System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving real-time communications from pilots and air traffic controllers; means for converting the received communications into text data; means for inputting the text data into a generative AI model for analysis; means for detecting errors that have occurred and generating warning messages; and means for transmitting the warning messages to terminals for display.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including 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] There is a risk of accidents occurring due to communication errors between pilots and air traffic controllers or human error during aircraft operation. This can cause significant damage to human life and property. Conventional systems have difficulty detecting errors in real time, and immediate action is required when an error occurs. The present invention aims to solve these problems and improve aircraft operation safety. [Means for solving the problem]

[0005] The present invention is a system that includes a means for receiving communication data from pilots and air traffic controllers in real time, a speech recognition means for converting the received speech data into text data, a means for inputting the text data into a generative AI model for analysis, a means for detecting errors that occur and generating a warning message, and a means for transmitting the warning message to a terminal for display. Furthermore, the system includes a preprocessing means for noise reduction and sound quality improvement, and a means for the generative AI model to perform analysis using a past database, thereby improving the accuracy of error detection. In this way, communication errors and human errors between pilots and air traffic controllers can be detected in real time and immediately addressed.

[0006] "Communications Data" refers to information exchanged between pilots and air traffic controllers, whether by voice or otherwise.

[0007] "Real time" means that communication data is sent and received immediately.

[0008] "Means for receiving" refers to a component of a device or system for obtaining communication data.

[0009] "Voice Data" refers to the content of voice communications between pilots and air traffic controllers.

[0010] "Text data" is voice data converted into character information.

[0011] "Speech recognition means" refers to technology or systems that convert voice data into text data.

[0012] "Generative AI models" refer to artificial intelligence algorithms for analyzing and generating data, such as generative adversarial networks and large-scale language models.

[0013] "Means of analysis" refers to the methods and techniques used to provide input data to a generative AI model and obtain results.

[0014] "Error" refers to miscommunication or human error that occurs between pilots and air traffic controllers.

[0015] A "warning message" refers to a message that calls attention to or urges correction of a detected error.

[0016] "Transmitting means" refers to a system or device for sending generated data or messages to other terminals.

[0017] "Terminal" refers to the communications and computing devices used by pilots and air traffic controllers.

[0018] "Noise reduction" refers to the technology of removing unnecessary background sounds from audio data.

[0019] "Sound quality improvement" refers to various processes for improving the quality of audio data.

[0020] "Preprocessing means" refers to methods and techniques that improve the quality of data before analysis or recognition.

[0021] "Historical database" refers to a database that stores previously recorded communication data and related information.

[0022] "Means for performing analysis" refers to a system or method that analyzes data and outputs results. [Brief explanation of the drawings]

[0023] [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. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0024] 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.

[0025] First, the terms used in the following description will be explained.

[0026] 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, a 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), and an APU (Accelerated Processing Unit).

[0027] 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.

[0028] 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.

[0029] 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), Bluetooth (registered trademark), etc.

[0030] 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."

[0031] [First embodiment]

[0032] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0033] 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.

[0034] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0035] 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.

[0036] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. 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 acquires the data indicating the user input.

[0037] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The 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.

[0038] 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.

[0039] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0040] 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.

[0041] 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.

[0042] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0043] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0044] This invention is a system that detects communication errors between aircraft pilots and air traffic controllers in real time to prevent accidents. This system includes a series of processes that consistently perform everything from receiving communication data to detecting errors and generating and transmitting warning messages.

[0045] System configuration

[0046] The system includes the following main components:

[0047] 1. Communication data receiving means

[0048] Server: Receives communication data from pilots and air traffic controllers in real time. This data is received in audio format and temporarily stored in the server's storage.

[0049] 2. Voice Recognition Method

[0050] Server: The received voice data is converted into text data using speech recognition technology, such as Google Cloud Speech-to-Text API or IBM Watson Speech to Text.

[0051] 3. Error Detection Methods

[0052] Server: The converted text data is fed into a generative AI model, which performs real-time analysis against a historical database to detect potential errors in the communication.

[0053] 4. Warning Message Generation Method

[0054] Server: If an error is detected, this information is used to generate an appropriate warning message, which will include the specific problem and a suggested solution.

[0055] 5. Means of transmission and display

[0056] Server: The generated warning messages are sent to the pilot and controller terminals via REST API.

[0057] Terminal: Receives warning messages and displays them on the user interface, allowing pilots and controllers to respond quickly.

[0058] Specific examples

[0059] 1. Receiving communication data

[0060] The server receives real-time voice data from the pilot saying, "Echo 123, requesting permission to descend." This data is immediately stored in the server's storage.

[0061] 2. Voice Recognition

[0062] The server sends the received voice data to a speech recognition engine and converts it into text data. The conversion result is text data that reads, "Echo 123, requesting permission to descend."

[0063] 3. Error Detection

[0064] The server then feeds this text data into a generative AI model, which analyzes it for signs of error. The model uses past data to determine, for example, that Echo 123 was being instructed to fly at a different altitude than other aircraft.

[0065] 4. Generating Warning Messages

[0066] The server generates a warning message saying "Echo 123 is being instructed to a different altitude. Please recheck."

[0067] 5. Transmission and Display

[0068] The server sends this warning message to the terminals of the pilot and the controller, and the message is displayed immediately. The user (pilot and controller) checks the warning and takes the necessary action.

[0069] Operation method

[0070] The system is designed to operate continuously while the aircraft is in operation. The server constantly receives and analyzes communication data, aiming to detect errors early. The terminal displays a warning message as soon as an error is detected, helping the user to take prompt action.

[0071] In this way, the present invention detects communication errors between pilots and air traffic controllers in real time, improving the safety of the entire system.

[0072] The processing flow will be explained below.

[0073] Step 1: Receiving communication data

[0074] The server receives real-time communication data from pilots and air traffic controllers, which is transmitted in voice format via the TCP / IP protocol.

[0075] The server temporarily stores the received audio data in a storage device, usually in a standard audio format such as WAV or MP3.

[0076] Step 2: Preprocessing the audio data

[0077] The server performs noise reduction on the received audio data, using Python libraries (e.g., Librosa and Pydub) to remove background noise and improve the audio quality.

[0078] The server prepares the pre-processed audio data for the next step.

[0079] Step 3: Voice Recognition

[0080] The server sends the preprocessed speech data to a speech recognition engine, which can use cloud-based speech recognition services such as Google Cloud Speech-to-Text API or IBM Watson Speech to Text.

[0081] The server receives the text data returned by the speech recognition engine and stores it as input data for the generative AI model.

[0082] Step 4: Analyzing text data and detecting errors

[0083] The server inputs the text data into a generative AI model, which uses a natural language processing engine such as GPT-3 or BERT.

[0084] The server uses a generative AI model to analyze the text data and detect signs of communication errors or human error based on a past database.

[0085] Step 5: Generate a warning message

[0086] The server generates a warning message based on the error information detected by the generative AI model, which includes the specific details of the error and suggested countermeasures.

