system

Abstract

The system according to the embodiment aims to translate conversations between airplane pilots and air traffic control systems in real time, extract important information, and reflect it in the operation of the aircraft. [Solution] The system according to the embodiment comprises a translation unit, an analysis unit, an automatic operation unit, a manual operation assistance unit, and an advice provision unit. The translation unit translates the conversation between the aircraft pilot and the air traffic control system in real time. The analysis unit analyzes the conversation translated by the translation unit and extracts important information. The automatic operation unit performs automatic operation of the aircraft based on the information extracted by the analysis unit. The manual operation assistance unit assists the operations performed by the automatic operation unit. The advice provision unit provides advice and suggestions in real time based on the operations assisted by the manual operation assistance unit.

Description

[Technical Field]

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

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

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technology does not adequately translate conversations between aircraft pilots and air traffic control systems in real time, extract important information, and incorporate it into aircraft operations; there is room for improvement.

[0005] The system according to the embodiment aims to translate conversations between airplane pilots and air traffic control systems in real time, extract important information, and reflect it in the operation of the aircraft. [Means for solving the problem]

[0006] The system according to the embodiment includes a translation unit, an analysis unit, an automatic operation unit, a manual operation assistance unit, and an advice providing unit. The translation unit translates conversations between an airplane pilot and an air traffic control system in real time. The analysis unit analyzes the conversations translated by the translation unit and extracts important information. The automatic operation unit automatically operates the aircraft based on the information extracted by the analysis unit. The manual operation assistance unit assists in operations performed by the automatic operation unit. The advice providing unit provides advice and suggestions in real time based on operations assisted by the manual operation assistance unit. [Effects of the Invention]

[0007] The system according to this embodiment can translate conversations between aircraft pilots and air traffic control systems in real time, extract important information, and reflect it in aircraft operations. [Brief explanation of the drawings]

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

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

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

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

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

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

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

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

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

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

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

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

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0024] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

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

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

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

[0028] (Example 1) An aircraft control system according to an embodiment of the present invention translates and analyzes conversations between airplane pilots and air traffic control systems in real time, interprets their emotions, and uses the results to simultaneously control (assist) the automatic and manual operation of the aircraft, ensuring safety. In this aircraft control system, a generation AI translates conversations between airplane pilots and air traffic control systems in real time into multiple languages, analyzes the translated conversations, and extracts important information. Furthermore, the generation AI interprets emotions from the conversations and determines the stress levels and urgency of the pilots and air traffic controllers. Based on this information, the generation AI controls the automatic and manual operation of the aircraft. Furthermore, the generation AI provides real-time, sequential advice and suggestions, proposing appropriate responses in emergencies. This ensures safe aircraft operation and facilitates smooth communication between pilots and air traffic controllers. Furthermore, the generation AI's real-time advice enables prompt and appropriate responses in emergencies, further improving aircraft safety. For example, the generation AI translates conversations between airplane pilots and air traffic control systems into multiple languages ​​in real time. For example, if a pilot speaks one language and an air traffic controller responds in another, the generative AI instantly translates it, ensuring smooth communication between the two. The generative AI then analyzes the translated conversation and extracts key information. For example, it analyzes information such as the aircraft's current position, speed, altitude, and destination to identify the necessary operations. Furthermore, the generative AI reads emotions from the conversation and determines the stress levels and urgency of the pilot and air traffic controller. For example, if a pilot is facing an emergency, the generative AI can sense the urgency and prompt a prompt response. Based on this information, the generative AI controls the aircraft's automatic and manual operations. For example, it automatically adjusts the aircraft's altitude or changes its course. Furthermore, when the pilot operates the aircraft manually, the generative AI provides appropriate advice and assists the pilot. Furthermore, the generative AI provides sequential advice and suggestions in real time. For example, it can suggest appropriate responses in an emergency and support the pilot's decisions. This improves aircraft safety and reduces the pilot's burden.This system ensures safe aircraft operation and facilitates smooth communication between pilots and air traffic controllers. Real-time advice from the generative AI also enables swift and appropriate response in emergencies, further improving aircraft safety. This allows the aircraft control system to translate and analyze conversations between the pilot and the air traffic control system in real time, read their emotions, and then simultaneously control (assist) the automatic and manual operation of the aircraft, ensuring safety.

[0029] An aircraft control system according to an embodiment includes a translation unit, an analysis unit, an automatic operation unit, a manual operation assistance unit, and an advice providing unit. The translation unit translates conversations between an airplane pilot and an air traffic control system in real time. For example, the translation unit translates conversations in different languages ​​in real time. For example, if a pilot speaks in English and an air traffic controller responds in French, the translation unit instantly translates the conversations, enabling smooth communication between the two parties. The translation unit can accurately translate the content of the conversation using a generation AI. The analysis unit analyzes the conversation translated by the translation unit and extracts important information. The analysis unit extracts information such as the airplane's current position, speed, altitude, and destination. For example, the analysis unit obtains the airplane's current position from GPS data, the speed from the aircraft's instrument data, the altitude from a barometric altimeter, and the destination from a flight plan. The analysis unit can analyze the content of the conversation and extract important information using a generation AI. The automatic operation unit automatically operates the aircraft based on the information extracted by the analysis unit. The automatic operation unit, for example, adjusts the altitude of the aircraft. For example, the automatic operation unit adjusts the altitude of the aircraft to a target altitude. The automatic operation unit can perform automatic operation of the aircraft using a generation AI. The manual operation assistance unit assists operations performed by the automatic operation unit. For example, the manual operation assistance unit provides appropriate advice when a pilot manually operates the aircraft. For example, the manual operation assistance unit displays operating procedures to the pilot. The manual operation assistance unit can assist the pilot's manual operation using a generation AI. The advice providing unit provides advice and suggestions in real time based on operations assisted by the manual operation assistance unit. For example, the advice providing unit suggests appropriate response methods in emergencies. For example, the advice providing unit suggests emergency landing procedures to the pilot. The advice providing unit can provide advice and suggestions in real time using a generation AI. As a result, the aircraft control system according to the embodiment can translate and analyze conversations between the aircraft pilot and the air traffic control system in real time, read emotions, and simultaneously control (assist) automatic and manual operations of the aircraft based on the emotions, thereby ensuring safety.

[0030] The translation unit can translate conversations in different languages ​​in real time. For example, if a pilot speaks in English and an air traffic controller replies in French, the translation unit can instantly translate this, allowing both parties to communicate smoothly. The translation unit can accurately translate the content of a conversation using a generation AI. For example, the generation AI uses a text generation AI (e.g., LLM) to translate conversations in different languages ​​in real time. The translation unit can also use a multimodal generation AI to translate speech and text simultaneously. For example, the generation AI uses speech recognition technology to convert the pilot's speech into text and then translate that text. This allows conversations in different languages ​​to be translated in real time, facilitating smooth communication between pilots and air traffic controllers.

[0031] The analysis unit can extract information about the aircraft's current position, speed, altitude, and destination from the translated conversation. For example, the analysis unit obtains the aircraft's current position from GPS data, its speed from the aircraft's instrument data, its altitude from a barometric altimeter, and its destination from a flight plan. The analysis unit can use a generation AI to analyze the content of the conversation and extract important information. For example, the generation AI uses a text generation AI (e.g., LLM) to extract information about the aircraft's current position, speed, altitude, and destination from the translated conversation. The analysis unit can also use a multimodal generation AI to simultaneously analyze speech and text. For example, the generation AI can use speech recognition technology to convert the pilot's speech into text and analyze the text. This can extract information such as the aircraft's current position, speed, altitude, and destination, thereby providing information for appropriate operation.

[0032] The automatic operation unit can adjust the altitude of the aircraft based on the extracted information. The automatic operation unit, for example, adjusts the altitude of the aircraft to a target altitude. For example, the automatic operation unit controls engine output and operates the elevators to adjust the altitude of the aircraft to the target altitude. The automatic operation unit can automatically operate the aircraft using a generation AI. For example, the generation AI uses a text generation AI (e.g., LLM) to adjust the altitude of the aircraft based on the extracted information. The automatic operation unit can also use a multimodal generation AI to simultaneously analyze voice and text and adjust the altitude of the aircraft. For example, the generation AI uses voice recognition technology to convert the pilot's voice into text and analyzes the text to adjust the altitude. This automatically adjusts the altitude of the aircraft, ensuring safe flight. Some or all of the above-mentioned processing in the automatic operation unit may be performed using AI, for example, or may be performed without using AI. For example, the automatic operation unit can input the extracted information to the generation AI and have the generation AI adjust the altitude.

[0033] The automatic operation unit can change the aircraft's course based on the extracted information. The automatic operation unit, for example, changes the aircraft's course to a target course. For example, the automatic operation unit controls engine output and operates the rudder to change the aircraft's course to the target course. The automatic operation unit can automatically operate the aircraft using a generation AI. For example, the generation AI uses a text generation AI (e.g., LLM) to change the aircraft's course based on the extracted information. The automatic operation unit can also use a multimodal generation AI to simultaneously analyze voice and text and change the aircraft's course. For example, the generation AI uses speech recognition technology to convert the pilot's voice into text and analyzes the text to change the course. This automatically changes the aircraft's course, ensuring a safe flight. Some or all of the above-mentioned processing in the automatic operation unit may be performed using AI, for example, or may be performed without using AI. For example, the automatic operation unit can input the extracted information to the generation AI and have the generation AI execute a course change.

[0034] The manual operation assistance unit can provide appropriate advice to the pilot when performing manual operation. The manual operation assistance unit can provide appropriate advice to the pilot when performing manual operation, for example. For example, the manual operation assistance unit can display operating procedures to the pilot. The manual operation assistance unit can use a generation AI to assist the pilot in manual operation. For example, the generation AI can use a text generation AI (e.g., LLM) to display operating procedures to the pilot. The manual operation assistance unit can also use a multimodal generation AI to simultaneously analyze voice and text and display operating procedures to the pilot. For example, the generation AI can use speech recognition technology to convert the pilot's voice into text, analyze the text, and display operating procedures. This can provide appropriate advice to the pilot when performing manual operation, thereby improving the accuracy of the operation. Some or all of the above-mentioned processing in the manual operation assistance unit can be performed using, for example, AI, or can be performed without using AI. For example, the manual operation assistance unit can input the pilot's voice into the generation AI and have the generation AI display operating procedures.

[0035] The advice providing unit can propose an appropriate response method in an emergency. The advice providing unit, for example, proposes an appropriate response method in an emergency. For example, the advice providing unit proposes an emergency landing procedure to the pilot. The advice providing unit can provide advice and suggestions in real time using a generation AI. For example, the generation AI uses a text generation AI (e.g., LLM) to propose an appropriate response method in an emergency. The advice providing unit can also use a multimodal generation AI to simultaneously analyze voice and text and propose an appropriate response method in an emergency. For example, the generation AI uses speech recognition technology to convert the pilot's voice into text, analyzes the text, and proposes an emergency landing procedure. This enables a prompt and appropriate response by proposing an appropriate response method in an emergency. Some or all of the above-described processing in the advice providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the advice providing unit can input the pilot's voice into the generation AI and have the generation AI execute a proposal for an emergency response method.

