the revision suggestion unit can input user emotion data into the generative AI and have the generative AI adjust the expression of the revision suggestion based on the emotions.

[0104] The correction suggestion unit can adjust the level of detail of its suggestions based on the importance of the input when making correction suggestions. For example, the correction suggestion unit can make detailed correction suggestions for important inputs. It can also make concise correction suggestions for less important inputs. Furthermore, the correction suggestion unit can make rapid correction suggestions for urgent inputs. This allows for detailed correction suggestions to be made for important inputs by adjusting the level of detail of the suggestions based on the importance of the input. Some or all of the above processing in the correction suggestion unit may be performed using AI, for example, or without AI. For example, the correction suggestion unit can input input importance data into a generating AI and have the generating AI adjust the level of detail of the suggestions based on importance.

[0105] The correction suggestion unit can apply different suggestion algorithms depending on the input category when making correction suggestions. For example, the correction suggestion unit can make formal correction suggestions for business-related inputs. It can also make relaxed correction suggestions for casual inputs. Furthermore, for technical inputs, the correction suggestion unit can make correction suggestions that include technical terms. By applying different suggestion algorithms depending on the input category, more appropriate correction suggestions can be made. Some or all of the above processing in the correction suggestion unit may be performed using AI, for example, or without AI. For example, the correction suggestion unit can input the input category data into a generating AI and have the generating AI execute the application of a suggestion algorithm according to the category.

[0106] The revision suggestion unit can estimate the user's emotions and adjust the length of the revision suggestion based on the estimated emotions. For example, if the user is stressed, the revision suggestion unit will provide a short, concise suggestion. If the user is relaxed, the revision suggestion unit can provide a more detailed suggestion. Furthermore, if the user is in a hurry, the revision suggestion unit can provide a brief suggestion. By adjusting the length of the revision suggestion based on the user's emotions, more appropriate suggestions can be made. 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 revision suggestion unit may be performed using AI or not. For example, the revision suggestion unit can input user emotion data into the generative AI and have the generative AI adjust the length of the revision suggestion based on the emotion.

[0107] The revision proposal unit can determine the order of revision proposals based on the submission timing of the inputs. For example, the revision proposal unit can prioritize revision proposals for inputs with high urgency. It can also quickly submit revision proposals for inputs with approaching submission deadlines. Furthermore, it can provide detailed revision proposals for inputs with distant submission deadlines. This allows for quick revision proposals for high-urgency inputs by determining the order of proposals based on the input submission timings. Some or all of the above processing in the revision proposal unit may be performed using AI, for example, or without AI. For example, the revision proposal unit can input input submission timing data into a generating AI and have the generating AI determine the order of proposals based on the submission timings.

[0108] The revision proposal unit can determine the order of proposals based on the relevance of the inputs when proposing revisions. For example, the revision proposal unit can prioritize revision proposals for highly relevant inputs. It can also postpone revision proposals for less relevant inputs. Furthermore, the revision proposal unit can provide detailed revision proposals for highly relevant inputs. In this way, by determining the order of proposals based on the relevance of the inputs, revision proposals can be prioritized for highly relevant inputs. Some or all of the above processing in the revision proposal unit may be performed using AI, for example, or without AI. For example, the revision proposal unit can input relevance data of the inputs into a generating AI and have the generating AI perform the determination of the order of proposals based on relevance.

[0109] The correction unit can estimate the user's emotions and adjust the means of correction based on the estimated emotions. For example, if the user is stressed, the correction unit can suggest a gentle correction method. If the user is relaxed, the correction unit can also suggest a detailed correction method. Furthermore, if the user is in a hurry, the correction unit can suggest a rapid correction method. This allows for more appropriate correction by adjusting the correction method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the correction unit may be performed using AI, for example, or not using AI. For example, the correction unit can input user emotion data into the generative AI and have the generative AI perform adjustments to the correction method based on the emotions.

[0110] The correction unit can analyze the user's past input history to select an appropriate correction method during the correction process. For example, the correction unit may prioritize suggesting correction methods previously used by the user. Furthermore, the correction unit can predict the optimal correction method based on the user's past input history. In addition, the correction unit can suggest similar correction methods by referencing content previously corrected by the user. This allows the correction unit to provide the optimal correction method by analyzing the user's past input history. Some or all of the above-described processes in the correction unit may be performed using AI, or without AI. For example, the correction unit can input the user's past input history data into a generating AI and have the generating AI select an appropriate correction method.

[0111] The correction unit can customize the correction method based on the user's current situation during the correction process. For example, the correction unit can suggest the optimal correction method based on the user's current situation. The correction unit can also determine the priority of corrections based on the user's current situation. Furthermore, the correction unit can adjust the level of detail of the corrections based on the user's current situation. This allows for more appropriate corrections by customizing the correction method based on the user's current situation. Some or all of the above processes in the correction unit may be performed using AI, for example, or without AI. For example, the correction unit can input the user's current situation data into a generating AI and have the generating AI perform a customization of the correction method based on the situation.