[0087] The server prepares the alert message for transmission.

[0088] Step 6: Sending a warning message

[0089] The server sends the generated warning messages to the pilot and air traffic controller terminals via a REST API using HTTP POST requests.

[0090] Step 7: Displaying warning messages

[0091] The terminal receives the alert messages sent by the server and visually displays them in the user interface, using a GUI library (e.g., Tkinter, JavaFX, etc.).

[0092] Users (pilots and air traffic controllers) check the displayed warning message and take necessary action, for example, rechecking and correcting the communication content in which the error was detected.

[0093] The above is the flow of the specific processing steps of this system. Each step works in conjunction with the others to detect and warn of communication errors in real time.

[0094] Example 1

[0095] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0096] Misunderstandings and errors in communication between aircraft pilots and air traffic controllers can have a significant impact on flight safety. These errors need to be detected in real time and dealt with promptly, but current systems lack the technology to do so. Therefore, a system is needed that can detect communication errors between pilots and air traffic controllers in real time and issue immediate warnings.

[0097] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0098] In this invention, the server includes a means for receiving communication data from pilots and air traffic controllers in real time, a speech recognition means for converting the received voice data into text data, a means for inputting the text data into a generative AI model for analysis, a means for detecting an error that has occurred and generating a warning message, and a means for transmitting the warning message to a terminal for display. This enables real-time analysis of communication data, rapid detection and warning of errors, and immediate notification to pilots and air traffic controllers.

[0099] The "communication data receiving means" is a function for receiving voice communication data from pilots and air traffic controllers in real time.

[0100] The "voice recognition means" is a processing function for converting received voice data into text data.

[0101] A "generative AI model" is an artificial intelligence model that performs real-time analysis based on a past database.

[0102] The "error detection means" is a function that uses a generative AI model to analyze text data and detect communication errors.

[0103] The "warning message generating means" is a function that generates a warning message based on a detected error.

[0104] The "warning message sending means" is a function for sending the generated warning message to the terminal via the REST API.

[0105] The "warning message display means" is a function for displaying the transmitted warning message on the user interface.

[0106] The "noise removal means" is a preprocessing function for removing noise from audio data and improving sound quality.

[0107] "Real-time analysis" refers to the process of quickly analyzing received data in real time.

[0108] "Input to a generative AI model" refers to the means of supplying text data to a generative AI model and having the model analyze it.

[0109] "REST API" is a type of API (application programming interface) for exchanging warning messages between systems, and is a protocol for communication via HTTP.

[0110] The present invention is a system for detecting communication errors between aircraft pilots and air traffic controllers in real time to prevent accidents. A specific embodiment of this system is described below.

[0111] System configuration

[0112] The system includes the following main components:

[0113] 1. Communication data receiving means

[0114] The server receives communication data from pilots and air traffic controllers in real time. This communication data is received in audio format and temporarily stored in the server's storage.

[0115] 2. Voice Recognition Method

[0116] The server uses speech recognition technology to convert the received voice data into text data. Specifically, it uses services such as Google Cloud Speech-to-Text API and IBM Watson Speech to Text. The voice data is sent to the speech recognition engine and converted into text data.

[0117] 3. Error Detection Methods

[0118] The server then feeds the converted text data into a generative AI model, which performs real-time analysis based on a historical database to detect potential errors in the communication.

[0119] 4. Warning Message Generation Method

[0120] If an error is detected, the server will generate an appropriate warning message, which will include the specific problem and a recommended solution.

[0121] 5. Means of transmission and display

[0122] The server sends the generated warning messages to the pilot and air traffic controller terminals via a REST API.

[0123] The terminal receives the warning message and displays it on the user interface, allowing users (pilots and air traffic controllers) to react quickly.

[0124] Specific examples

[0125] A specific example of this system is shown below.

[0126] 1. Receiving communication data

[0127] The server receives the pilot's voice communication data in real time, such as "Echo 123, requesting permission to descend." This voice data is then stored in storage.

[0128] 2. Voice Recognition

[0129] The server uses the Google Cloud Speech-to-Text API to convert the received voice data into text data, for example, "Echo 123, requesting permission to descend."

[0130] 3. Error Detection

[0131] The server inputs this text data into a generative AI model for analysis, which uses past data to detect that Echo 123 was being instructed to fly at a different altitude than other aircraft.

[0132] 4. Generating Warning Messages

[0133] Based on the detected error information, the server generates a warning message saying "Echo 123 is being instructed to a different altitude. Please check again."

[0134] 5. Transmission and Display

[0135] The server sends this warning message to the terminals of the pilot and air traffic controller via REST API, where the users (pilot and air traffic controller) can check the warning message and take prompt action.

[0136] Examples of prompt statements

[0137] Here are some examples of specific prompts:

[0138] It receives voice data such as "Echo 123, requesting permission to descend" and specifies the prompt text that generates a warning message upon error detection.

[0139] In this way, this system will be able to detect communication errors between pilots and air traffic controllers in real time and quickly address them, which is expected to significantly improve the safety of aircraft operations.

[0140] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0141] Step 1:

[0142] Receiving communication data

[0143] The server receives voice communication data from pilots and air traffic controllers in real time. The input is the communication voice from the pilot or air traffic controller, which is temporarily stored in the server's storage. Specific operations include a process of capturing voice data through communication equipment and storing it in a storage device. The output is the voice data stored in the storage.

[0144] Step 2:

[0145] Voice Recognition

[0146] The server sends the stored voice data to the voice recognition engine. The input is the voice data stored in storage. The server converts the voice data into text data using a voice recognition service such as Google Cloud Speech-to-Text API or IBM Watson Speech to Text. Specific operations include making an API call and seamlessly converting the voice data into text. The output is text data.

[0147] Step 3:

[0148] Error Detection

[0149] The server inputs the converted text data into the generative AI model. The input is the text data generated in the speech recognition step. The server inputs this text data into the generative AI model and analyzes it in real time. Specific operations include the process of supplying text to the generative AI model and comparing it with a past database to identify errors. The output is information about the detected errors.

[0150] Step 4:

[0151] Generate a warning message

[0152] The server generates a warning message based on the error detection results. The input is the error information output in the error detection step. The server generates a warning message containing details of the error and suggests appropriate countermeasures. Specific operations include a process for dynamically generating a warning message based on the error information. The output is a warning message containing the specific problem and a suggested countermeasure.

[0153] Step 5:

[0154] Send and display

[0155] The server sends the generated warning message to the pilot's and air traffic controller's terminals via the REST API. The input is the warning message generated in the warning message generation step. The terminal displays the received warning message on its user interface. Specific operations include making a REST API call, sending a message, and displaying it on the user interface on the terminal side. The output is the warning message displayed on the terminal, which the user confirms.