[0036] The translation unit can automatically recognize technical terms and abbreviations during translation and provide appropriate translations. For example, the translation unit can automatically recognize abbreviations specific to the aviation industry and provide appropriate translations. For example, the translation unit can automatically recognize technical terms used by pilots and provide accurate translations. The translation unit can also automatically recognize abbreviations used by air traffic controllers and provide appropriate translations. The translation unit can automatically recognize technical terms and abbreviations using generation AI and provide appropriate translations. For example, the generation AI can automatically recognize technical terms and abbreviations using text generation AI (e.g., LLM) and provide appropriate translations. The translation unit can also use multimodal generation AI to simultaneously analyze speech and text, recognize technical terms and abbreviations, and provide appropriate translations. For example, the generation AI can use speech recognition technology to convert the pilot's speech into text, analyze the text to recognize technical terms and abbreviations, and provide appropriate translations. This enables accurate information transmission by automatically recognizing technical terms and abbreviations and providing appropriate translations. Some or all of the above-described processing in the translation unit may be performed using, for example, AI, or may be performed without using AI. For example, the translation unit may input the pilot's voice into a generation AI and have the generation AI recognize and translate technical terms and abbreviations.

[0037] The translation unit can provide more natural translations by considering the context of the conversation during translation. For example, the translation unit can understand the flow of a conversation between a pilot and an air traffic controller and provide a natural translation that is appropriate to the context. For example, the translation unit can consider the context of the conversation and select appropriate expressions for translation. Furthermore, the translation unit can understand the intent of the conversation and provide a natural translation that is in line with the context. The translation unit can provide more natural translations by considering the context of the conversation using generative AI. For example, the generative AI uses text generation AI (e.g., LLM) to translate while considering the context of the conversation. Furthermore, the translation unit can also use multimodal generative AI to simultaneously analyze speech and text and provide a natural translation that is appropriate to the context. For example, the generative AI uses speech recognition technology to convert the pilot's speech into text, analyzes that text to understand the context, and provides a natural translation. This enables more natural communication by considering the context of the conversation during translation. Some or all of the above processes in the translation unit may be performed using AI, for example, or without AI. For example, the translation unit can input the pilot's voice into a generation AI and have the AI ​​perform a translation that takes context into account.

[0038] The translation unit can take regional expressions and dialects into consideration when translating. For example, the translation unit can recognize regional expressions used by pilots and provide appropriate translations. It can also recognize dialects used by air traffic controllers and provide accurate translations. Furthermore, the translation unit can consider regional expressions and provide natural-sounding translations. The translation unit can use generative AI to recognize regional expressions and dialects and provide appropriate translations. For example, the generative AI can use text generation AI (e.g., LLM) to recognize regional expressions and dialects and provide appropriate translations. The translation unit can also use multimodal generative AI to simultaneously analyze speech and text, recognize regional expressions and dialects, and provide appropriate translations. For example, the generative AI can use speech recognition technology to convert a pilot's speech into text, analyze that text to recognize regional expressions and dialects, and provide appropriate translations. This allows for more accurate information transmission by taking regional expressions and dialects into consideration when translating. Some or all of the above-described processes in the translation unit may be performed using AI, for example, or without AI. For example, the translation unit can input the pilot's voice into a generating AI and have the generating AI perform recognition and translation of regional expressions and dialects.

[0039] The translation unit can optimize real-time translation by considering the speed and rhythm of the conversation. For example, if a pilot speaks quickly, the generation AI can quickly translate at that speed. Similarly, if an air traffic controller speaks slowly, the generation AI can translate at that rhythm. Furthermore, the translation unit can optimize the translation in real time according to the speed of the conversation. The translation unit can optimize real-time translation by considering the speed and rhythm of the conversation using generation AI. For example, the generation AI can use text generation AI (e.g., LLM) to translate while considering the speed and rhythm of the conversation. The translation unit can also use multimodal generation AI to simultaneously analyze speech and text and optimize translation while considering the speed and rhythm of the conversation. For example, the generation AI can use speech recognition technology to convert the pilot's speech into text, analyze that text, and translate while considering the speed and rhythm of the conversation. This enables accurate information transmission in real time by considering the speed and rhythm of the conversation. 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 the pilot's voice into the generation AI and have the generation AI perform a translation that takes into account the speed and rhythm of the conversation.

[0040] The analysis unit can improve the accuracy of extracting important information by referring to past conversation data during analysis. For example, the analysis unit learns patterns for extracting important information based on past conversation data. The analysis unit can also refer to past conversation data and extract important information in similar situations. Furthermore, the analysis unit can analyze past conversation data to improve the accuracy of extracting important information. The analysis unit can use generative AI to refer to past conversation data and improve the accuracy of extracting important information. For example, the generative AI uses text generation AI (e.g., LLM) to refer to past conversation data and extract important information. The analysis unit can also use multimodal generative AI to simultaneously analyze speech and text and extract important information by referring to past conversation data. For example, the generative AI uses speech recognition technology to convert past conversation data into text, analyze that text, and extract important information. This improves the accuracy of extracting important information by referring to past conversation data. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input past conversation data into the generation AI and have the generation AI extract important information.

[0041] The analysis unit can extract more accurate information by considering the context of the conversation during analysis. For example, the analysis unit can understand the context of the conversation and extract important information based on that context. Furthermore, the analysis unit can understand the intent of the conversation and extract accurate information in line with the context. In addition, the analysis unit can consider the flow of the conversation and extract necessary information based on the context. The analysis unit can extract more accurate information by considering the context of the conversation using generative AI. For example, the generative AI uses text generation AI (e.g., LLM) to extract information while considering the context of the conversation. The analysis unit can also use multimodal generative AI to simultaneously analyze speech and text and extract accurate information based on the context. For example, the generative AI uses speech recognition technology to convert the pilot's speech into text, analyzes that text to understand the context, and extracts accurate information. This makes it possible to extract more accurate information by considering the context of the conversation during analysis. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the pilot's voice into the generation AI and have the generation AI extract information taking context into account.

[0042] The analysis unit can optimize the analysis in real time by taking into account the speed and rhythm of the conversation during analysis. For example, if a pilot speaks quickly, the analysis unit allows the generation AI to quickly perform analysis at a pace that matches the speed. Furthermore, if an air traffic controller speaks slowly, the analysis unit allows the generation AI to perform analysis at a pace that matches the rhythm. Furthermore, the analysis unit can optimize the analysis in real time according to the speed of the conversation. The analysis unit can optimize the analysis in real time by using the generation AI to take into account the speed and rhythm of the conversation. For example, the generation AI uses a text generation AI (e.g., LLM) to perform analysis taking into account the speed and rhythm of the conversation. Furthermore, the analysis unit can use a multimodal generation AI to simultaneously analyze speech and text and optimize the analysis taking into account the speed and rhythm of the conversation. For example, the generation AI uses speech recognition technology to convert the pilot's speech into text, analyzes the text, and performs analysis taking into account the speed and rhythm of the conversation. This makes it possible to extract appropriate information in real time by performing analysis taking into account the speed and rhythm of the conversation. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the pilot's voice into the generation AI and have the generation AI perform an analysis that takes into account the speed and rhythm of the conversation.

[0043] During analysis, the analysis unit can extract more detailed information by referring to background information of the conversation. For example, the analysis unit learns patterns for extracting important information based on the background information of the conversation. The analysis unit can also refer to the background information of the conversation to extract important information in similar situations. Furthermore, the analysis unit can analyze the background information of the conversation and improve the accuracy of extracting important information. The analysis unit can use a generation AI to refer to the background information of the conversation and improve the accuracy of extracting important information. For example, the generation AI uses a text generation AI (e.g., LLM) to refer to the background information of the conversation and extract important information. The analysis unit can also use a multimodal generation AI to simultaneously analyze speech and text and extract important information by referring to the background information of the conversation. For example, the generation AI uses speech recognition technology to convert the background information of the conversation into text and analyze the text to extract important information. As a result, by referring to the background information of the conversation, the accuracy of extracting important information is improved. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI or without AI. For example, the analysis unit can input background information about the conversation into the generating AI and have the generating AI extract important information.

[0044] During automatic operation, the automatic operation unit can improve the accuracy of operation by referring to past operation data. For example, the automatic operation unit learns the optimal operation method based on the past operation data. The automatic operation unit can also refer to the past operation data and perform the optimal operation in a similar situation. Furthermore, the automatic operation unit can analyze the past operation data and improve the accuracy of operation. The automatic operation unit can improve the accuracy of operation by referring to the past operation data using a generation AI. For example, the generation AI uses a text generation AI (e.g., LLM) to refer to the past operation data and learn the optimal operation method. The automatic operation unit can also use a multimodal generation AI to simultaneously analyze voice and text and perform the optimal operation by referring to the past operation data. For example, the generation AI uses voice recognition technology to convert the past operation data into text and analyzes the text to learn the optimal operation method. As a result, the accuracy of operation is improved by referring to the past operation data. Some or all of the above-mentioned processing in the automatic operation unit may be performed, for example, using AI or without AI. For example, the automatic operation unit can input past operation data into the generation AI and have the generation AI improve the accuracy of the operation.

[0045] During automatic operation, the automatic operation unit can monitor the current status of the aircraft in real time and perform optimal operations. For example, the automatic operation unit can monitor information such as the aircraft's altitude, speed, and position in real time and perform optimal operations. The automatic operation unit can also monitor the aircraft's engine status and fuel level in real time and perform necessary operations. Furthermore, the automatic operation unit can monitor the situation around the aircraft in real time and perform optimal operations. The automatic operation unit can use a generation AI to monitor the current status of the aircraft in real time and perform optimal operations. For example, the generation AI can use a text generation AI (e.g., LLM) to monitor information such as the aircraft's altitude, speed, and position in real time and perform optimal operations. The automatic operation unit can also use a multimodal generation AI to simultaneously analyze voice and text, monitor the current status of the aircraft in real time, and perform optimal operations. For example, the generation AI can use voice recognition technology to convert the aircraft's engine status and fuel level into text, analyze the text, and perform necessary operations. This makes it possible to monitor the current status of the aircraft in real time and perform optimal operations. Some or all of the above-described processing in the automatic operation unit may be performed using, for example, AI, or may be performed without using AI. For example, the automatic operation unit may input the current situation of the airplane into the generation AI and have the generation AI execute the optimal operation.