[0112] The editing unit can estimate the user's emotions and determine the order of corrections based on the estimated emotions. For example, if the user is stressed, the editing unit will prioritize important corrections. If the user is relaxed, the editing unit can also perform all corrections equally. Furthermore, if the user is in a hurry, the editing unit can prioritize urgent corrections. This allows for prioritizing important corrections by determining the priority of corrections based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may 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 editing unit may be performed using AI or not. For example, the editing unit can input user emotion data into a generative AI and have the generative AI determine the order of corrections based on emotions.

[0113] The correction unit can select an appropriate correction method when making corrections, taking into account the user's geographical location information. For example, if the user is in a specific region, the correction unit can suggest a correction method related to that region. Furthermore, if the user is traveling, the correction unit can suggest a correction method related to their travel destination. Additionally, if the user is at home, the correction unit can suggest a correction method related to their home. This allows the correction unit to provide the optimal correction method by considering the user's geographical location information. Some or all of the above processing in the correction unit may be performed using AI, for example, or without AI. For example, the correction unit can input the user's geographical location data into a generating AI and have the generating AI select an appropriate correction method.

[0114] The correction unit can analyze the user's social media activity and propose correction methods during the correction process. For example, the correction unit can propose relevant correction measures based on information shared by the user on social media. The correction unit can also analyze the user's social media activity history and propose relevant correction measures. Furthermore, the correction unit can propose relevant correction measures based on the accounts the user follows on social media. In this way, relevant correction measures can be provided by analyzing the user's social media activity. Some or all of the above processing in the correction unit may be performed using AI, for example, or without AI. For example, the correction unit can input the user's social media activity data into a generating AI and have the generating AI execute the proposal of correction methods.

[0115] The translation unit can estimate the user's emotions and adjust the translation's expression based on those emotions. For example, if the user is stressed, the translation unit will use calmer language. If the user is relaxed, the translation unit can provide a more detailed translation. Furthermore, if the user is in a hurry, the translation unit can provide a concise translation. By adjusting the translation's expression based on the user's emotions, a more appropriate translation becomes possible. 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 AI, or not. For example, the translation unit can input user emotion data into the generative AI and have the generative AI adjust the translation expression based on the emotion.

[0116] The translation unit can adjust the level of detail of the translation based on the importance of the input during translation. For example, the translation unit will provide a detailed translation for important inputs. It can also provide a concise translation for less important inputs. Furthermore, the translation unit can provide a rapid translation for urgent inputs. This allows for detailed translations of important inputs by adjusting the level of detail based on the importance of the input. Some or all of the above processing in the translation unit may be performed using AI, for example, or without AI. For example, the translation unit can input input importance data into a generating AI and have the generating AI adjust the level of detail of the translation based on importance.

[0117] The translation unit can apply different translation algorithms depending on the input category during translation. For example, the translation unit can perform formal translations for business-related inputs, and relaxed translations for casual inputs. Furthermore, it can perform translations that include technical terms for technical inputs. By applying different translation algorithms depending on the input category, more appropriate translations can be achieved. Some or all of the above processing in the translation unit may be performed using AI, for example, or not. For example, the translation unit can input input category data into a generating AI and have the generating AI apply a translation algorithm appropriate to the category.

[0118] The translation unit can estimate the user's emotions and adjust the translation length based on the estimated emotions. For example, if the user is stressed, the translation unit will produce a short, concise translation. If the user is relaxed, the translation unit can produce a more detailed translation. Furthermore, if the user is in a hurry, the translation unit can produce a brief translation. By adjusting the translation length based on the user's emotions, a more appropriate translation becomes possible. 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 AI or not. For example, the translation unit can input user emotion data into the generative AI and have the generative AI adjust the translation length based on the emotions.

[0119] The translation unit can determine the order of translations based on the submission date of the inputs during the translation process. For example, the translation unit can prioritize translating urgent inputs. It can also quickly translate inputs with upcoming submission dates. Furthermore, it can perform detailed translations on inputs with later submission dates. This allows for quick translation of urgent inputs by determining the order of translations based on the submission date. Some or all of the above processes in the translation unit may be performed using AI, for example, or not. For example, the translation unit can input input submission date data into a generating AI and have the generating AI determine the order of translations based on the submission date.

[0120] The translation unit can determine the order of translations based on the relevance of the inputs during translation. For example, the translation unit will prioritize translating highly relevant inputs. It can also postpone translating less relevant inputs. Furthermore, the translation unit can perform detailed translations for highly relevant inputs. This allows for prioritizing the translation of highly relevant inputs by determining the order of translations based on their relevance. Some or all of the above processing in the translation unit may be performed using AI, for example, or without AI. For example, the translation unit can input relevance data of the inputs into a generating AI and have the generating AI perform the determination of the translation order based on relevance.