[0156] (Application example 1)

[0157] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0158] In autonomous vehicles, communication errors between the driver and the system, or between vehicles, can lead to accidents or serious problems. There is a need for technology that can detect such errors in real time and warn the driver in advance. Currently, the means to detect these types of errors and respond quickly are not sufficiently developed, making improving safety a challenge.

[0159] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0160] In this invention, the server includes: means for receiving communication data from pilots and air traffic controllers in real time; speech recognition means for converting the received speech data into text data; means for inputting the text data into a generative AI model and analyzing it; means for detecting errors and generating warning messages; means for sending and displaying the warning messages on a terminal; means for monitoring voice and text communications between a driver and the autonomous driving system in real time in an autonomous driving vehicle system; means for analyzing whether the driver's instructions and the system's responses match; and means for generating warning messages and displaying them on a vehicle display or head-up display if they do not match. This enables real-time detection of communication errors and immediate warnings in autonomous driving vehicles.

[0161] A "pilot" is a person who is qualified to fly an aircraft and who actually operates the aircraft.

[0162] An "air traffic controller" is a person whose job is to monitor and direct the movements of aircraft in the air and on the ground in order to ensure the safe operation of aircraft.

[0163] "Communications Data" means information in the form of voice and text exchanged between pilots and air traffic controllers, or drivers and automated driving systems.

[0164] "Means for receiving in real time" refers to functions or devices for receiving communication data immediately without delay.

[0165] "Audio data" means information recorded or transmitted in the form of sound.

[0166] "Text data" refers to information expressed in characters and symbols.

[0167] "Speech recognition means" refers to technology or devices that convert voice data into text data.

[0168] A "generative AI model" is a model that uses artificial intelligence to analyze text data and detect errors.

[0169] An "occurring error" is an unintentional error or discrepancy that occurs in communication.

[0170] A "warning message" is information that is generated based on an error that has occurred, and that prompts attention or reconfirmation.

[0171] "Means for sending to and displaying at a terminal" refers to a function or device for sending the generated alert message to a specific device and displaying it to the user of that device.

[0172] An "autonomous vehicle system" is a vehicle system that incorporates technology and devices for automatically driving and controlling a vehicle.

[0173] The means for analyzing whether the "driver's instructions and the system's response" match refers to functions and devices for determining whether the instructions given by the driver and the response of the automated driving system match accurately.

[0174] A "display" is an electronic device for visually displaying information.

[0175] A "head-up display" is a device that displays information in front of the driver so that the driver can check it at the edge of their field of vision without having to look down.

[0176] This invention is a system that detects communication errors between the driver and the autonomous driving system in an autonomous vehicle, and between vehicles in real time, and generates and transmits warning messages. This system includes the following main components:

[0177] Hardware:

[0178] 1. Voice input system: A microphone for collecting the driver's instructions as voice data.

[0179] 2. On-board computer: A central processing unit that processes data.

[0180] 3. Display and Head-Up Display (HUD): A display device for displaying warning messages to the driver.

[0181] software:

[0182] 1. Speech recognition software: Technology that converts voice data into text data (e.g., Google Cloud Speech-to-Text API).

[0183] 2. Generative AI model: An artificial intelligence model (e.g., OpenAI API) for analyzing text data and detecting errors.

[0184] 3. Communication module: Software for sending and receiving communication data.

[0185] Server Processing

[0186] 1. Receiving audio data:

[0187] The server receives the driver's instructions as voice data from the autonomous vehicle's voice input system and temporarily stores them in storage.

[0188] 2. Audio to text conversion:

[0189] The server then sends the received audio data to speech recognition software, which converts it into text using a service like the Google Cloud Speech-to-Text API.

[0190] 3. Error detection:

[0191] The server then feeds the converted text data into a generative AI model that analyzes communication errors. The model uses a historical database and performs real-time analysis to detect potential errors.

[0192] 4. Generate a warning message:

[0193] If an error is detected, the server generates a warning message that describes the specific problem and suggests a solution.

[0194] 5. Sending and displaying warning messages:

[0195] The server sends the generated warning message to the vehicle's display or head-up display for display to the driver.

[0196] Specific examples

[0197] When the driver issues a voice command such as "Switch to autonomous driving mode," the voice data is received by the server and instantly converted into text data. The text data is then analyzed by a generative AI model to verify that the command was executed correctly. If the system's response does not match, a warning message such as "Switch to autonomous driving mode failed. Please continue manual operation" is generated and displayed on the vehicle's display.

[0198] Examples of prompts include:

[0199] Analyze the following communication for errors: "Switch to autopilot mode."

[0200] This will enable real-time detection of communication errors and immediate warnings in autonomous vehicles.

[0201] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0202] Step 1:

[0203] Receiving audio data

[0204] The server receives the driver's voice data in real time from the voice input system (microphone) of the autonomous vehicle. The input is the driver's voice command such as "switch to autonomous driving mode," and this voice data is temporarily stored in the server's storage.

[0205] Step 2:

[0206] Converting audio data to text

[0207] The server sends the received voice data to speech recognition software (e.g., Google Cloud Speech-to-Text API) and converts it into text data. The input is voice data, which undergoes speech recognition as data processing, and the output is the text data "Switch to autonomous driving mode."

[0208] Step 3:

[0209] Text data analysis

[0210] The server inputs the converted text data into a generative AI model (e.g., OpenAI API) and analyzes errors in the communication. The input is text data, which is analyzed by the AI ​​model as data processing and data calculation. The output is the result of whether or not an error exists. Specifically, the generative AI model is input with the prompt "Analyze the following communication for errors: 'Switch to autopilot mode.'" and the text data is analyzed.

[0211] Step 4:

[0212] Detecting errors

[0213] If an error occurs in the analysis results, the server extracts detailed information. The input is the analysis results from the generative AI model, and the server determines whether there is an error as a data calculation and identifies the part where the error occurred. The output is error information.

[0214] Step 5:

[0215] Generate a warning message

[0216] The server generates a warning message based on detailed error information. The input is the error information, and an appropriate warning text message is created by processing the data. Specifically, a warning message such as "Switching to autonomous driving mode has failed. Please continue manual operation" is output.

[0217] Step 6:

[0218] Sending and displaying warning messages

[0219] The server sends the generated warning message to the vehicle's display or head-up display (HUD) for display to the driver. The input is the warning message, and the message is sent via the communication module as data processing. The output is a warning display that the driver can check.

[0220] Through these steps, a system will be created that monitors in real time whether the driver's voice instructions are being properly reflected in the autonomous driving system, and if an error is detected, it will quickly generate a warning to notify the driver.

[0221] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0222] The present invention improves the effectiveness of error handling by combining a system that detects communication errors between pilots and air traffic controllers and provides warnings in real time with an emotion engine that recognizes user emotions. This system includes a series of processes that receive communication data, recognize voice, detect errors, generate and send warning messages, and analyze emotions.

[0223] System configuration

[0224] The system includes the following main components:

[0225] 1. Communication data receiving means

[0226] Server: Receives communication data from pilots and air traffic controllers in real time. This data is received in audio format and temporarily stored in the server's storage.