[0046] The automated control unit can perform optimal operations by considering the aircraft's geographical location information during automated operation. For example, if the aircraft is flying over mountainous terrain, the generating AI can adjust the altitude. Similarly, if the aircraft is flying over the sea, the generating AI can adjust the course. Furthermore, if the aircraft is flying over urban areas, the generating AI can adjust the speed. The automated control unit can use the generating AI to perform optimal operations by considering the aircraft's geographical location information. For example, the generating AI can use text generation AI (e.g., LLM) to perform operations while considering the aircraft's geographical location information. The automated control unit can also use multimodal generating AI to simultaneously analyze speech and text and perform operations while considering geographical location information. For example, the generating AI can use speech recognition technology to convert the aircraft's geographical location information into text, analyze that text, and perform optimal operations. This allows for safer flight by considering the aircraft's geographical location information during operation. Some or all of the above-described processes in the automated control unit may be performed using AI, or without AI. For example, the automatic operation unit can input the aircraft's geographical location information into the generation AI and have the generation AI perform the optimal operation.

[0047] The automated control unit can monitor the aircraft's surroundings in real time during automated operation and perform optimal maneuvers. For example, if another aircraft is approaching, the generating AI can change the aircraft's course. Furthermore, if adverse weather conditions occur around the aircraft, the generating AI can adjust the altitude. Additionally, if there are obstacles around the aircraft, the generating AI can perform evasive maneuvers. The automated control unit uses the generating AI to monitor the aircraft's surroundings in real time and perform optimal maneuvers. For example, the generating AI can use text generation AI (e.g., LLM) to monitor the aircraft's surroundings in real time and perform optimal maneuvers. The automated control unit can also use multimodal generating AI to simultaneously analyze speech and text, monitor the aircraft's surroundings in real time, and perform optimal maneuvers. For example, the generating AI can use speech recognition technology to convert the aircraft's surroundings into text, analyze that text, and perform optimal maneuvers. This allows for optimal maneuvers by monitoring the aircraft's surroundings in real time. Some or all of the above-described processing in the automatic operation unit may be performed using, for example, AI, or may be performed without using AI. For example, the automatic operation unit may input the situation around the airplane into the generation AI and have the generation AI perform the optimal operation.

[0048] The manual operation assistance unit can improve the accuracy of assistance by referring to past operation data when providing manual operation assistance. The manual operation assistance unit, for example, learns the optimal assistance method based on the past operation data. The manual operation assistance unit can also refer to the past operation data to provide optimal assistance in similar situations. Furthermore, the manual operation assistance unit can analyze the past operation data to improve the accuracy of assistance. The manual operation assistance unit can improve the accuracy of assistance by referring to the past operation data using a generation AI. For example, the generation AI uses a text generation AI (e.g., LLM) to refer to the past operation data and learn the optimal assistance method. The manual operation assistance unit can also use a multimodal generation AI to simultaneously analyze voice and text and provide optimal assistance by referring to the past operation data. For example, the generation AI uses voice recognition technology to convert the past operation data into text and analyzes the text to learn the optimal assistance method. As a result, the accuracy of assistance is improved by referring to the past operation data. Some or all of the above-described processing in the manual operation assistance unit may be performed, for example, using AI or without AI. For example, the manual operation assistance unit can input past operation data into the generation AI and cause the generation AI to improve the accuracy of assistance.

[0049] The manual operation assistance unit can monitor the current status of the aircraft in real time during manual operation assistance and provide optimal assistance. For example, the manual operation assistance unit can monitor information such as the aircraft's altitude, speed, and position in real time and provide optimal assistance. The manual operation assistance unit can also monitor the aircraft's engine status and fuel level in real time and provide necessary assistance. The manual operation assistance unit can also monitor the situation around the aircraft in real time and provide optimal assistance. The manual operation assistance unit can use a generation AI to monitor the current status of the aircraft in real time and provide optimal assistance. For example, the generation AI can use a text generation AI (e.g., LLM) to monitor information such as the aircraft's altitude, speed, and position in real time and provide optimal assistance. The manual operation assistance unit can also use a multimodal generation AI to simultaneously analyze voice and text, monitor the current status of the aircraft in real time, and provide optimal assistance. For example, the generation AI can use voice recognition technology to convert the aircraft's engine status and fuel level into text, analyze the text, and provide necessary assistance. This makes it possible to provide optimal assistance by monitoring the aircraft's current status in real time. Some or all of the above-described processes in the manual operation assistance unit may be performed using AI, for example, or without AI. For example, the manual operation assistance unit can input the current status of the aircraft into a generating AI and cause the generating AI to perform the optimal assistance.

[0050] The advice providing unit can improve the accuracy of advice by referring to past advice data when providing advice. The advice providing unit, for example, learns the optimal advice method based on past advice data. The advice providing unit can also refer to the past advice data and provide optimal advice for similar situations. The advice providing unit can analyze the past advice data and improve the accuracy of advice. The advice providing unit can improve the accuracy of advice by referring to the past advice data using a generation AI. For example, the generation AI uses a text generation AI (e.g., LLM) to refer to the past advice data and learn the optimal advice method. The advice providing unit can also use a multimodal generation AI to simultaneously analyze speech and text and provide optimal advice by referring to the past advice data. For example, the generation AI uses speech recognition technology to convert the past advice data into text and analyzes the text to learn the optimal advice method. As a result, the accuracy of advice is improved by referring to the past advice data. Some or all of the above-mentioned processing in the advice providing unit may be performed, for example, using AI or without using AI. For example, the advice provision unit can input past advice data into the generating AI and have the generating AI improve the accuracy of the advice.

[0051] The advice-providing unit can monitor the aircraft's current status in real time and provide optimal advice. For example, the advice-providing unit can monitor information such as the aircraft's altitude, speed, and position in real time and provide optimal advice. It can also monitor the aircraft's engine status and fuel level in real time and provide necessary advice. Furthermore, the advice-providing unit can monitor the aircraft's surroundings in real time and provide optimal advice. The advice-providing unit can use generative AI to monitor the aircraft's current status in real time and provide optimal advice. For example, the generative AI can use text generation AI (e.g., LLM) to monitor information such as the aircraft's altitude, speed, and position in real time and provide optimal advice. The advice-providing unit can also use multimodal generative AI to simultaneously analyze speech and text, monitor the aircraft's current status in real time, and provide optimal advice. For example, the generative AI can use speech recognition technology to convert the aircraft's engine status and fuel level into text, analyze that text, and provide necessary advice. This makes it possible to provide optimal advice by monitoring the aircraft's current status in real time. Some or all of the above-described processes in the advice provision unit may be performed using AI, for example, or without AI. For example, the advice provision unit can input the current status of the aircraft into a generating AI and have the generating AI execute the optimal advice.

[0052] When providing advice, the advice providing unit can provide optimal advice by taking into account the geographical location information of the aircraft. For example, if the aircraft is flying in a mountainous area, the generation AI can provide advice to adjust the altitude. Furthermore, if the aircraft is flying over the ocean, the generation AI can provide advice to adjust the course. Furthermore, if the aircraft is flying in an urban area, the generation AI can provide advice to adjust the speed. The advice providing unit can use the generation AI to provide optimal advice by taking into account the geographical location information of the aircraft. For example, the generation AI can use a text generation AI (e.g., LLM) to provide advice by taking into account the geographical location information of the aircraft. Furthermore, the advice providing unit can use a multimodal generation AI to simultaneously analyze speech and text and provide advice by taking into account the geographical location information. For example, the generation AI can use speech recognition technology to convert the geographical location information of the aircraft into text, analyze the text, and provide optimal advice. This allows for safer flights by providing advice by taking into account the geographical location information of the aircraft. Some or all of the above-described processing in the advice providing unit can be performed, for example, using AI, or can be performed without using AI. For example, the advice-providing unit can input the aircraft's geographical location information into a generating AI and have the AI ​​generate optimal advice.

[0053] When providing advice, the advice providing unit can monitor the situation around the aircraft in real time and provide optimal advice. For example, if another aircraft is approaching the aircraft, the advice providing unit can provide advice to change course. Furthermore, if bad weather is occurring around the aircraft, the advice providing unit can provide advice to adjust altitude. Furthermore, if there is an obstacle around the aircraft, the advice providing unit can provide advice to perform evasive maneuvers. The advice providing unit can use the generation AI to monitor the situation around the aircraft in real time and provide optimal advice. For example, the generation AI can use a text generation AI (e.g., LLM) to monitor the situation around the aircraft in real time and provide optimal advice. Furthermore, the advice providing unit can use a multimodal generation AI to simultaneously analyze voice and text, monitor the situation around the aircraft in real time, and provide optimal advice. For example, the generation AI can use voice recognition technology to convert the situation around the aircraft into text, analyze the text, and provide optimal advice. This makes it possible to provide optimal advice by monitoring the situation around the aircraft in real time. Some or all of the above-described processes in the advice provision unit may be performed using AI, for example, or without AI. For example, the advice provision unit can input the conditions around the aircraft into a generating AI and have the generating AI execute the optimal advice.

[0054] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0055] The aircraft control system may further include a weather information acquisition unit. The weather information acquisition unit collects weather data in real time and provides it to the analysis unit. For example, the weather information acquisition unit acquires weather information along the aircraft's route, and the analysis unit can optimize the aircraft's route based on that information. The weather information acquisition unit may also detect weather conditions that affect the aircraft's altitude, and the analysis unit may adjust the altitude based on that information. Furthermore, the weather information acquisition unit may monitor the weather conditions around the aircraft in real time, and the analysis unit may take appropriate action based on that information. This enables optimal flight according to weather conditions, improving aircraft safety.

[0056] The aircraft control system may further include a passenger information acquisition unit. The passenger information acquisition unit collects passenger statuses and requests and provides them to the analysis unit. For example, the passenger information acquisition unit may monitor the health status of passengers, and the analysis unit may take appropriate action based on the information. The passenger information acquisition unit may also collect information on passenger comfort, and the analysis unit may adjust the in-flight environment based on the information. Furthermore, the passenger information acquisition unit may collect passenger requests and feedback, and the analysis unit may improve services based on the information. This improves passenger comfort and safety and provides a better flight experience.

[0057] The aircraft control system may further include a fuel management unit. The fuel management unit monitors the fuel consumption of the aircraft in real time and provides the information to the analysis unit. For example, the fuel management unit monitors the remaining fuel level of the aircraft, and the analysis unit can create an optimal fuel consumption plan based on that information. The fuel management unit may also analyze the fuel consumption pattern of the aircraft, and the analysis unit may suggest operations to improve fuel efficiency based on that information. Furthermore, the fuel management unit may optimize the timing of refueling the aircraft, and the analysis unit may create an appropriate refueling plan based on that information. This enables efficient use of fuel and reduces the operating costs of the aircraft.

[0058] The aircraft control system may further include an aircraft status monitoring unit. The aircraft status monitoring unit monitors the aircraft's status in real time and provides the information to the analysis unit. For example, the aircraft status monitoring unit monitors the status of the aircraft's engines, and the analysis unit can propose appropriate maintenance based on that information. The aircraft status monitoring unit may also detect abnormalities in the aircraft's airframe structure, and the analysis unit can take prompt action based on that information. Furthermore, the aircraft status monitoring unit monitors the status of the entire aircraft system, and the analysis unit can create an optimal flight plan based on that information. This improves the safety and reliability of the aircraft and improves flight efficiency.