[0121] The output unit can estimate the user's emotions and adjust the output's presentation based on the estimated emotions. For example, if the user is stressed, the output unit will use calmer language. If the user is relaxed, the output unit can also provide more detailed output. Furthermore, if the user is in a hurry, the output unit can provide concise output. By adjusting the output's presentation based on the user's emotions, more appropriate output becomes possible. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the output unit may be performed using AI, or not. For example, the output unit can input user emotion data into a generative AI and have the generative AI adjust the output's presentation based on the emotion.

[0122] The output unit can analyze the user's past output history and select an appropriate output method at the time of output. For example, the output unit may preferentially suggest output methods that the user has used in the past. The output unit can also predict the optimal output method from the user's past output history. Furthermore, the output unit can suggest similar output methods by referring to content that the user has output in the past. In this way, the optimal output method can be provided by analyzing the user's past output history. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can input the user's past output history data into a generating AI and have the generating AI select an appropriate output method.

[0123] The output unit can customize the output method based on the user's current situation at the time of output. For example, the output unit can suggest the optimal output method based on the user's current situation. The output unit can also determine the output priority based on the user's current situation. Furthermore, the output unit can adjust the level of detail of the output based on the user's current situation. This allows for more appropriate output by customizing the output method based on the user's current situation. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can input the user's current situation data into a generating AI and have the generating AI perform the customization of the output method based on the situation.

[0124] The output unit can estimate the user's emotions and determine the order of outputs based on the estimated emotions. For example, if the user is stressed, the output unit will prioritize important outputs. If the user is relaxed, the output unit can also prioritize all outputs equally. Furthermore, if the user is in a hurry, the output unit can prioritize urgent outputs. In this way, important outputs can be prioritized by determining the priority of outputs based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the output unit may be performed using AI or not using AI. For example, the output unit can input user emotion data into a generative AI and have the generative AI determine the order of outputs based on emotions.

[0125] The output unit can select an appropriate output method when outputting data, taking into account the user's geographical location information. For example, if the user is in a specific region, the output unit can suggest an output method related to that region. Furthermore, if the user is traveling, the output unit can suggest an output method related to their travel destination. Additionally, if the user is at home, the output unit can suggest an output method related to their home. This allows the system to provide the optimal output method by considering the user's geographical location information. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can input the user's geographical location data into a generating AI and have the generating AI select an appropriate output method.

[0126] The output unit can analyze the user's social media activity and propose output methods at the time of output. For example, the output unit can propose relevant output methods based on information shared by the user on social media. The output unit can also analyze the user's social media activity history and propose relevant output methods. Furthermore, the output unit can propose relevant output methods based on accounts followed by the user on social media. In this way, relevant output methods can be provided by analyzing the user's social media activity. Some or all of the above processing in the output unit may be performed using AI, for example, or without AI. For example, the output unit can input the user's social media activity data into a generating AI and have the generating AI execute the proposal of output methods.

[0127] The evaluation unit can estimate the user's emotions and adjust the evaluation criteria based on the estimated emotions. For example, if the user is stressed, the evaluation unit can use mild criteria for evaluation. If the user is relaxed, the evaluation unit can use detailed criteria for evaluation. Furthermore, if the user is in a hurry, the evaluation unit can use concise criteria for evaluation. This allows for a more appropriate evaluation by adjusting the evaluation criteria based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI 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 evaluation unit may be performed using AI or not. For example, the evaluation unit can input user emotion data into a generative AI and have the generative AI adjust the evaluation criteria based on the emotions.

[0128] The evaluation unit can improve the accuracy of its evaluation by considering the interrelationships of the dialogue during the evaluation process. For example, the evaluation unit can analyze the flow of the dialogue and perform an evaluation while considering the interrelationships. It can also analyze the content of the dialogue and perform an evaluation while considering the interrelationships. Furthermore, the evaluation unit can analyze the statements of the dialogue participants and perform an evaluation while considering the interrelationships. In this way, the accuracy of the evaluation can be improved by considering the interrelationships of the dialogue. Some or all of the above processing in the evaluation unit may be performed using AI, for example, or without using AI. For example, the evaluation unit can input dialogue interrelationship data into a generating AI and have the generating AI perform an improvement in the accuracy of the evaluation based on the interrelationships.

[0129] The evaluation unit can perform evaluations while considering information about the dialogue participants. For example, the evaluation unit can perform evaluations while considering the age of the dialogue participants. It can also perform evaluations while considering the occupation of the dialogue participants. Furthermore, the evaluation unit can perform evaluations while considering the interests of the dialogue participants. This makes it possible to perform more appropriate evaluations by considering the attribute information of the dialogue participants. Some or all of the above processing in the evaluation unit may be performed using AI, for example, or without using AI. For example, the evaluation unit can input attribute information data of the dialogue participants into a generating AI and have the generating AI perform an evaluation based on the attribute information.