[0227] 2. Voice Recognition Method

[0228] Server: The received voice data is converted into text data using speech recognition technology, such as Google Cloud Speech-to-Text API or IBM Watson Speech to Text.

[0229] 3. Error Detection Methods

[0230] Server: The converted text data is fed into a generative AI model, which performs real-time analysis against a historical database to detect potential errors in the communication.

[0231] 4. Warning Message Generation Method

[0232] Server: If an error is detected, this information is used to generate an appropriate warning message, which will include the specific problem and a suggested solution.

[0233] 5. Means of transmission and display

[0234] Server: The generated warning messages are sent to the pilot and controller terminals via REST API.

[0235] Terminal: Receives warning messages and displays them on the user interface, allowing pilots and controllers to respond quickly.

[0236] 6. Emotion Engine

[0237] Server: Contains an emotion engine that analyzes the emotions of users (pilots and air traffic controllers) in real time from voice data. This engine uses voice analysis technology to provide emotion data to the generative AI model.

[0238] Specific examples

[0239] 1. Receiving communication data

[0240] The server receives real-time voice data from the pilot saying, "Echo 123, requesting permission to descend." This data is immediately stored in the server's storage.

[0241] 2. Voice Recognition

[0242] The server sends the received voice data to a speech recognition engine and converts it into text data. The conversion result is text data that reads, "Echo 123, requesting permission to descend."

[0243] 3. Emotion analysis

[0244] The server uses an emotion engine to analyze the user's emotions from the voice data. For example, if the pilot is anxious, the emotion engine will detect "stress."

[0245] 4. Error Detection

[0246] The server inputs text and emotion data into the generative AI model, which analyzes it for signs of error. The model compares it with past data and detects that Echo 123 was being instructed to fly at a different altitude than other aircraft.

[0247] 5. Generating Warning Messages

[0248] The server generates a warning message saying, "Echo 123 is being instructed to a different altitude. Please recheck. Pilot appears stressed."

[0249] 6. Transmission and Display

[0250] The server sends this warning message to the terminals of the pilot and the controller, and the message is displayed immediately. The user (pilot and controller) checks the warning and takes the necessary action.

[0251] Operation method

[0252] The system is designed to operate continuously while the aircraft is in operation. The server constantly receives and analyzes communication data, aiming for early detection of errors and emotions. The terminal displays an emotion-based warning message upon detecting an error, helping the user to take prompt and appropriate action.

[0253] In this way, the present invention detects pilot and air traffic controller communication errors and emotional states in real time, improving overall system safety and effective response.

[0254] The processing flow will be explained below.

[0255] Step 1: Receiving communication data

[0256] The server receives real-time communication data from pilots and air traffic controllers, which is transmitted in voice format via the TCP / IP protocol.

[0257] The server temporarily stores the received audio data in a storage device, usually in a standard audio format such as WAV or MP3.

[0258] Step 2: Preprocessing the audio data

[0259] The server performs noise reduction on the received audio data, using Python libraries (e.g., Librosa and Pydub) to remove background noise and improve the audio quality.

[0260] The server prepares the pre-processed audio data for the next step.

[0261] Step 3: Voice Recognition

[0262] The server sends the preprocessed speech data to a speech recognition engine, which can use cloud-based speech recognition services such as Google Cloud Speech-to-Text API or IBM Watson Speech to Text.

[0263] The server receives the text data returned by the speech recognition engine and stores it as input data for the generative AI model.

[0264] Step 4: Sentiment Analysis

[0265] The server inputs the preprocessed voice data or the text returned by the speech recognition engine into the emotion engine, which analyzes the user's emotions from the voice or text and identifies their emotional state, such as stress, anger, or joy.

[0266] The server converts and stores the emotion analysis results in a format that can be used by the generative AI model.

[0267] Step 5: Analyze text data and detect errors

[0268] The server inputs text and emotion data into a generative AI model, which uses natural language processing engines such as GPT-3 and BERT.

[0269] The server uses a generative AI model to analyze text data and emotional data, and compares it with a past database to detect signs of communication errors or human error.

[0270] Step 6: Generate a warning message

[0271] The server generates a warning message based on the error information and emotional information detected by the generative AI model. The warning message includes the specific details of the error, suggested countermeasures, and additional precautions according to the user's emotional state.

[0272] The server prepares the alert message for transmission.

[0273] Step 7: Sending a warning message

[0274] The server sends the generated warning messages to the pilot and air traffic controller terminals via a REST API using HTTP POST requests.

[0275] Step 8: Displaying warning messages

[0276] The terminal receives the alert messages sent by the server and visually displays them in the user interface, using a GUI library (e.g., Tkinter, JavaFX, etc.).

[0277] Users (pilots and air traffic controllers) check the displayed warning message and take necessary action, for example, rechecking and correcting the communication content in which the error was detected.

[0278] These are the specific processing steps of the system that combines the emotion engine. By linking these steps together, real-time detection of communication errors and emotional states and warnings are realized, further improving the operational safety of aircraft.

[0279] Example 2

[0280] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0281] Communications between pilots and air traffic controllers are prone to misunderstandings and miscommunications. Furthermore, the emotional state of the user during these communications (e.g., stress or impatience) can affect the detection and response to errors. While conventional systems recognize voice data and detect errors, they are unable to analyze the user's emotional state in real time and utilize it to improve response. This makes it difficult to detect errors early and improve the quality of response.

[0282] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0283] In this invention, the server includes a means for receiving communication data from pilots and air traffic controllers in real time, a speech recognition device for converting the received speech data into text data, a device for inputting the text data into a generative AI model for analysis, a device for detecting errors that have occurred and generating a warning message, a device for transmitting the warning message to a terminal and displaying it, an emotion recognition engine for analyzing user emotions in real time, and a device for inputting emotion data into the generative AI model for analysis. This makes it possible to detect errors in communication data in real time and quickly generate and provide appropriate warning messages that take the user's emotional state into consideration.

[0284] "Communication Data" means data in the form of voice exchanged between pilots and air traffic controllers.

[0285] "Speech recognition device" refers to a technology or device for converting voice data into text data.

[0286] A "generative AI model" refers to an artificial intelligence model that analyzes voice and text data based on learned past data.

[0287] "Error detection device" refers to a device that uses a generative AI model to detect potential errors in text data.

[0288] The term "warning message generating device" refers to a device that generates a warning message based on detected error information.

[0289] "Warning message transmitting device" refers to a device that transmits the generated warning messages to the terminals of pilots and air traffic controllers.

[0290] "Warning message display device" refers to a device that displays a received warning message on a user interface.

[0291] "Emotion recognition engine" refers to a technology or device that analyzes a user's emotional state from voice data.

[0292] "Emotion Data" refers to data regarding a user's emotional state analyzed by an emotion recognition engine.