[0059] The aircraft control system may further include a crew support unit. The crew support unit supports the crew's work and provides information to the analysis unit. For example, the crew support unit manages the crew's work schedule, and the analysis unit can propose optimal work allocation based on that information. The crew support unit may also monitor the crew's health status, and the analysis unit may propose appropriate breaks and shifts based on that information. Furthermore, the crew support unit provides tools and resources to improve the crew's work efficiency, and the analysis unit can optimize the work based on that information. This reduces the crew's burden and improves work efficiency.

[0060] The processing flow of the first embodiment will be briefly explained below.

[0061] Step 1: The translation unit translates the conversation between the aircraft pilot and the air traffic control system in real time. For example, if the pilot speaks in English and the air traffic controller responds in French, the translation unit translates this instantly to ensure smooth communication between the two parties. The translation unit can use generative AI to accurately translate the content of the conversation. Step 2: The analysis unit analyzes the conversation translated by the translation unit and extracts important information, such as the plane's current position, speed, altitude, and destination. The analysis unit can use the generation AI to analyze the content of the conversation and extract important information. Step 3: The automated control unit performs automated aircraft control based on the information extracted by the analysis unit. For example, it adjusts the aircraft's altitude to a target altitude. The automated control unit can perform automated aircraft control using generated AI. Step 4: The manual operation assistance unit assists with operations performed by the automatic operation unit. For example, it provides appropriate advice when the pilot is performing manual operations. The manual operation assistance unit can use generated AI to assist the pilot's manual operations. Step 5: The advice-providing unit provides real-time advice and suggestions based on operations assisted by the manual operation support unit. For example, it suggests appropriate response methods in emergencies. The advice-providing unit can provide real-time advice and suggestions using generated AI.

[0062] (Example 2) An aircraft control system according to an embodiment of the present invention translates and analyzes conversations between airplane pilots and air traffic control systems in real time, interprets their emotions, and uses the results to simultaneously control (assist) the automatic and manual operation of the aircraft, ensuring safety. In this aircraft control system, a generation AI translates conversations between airplane pilots and air traffic control systems in real time into multiple languages, analyzes the translated conversations, and extracts important information. Furthermore, the generation AI interprets emotions from the conversations and determines the stress levels and urgency of the pilots and air traffic controllers. Based on this information, the generation AI controls the automatic and manual operation of the aircraft. Furthermore, the generation AI provides real-time, sequential advice and suggestions, proposing appropriate responses in emergencies. This ensures safe aircraft operation and facilitates smooth communication between pilots and air traffic controllers. Furthermore, the generation AI's real-time advice enables prompt and appropriate responses in emergencies, further improving aircraft safety. For example, the generation AI translates conversations between airplane pilots and air traffic control systems into multiple languages ​​in real time. For example, if a pilot speaks one language and an air traffic controller responds in another, the generative AI instantly translates it, ensuring smooth communication between the two. The generative AI then analyzes the translated conversation and extracts key information. For example, it analyzes information such as the aircraft's current position, speed, altitude, and destination to identify the necessary operations. Furthermore, the generative AI reads emotions from the conversation and determines the stress levels and urgency of the pilot and air traffic controller. For example, if a pilot is facing an emergency, the generative AI can sense the urgency and prompt a prompt response. Based on this information, the generative AI controls the aircraft's automatic and manual operations. For example, it automatically adjusts the aircraft's altitude or changes its course. Furthermore, when the pilot operates the aircraft manually, the generative AI provides appropriate advice and assists the pilot. Furthermore, the generative AI provides sequential advice and suggestions in real time. For example, it can suggest appropriate responses in an emergency and support the pilot's decisions. This improves aircraft safety and reduces the pilot's burden.This system ensures safe aircraft operation and facilitates smooth communication between pilots and air traffic controllers. Real-time advice from the generative AI also enables swift and appropriate response in emergencies, further improving aircraft safety. This allows the aircraft control system to translate and analyze conversations between the pilot and the air traffic control system in real time, read their emotions, and then simultaneously control (assist) the automatic and manual operation of the aircraft, ensuring safety.

[0063] An aircraft control system according to an embodiment includes a translation unit, an analysis unit, an automatic operation unit, a manual operation assistance unit, and an advice providing unit. The translation unit translates conversations between an airplane pilot and an air traffic control system in real time. For example, the translation unit translates conversations in different languages ​​in real time. For example, if a pilot speaks in English and an air traffic controller responds in French, the translation unit instantly translates the conversations, enabling smooth communication between the two parties. The translation unit can accurately translate the content of the conversation using a generation AI. The analysis unit analyzes the conversation translated by the translation unit and extracts important information. The analysis unit extracts information such as the airplane's current position, speed, altitude, and destination. For example, the analysis unit obtains the airplane's current position from GPS data, the speed from the aircraft's instrument data, the altitude from a barometric altimeter, and the destination from a flight plan. The analysis unit can analyze the content of the conversation and extract important information using a generation AI. The automatic operation unit automatically operates the aircraft based on the information extracted by the analysis unit. The automatic operation unit, for example, adjusts the altitude of the aircraft. For example, the automatic operation unit adjusts the altitude of the aircraft to a target altitude. The automatic operation unit can perform automatic operation of the aircraft using a generation AI. The manual operation assistance unit assists operations performed by the automatic operation unit. For example, the manual operation assistance unit provides appropriate advice when a pilot manually operates the aircraft. For example, the manual operation assistance unit displays operating procedures to the pilot. The manual operation assistance unit can assist the pilot's manual operation using a generation AI. The advice providing unit provides advice and suggestions in real time based on operations assisted by the manual operation assistance unit. For example, the advice providing unit suggests appropriate response methods in emergencies. For example, the advice providing unit suggests emergency landing procedures to the pilot. The advice providing unit can provide advice and suggestions in real time using a generation AI. As a result, the aircraft control system according to the embodiment can translate and analyze conversations between the aircraft pilot and the air traffic control system in real time, read emotions, and simultaneously control (assist) automatic and manual operations of the aircraft based on the emotions, thereby ensuring safety.

[0064] The translation unit can translate conversations in different languages ​​in real time. For example, if a pilot speaks in English and an air traffic controller replies in French, the translation unit can instantly translate this, allowing both parties to communicate smoothly. The translation unit can accurately translate the content of a conversation using a generation AI. For example, the generation AI uses a text generation AI (e.g., LLM) to translate conversations in different languages ​​in real time. The translation unit can also use a multimodal generation AI to translate speech and text simultaneously. For example, the generation AI uses speech recognition technology to convert the pilot's speech into text and then translate that text. This allows conversations in different languages ​​to be translated in real time, facilitating smooth communication between pilots and air traffic controllers.

[0065] The analysis unit can extract information about the aircraft's current position, speed, altitude, and destination from the translated conversation. For example, the analysis unit obtains the aircraft's current position from GPS data, its speed from the aircraft's instrument data, its altitude from a barometric altimeter, and its destination from a flight plan. The analysis unit can use a generation AI to analyze the content of the conversation and extract important information. For example, the generation AI uses a text generation AI (e.g., LLM) to extract information about the aircraft's current position, speed, altitude, and destination from the translated conversation. The analysis unit can also use a multimodal generation AI to simultaneously analyze speech and text. For example, the generation AI can use speech recognition technology to convert the pilot's speech into text and analyze the text. This can extract information such as the aircraft's current position, speed, altitude, and destination, thereby providing information for appropriate operation.

[0066] The analysis unit can analyze emotions from conversations and determine the stress level and urgency of pilots and air traffic controllers. The analysis unit can, for example, analyze the content of the conversation and the tone of voice to read the emotions of pilots and air traffic controllers. For example, if a pilot is facing an emergency, the analysis unit can sense the urgency and prompt a prompt response. The analysis unit can use a generation AI to analyze the content of the conversation and the tone of voice to read emotions. For example, the generation AI can analyze the content of the conversation and read emotions using a text generation AI (e.g., LLM). The analysis unit can also simultaneously analyze voice and text using a multimodal generation AI. For example, the generation AI can convert the pilot's voice into text using speech recognition technology and analyze the text. This can determine the stress level and urgency of the pilot or air traffic controller, thereby prompting an appropriate response. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may input the content of a conversation into the generation AI and have the generation AI estimate emotions.

[0067] The automatic operation unit can adjust the altitude of the aircraft based on the extracted information. The automatic operation unit, for example, adjusts the altitude of the aircraft to a target altitude. For example, the automatic operation unit controls engine output and operates the elevators to adjust the altitude of the aircraft to the target altitude. The automatic operation unit can automatically operate the aircraft using a generation AI. For example, the generation AI uses a text generation AI (e.g., LLM) to adjust the altitude of the aircraft based on the extracted information. The automatic operation unit can also use a multimodal generation AI to simultaneously analyze voice and text and adjust the altitude of the aircraft. For example, the generation AI uses voice recognition technology to convert the pilot's voice into text and analyzes the text to adjust the altitude. This automatically adjusts the altitude of the aircraft, ensuring safe flight. Some or all of the above-mentioned processing in the automatic operation unit may be performed using AI, for example, or may be performed without using AI. For example, the automatic operation unit can input the extracted information to the generation AI and have the generation AI adjust the altitude.

[0068] The automatic operation unit can change the aircraft's course based on the extracted information. The automatic operation unit, for example, changes the aircraft's course to a target course. For example, the automatic operation unit controls engine output and operates the rudder to change the aircraft's course to the target course. The automatic operation unit can automatically operate the aircraft using a generation AI. For example, the generation AI uses a text generation AI (e.g., LLM) to change the aircraft's course based on the extracted information. The automatic operation unit can also use a multimodal generation AI to simultaneously analyze voice and text and change the aircraft's course. For example, the generation AI uses speech recognition technology to convert the pilot's voice into text and analyzes the text to change the course. This automatically changes the aircraft's course, ensuring a safe flight. Some or all of the above-mentioned processing in the automatic operation unit may be performed using AI, for example, or may be performed without using AI. For example, the automatic operation unit can input the extracted information to the generation AI and have the generation AI execute a course change.

[0069] The manual operation assistance unit can provide appropriate advice to the pilot when performing manual operation. The manual operation assistance unit can provide appropriate advice to the pilot when performing manual operation, for example. For example, the manual operation assistance unit can display operating procedures to the pilot. The manual operation assistance unit can use a generation AI to assist the pilot in manual operation. For example, the generation AI can use a text generation AI (e.g., LLM) to display operating procedures to the pilot. The manual operation assistance unit can also use a multimodal generation AI to simultaneously analyze voice and text and display operating procedures to the pilot. For example, the generation AI can use speech recognition technology to convert the pilot's voice into text, analyze the text, and display operating procedures. This can provide appropriate advice to the pilot when performing manual operation, thereby improving the accuracy of the operation. Some or all of the above-mentioned processing in the manual operation assistance unit can be performed using, for example, AI, or can be performed without using AI. For example, the manual operation assistance unit can input the pilot's voice into the generation AI and have the generation AI display operating procedures.