[0130] The evaluation unit can estimate the user's emotions and determine the order in which to display the evaluation results based on the estimated emotions. For example, if the user is feeling stressed, the evaluation unit can prioritize displaying important evaluation results. If the user is relaxed, the evaluation unit can also display all evaluation results equally. Furthermore, if the user is in a hurry, the evaluation unit can prioritize displaying evaluation results of high urgency. This allows for prioritizing the display of important evaluation results by adjusting the order in which evaluation results are displayed based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may 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 evaluation unit may be performed using AI, or not. For example, the evaluation unit can input user emotion data into a generative AI and have the generative AI determine the display order of evaluation results based on emotions.

[0131] The evaluation unit can perform evaluations based on the geographical distribution of dialogues. For example, if the dialogue participants are in different regions, the evaluation unit can perform evaluations considering the characteristics of those regions. Furthermore, if the dialogue participants are in the same region, the evaluation unit can perform evaluations considering the characteristics of that region. In addition, if the dialogue participants are concentrated in a particular region, the evaluation unit can perform evaluations considering the characteristics of that region. This allows for more appropriate evaluations by considering the geographical distribution of dialogues. Some or all of the above processing in the evaluation unit may be performed using AI, for example, or without AI. For example, the evaluation unit can input the geographical distribution data of dialogues into a generating AI and have the generating AI perform evaluations based on the geographical distribution.

[0132] The evaluation unit can improve the accuracy of its evaluation by referencing relevant literature related to the dialogue during the evaluation process. For example, the evaluation unit can perform its evaluation by referring to literature related to the content of the dialogue. It can also perform its evaluation by referring to literature related to the theme of the dialogue. Furthermore, the evaluation unit can perform its evaluation by referring to literature related to the statements made by the dialogue participants. In this way, the accuracy of the evaluation can be improved by referring to relevant literature related to the dialogue. Some or all of the above processing in the evaluation unit may be performed using AI, for example, or without using AI. For example, the evaluation unit can input dialogue-related literature data into a generating AI and have the generating AI perform an improvement in the accuracy of the evaluation based on the relevant literature.

[0133] The feedback unit can estimate the user's emotions and adjust the way it expresses feedback based on those emotions. For example, if the user is stressed, the feedback unit will provide feedback in a calm manner. If the user is relaxed, the feedback unit can provide detailed feedback. Furthermore, if the user is in a hurry, the feedback unit can provide concise feedback. This allows for more appropriate feedback by adjusting the expression of feedback based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may 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 feedback unit may be performed using AI, or not. For example, the feedback unit can input user emotion data into the generative AI and have the generative AI adjust the feedback expression based on those emotions.

[0134] The feedback unit can adjust the level of detail of the feedback based on the importance of the dialogue. For example, the feedback unit provides detailed feedback for important dialogues. It can also provide concise feedback for less important dialogues. Furthermore, the feedback unit can provide rapid feedback for urgent dialogues. This allows for detailed feedback on important dialogues by adjusting the level of detail based on the importance of the dialogue. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input dialogue importance data into a generating AI and have the generating AI adjust the level of detail of the feedback based on importance.

[0135] The feedback unit can apply a feedback algorithm according to the category of the dialogue during the feedback process. For example, the feedback unit can provide formal feedback for business-related dialogues, and relaxed feedback for casual dialogues. Furthermore, it can provide feedback that includes technical jargon for technical dialogues. By applying different feedback algorithms depending on the dialogue category, more appropriate feedback becomes possible. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input dialogue category data into a generating AI and have the generating AI apply a feedback algorithm according to the category.

[0136] The feedback unit can estimate the user's emotions and adjust the length of the feedback based on the estimated emotions. For example, if the user is stressed, the feedback unit can provide short, concise feedback. If the user is relaxed, the feedback unit can provide detailed feedback. Furthermore, if the user is in a hurry, the feedback unit can provide brief feedback. By adjusting the length of the feedback based on the user's emotions, more appropriate feedback becomes possible. 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 feedback unit may be performed using AI, or not using AI. For example, the feedback unit can input user emotion data into the generative AI and have the generative AI adjust the length of the feedback based on the emotion.

[0137] The feedback unit can determine the order of feedback based on the submission date of the dialogues. For example, the feedback unit can prioritize feedback for dialogues with high urgency. It can also provide rapid feedback for dialogues with upcoming submission dates. Furthermore, it can provide detailed feedback for dialogues with later submission dates. By determining the order of feedback based on the submission date of the dialogues, it is possible to provide rapid feedback for dialogues with high urgency. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input dialogue submission date data into a generating AI and have the generating AI determine the order of feedback based on the submission date.

[0138] The feedback unit can determine the order of feedback based on the relevance of the dialogues during the feedback process. For example, the feedback unit can prioritize feedback for highly relevant dialogues. It can also postpone feedback for less relevant dialogues. Furthermore, the feedback unit can provide detailed feedback for highly relevant dialogues. In this way, by determining the order of feedback based on the relevance of the dialogues, feedback can be prioritized for highly relevant dialogues. Some or all of the above processing in the feedback unit may be performed using AI, for example, or without AI. For example, the feedback unit can input dialogue relevance data into a generating AI and have the generating AI determine the order of feedback based on relevance.