[0293] Overall structure

[0294] The present invention is a system that detects communication errors between pilots and air traffic controllers and provides warnings in real time. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system enhances the effectiveness of error response. The system includes a series of processes that receive communication data, recognize voice, detect errors, generate and send warning messages, and analyze emotions.

[0295] Components

[0296] 1. Communication data receiving means:

[0297] The server receives real-time communication data from pilots and air traffic controllers. This data is received in audio format and temporarily stored in the server's storage.

[0298] 2. Voice recognition means:

[0299] The server converts the received voice data into text data using speech recognition technology, such as Google Cloud Speech-to-Text API or IBM Watson Speech to Text.

[0300] 3. Emotion Recognition Engine:

[0301] The server uses an emotion engine that analyzes the emotions of users (pilots and air traffic controllers) in real time from voice data. This engine uses voice analysis technology and provides emotion data to the generative AI model.

[0302] 4. Error detection methods:

[0303] The server then inputs the converted text and emotion data into a generative AI model, which performs real-time analysis based on a historical database to detect potential errors in communication.

[0304] 5. Warning message generation method:

[0305] If an error is detected, the server uses this information to generate an appropriate warning message, which includes the specific problem and a suggested solution.

[0306] 6. Means of transmission and display:

[0307] The server sends the generated warning messages to the pilot and controller terminals via a REST API.

[0308] The terminal receives the warning message and displays it on the user interface, allowing users (pilots and controllers) to respond quickly.

[0309] Specific examples

[0310] 1. Receiving communication data:

[0311] The server receives real-time voice data from the pilot saying, "Echo 123, requesting permission to descend." This data is immediately stored in the server's storage.

[0312] 2. Speech Recognition:

[0313] The server sends the received voice data to a speech recognition engine and converts it into text data. The conversion result is text data that reads, "Echo 123, requesting permission to descend."

[0314] 3. Emotion analysis:

[0315] The server uses an emotion engine to analyze the user's emotions from the voice data. For example, if the pilot is anxious, the emotion engine will detect "stress."

[0316] 4. Error detection:

[0317] The server inputs text data and emotion data into the generative AI model, which analyzes the error signs. The model compares it with past data and detects that Echo 123 was instructed to fly at a different altitude than other aircraft. An example prompt is "Please detect errors based on past communication data and emotion data."

[0318] 5. Generate warning messages:

[0319] The server generates a warning message saying, "Echo 123 is being instructed to a different altitude. Please recheck. Pilot appears stressed."

[0320] 6. Transmission and Display:

[0321] The server sends this warning message to the terminals of the pilot and the controller, and the message is displayed immediately. The user (pilot and controller) checks the warning and takes the necessary action.

[0322] Operation method

[0323] The system is designed to operate continuously while the aircraft is in operation. The server constantly receives and analyzes communication data, aiming for early detection of errors and emotions. The terminal displays an emotion-based warning message upon detecting an error, helping the user to take prompt and appropriate action.

[0324] In this way, the present invention detects pilot and air traffic controller communication errors and emotional states in real time, improving overall system safety and effective response.

[0325] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0326] Step 1: Receiving communication data

[0327] The server receives voice communication data transmitted in real time by pilots and air traffic controllers.

[0328] Input: Voice communication data from pilots and air traffic controllers

[0329] Specific operation: The server captures voice data via the aircraft's communication device and temporarily stores it in storage.

[0330] Output: Saved audio data

[0331] Step 2: Voice Recognition

[0332] The server sends the stored voice data to a voice recognition engine for conversion into text data.

[0333] Input: Saved audio data

[0334] Specific operation: The server connects to a speech recognition engine (e.g., Google Cloud Speech-to-Text API) and uploads the voice data. The speech recognition engine analyzes the voice data and generates corresponding text data.

[0335] Output: Converted text data

[0336] Step 3: Sentiment Analysis

[0337] The server sends the voice data to an emotion recognition engine to analyze the user's emotional state.

[0338] Input: Saved audio data

[0339] How it works: The server connects to the emotion recognition engine and uploads the voice data. The emotion recognition engine analyzes the tone, rhythm, and speed of the voice and generates emotion data (e.g., "stressed," "calm").

[0340] Output: Parsed emotion data

[0341] Step 4: Error detection

[0342] The server inputs the converted text data and emotion data into a generative AI model and analyzes it for signs of error.

[0343] Input: Converted text data and emotion data

[0344] How it works: The server uses the prompt "Please detect errors based on past communication data and emotion data" to input the data into the generative AI model, which then compares it with the past database to detect anomalies and inconsistencies.

[0345] Output: Detected error data

[0346] Step 5: Generate a warning message

[0347] The server generates a warning message based on the detected error data and emotion data.

[0348] Input: Detected error data and emotion data

[0349] Specific behavior: The server uses the generated error data and emotion data to generate an appropriate warning message, including the specific problem and a suggested solution (e.g., "Echo 123 is being instructed to a different altitude. Please reconfirm. The pilot appears stressed.").

[0350] Output: Generated warning message

[0351] Step 6: Send and display warning messages

[0352] The server transmits the generated warning messages to the terminals of the pilots and the controllers, and the terminals display the received warning messages on their user interfaces.

[0353] Input: The generated warning message

[0354] Specific operation: The server sends a warning message via the REST API, and the device displays the warning message on the user interface after receiving it.

[0355] Output: The displayed warning message

[0356] Step 7: User Action

[0357] Users (pilots and controllers) check the warning message and take necessary action.

[0358] Input: The displayed warning message

[0359] Specific Action: The user reads the warning message and acts based on the indicated problem and suggested solution. For example, the pilot reconfirms the instructions and recommunicates if necessary.

[0360] Output: Corresponding results

[0361] (Application example 2)

[0362] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0363] Communication between pilots and air traffic controllers is crucial for the safe operation of aircraft, but problems can occur due to communication errors or emotional states. A system is needed to detect such communication errors and emotional states in real time and respond quickly.

[0364] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving communication data from pilots and air traffic controllers in real time, speech recognition means for converting the received voice data into text data, means for inputting the text data into a generative AI model and analyzing it, means for detecting an error that has occurred and generating a warning message, means for sending the warning message to a terminal and displaying it, emotion engine means for analyzing emotions from the voice data, and means for generating a warning message based on the emotion analysis result and the error detection result. This makes it possible to detect communication errors and the user's emotional state in real time and respond quickly and appropriately.

[0365] "Pilot" refers to a person whose job is to operate and fly an aircraft.

[0366] "Air traffic controller" refers to an official whose job is to direct and manage the course and altitude of aircraft to ensure the safety and efficiency of air traffic.

[0367] "Communications data" refers to information such as voice and text messages exchanged between pilots and air traffic controllers.

[0368] "Real-time" refers to the immediate processing and reflection of events and data occurring in the present moment.

[0369] "Server" refers to a computer system for processing, storing, and managing data over a network.

[0370] "Audio data" refers to information recorded as audio.

[0371] "Text data" refers to digital information in the form of text that has been converted from voice or other data.