[0070] The advice providing unit can propose an appropriate response method in an emergency. The advice providing unit, for example, proposes an appropriate response method in an emergency. For example, the advice providing unit proposes an emergency landing procedure to the pilot. The advice providing unit can provide advice and suggestions in real time using a generation AI. For example, the generation AI uses a text generation AI (e.g., LLM) to propose an appropriate response method in an emergency. The advice providing unit can also use a multimodal generation AI to simultaneously analyze voice and text and propose an appropriate response method in an emergency. For example, the generation AI uses speech recognition technology to convert the pilot's voice into text, analyzes the text, and proposes an emergency landing procedure. This enables a prompt and appropriate response by proposing an appropriate response method in an emergency. Some or all of the above-described processing in the advice providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the advice providing unit can input the pilot's voice into the generation AI and have the generation AI execute a proposal for an emergency response method.

[0071] The translation unit can estimate the emotions of pilots and air traffic controllers and adjust the tone and expression of the translation based on the estimated emotions. For example, if the pilot is nervous, the generation AI can translate in a calm tone and use reassuring expressions. If the air traffic controller is in a hurry, the generation AI can provide a quick and concise translation to instantly convey the necessary information. If the pilot is relaxed, the generation AI can translate in a friendly tone and use familiar expressions. The translation unit can use the generation AI to estimate the emotions of pilots and air traffic controllers and adjust the tone and expression of the translation based on that emotion. For example, the generation AI can use a text generation AI (e.g., LLM) to estimate emotions and adjust the tone and expression of the translation based on that emotion. The translation unit can also use multimodal generation AI to simultaneously analyze speech and text and adjust the tone and expression of the translation. For example, the generation AI can use speech recognition technology to convert the pilot's speech into text, analyze the text to estimate emotions, and adjust the tone and expression of the translation. This allows for more appropriate communication by adjusting the tone and expression of the translation based on the emotion. Emotion estimation is realized, for example, using an emotion estimation function using an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processing in the translation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the translation unit may input the pilot's voice into the generation AI and have the generation AI perform emotion estimation.

[0072] The translation unit can automatically recognize technical terms and abbreviations during translation and provide appropriate translations. For example, the translation unit can automatically recognize abbreviations specific to the aviation industry and provide appropriate translations. For example, the translation unit can automatically recognize technical terms used by pilots and provide accurate translations. The translation unit can also automatically recognize abbreviations used by air traffic controllers and provide appropriate translations. The translation unit can automatically recognize technical terms and abbreviations using generation AI and provide appropriate translations. For example, the generation AI can automatically recognize technical terms and abbreviations using text generation AI (e.g., LLM) and provide appropriate translations. The translation unit can also use multimodal generation AI to simultaneously analyze speech and text, recognize technical terms and abbreviations, and provide appropriate translations. For example, the generation AI can use speech recognition technology to convert the pilot's speech into text, analyze the text to recognize technical terms and abbreviations, and provide appropriate translations. This enables accurate information transmission by automatically recognizing technical terms and abbreviations and providing appropriate translations. Some or all of the above-described processing in the translation unit may be performed using, for example, AI, or may be performed without using AI. For example, the translation unit may input the pilot's voice into a generation AI and have the generation AI recognize and translate technical terms and abbreviations.

[0073] The translation unit can provide more natural translations by considering the context of the conversation during translation. For example, the translation unit can understand the flow of a conversation between a pilot and an air traffic controller and provide a natural translation that is appropriate to the context. For example, the translation unit can consider the context of the conversation and select appropriate expressions for translation. Furthermore, the translation unit can understand the intent of the conversation and provide a natural translation that is in line with the context. The translation unit can provide more natural translations by considering the context of the conversation using generative AI. For example, the generative AI uses text generation AI (e.g., LLM) to translate while considering the context of the conversation. Furthermore, the translation unit can also use multimodal generative AI to simultaneously analyze speech and text and provide a natural translation that is appropriate to the context. For example, the generative AI uses speech recognition technology to convert the pilot's speech into text, analyzes that text to understand the context, and provides a natural translation. This enables more natural communication by considering the context of the conversation during translation. Some or all of the above processes in the translation unit may be performed using AI, for example, or without AI. For example, the translation unit can input the pilot's voice into a generation AI and have the AI ​​perform a translation that takes context into account.

[0074] The translation unit can estimate the emotions of pilots and air traffic controllers and determine translation priorities based on the estimated emotions. For example, if a pilot is facing an emergency, the generation AI can prioritize translating that conversation. Furthermore, if a controller is feeling stressed, the generation AI can prioritize translating that conversation. Furthermore, if the pilot is relaxed, the generation AI can prioritize translating other important conversations. The translation unit can use the generation AI to estimate the emotions of pilots and air traffic controllers and determine translation priorities based on those emotions. For example, the generation AI can use a text generation AI (e.g., LLM) to estimate emotions and determine translation priorities based on those emotions. The translation unit can also use a multimodal generation AI to simultaneously analyze speech and text, estimate emotions, and determine translation priorities. For example, the generation AI can use speech recognition technology to convert the pilot's speech into text, analyze the text to estimate emotions, and determine translation priorities. This enables important information to be communicated quickly by prioritizing translations based on emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the translation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the translation unit may input the pilot's voice into the generation AI and have the generation AI perform emotion estimation and determine translation priorities.

[0075] The translation unit can take regional expressions and dialects into consideration when translating. For example, the translation unit can recognize regional expressions used by pilots and provide appropriate translations. It can also recognize dialects used by air traffic controllers and provide accurate translations. Furthermore, the translation unit can consider regional expressions and provide natural-sounding translations. The translation unit can use generative AI to recognize regional expressions and dialects and provide appropriate translations. For example, the generative AI can use text generation AI (e.g., LLM) to recognize regional expressions and dialects and provide appropriate translations. The translation unit can also use multimodal generative AI to simultaneously analyze speech and text, recognize regional expressions and dialects, and provide appropriate translations. For example, the generative AI can use speech recognition technology to convert a pilot's speech into text, analyze that text to recognize regional expressions and dialects, and provide appropriate translations. This allows for more accurate information transmission by taking regional expressions and dialects into consideration when translating. Some or all of the above-described processes in the translation unit may be performed using AI, for example, or without AI. For example, the translation unit can input the pilot's voice into a generating AI and have the generating AI perform recognition and translation of regional expressions and dialects.

[0076] The translation unit can optimize real-time translation by considering the speed and rhythm of the conversation. For example, if a pilot speaks quickly, the generation AI can quickly translate at that speed. Similarly, if an air traffic controller speaks slowly, the generation AI can translate at that rhythm. Furthermore, the translation unit can optimize the translation in real time according to the speed of the conversation. The translation unit can optimize real-time translation by considering the speed and rhythm of the conversation using generation AI. For example, the generation AI can use text generation AI (e.g., LLM) to translate while considering the speed and rhythm of the conversation. The translation unit can also use multimodal generation AI to simultaneously analyze speech and text and optimize translation while considering the speed and rhythm of the conversation. For example, the generation AI can use speech recognition technology to convert the pilot's speech into text, analyze that text, and translate while considering the speed and rhythm of the conversation. This enables accurate information transmission in real time by considering the speed and rhythm of the conversation. 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 the pilot's voice into the generation AI and have the generation AI perform a translation that takes into account the speed and rhythm of the conversation.

[0077] The analysis unit can estimate the emotions of pilots and air traffic controllers and adjust the accuracy of the analysis based on the estimated emotions. For example, if a pilot is tense, the generation AI will improve the accuracy of the analysis to ensure that important information is not missed. Similarly, if an air traffic controller is relaxed, the generation AI will adjust the accuracy of the analysis to appropriately extract the necessary information. Furthermore, if a pilot is stressed, the generation AI will improve the accuracy of the analysis to prioritize the extraction of high-priority information. The analysis unit can use generation AI to estimate the emotions of pilots and air traffic controllers and adjust the accuracy of the analysis based on those emotions. For example, the generation AI can use text generation AI (e.g., LLM) to estimate emotions and adjust the accuracy of the analysis based on those emotions. The analysis unit can also use multimodal generation AI to simultaneously analyze speech and text, estimate emotions, and adjust the accuracy of the analysis. For example, the generation AI can use speech recognition technology to convert the pilot's speech into text, analyze that text to estimate emotions, and adjust the accuracy of the analysis. This allows for the extraction of important information without missing anything by adjusting the accuracy of the analysis based on emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the pilot's voice into the generative AI and have the generative AI perform emotion estimation and adjust the accuracy of the analysis.

[0078] The analysis unit can improve the accuracy of extracting important information by referring to past conversation data during analysis. For example, the analysis unit learns patterns for extracting important information based on past conversation data. The analysis unit can also refer to past conversation data and extract important information in similar situations. Furthermore, the analysis unit can analyze past conversation data to improve the accuracy of extracting important information. The analysis unit can use generative AI to refer to past conversation data and improve the accuracy of extracting important information. For example, the generative AI uses text generation AI (e.g., LLM) to refer to past conversation data and extract important information. The analysis unit can also use multimodal generative AI to simultaneously analyze speech and text and extract important information by referring to past conversation data. For example, the generative AI uses speech recognition technology to convert past conversation data into text, analyze that text, and extract important information. This improves the accuracy of extracting important information by referring to past conversation data. Some or all of the above processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input past conversation data into the generation AI and have the generation AI extract important information.

[0079] The analysis unit can extract more accurate information by considering the context of the conversation during analysis. For example, the analysis unit can understand the context of the conversation and extract important information based on that context. Furthermore, the analysis unit can understand the intent of the conversation and extract accurate information in line with the context. In addition, the analysis unit can consider the flow of the conversation and extract necessary information based on the context. The analysis unit can extract more accurate information by considering the context of the conversation using generative AI. For example, the generative AI uses text generation AI (e.g., LLM) to extract information while considering the context of the conversation. The analysis unit can also use multimodal generative AI to simultaneously analyze speech and text and extract accurate information based on the context. For example, the generative AI uses speech recognition technology to convert the pilot's speech into text, analyzes that text to understand the context, and extracts accurate information. This makes it possible to extract more accurate information by considering the context of the conversation during analysis. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the pilot's voice into the generation AI and have the generation AI extract information taking context into account.

[0080] The analysis unit can estimate the emotions of pilots and air traffic controllers and adjust the display method of the analysis results based on the estimated emotions. For example, if a pilot is tense, the generating AI can provide a simple and highly visible display method. If an air traffic controller is relaxed, the analysis unit can provide a display method that includes detailed information. Furthermore, if a pilot is in a hurry, the analysis unit can provide a display method that gets straight to the point. The analysis unit can use the generating AI to estimate the emotions of pilots and air traffic controllers and adjust the display method of the analysis results based on those emotions. For example, the generating AI can use text generation AI (e.g., LLM) to estimate emotions and adjust the display method based on those emotions. The analysis unit can also use multimodal generating AI to simultaneously analyze speech and text, estimate emotions, and adjust the display method. For example, the generating AI can use speech recognition technology to convert the pilot's speech into text, analyze that text to estimate emotions, and adjust the display method. This allows for the provision of highly visible information by adjusting the display method of the analysis results based on emotions. Emotion estimation is achieved using an emotion estimation function, for example, with 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 analysis unit may be performed using AI or not using AI. For example, the analysis unit can input the pilot's voice into the generative AI and have the generative AI perform emotion estimation and adjustment of the display method.