[0139] The training unit can estimate the user's emotions and adjust the training method based on the estimated emotions. For example, if the user is stressed, the training unit can provide relaxing training content. It can also provide detailed training content if the user is relaxed. Furthermore, if the user is in a hurry, the training unit can provide concise training content. This allows for more appropriate training by adjusting the training content based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may 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 training unit may be performed using AI, or not. For example, the training unit can input user emotion data into a generative AI and have the generative AI adjust the training content based on the emotion.

[0140] The training unit can analyze the user's past training history during training to select an appropriate training method. For example, the training unit can prioritize suggesting training methods the user has used in the past. The training unit can also predict the optimal training method based on the user's past training history. Furthermore, the training unit can suggest similar training methods by referring to the content the user has trained on in the past. In this way, by analyzing the user's past training history, the optimal training method can be provided. Some or all of the above processing in the training unit may be performed using AI, for example, or without AI. For example, the training unit can input the user's past training history data into a generating AI and have the generating AI select an appropriate training method.

[0141] The training unit can customize the training method based on the user's current situation during training. For example, the training unit can suggest the optimal training method based on the user's current situation. The training unit can also determine the priority of training based on the user's current situation. Furthermore, the training unit can adjust the level of detail of the training based on the user's current situation. This allows for more appropriate training by customizing the training method based on the user's current situation. Some or all of the above processes in the training unit may be performed using AI, for example, or without AI. For example, the training unit can input the user's current situation data into a generating AI and have the generating AI perform the customization of the training method based on the situation.

[0142] The training unit can estimate the user's emotions and determine the order of training based on those emotions. For example, if the user is stressed, the training unit will prioritize important training. If the user is relaxed, the training unit can also distribute all training equally. Furthermore, if the user is in a hurry, the training unit can prioritize training of high urgency. This allows for prioritizing important training based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may 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 training unit may be performed using AI or not. For example, the training unit can input user emotion data into a generative AI and have the generative AI determine the order of training based on emotions.

[0143] The training unit can select an appropriate training method during training, taking into account the user's geographical location. For example, if the user is in a specific region, the training unit can suggest a training method relevant to that region. Furthermore, if the user is traveling, the training unit can suggest a training method relevant to their travel destination. Additionally, if the user is at home, the training unit can suggest a training method relevant to their home. This allows the system to provide the optimal training method by considering the user's geographical location. Some or all of the above processing in the training unit may be performed using AI, or without AI. For example, the training unit can input the user's geographical location data into a generating AI and have the generating AI select an appropriate training method.

[0144] The training unit can analyze a user's social media activity during training and propose training methods. For example, the training unit can propose relevant training methods based on information shared by the user on social media. The training unit can also analyze a user's social media activity history and propose relevant training methods. Furthermore, the training unit can propose relevant training methods based on the accounts the user follows on social media. In this way, relevant training methods can be provided by analyzing the user's social media activity. Some or all of the above processing in the training unit may be performed using AI, for example, or without AI. For example, the training unit can input the user's social media activity data into a generating AI and have the generating AI execute the proposal of training methods.

[0145] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0146] The AI ​​communication assistant analyzes the user's past conversation history and can predict the next statement based on the flow and content of the conversation. For example, if the user previously typed "Hello, what are your plans for today?", the AI ​​can predict "I have a meeting this afternoon" as the next statement. Similarly, if the user previously typed "Good work, how is the progress?", the AI ​​can predict "It's going smoothly" as the next statement. Furthermore, if the user previously typed "Good morning, what's the weather like today?", the AI ​​can predict "It's sunny" as the next statement. In this way, by analyzing the user's past conversation history, the AI ​​can predict the next statement and support smoother conversations.

[0147] AI communication assistants can customize the content of conversations by considering the profile information of the person the user is talking to. For example, if the person is a business partner, they can use formal language. If the person is a friend, they can use casual language. Furthermore, if the person is an expert, they can use language that includes technical terms. In this way, by considering the profile information of the person being spoken to, they can provide more appropriate conversation content.

[0148] AI communication assistants can estimate a user's emotions and adjust the tone of conversation based on those estimates. For example, if a user is stressed, the assistant can proceed with the conversation in a calm tone. If the user is relaxed, the assistant can proceed in a friendly tone. Furthermore, if the user is in a hurry, the assistant can proceed in a rapid tone. By adjusting the tone of conversation based on the user's emotions, more appropriate conversations become possible.

[0149] AI communication assistants can estimate the emotions of the person the user is talking to and adjust the content of the conversation based on those emotions. For example, if the person is angry, they can use calm language. If the person is happy, they can use positive language. Furthermore, if the person is sad, they can use comforting language. By adjusting the content of the conversation based on the emotions of the person being spoken to, more appropriate communication becomes possible.

[0150] The AI ​​communication assistant can analyze the past statements of the person the user is talking to and predict the flow of the conversation. For example, if the person previously said, "Hello, what are your plans for today?", it can predict the next statement to be, "I have a meeting this afternoon." Similarly, if the person previously said, "Good work today, how is the progress?", it can predict the next statement to be, "It's going smoothly." Furthermore, if the person previously said, "Good morning, what's the weather like today?", it can predict the next statement to be, "It's sunny." In this way, by analyzing the past statements of the person the user is talking to, it can predict the next statement and support smoother conversations.