[0372] "Speech recognition means" refers to technology or devices for analyzing voice data and converting it into corresponding text data.

[0373] A "generative AI model" refers to an artificial intelligence model that generates new data and analytical results based on past data.

[0374] An "emotion engine" refers to technology or software for analyzing a user's emotional state from voice data, etc.

[0375] "Error detection means" refers to technology or devices for detecting abnormalities or errors in communication data or analysis data.

[0376] "Warning message" refers to a message containing a detected error or a warning.

[0377] "Terminal" refers to a device that a user directly operates to send and receive information.

[0378] "Means of analysis" refers to the technology or equipment used to process received data and understand and judge its contents.

[0379] "Emotion analysis results" refers to information about the user's emotional state obtained using the emotion engine.

[0380] "Means for generating a warning message" refers to a technology or device that creates a warning message based on the detected error or the results of sentiment analysis.

[0381] The present invention is applied to a security service system that detects communication errors and emotional states of pilots and air traffic controllers in real time and provides warning messages. The operation mode of the system and its implementation will be described below.

[0382] Main system components

[0383] The system includes the following main components:

[0384] 1. Communication data receiving means: The server receives voice communication data from pilots and air traffic controllers in real time. This data is temporarily stored in the server's storage.

[0385] 2. Speech recognition means: The server converts the received voice data into text data using a voice recognition engine (e.g., Google Cloud Speech-to-Text API or IBM Watson Speech to Text).

[0386] 3. Error detection method: The server inputs the text data into a generative AI model for analysis. The model uses a historical database to detect errors and abnormal conditions.

[0387] 4. Emotion engine means: The server analyzes the user's emotional state from the voice data. This engine uses voice analysis technology to detect emotions such as "stress" and "anxiety."

[0388] 5. Warning message generation method: Based on the results of sentiment analysis and error detection, the server generates a warning message, which includes specific problems and suggested solutions.

[0389] 6. Warning message sending means: The server generates a warning message and sends it to the device via REST API. The device can be a smartphone or smart glasses.

[0390] 7. Display means: The terminal displays the received warning message to the user, allowing the user to take prompt action.

[0391] Program processing explanation

[0392] The server receives voice communication data from pilots and air traffic controllers in real time via a communication data receiving means. It converts the received voice data into text data using a voice recognition means, and inputs the text data into a generative AI model for analysis. It then uses an emotion engine means to analyze the user's emotional state from the voice data. Based on the emotion analysis results and the data analyzed by the generative AI model, it detects the occurrence of an error and generates a warning message. Finally, it sends this warning message to the terminal via a REST API and displays it to the user.

[0393] Specific examples

[0394] For example, if a security operator says, "An emergency has occurred, please lock the door," this voice data is sent to the server in real time. The server uses speech recognition means to convert this into text data saying, "An emergency has occurred, please lock the door," and inputs it into the generative AI model and emotion engine. The generative AI model analyzes it and detects errors, and the emotion engine detects a "stressed" state. Based on this, the server generates a warning message such as, "An emergency has occurred. The operator appears to be stressed. Please respond quickly," which is sent to the terminal and displayed to the user.

[0395] Example prompt for a generative AI model:

[0396] This audio data contains an urgent message and emotion. Convert it to text and detect the text "Emergency, please lock the doors" and the emotion of stress.

[0397] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0398] Step 1:

[0399] The server receives communication data from pilots and air traffic controllers in real time. Specifically, the server's communication module receives voice data and temporarily stores it in storage. This step includes the process of acquiring communication data (input) in real time and storing it in the server's storage (output).

[0400] Step 2:

[0401] The server converts the received voice data into text data using a voice recognition means. Specifically, it uses the server's internal voice recognition engine (Google Cloud Speech-to-Text API or IBM Watson Speech to Text) to convert the voice data into text data. In this step, the voice data (input) is converted into text data (output).

[0402] Step 3:

[0403] The server inputs the converted text data into a generative AI model for analysis. Specifically, it identifies errors and anomalies in the text data based on a historical database. This involves the process of parsing text data (input) into error data (output).

[0404] Step 4:

[0405] The server analyzes the user's emotional state from the voice data using an emotion engine. Specifically, it uses voice analysis technology to detect emotions such as "stress" and "impatience" from the voice data. This step includes processing to generate emotion analysis results (output) from the voice data (input).

[0406] Step 5:

[0407] The server generates a warning message based on the emotion analysis results and error data. Specifically, it summarizes the detected error and content according to the emotional state into a warning message. In this step, the process of creating a warning message (output) from the error data and emotion analysis results (input) is carried out.

[0408] Step 6:

[0409] The server sends the generated warning message to the terminal via the REST API. Specifically, the warning message is sent to the terminal so that it is immediately displayed in the user interface. This step includes the process of sending the warning message (input) to the terminal and displaying it (output).

[0410] Step 7:

[0411] The terminal displays the received warning message to the user. The user can check this warning message and take prompt and appropriate action. In this step, the received warning message (input) is displayed on the user interface (output).

[0412] 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.

[0413] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. 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 a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0414] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0415] [Second embodiment]

[0416] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0417] 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.

[0418] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0419] 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.

[0420] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0421] 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 surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0422] 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.

[0423] 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.

[0424] 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 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.

[0425] 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.

[0426] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0427] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0428] This invention is a system that detects communication errors between aircraft pilots and air traffic controllers in real time to prevent accidents. This system includes a series of processes that consistently perform everything from receiving communication data to detecting errors and generating and transmitting warning messages.

[0429] System configuration

[0430] The system includes the following main components:

[0431] 1. Communication data receiving means

[0432] Server: Receives communication data from pilots and air traffic controllers in real time. This data is received in audio format and temporarily stored in the server's storage.

[0433] 2. Voice Recognition Method

[0434] Server: The received voice data is converted into text data using speech recognition technology, such as Google Cloud Speech-to-Text API or IBM Watson Speech to Text.

[0435] 3. Error Detection Methods

[0436] Server: The converted text data is fed into a generative AI model, which performs real-time analysis against a historical database to detect potential errors in the communication.

[0437] 4. Warning Message Generation Method

[0438] Server: If an error is detected, this information is used to generate an appropriate warning message, which will include the specific problem and a suggested solution.

[0439] 5. Means of transmission and display

[0440] Server: The generated warning messages are sent to the pilot and controller terminals via REST API.

[0441] Terminal: Receives warning messages and displays them on the user interface, allowing pilots and controllers to respond quickly.

[0442] Specific examples

[0443] 1. Receiving communication data

[0444] The server receives real-time voice data from the pilot saying, "Echo 123, requesting permission to descend." This data is immediately stored in the server's storage.

[0445] 2. Voice Recognition

[0446] The server sends the received voice data to a speech recognition engine and converts it into text data. The conversion result is text data that reads, "Echo 123, requesting permission to descend."