[0081] The analysis unit can optimize the analysis in real time by taking into account the speed and rhythm of the conversation during analysis. For example, if a pilot speaks quickly, the analysis unit allows the generation AI to quickly perform analysis at a pace that matches the speed. Furthermore, if an air traffic controller speaks slowly, the analysis unit allows the generation AI to perform analysis at a pace that matches the rhythm. Furthermore, the analysis unit can optimize the analysis in real time according to the speed of the conversation. The analysis unit can optimize the analysis in real time by using the generation AI to take into account the speed and rhythm of the conversation. For example, the generation AI uses a text generation AI (e.g., LLM) to perform analysis taking into account the speed and rhythm of the conversation. Furthermore, the analysis unit can use a multimodal generation AI to simultaneously analyze speech and text and optimize the analysis taking into account the speed and rhythm of the conversation. For example, the generation AI uses speech recognition technology to convert the pilot's speech into text, analyzes the text, and performs analysis taking into account the speed and rhythm of the conversation. This makes it possible to extract appropriate information in real time by performing analysis taking into account the speed and rhythm of the conversation. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the pilot's voice into the generation AI and have the generation AI perform an analysis that takes into account the speed and rhythm of the conversation.

[0082] During analysis, the analysis unit can extract more detailed information by referring to background information of the conversation. For example, the analysis unit learns patterns for extracting important information based on the background information of the conversation. The analysis unit can also refer to the background information of the conversation to extract important information in similar situations. Furthermore, the analysis unit can analyze the background information of the conversation and improve the accuracy of extracting important information. The analysis unit can use a generation AI to refer to the background information of the conversation and improve the accuracy of extracting important information. For example, the generation AI uses a text generation AI (e.g., LLM) to refer to the background information of the conversation and extract important information. The analysis unit can also use a multimodal generation AI to simultaneously analyze speech and text and extract important information by referring to the background information of the conversation. For example, the generation AI uses speech recognition technology to convert the background information of the conversation into text and analyze the text to extract important information. As a result, by referring to the background information of the conversation, the accuracy of extracting important information is improved. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI or without AI. For example, the analysis unit can input background information about the conversation into the generating AI and have the generating AI extract important information.

[0083] The automated control unit can estimate the emotions of pilots and air traffic controllers and determine the priority of automated operations based on those estimated emotions. For example, if a pilot is facing an emergency, the generating AI will prioritize that operation. Similarly, if an air traffic controller is feeling stressed, the generating AI will prioritize that operation. Furthermore, if a pilot is relaxed, the generating AI can prioritize other important operations. The automated control unit can use the generating AI to estimate the emotions of pilots and air traffic controllers and determine the priority of automated operations based on those emotions. For example, the generating AI can use text generation AI (e.g., LLM) to estimate emotions and determine the priority of automated operations based on those emotions. The automated control unit can also use multimodal generating AI to simultaneously analyze speech and text, estimate emotions, and determine the priority of automated operations. For example, the generating AI can use speech recognition technology to convert the pilot's speech into text, analyze that text to estimate emotions, and determine the priority of automated operations. This allows for the rapid execution of critical operations by prioritizing automated operations based on 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 automated operation unit may be performed using AI or not. For example, the automated operation unit can input the pilot's voice into a generative AI and have the generative AI perform emotion estimation and determine the priority of automated operations.

[0084] During automatic operation, the automatic operation unit can improve the accuracy of operation by referring to past operation data. For example, the automatic operation unit learns the optimal operation method based on the past operation data. The automatic operation unit can also refer to the past operation data and perform the optimal operation in a similar situation. Furthermore, the automatic operation unit can analyze the past operation data and improve the accuracy of operation. The automatic operation unit can improve the accuracy of operation by referring to the past operation data using a generation AI. For example, the generation AI uses a text generation AI (e.g., LLM) to refer to the past operation data and learn the optimal operation method. The automatic operation unit can also use a multimodal generation AI to simultaneously analyze voice and text and perform the optimal operation by referring to the past operation data. For example, the generation AI uses voice recognition technology to convert the past operation data into text and analyzes the text to learn the optimal operation method. As a result, the accuracy of operation is improved by referring to the past operation data. Some or all of the above-mentioned processing in the automatic operation unit may be performed, for example, using AI or without AI. For example, the automatic operation unit can input past operation data into the generation AI and have the generation AI improve the accuracy of the operation.

[0085] During automatic operation, the automatic operation unit can monitor the current status of the aircraft in real time and perform optimal operations. For example, the automatic operation unit can monitor information such as the aircraft's altitude, speed, and position in real time and perform optimal operations. The automatic operation unit can also monitor the aircraft's engine status and fuel level in real time and perform necessary operations. Furthermore, the automatic operation unit can monitor the situation around the aircraft in real time and perform optimal operations. The automatic operation unit can use a generation AI to monitor the current status of the aircraft in real time and perform optimal operations. For example, the generation AI can use a text generation AI (e.g., LLM) to monitor information such as the aircraft's altitude, speed, and position in real time and perform optimal operations. The automatic operation unit can also use a multimodal generation AI to simultaneously analyze voice and text, monitor the current status of the aircraft in real time, and perform optimal operations. For example, the generation AI can use voice recognition technology to convert the aircraft's engine status and fuel level into text, analyze the text, and perform necessary operations. This makes it possible to monitor the current status of the aircraft in real time and perform optimal operations. Some or all of the above-described processing in the automatic operation unit may be performed using, for example, AI, or may be performed without using AI. For example, the automatic operation unit may input the current situation of the airplane into the generation AI and have the generation AI execute the optimal operation.

[0086] The automated control unit can estimate the emotions of pilots and air traffic controllers and adjust the automated control method based on the estimated emotions. For example, if the pilot is tense, the generating AI can select a cautious control method. If the air traffic controller is relaxed, the generating AI can select a normal control method. Furthermore, if the pilot is in a hurry, the generating AI can select a rapid control method. The automated control unit can use the generating AI to estimate the emotions of pilots and air traffic controllers and adjust the automated control method based on those emotions. For example, the generating AI can use text generation AI (e.g., LLM) to estimate emotions and adjust the control method based on those emotions. The automated control unit can also use multimodal generating AI to simultaneously analyze speech and text to estimate emotions and adjust the control method. For example, the generating AI can use speech recognition technology to convert the pilot's speech into text, analyze that text to estimate emotions, and adjust the control method. This allows for more appropriate operation by adjusting the automated control method based on emotions. Emotion estimation is achieved using an emotion estimation function, for example, by 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 automated operation unit may be performed using AI, for example, or without AI. For example, the automated operation unit can input the pilot's voice into the generative AI and have the generative AI perform emotion estimation and adjustment of the operation method.

[0087] The automated control unit can perform optimal operations by considering the aircraft's geographical location information during automated operation. For example, if the aircraft is flying over mountainous terrain, the generating AI can adjust the altitude. Similarly, if the aircraft is flying over the sea, the generating AI can adjust the course. Furthermore, if the aircraft is flying over urban areas, the generating AI can adjust the speed. The automated control unit can use the generating AI to perform optimal operations by considering the aircraft's geographical location information. For example, the generating AI can use text generation AI (e.g., LLM) to perform operations while considering the aircraft's geographical location information. The automated control unit can also use multimodal generating AI to simultaneously analyze speech and text and perform operations while considering geographical location information. For example, the generating AI can use speech recognition technology to convert the aircraft's geographical location information into text, analyze that text, and perform optimal operations. This allows for safer flight by considering the aircraft's geographical location information during operation. Some or all of the above-described processes in the automated control unit may be performed using AI, or without AI. For example, the automatic operation unit can input the aircraft's geographical location information into the generation AI and have the generation AI perform the optimal operation.

[0088] The automated control unit can monitor the aircraft's surroundings in real time during automated operation and perform optimal maneuvers. For example, if another aircraft is approaching, the generating AI can change the aircraft's course. Furthermore, if adverse weather conditions occur around the aircraft, the generating AI can adjust the altitude. Additionally, if there are obstacles around the aircraft, the generating AI can perform evasive maneuvers. The automated control unit uses the generating AI to monitor the aircraft's surroundings in real time and perform optimal maneuvers. For example, the generating AI can use text generation AI (e.g., LLM) to monitor the aircraft's surroundings in real time and perform optimal maneuvers. The automated control unit can also use multimodal generating AI to simultaneously analyze speech and text, monitor the aircraft's surroundings in real time, and perform optimal maneuvers. For example, the generating AI can use speech recognition technology to convert the aircraft's surroundings into text, analyze that text, and perform optimal maneuvers. This allows for optimal maneuvers by monitoring the aircraft's surroundings in real time. Some or all of the above-described processing in the automatic operation unit may be performed using, for example, AI, or may be performed without using AI. For example, the automatic operation unit may input the situation around the airplane into the generation AI and have the generation AI perform the optimal operation.

[0089] The manual operation assistance unit can estimate the emotions of pilots and air traffic controllers and adjust its manual operation assistance methods based on the estimated emotions. For example, if the pilot is tense, the generating AI can provide cautious assistance. If the air traffic controller is relaxed, the generating AI can provide normal assistance. Furthermore, if the pilot is in a hurry, the generating AI can provide rapid assistance. The manual operation assistance unit can use the generating AI to estimate the emotions of pilots and air traffic controllers and adjust its manual operation assistance methods based on those emotions. For example, the generating AI can use text generation AI (e.g., LLM) to estimate emotions and adjust its assistance methods based on those emotions. The manual operation assistance unit can also use multimodal generating AI to simultaneously analyze speech and text, estimate emotions, and adjust its assistance methods. For example, the generating AI can use speech recognition technology to convert the pilot's speech into text, analyze that text to estimate emotions, and adjust its assistance methods. This allows for more appropriate assistance by adjusting the manual operation assistance methods based on emotions. Emotion estimation is achieved using an emotion estimation function, for example, by 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 manual operation assistance unit may be performed using AI, for example, or without AI. For example, the manual operation assistance unit can input the pilot's voice into the generative AI and have the generative AI perform emotion estimation and adjustment of the assistance method.