[0151] AI communication assistants can customize the content of conversations by considering the cultural background of the person the user is talking to. For example, if the person is familiar with Japanese culture, the assistant will use expressions based on Japanese customs and etiquette. Similarly, if the person is familiar with American culture, the assistant can use expressions based on American customs and etiquette. Furthermore, if the person is familiar with French culture, the assistant can use expressions based on French customs and etiquette. This allows the assistant to provide more appropriate conversation content by considering the cultural background of the person they are talking to.

[0152] The AI ​​communication assistant can select conversation topics by considering the interests of the person the user is talking to. For example, if the person is interested in sports, it can select topics related to sports. Similarly, if the person is interested in music, it can select topics related to music. Furthermore, if the person is interested in travel, it can select topics related to travel. This allows the AI ​​to provide more appropriate conversation topics by considering the interests of the person it is talking to.

[0153] AI communication assistants can adjust the content of conversations by considering the language skills of the person the user is talking to. For example, if the person is a beginner, they will use simple expressions. If the person is an intermediate speaker, they can use slightly more complex expressions. Furthermore, if the person is an advanced speaker, they can use more advanced expressions. In this way, by considering the language skills of the person being spoken to, they can provide more appropriate conversation content.

[0154] The AI ​​communication assistant can estimate the emotions of the person the user is talking to and adjust the pace of the conversation based on that estimation. For example, if the person is stressed, the conversation will proceed at a slower pace. If the person is relaxed, the conversation can proceed at a normal pace. Furthermore, if the person is in a hurry, the conversation can proceed at a faster pace. By adjusting the pace of the conversation based on the emotions of the person talking to, a more appropriate conversation becomes possible.

[0155] The AI ​​communication assistant can analyze past feedback from the user's conversation partner and suggest ways to improve the conversation. For example, if the conversation partner previously commented that they wanted more specific questions, the AI ​​assistant will suggest more specific questions in the next conversation. Similarly, if the conversation partner previously commented that they wanted a more relaxed tone, the AI ​​assistant can suggest a more relaxed tone in the next conversation. Furthermore, if the conversation partner previously commented that they wanted a quicker response, the AI ​​assistant can suggest a quicker response in the next conversation. In this way, by analyzing past feedback from the conversation partner, the AI ​​assistant can suggest ways to improve the conversation and support better communication.

[0156] The following briefly describes the processing flow for example form 2.

[0157] Step 1: The reception desk accepts natural language input from the user. This natural language input may include, but is not limited to, English, Japanese, or other languages. The reception desk may also accept voice input or text input, for example. Step 2: The correction suggestion unit makes correction suggestions for the input received by the reception unit. The correction suggestion unit makes correction suggestions using methods such as grammatical correction, semantic correction, and style correction. For example, the correction suggestion unit can detect grammatical errors and make correction suggestions to the user. The correction suggestion unit can also detect semantic errors and make correction suggestions to the user. For example, the correction suggestion unit can detect grammatical errors using grammatical rules and syntactic analysis. Semantic errors can be detected using methods such as semantic analysis and contextual understanding. Step 3: The correction unit corrects the input received by the reception unit according to the user's response to the correction proposal from the correction proposal unit. For example, if the user corrects the input in response to the correction proposal, the correction unit reflects the result of that correction. Step 4: The translation unit translates the corrections made by the editing unit into a specific language. The translation unit may use machine translation to translate the corrections. The translation unit may translate into English, Japanese, or other languages. The translation unit takes into account the handling of technical terms and translation accuracy. Step 5: The output unit outputs the translation result from the translation unit in either audio or text. The output unit can output the translation result in audio, for example, using speech synthesis technology. Alternatively, the output unit can output the translation result in text using a text display method.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] For example, the reception unit is implemented by the reception device 38 of the smart device 14, which receives voice and text input from the user. The correction suggestion unit is implemented by the specific processing unit 290 of the data processing device 12, which detects grammatical and semantic errors and makes correction suggestions. The correction unit is implemented by the specific processing unit 290 of the data processing device 12, which corrects the input according to the user's response. The translation unit is implemented by the specific processing unit 290 of the data processing device 12, which translates the correction result into a specific language. The output unit is implemented by the output device 40 of the smart device 14, which outputs the translation result as voice or text. The correspondence between each unit and the devices and control units is not limited to the example described above, and various changes are possible.

[0162] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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).

[0168] 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.

[0169] 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.

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

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

[0172] In 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.

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

[0174] The specific processing unit 290 transmits the result of the specific processing to the 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.

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

[0176] The data processing system 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.