[0447] 3. Error Detection

[0448] The server then feeds this text data into a generative AI model, which analyzes it for signs of error. The model uses past data to determine, for example, that Echo 123 was being instructed to fly at a different altitude than other aircraft.

[0449] 4. Generating Warning Messages

[0450] The server generates a warning message saying "Echo 123 is being instructed to a different altitude. Please recheck."

[0451] 5. Transmission and Display

[0452] The server sends this warning message to the terminals of the pilot and the controller, and the message is displayed immediately. The user (pilot and controller) checks the warning and takes the necessary action.

[0453] Operation method

[0454] The system is designed to operate continuously while the aircraft is in operation. The server constantly receives and analyzes communication data, aiming to detect errors early. The terminal displays a warning message as soon as an error is detected, helping the user to take prompt action.

[0455] In this way, the present invention detects communication errors between pilots and air traffic controllers in real time, improving the safety of the entire system.

[0456] The processing flow will be explained below.

[0457] Step 1: Receiving communication data

[0458] The server receives real-time communication data from pilots and air traffic controllers, which is transmitted in voice format via the TCP / IP protocol.

[0459] The server temporarily stores the received audio data in a storage device, usually in a standard audio format such as WAV or MP3.

[0460] Step 2: Preprocessing the audio data

[0461] The server performs noise reduction on the received audio data, using Python libraries (e.g., Librosa and Pydub) to remove background noise and improve the audio quality.

[0462] The server prepares the pre-processed audio data for the next step.

[0463] Step 3: Voice Recognition

[0464] The server sends the preprocessed speech data to a speech recognition engine, which can use cloud-based speech recognition services such as Google Cloud Speech-to-Text API or IBM Watson Speech to Text.

[0465] The server receives the text data returned by the speech recognition engine and stores it as input data for the generative AI model.

[0466] Step 4: Analyzing text data and detecting errors

[0467] The server inputs the text data into a generative AI model, which uses a natural language processing engine such as GPT-3 or BERT.

[0468] The server uses a generative AI model to analyze the text data and detect signs of communication errors or human error based on a past database.

[0469] Step 5: Generate a warning message

[0470] The server generates a warning message based on the error information detected by the generative AI model, which includes the specific details of the error and suggested countermeasures.

[0471] The server prepares the alert message for transmission.

[0472] Step 6: Sending a warning message

[0473] The server sends the generated warning messages to the pilot and air traffic controller terminals via a REST API using HTTP POST requests.

[0474] Step 7: Displaying warning messages

[0475] The terminal receives the alert messages sent by the server and visually displays them in the user interface, using a GUI library (e.g., Tkinter, JavaFX, etc.).

[0476] Users (pilots and air traffic controllers) check the displayed warning message and take necessary action, for example, rechecking and correcting the communication content in which the error was detected.

[0477] The above is the flow of the specific processing steps of this system. Each step works in conjunction with the others to detect and warn of communication errors in real time.

[0478] Example 1

[0479] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0480] Misunderstandings and errors in communication between aircraft pilots and air traffic controllers can have a significant impact on flight safety. These errors need to be detected in real time and dealt with promptly, but current systems lack the technology to do so. Therefore, a system is needed that can detect communication errors between pilots and air traffic controllers in real time and issue immediate warnings.

[0481] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0482] In this invention, the server includes a means for receiving communication data from pilots and air traffic controllers in real time, a speech recognition means for converting the received voice data into text data, a means for inputting the text data into a generative AI model for analysis, a means for detecting an error that has occurred and generating a warning message, and a means for transmitting the warning message to a terminal for display. This enables real-time analysis of communication data, rapid detection and warning of errors, and immediate notification to pilots and air traffic controllers.

[0483] The "communication data receiving means" is a function for receiving voice communication data from pilots and air traffic controllers in real time.

[0484] The "voice recognition means" is a processing function for converting received voice data into text data.

[0485] A "generative AI model" is an artificial intelligence model that performs real-time analysis based on a past database.

[0486] The "error detection means" is a function that uses a generative AI model to analyze text data and detect communication errors.

[0487] The "warning message generating means" is a function that generates a warning message based on a detected error.

[0488] The "warning message sending means" is a function for sending the generated warning message to the terminal via the REST API.

[0489] The "warning message display means" is a function for displaying the transmitted warning message on the user interface.

[0490] The "noise removal means" is a preprocessing function for removing noise from audio data and improving sound quality.

[0491] "Real-time analysis" refers to the process of quickly analyzing received data in real time.

[0492] "Input to a generative AI model" refers to the means of supplying text data to a generative AI model and having the model analyze it.

[0493] "REST API" is a type of API (application programming interface) for exchanging warning messages between systems, and is a protocol for communication via HTTP.

[0494] The present invention is a system for detecting communication errors between aircraft pilots and air traffic controllers in real time to prevent accidents. A specific embodiment of this system is described below.

[0495] System configuration

[0496] The system includes the following main components:

[0497] 1. Communication data receiving means

[0498] The server receives communication data from pilots and air traffic controllers in real time. This communication data is received in audio format and temporarily stored in the server's storage.

[0499] 2. Voice Recognition Method

[0500] The server uses speech recognition technology to convert the received voice data into text data. Specifically, it uses services such as Google Cloud Speech-to-Text API and IBM Watson Speech to Text. The voice data is sent to the speech recognition engine and converted into text data.

[0501] 3. Error Detection Methods

[0502] The server then feeds the converted text data into a generative AI model, which performs real-time analysis based on a historical database to detect potential errors in the communication.

[0503] 4. Warning Message Generation Method

[0504] If an error is detected, the server will generate an appropriate warning message, which will include the specific problem and a recommended solution.

[0505] 5. Means of transmission and display

[0506] The server sends the generated warning messages to the pilot and air traffic controller terminals via a REST API.

[0507] The terminal receives the warning message and displays it on the user interface, allowing users (pilots and air traffic controllers) to react quickly.

[0508] Specific examples

[0509] A specific example of this system is shown below.

[0510] 1. Receiving communication data

[0511] The server receives the pilot's voice communication data in real time, such as "Echo 123, requesting permission to descend." This voice data is then stored in storage.

[0512] 2. Voice Recognition

[0513] The server uses the Google Cloud Speech-to-Text API to convert the received voice data into text data, for example, "Echo 123, requesting permission to descend."

[0514] 3. Error Detection

[0515] The server inputs this text data into a generative AI model for analysis, which uses past data to detect that Echo 123 was being instructed to fly at a different altitude than other aircraft.

[0516] 4. Generating Warning Messages

[0517] Based on the detected error information, the server generates a warning message saying "Echo 123 is being instructed to a different altitude. Please check again."

[0518] 5. Transmission and Display

[0519] The server sends this warning message to the terminals of the pilot and air traffic controller via REST API, where the users (pilot and air traffic controller) can check the warning message and take prompt action.

[0520] Examples of prompt statements

[0521] Here are some examples of specific prompts:

[0522] It receives voice data such as "Echo 123, requesting permission to descend" and specifies the prompt text that generates a warning message upon error detection.