[0090] The manual operation assistance unit can improve the accuracy of assistance by referring to past operation data when providing manual operation assistance. The manual operation assistance unit, for example, learns the optimal assistance method based on the past operation data. The manual operation assistance unit can also refer to the past operation data to provide optimal assistance in similar situations. Furthermore, the manual operation assistance unit can analyze the past operation data to improve the accuracy of assistance. The manual operation assistance unit can improve the accuracy of assistance by referring to the past operation data using a generation AI. For example, the generation AI uses a text generation AI (e.g., LLM) to refer to the past operation data and learn the optimal assistance method. The manual operation assistance unit can also use a multimodal generation AI to simultaneously analyze voice and text and provide optimal assistance by referring to the past operation data. For example, the generation AI uses voice recognition technology to convert the past operation data into text and analyzes the text to learn the optimal assistance method. As a result, the accuracy of assistance is improved by referring to the past operation data. Some or all of the above-described processing in the manual operation assistance unit may be performed, for example, using AI or without AI. For example, the manual operation assistance unit can input past operation data into the generation AI and cause the generation AI to improve the accuracy of assistance.

[0091] The manual operation assistance unit can estimate the emotions of pilots and air traffic controllers and determine the priority of manual operations based on those estimated emotions. For example, if a pilot is facing an emergency, the generating AI will prioritize assisting with that operation. Similarly, if an air traffic controller is feeling stressed, the generating AI can prioritize assisting with that operation. Furthermore, if a pilot is relaxed, the generating AI can prioritize assisting with other important operations. The manual operation assistance unit can use the generating AI to estimate the emotions of pilots and air traffic controllers and determine the priority of manual operations based on those emotions. For example, the generating AI can use text generation AI (e.g., LLM) to estimate emotions and determine the priority of manual operations based on those emotions. The manual operation assistance unit can also use multimodal generating AI to simultaneously analyze speech and text, estimate emotions, and determine the priority of manual operations. For example, the generating AI can use speech recognition technology to convert the pilot's speech into text, analyze that text to estimate emotions, and determine the priority of manual operations. This allows for the rapid assistance of critical operations by prioritizing manual operations based on 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 manual operation assistance unit may be performed using AI, for example, or without AI. For example, the manual operation assistance unit can input the pilot's voice into the generative AI and have the generative AI perform emotion estimation and determination of manual operation priorities.

[0092] The manual operation assistance unit can monitor the current status of the aircraft in real time during manual operation assistance and provide optimal assistance. For example, the manual operation assistance unit can monitor information such as the aircraft's altitude, speed, and position in real time and provide optimal assistance. The manual operation assistance unit can also monitor the aircraft's engine status and fuel level in real time and provide necessary assistance. The manual operation assistance unit can also monitor the situation around the aircraft in real time and provide optimal assistance. The manual operation assistance unit can use a generation AI to monitor the current status of the aircraft in real time and provide optimal assistance. For example, the generation AI can use a text generation AI (e.g., LLM) to monitor information such as the aircraft's altitude, speed, and position in real time and provide optimal assistance. The manual operation assistance unit can also use a multimodal generation AI to simultaneously analyze voice and text, monitor the current status of the aircraft in real time, and provide optimal assistance. For example, the generation AI can use voice recognition technology to convert the aircraft's engine status and fuel level into text, analyze the text, and provide necessary assistance. This makes it possible to provide optimal assistance by monitoring the aircraft's current status in real time. Some or all of the above-described processes in the manual operation assistance unit may be performed using AI, for example, or without AI. For example, the manual operation assistance unit can input the current status of the aircraft into a generating AI and cause the generating AI to perform the optimal assistance.

[0093] The advice-providing unit can estimate the emotions of pilots and air traffic controllers and adjust the content of the advice based on those estimated emotions. For example, if a pilot is nervous, the generating AI will provide advice in a calm tone. If an air traffic controller is relaxed, the generating AI can provide detailed advice. Furthermore, if a pilot is in a hurry, the generating AI can provide quick and concise advice. The advice-providing unit can use the generating AI to estimate the emotions of pilots and air traffic controllers and adjust the content of the advice based on those emotions. For example, the generating AI can use text generation AI (e.g., LLM) to estimate emotions and adjust the content of the advice based on those emotions. The advice-providing unit can also use multimodal generating AI to simultaneously analyze speech and text, estimate emotions, and adjust the content of the advice. For example, the generating AI can use speech recognition technology to convert the pilot's speech into text, analyze that text to estimate emotions, and adjust the content of the advice. This allows for more appropriate advice by adjusting the content of the advice based on emotions. Emotion estimation is achieved using an emotion estimation function, for example, by 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 advice provision unit may be performed using AI, for example, or without AI. For example, the advice provision unit can input the pilot's voice into the generative AI and have the generative AI perform emotion estimation and adjust the content of the advice.

[0094] The advice providing unit can improve the accuracy of advice by referring to past advice data when providing advice. The advice providing unit, for example, learns the optimal advice method based on past advice data. The advice providing unit can also refer to the past advice data and provide optimal advice for similar situations. The advice providing unit can analyze the past advice data and improve the accuracy of advice. The advice providing unit can improve the accuracy of advice by referring to the past advice data using a generation AI. For example, the generation AI uses a text generation AI (e.g., LLM) to refer to the past advice data and learn the optimal advice method. The advice providing unit can also use a multimodal generation AI to simultaneously analyze speech and text and provide optimal advice by referring to the past advice data. For example, the generation AI uses speech recognition technology to convert the past advice data into text and analyzes the text to learn the optimal advice method. As a result, the accuracy of advice is improved by referring to the past advice data. Some or all of the above-mentioned processing in the advice providing unit may be performed, for example, using AI or without using AI. For example, the advice provision unit can input past advice data into the generating AI and have the generating AI improve the accuracy of the advice.

[0095] The advice-providing unit can monitor the aircraft's current status in real time and provide optimal advice. For example, the advice-providing unit can monitor information such as the aircraft's altitude, speed, and position in real time and provide optimal advice. It can also monitor the aircraft's engine status and fuel level in real time and provide necessary advice. Furthermore, the advice-providing unit can monitor the aircraft's surroundings in real time and provide optimal advice. The advice-providing unit can use generative AI to monitor the aircraft's current status in real time and provide optimal advice. For example, the generative AI can use text generation AI (e.g., LLM) to monitor information such as the aircraft's altitude, speed, and position in real time and provide optimal advice. The advice-providing unit can also use multimodal generative AI to simultaneously analyze speech and text, monitor the aircraft's current status in real time, and provide optimal advice. For example, the generative AI can use speech recognition technology to convert the aircraft's engine status and fuel level into text, analyze that text, and provide necessary advice. This makes it possible to provide optimal advice by monitoring the aircraft's current status in real time. Some or all of the above-described processes in the advice provision unit may be performed using AI, for example, or without AI. For example, the advice provision unit can input the current status of the aircraft into a generating AI and have the generating AI execute the optimal advice.

[0096] The advice-providing unit can estimate the emotions of pilots and air traffic controllers and prioritize advice based on those estimated emotions. For example, if a pilot is facing an emergency, the generating AI will provide that advice as a top priority. Similarly, if an air traffic controller is feeling stressed, the generating AI can prioritize that advice. Furthermore, if a pilot is relaxed, the generating AI can prioritize other important advice. The advice-providing unit can use the generating AI to estimate the emotions of pilots and air traffic controllers and prioritize advice based on those emotions. For example, the generating AI can use text generation AI (e.g., LLM) to estimate emotions and prioritize advice based on those emotions. The advice-providing unit can also use multimodal generating AI to simultaneously analyze speech and text to estimate emotions and prioritize advice. For example, the generating AI can use speech recognition technology to convert a pilot's speech into text, analyze that text to estimate emotions, and prioritize advice. This allows for the rapid provision of important advice by prioritizing advice based on emotions. Emotion estimation is achieved using an emotion estimation function, for example, by 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 advice provision unit may be performed using AI, for example, or not using AI. For example, the advice provision unit can input the pilot's voice into the generative AI and have the generative AI perform emotion estimation and determine the priority of advice.

[0097] When providing advice, the advice providing unit can provide optimal advice by taking into account the geographical location information of the aircraft. For example, if the aircraft is flying in a mountainous area, the generation AI can provide advice to adjust the altitude. Furthermore, if the aircraft is flying over the ocean, the generation AI can provide advice to adjust the course. Furthermore, if the aircraft is flying in an urban area, the generation AI can provide advice to adjust the speed. The advice providing unit can use the generation AI to provide optimal advice by taking into account the geographical location information of the aircraft. For example, the generation AI can use a text generation AI (e.g., LLM) to provide advice by taking into account the geographical location information of the aircraft. Furthermore, the advice providing unit can use a multimodal generation AI to simultaneously analyze speech and text and provide advice by taking into account the geographical location information. For example, the generation AI can use speech recognition technology to convert the geographical location information of the aircraft into text, analyze the text, and provide optimal advice. This allows for safer flights by providing advice by taking into account the geographical location information of the aircraft. Some or all of the above-described processing in the advice providing unit can be performed, for example, using AI, or can be performed without using AI. For example, the advice-providing unit can input the aircraft's geographical location information into a generating AI and have the AI ​​generate optimal advice.

[0098] When providing advice, the advice providing unit can monitor the situation around the aircraft in real time and provide optimal advice. For example, if another aircraft is approaching the aircraft, the advice providing unit can provide advice to change course. Furthermore, if bad weather is occurring around the aircraft, the advice providing unit can provide advice to adjust altitude. Furthermore, if there is an obstacle around the aircraft, the advice providing unit can provide advice to perform evasive maneuvers. The advice providing unit can use the generation AI to monitor the situation around the aircraft in real time and provide optimal advice. For example, the generation AI can use a text generation AI (e.g., LLM) to monitor the situation around the aircraft in real time and provide optimal advice. Furthermore, the advice providing unit can use a multimodal generation AI to simultaneously analyze voice and text, monitor the situation around the aircraft in real time, and provide optimal advice. For example, the generation AI can use voice recognition technology to convert the situation around the aircraft into text, analyze the text, and provide optimal advice. This makes it possible to provide optimal advice by monitoring the situation around the aircraft in real time. Some or all of the above-described processes in the advice provision unit may be performed using AI, for example, or without AI. For example, the advice provision unit can input the conditions around the aircraft into a generating AI and have the generating AI execute the optimal advice. === Hard Collateral 1-1 === Each of the multiple elements, including the translation unit, analysis unit, automatic operation unit, manual operation assistance unit, and advice providing unit, described above, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the translation unit is realized by the control unit 46A of the smart device 14 and translates conversations between an airplane pilot and an air traffic control system in real time. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the translated conversations and extracts important information. The automatic operation unit is realized by the specific processing unit 290 of the data processing device 12 and performs automatic operation of the aircraft. The manual operation assistance unit is realized by the control unit 46A of the smart device 14 and provides appropriate advice to the pilot when manually operating the aircraft. The advice providing unit is realized by the specific processing unit 290 of the data processing device 12 and provides advice and suggestions in real time. === Hard Collateral 1-2 === Each of the multiple elements, including the translation unit, analysis unit, automatic operation unit, manual operation assistance unit, and advice providing unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the translation unit is realized by the control unit 46A of the smart glasses 214 and translates conversations between an airplane pilot and an air traffic control system in real time. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the translated conversations and extracts important information. The automatic operation unit is realized by the specific processing unit 290 of the data processing device 12 and performs automatic operation of the aircraft. The manual operation assistance unit is realized by the control unit 46A of the smart glasses 214 and provides appropriate advice to the pilot when manually operating the aircraft. The advice providing unit is realized by the specific processing unit 290 of the data processing device 12 and provides advice and suggestions in real time. === Hard Collateral 1-3 === Each of the multiple elements, including the translation unit, analysis unit, automatic operation unit, manual operation assistance unit, and advice providing unit, described above, is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the translation unit is realized by the control unit 46A of the headset-type terminal 314 and translates the conversation between the airplane pilot and the air traffic control system in real time. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the translated conversation and extracts important information. The automatic operation unit is realized by the specific processing unit 290 of the data processing device 12 and performs automatic operation of the aircraft. The manual operation assistance unit is realized by the control unit 46A of the headset-type terminal 314 and provides appropriate advice to the pilot when manually operating the aircraft. The advice providing unit is realized by the specific processing unit 290 of the data processing device 12 and provides advice and suggestions in real time. === Hard Collateral 1-4 === Each of the multiple elements, including the translation unit, analysis unit, automatic operation unit, manual operation assistance unit, and advice providing unit, described above, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the translation unit is realized by the control unit 46A of the robot 414 and translates the conversation between the airplane pilot and the air traffic control system in real time. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the translated conversation and extracts important information. The automatic operation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and performs automatic operation of the aircraft. The manual operation assistance unit is realized, for example, by the control unit 46A of the robot 414 and provides appropriate advice to the pilot when he or she manually operates the aircraft. The advice providing unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and provides advice and suggestions in real time.