[0177] For example, the reception unit is implemented by the microphone 238 of the smart glasses 214 and receives voice input from the user. The correction suggestion unit is implemented by the specific processing unit 290 of the data processing device 12 and detects grammatical and semantic errors and makes correction suggestions. The correction unit is implemented by the specific processing unit 290 of the data processing device 12 and corrects the input according to the user's response. The translation unit is implemented by the specific processing unit 290 of the data processing device 12 and translates the correction result into a specific language. The output unit is implemented by the speaker 240 of the smart glasses 214 and outputs the translation result as voice. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0178] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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).

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.).

[0190] 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.

[0191] 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.

[0192] 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.

[0193] For example, the reception unit is implemented by the microphone 238 of the headset terminal 314 and receives voice input from the user. The correction suggestion unit is implemented by the specific processing unit 290 of the data processing device 12 and detects grammatical and semantic errors and makes correction suggestions. The correction unit is implemented by the specific processing unit 290 of the data processing device 12 and corrects the input according to the user's response. The translation unit is implemented by the specific processing unit 290 of the data processing device 12 and translates the correction result into a specific language. The output unit is implemented by the speaker 240 of the headset terminal 314 and outputs the translation result as voice. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0194] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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).

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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.).

[0207] 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.

[0208] 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.

[0209] 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.

[0210] For example, the reception unit is implemented by the microphone 238 of the robot 414 and receives voice input from the user. The correction suggestion unit is implemented by the specific processing unit 290 of the data processing device 12 and detects grammatical and semantic errors and makes correction suggestions. The correction unit is implemented by the specific processing unit 290 of the data processing device 12 and corrects the input according to the user's response. The translation unit is implemented by the specific processing unit 290 of the data processing device 12 and translates the correction result into a specific language. The output unit is implemented by the speaker 240 of the robot 414 and outputs the translation result as voice. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] 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."

[0217] 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.

[0218] 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.

[0219] 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.

[0220] 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.

[0221] 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.

[0222] 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.

[0223] 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.

[0224] 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.

[0225] 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.

[0226] 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.

[0227] 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.

[0228] 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.

[0229] (Note 1) A reception unit that accepts natural language input from users, A correction proposal unit that makes correction suggestions for input received by the aforementioned reception unit, A modification unit modifies the input received by the receiving unit in accordance with the user's response to the modification proposal made by the modification proposal unit, A translation unit that translates the results of the corrections made by the correction unit into language, The system includes an output unit that outputs the translation result from the translation unit as audio or text. A system characterized by the following features. (Note 2) The aforementioned reception unit is The system accepts input from the user's conversation partner. The aforementioned translation department, Translate the input from the aforementioned conversation partner, The output unit is, The translation unit outputs the translation result of the input from the conversation partner as audio or text. The system described in Appendix 1, characterized by the features described herein. (Note 3) An evaluation unit that evaluates the conversation, The system includes a feedback unit that provides feedback of the evaluation results from the evaluation unit to the user. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned revision proposal unit, Detects grammatical and semantic errors in the user's input. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned revision proposal unit, We will provide modification suggestions tailored to the user's situation. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned revision proposal unit, Analyzing the emotions of the person with whom we were having the conversation, Make revision suggestions based on emotions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned revision proposal unit, Provide correction suggestions tailored to the user's language skills. The system described in Appendix 1, characterized by the features described herein. (Note 8) We have a training department to improve communication skills. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reception unit is To estimate the user's emotions, Adjust the timing of input based on the estimated user's emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned reception unit is By analyzing the user's past input history, Select the appropriate application method. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned reception unit is When receiving input, Filter based on the user's situation and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned reception unit is To estimate the user's emotions, Prioritize input based on estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned reception unit is When receiving input, Prioritize input based on the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned reception unit is When receiving input, Analyze users' social media activity, Accept input The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned revision proposal unit, To estimate the user's emotions, Adjust the method of suggesting modifications based on estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned revision proposal unit, When proposing revisions, Adjust the details of the proposal based on the importance of the input. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned revision proposal unit, When proposing revisions, Apply the proposed algorithm according to the input category. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned revision proposal unit, To estimate the user's emotions, Adjust the suggested revisions based on estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned revision proposal unit, When proposing revisions, The order of proposals will be determined based on the submission date of the input. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned revision proposal unit, When proposing revisions, The order of proposals is determined based on the relevance of the inputs. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned modification section is, To estimate the user's emotions, Adjust the means of correction based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned modification section is, When making corrections, Analyze the user's past input history to select the appropriate correction method. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned modification section is, When making corrections, Customize the correction method based on the user's current situation. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned modification section is, To estimate the user's emotions, The order of modifications is determined based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned modification section is, When making corrections, Select the appropriate correction method considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned modification section is, When making corrections, We analyze users' social media activity and suggest ways to improve it. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned translation department, To estimate the user's emotions, The translation method is adjusted based on the estimated user's sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned translation department, When translating, Adjust translation details based on the importance of the input. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned translation department, When translating, Apply a translation algorithm based on the input category. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned translation department, To estimate the user's emotions, Adjust the content of the translation based on the presumed user sentiment The system according to Appendix 1, characterized by the above (Appendix 31) The translation unit When translating Determine the order of translation based on the submission time of the input The system according to Appendix 1, characterized by the above (Appendix 32) The translation unit When translating Determine the order of translation based on the relevance of the input The system according to Appendix 1, characterized by the above (Appendix 33) The output unit Presume the user sentiment Adjust the output method based on the presumed user sentiment The system according to Appendix 1, characterized by the above (Appendix 34) The output unit When outputting Analyze the user's past output history to select an appropriate output method The system according to Appendix 1, characterized by the above (Appendix 35) The output unit When outputting Customize the output method based on the user's current situation The system according to Appendix 1, characterized by the above (Appendix 36) The output unit Presume the user sentiment Determine the order of output based on the presumed user sentiment The system according to Appendix 1, characterized by the above (Appendix 37) The output unit When outputting Consider the user's geographical location information to select an appropriate output method The system according to Appendix 1, characterized by the above (Appendix 38) The output unit is, When outputting, We analyze users' social media activity and propose methods for outputting the results. The system described in Appendix 1, characterized by the features described herein. (Note 39) The evaluation unit, To estimate the user's emotions, Adjust the evaluation method based on estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 40) The evaluation unit, During the evaluation, Improve the accuracy of evaluation by considering the interrelationships of dialogue. The system described in Appendix 1, characterized by the features described herein. (Note 41) The evaluation unit, During the evaluation, The evaluation will take into account the information of the dialogue participants. The system described in Appendix 1, characterized by the features described herein. (Note 42) The evaluation unit, To estimate the user's emotions, The order in which evaluation results are displayed is determined based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 43) The evaluation unit, During the evaluation, The evaluation will be based on the geographical distribution of the dialogue. The system described in Appendix 1, characterized by the features described herein. (Note 44) The evaluation unit, During the evaluation, Improve the accuracy of evaluations based on relevant literature on dialogue. The system described in Appendix 1, characterized by the features described herein. (Note 45) The aforementioned feedback unit is To estimate the user's emotions, Adjust the feedback method based on estimated user sentiment. The system according to Appendix 1, characterized in that... (Appendix 46) The feedback unit During feedback, Adjusts the details of the feedback based on the importance of the conversation The system according to Appendix 1, characterized in that... (Appendix 47) The feedback unit During feedback, Applies a feedback algorithm according to the category of the conversation The system according to Appendix 1, characterized in that... (Appendix 48) The feedback unit Estimates the user's emotion Adjusts the content of the feedback based on the estimated user's emotion The system according to Appendix 1, characterized in that... (Appendix 49) The feedback unit During feedback, Determines the order of feedback based on the timing of the conversation submission The system according to Appendix 1, characterized in that... (Appendix 50) The feedback unit During feedback, Determines the order of feedback based on the relevance of the conversation The system according to Appendix 1, characterized in that... (Appendix 51) The training unit Estimates the user's emotion Adjusts the training method based on the estimated user's emotion The system according to Appendix 1, characterized in that... (Appendix 52) The training unit During training, Analyzes the user's past training history to select an appropriate training method The system described in Appendix 1, characterized by the features described herein. (Note 53) The aforementioned training department During training, Customize the training method based on the user's current status. The system described in Appendix 1, characterized by the features described herein. (Note 54) The aforementioned training department To estimate the user's emotions, The training sequence is determined based on the estimated user's emotions. The system described in Appendix 1, characterized by the features described herein. (Note 55) The aforementioned training department During training, Select an appropriate training method considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 56) The aforementioned training department During training, We analyze users' social media activity and suggest training methods. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0230] 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 unit that accepts natural language input from users, A correction proposal unit that makes correction suggestions for input received by the aforementioned reception unit, A modification unit modifies the input received by the receiving unit in accordance with the user's response to the modification proposal made by the modification proposal unit, A translation unit that translates the results of the corrections made by the correction unit into language, The system includes an output unit that outputs the translation result from the translation unit as audio or text. A system characterized by the following features.

2. The aforementioned reception unit is The system accepts input from the user's conversation partner. The aforementioned translation department, Translate the input from the aforementioned conversation partner, The output unit is, The translation unit outputs the translation result of the input from the conversation partner as audio or text. The system according to feature 1.

3. An evaluation unit that evaluates the conversation, The system includes a feedback unit that provides feedback of the evaluation results from the evaluation unit to the user. The system according to feature 1.

4. The aforementioned revision proposal unit, Detects grammatical and semantic errors in the user's input. The system according to feature 1.

5. The aforementioned revision proposal unit, We will provide modification suggestions tailored to the user's situation. The system according to feature 1.

6. The aforementioned revision proposal unit, Analyzing the emotions of the person with whom we were having the conversation, Make revision suggestions based on emotions. The system according to feature 2.

7. The aforementioned revision proposal unit, Provide correction suggestions tailored to the user's language skills. The system according to feature 1.

8. We have a training department to improve communication skills. The system according to feature 1.

Images