[0099] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0100] The aircraft control system may further include a weather information acquisition unit. The weather information acquisition unit collects weather data in real time and provides it to the analysis unit. For example, the weather information acquisition unit acquires weather information along the aircraft's route, and the analysis unit can optimize the aircraft's route based on that information. The weather information acquisition unit may also detect weather conditions that affect the aircraft's altitude, and the analysis unit may adjust the altitude based on that information. Furthermore, the weather information acquisition unit may monitor the weather conditions around the aircraft in real time, and the analysis unit may take appropriate action based on that information. This enables optimal flight according to weather conditions, improving aircraft safety.

[0101] The aircraft control system may further include a passenger information acquisition unit. The passenger information acquisition unit collects passenger statuses and requests and provides them to the analysis unit. For example, the passenger information acquisition unit may monitor the health status of passengers, and the analysis unit may take appropriate action based on the information. The passenger information acquisition unit may also collect information on passenger comfort, and the analysis unit may adjust the in-flight environment based on the information. Furthermore, the passenger information acquisition unit may collect passenger requests and feedback, and the analysis unit may improve services based on the information. This improves passenger comfort and safety and provides a better flight experience.

[0102] The aircraft control system may further include a fuel management unit. The fuel management unit monitors the fuel consumption of the aircraft in real time and provides the information to the analysis unit. For example, the fuel management unit monitors the remaining fuel level of the aircraft, and the analysis unit can create an optimal fuel consumption plan based on that information. The fuel management unit may also analyze the fuel consumption pattern of the aircraft, and the analysis unit may suggest operations to improve fuel efficiency based on that information. Furthermore, the fuel management unit may optimize the timing of refueling the aircraft, and the analysis unit may create an appropriate refueling plan based on that information. This enables efficient use of fuel and reduces the operating costs of the aircraft.

[0103] The aircraft control system may further include an aircraft status monitoring unit. The aircraft status monitoring unit monitors the aircraft's status in real time and provides the information to the analysis unit. For example, the aircraft status monitoring unit monitors the status of the aircraft's engines, and the analysis unit can propose appropriate maintenance based on that information. The aircraft status monitoring unit may also detect abnormalities in the aircraft's airframe structure, and the analysis unit can take prompt action based on that information. Furthermore, the aircraft status monitoring unit monitors the status of the entire aircraft system, and the analysis unit can create an optimal flight plan based on that information. This improves the safety and reliability of the aircraft and improves flight efficiency.

[0104] The aircraft control system may further include a crew support unit. The crew support unit supports the crew's work and provides information to the analysis unit. For example, the crew support unit manages the crew's work schedule, and the analysis unit can propose optimal work allocation based on that information. The crew support unit may also monitor the crew's health status, and the analysis unit may propose appropriate breaks and shifts based on that information. Furthermore, the crew support unit provides tools and resources to improve the crew's work efficiency, and the analysis unit can optimize the work based on that information. This reduces the crew's burden and improves work efficiency.

[0105] The aircraft control system can further include an emotion feedback unit. The emotion feedback unit monitors the emotions of the pilot and the controller in real time and provides the information to the analysis unit. For example, if the pilot is nervous, the emotion feedback unit provides that information to the analysis unit, and the analysis unit can provide appropriate advice based on that information. Also, if the controller is feeling stressed, the emotion feedback unit provides that information to the analysis unit, and the analysis unit can take appropriate action based on that information. Furthermore, the emotion feedback unit monitors changes in the emotions of the pilot and the controller in real time, and the analysis unit can suggest optimal operations based on that information. This enables appropriate responses based on emotions, improving aircraft safety.

[0106] The aircraft control system can further include a stress reduction unit. The stress reduction unit monitors the stress levels of pilots and air traffic controllers in real time and provides the data to the analysis unit. For example, if the pilot is feeling high stress, the stress reduction unit provides that information to the analysis unit, which can then suggest relaxation methods based on that information. Also, if the controller is feeling stressed, the stress reduction unit provides that information to the analysis unit, which can then suggest appropriate breaks based on that information. Furthermore, the stress reduction unit monitors changes in the stress levels of pilots and air traffic controllers in real time, and the analysis unit can take optimal measures based on that information. This enables appropriate responses based on stress, improving aircraft safety.

[0107] The aircraft control system may further include an emotion prediction unit. The emotion prediction unit predicts emotional changes in the pilot or air traffic controller and provides the prediction information to the analysis unit. For example, the emotion prediction unit may detect signs that the pilot is beginning to become nervous and provide the information to the analysis unit, which can then take early action based on the information. The emotion prediction unit may also detect signs that the air traffic controller is beginning to feel stressed and provide the information to the analysis unit, which can then take appropriate action based on the information. Furthermore, the emotion prediction unit may predict emotional changes in the pilot or air traffic controller, which can then suggest optimal operations based on the information. This enables early action based on emotional changes, improving aircraft safety.

[0108] The aircraft control system can further include an emotion history management unit. The emotion history management unit records the emotion history of the pilot and the controller and provides it to the analysis unit. For example, the emotion history management unit records the pilot's past emotion data, and the analysis unit can take appropriate action based on that information. The emotion history management unit also records the controller's past emotion data, and the analysis unit can take appropriate action based on that information. Furthermore, the emotion history management unit analyzes the emotion history of the pilot and the controller, and the analysis unit can suggest optimal operations based on that information. This enables appropriate action based on past emotion data, improving aircraft safety.

[0109] The aircraft control system can further include an emotion sharing unit. The emotion sharing unit shares the emotions of the pilot and air traffic controller with other crew members and related parties and provides them to the analysis unit. For example, if the pilot is nervous, the emotion sharing unit shares that information with other crew members, and the analysis unit can take appropriate action based on that information. Also, if the controller is feeling stressed, the emotion sharing unit shares that information with related parties, and the analysis unit can take appropriate action based on that information. Furthermore, the emotion sharing unit shares the emotions of the pilot and air traffic controller in real time, and the analysis unit can suggest optimal operations based on that information. This enables appropriate responses based on emotions, improving aircraft safety.

[0110] The processing flow of the second embodiment will be briefly explained below.

[0111] Step 1: The translation unit translates the conversation between the aircraft pilot and the air traffic control system in real time. For example, if the pilot speaks in English and the air traffic controller responds in French, the translation unit translates this instantly to ensure smooth communication between the two parties. The translation unit can use generative AI to accurately translate the content of the conversation. Step 2: The analysis unit analyzes the conversation translated by the translation unit and extracts important information, such as the plane's current position, speed, altitude, and destination. The analysis unit can use the generation AI to analyze the content of the conversation and extract important information. Step 3: The automated control unit performs automated aircraft control based on the information extracted by the analysis unit. For example, it adjusts the aircraft's altitude to a target altitude. The automated control unit can perform automated aircraft control using generated AI. Step 4: The manual operation assistance unit assists with operations performed by the automatic operation unit. For example, it provides appropriate advice when the pilot is performing manual operations. The manual operation assistance unit can use generated AI to assist the pilot's manual operations. Step 5: The advice-providing unit provides real-time advice and suggestions based on operations assisted by the manual operation support unit. For example, it suggests appropriate response methods in emergencies. The advice-providing unit can provide real-time advice and suggestions using generated AI.

[0112] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0113] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0114] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information 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.

[0115] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0116] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0117] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0118] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0119] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0120] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0121] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0122] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0123] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0124] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0125] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0126] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0127] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0128] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0129] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, 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), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0130] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0131] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0132] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0133] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0134] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0135] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0136] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0137] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0138] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0139] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0140] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0141] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0142] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0143] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0144] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0145] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, 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), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0146] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0147] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0148] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0149] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0150] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0151] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0152] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0153] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0154] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0155] The control 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0156] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0157] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0158] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0159] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0160] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0161] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0162] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, 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), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0163] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0164] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0165] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0166] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0167] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0168] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0169] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0170] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0171] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0172] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0173] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0174] 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.

[0175] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0176] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0177] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0178] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0179] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0180] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0181] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0182] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0183] [Explanation of symbols]

[0184] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A translation department that translates conversations between airplane pilots and air traffic control systems in real time, an analysis unit that analyzes the conversation translated by the translation unit and extracts important information; an automatic operation unit that automatically operates the aircraft based on the information extracted by the analysis unit; a manual operation assisting unit that assists the operation performed by the automatic operation unit; an advice providing unit that provides advice or suggestions in real time based on the operation assisted by the manual operation assist unit; A system characterized by:

2. The aforementioned translation department, Translate conversations in different languages ​​in real time 2. The system of claim 1.

3. The analysis unit Extract information about the plane's current position, speed, altitude, and destination from the translated conversation 2. The system of claim 1.

4. The analysis unit Analyzing emotions from conversations to determine the stress level and urgency of pilots and controllers 2. The system of claim 1.

5. The automatic operation unit is, Adjusting the aircraft's altitude based on the extracted information 2. The system of claim 1.

6. The automatic operation unit is, Change the aircraft's course based on the extracted information 2. The system of claim 1.

7. The manual operation assist unit is, Providing appropriate advice to pilots when operating manually 2. The system of claim 1.

8. The aforementioned advice-providing unit, Propose appropriate measures in emergencies 2. The system of claim 1.

9. The aforementioned translation department, Estimate the emotions of pilots and controllers and adjust the tone and expression of translations based on the estimated emotions 2. The system of claim 1.

Images