[0523] In this way, this system will be able to detect communication errors between pilots and air traffic controllers in real time and quickly address them, which is expected to significantly improve the safety of aircraft operations.

[0524] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0525] Step 1:

[0526] Receiving communication data

[0527] The server receives voice communication data from pilots and air traffic controllers in real time. The input is the communication voice from the pilot or air traffic controller, which is temporarily stored in the server's storage. Specific operations include a process of capturing voice data through communication equipment and storing it in a storage device. The output is the voice data stored in the storage.

[0528] Step 2:

[0529] Voice Recognition

[0530] The server sends the stored voice data to the voice recognition engine. The input is the voice data stored in storage. The server converts the voice data into text data using a voice recognition service such as Google Cloud Speech-to-Text API or IBM Watson Speech to Text. Specific operations include making an API call and seamlessly converting the voice data into text. The output is text data.

[0531] Step 3:

[0532] Error Detection

[0533] The server inputs the converted text data into the generative AI model. The input is the text data generated in the speech recognition step. The server inputs this text data into the generative AI model and analyzes it in real time. Specific operations include the process of supplying text to the generative AI model and comparing it with a past database to identify errors. The output is information about the detected errors.

[0534] Step 4:

[0535] Generate a warning message

[0536] The server generates a warning message based on the error detection results. The input is the error information output in the error detection step. The server generates a warning message containing details of the error and suggests appropriate countermeasures. Specific operations include a process for dynamically generating a warning message based on the error information. The output is a warning message containing the specific problem and a suggested countermeasure.

[0537] Step 5:

[0538] Send and display

[0539] The server sends the generated warning message to the pilot's and air traffic controller's terminals via the REST API. The input is the warning message generated in the warning message generation step. The terminal displays the received warning message on its user interface. Specific operations include making a REST API call, sending a message, and displaying it on the user interface on the terminal side. The output is the warning message displayed on the terminal, which the user confirms.

[0540] (Application example 1)

[0541] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0542] In autonomous vehicles, communication errors between the driver and the system, or between vehicles, can lead to accidents or serious problems. There is a need for technology that can detect such errors in real time and warn the driver in advance. Currently, the means to detect these types of errors and respond quickly are not sufficiently developed, making improving safety a challenge.

[0543] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0544] In this invention, the server includes: means for receiving communication data from pilots and air traffic controllers in real time; speech recognition means for converting the received speech data into text data; means for inputting the text data into a generative AI model and analyzing it; means for detecting errors and generating warning messages; means for sending and displaying the warning messages on a terminal; means for monitoring voice and text communications between a driver and the autonomous driving system in real time in an autonomous driving vehicle system; means for analyzing whether the driver's instructions and the system's responses match; and means for generating warning messages and displaying them on a vehicle display or head-up display if they do not match. This enables real-time detection of communication errors and immediate warnings in autonomous driving vehicles.

[0545] A "pilot" is a person who is qualified to fly an aircraft and who actually operates the aircraft.

[0546] An "air traffic controller" is a person whose job is to monitor and direct the movements of aircraft in the air and on the ground in order to ensure the safe operation of aircraft.

[0547] "Communications Data" means information in the form of voice and text exchanged between pilots and air traffic controllers, or drivers and automated driving systems.

[0548] "Means for receiving in real time" refers to functions or devices for receiving communication data immediately without delay.

[0549] "Audio data" means information recorded or transmitted in the form of sound.

[0550] "Text data" refers to information expressed in characters and symbols.

[0551] "Speech recognition means" refers to technology or devices that convert voice data into text data.

[0552] A "generative AI model" is a model that uses artificial intelligence to analyze text data and detect errors.

[0553] An "occurring error" is an unintentional error or discrepancy that occurs in communication.

[0554] A "warning message" is information that is generated based on an error that has occurred, and that prompts attention or reconfirmation.

[0555] "Means for sending to and displaying at a terminal" refers to a function or device for sending the generated alert message to a specific device and displaying it to the user of that device.

[0556] An "autonomous vehicle system" is a vehicle system that incorporates technology and devices for automatically driving and controlling a vehicle.

[0557] The means for analyzing whether the "driver's instructions and the system's response" match refers to functions and devices for determining whether the instructions given by the driver and the response of the automated driving system match accurately.

[0558] A "display" is an electronic device for visually displaying information.

[0559] A "head-up display" is a device that displays information in front of the driver so that the driver can check it at the edge of their field of vision without having to look down.

[0560] This invention is a system that detects communication errors between the driver and the autonomous driving system in an autonomous vehicle, and between vehicles in real time, and generates and transmits warning messages. This system includes the following main components:

[0561] Hardware:

[0562] 1. Voice input system: A microphone for collecting the driver's instructions as voice data.

[0563] 2. On-board computer: A central processing unit that processes data.

[0564] 3. Display and Head-Up Display (HUD): A display device for displaying warning messages to the driver.

[0565] software:

[0566] 1. Speech recognition software: Technology that converts voice data into text data (e.g., Google Cloud Speech-to-Text API).

[0567] 2. Generative AI model: An artificial intelligence model (e.g., OpenAI API) for analyzing text data and detecting errors.

[0568] 3. Communication module: Software for sending and receiving communication data.

[0569] Server Processing

[0570] 1. Receiving audio data:

[0571] The server receives the driver's instructions as voice data from the autonomous vehicle's voice input system and temporarily stores them in storage.

[0572] 2. Audio to text conversion:

[0573] The server then sends the received audio data to speech recognition software, which converts it into text using a service like the Google Cloud Speech-to-Text API.

[0574] 3. Error detection:

[0575] The server then feeds the converted text data into a generative AI model that analyzes communication errors. The model uses a historical database and performs real-time analysis to detect potential errors.

[0576] 4. Generate a warning message:

[0577] If an error is detected, the server generates a warning message that describes the specific problem and suggests a solution.

[0578] 5. Sending and displaying warning messages:

[0579] The server sends the generated warning message to the vehicle's display or head-up display for display to the driver.

[0580] Specific examples

[0581] When the driver issues a voice command such as "Switch to autonomous driving mode," the voice data is received by the server and instantly converted into text data. The text data is then analyzed by a generative AI model to verify that the command was executed correctly. If the system's response does not match, a warning message such as "Switch to autonomous driving mode failed. Please continue manual operation" is generated and displayed on the vehicle's display.

[0582] Examples of prompts include:

[0583] Analyze the following communication for errors: "Switch to autopilot mode."

[0584] This will enable real-time detection of communication errors and immediate warnings in autonomous vehicles.

[0585] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0586] Step 1:

[0587] Receiving audio data

[0588] The server receives the driver's voice data in real time from the voice input system (microphone) of the autonomous vehicle. The input is the driver's voice command such as "switch to autonomous driving mode," and this voice data is temporarily stored in the server's storage.

[0589] Step 2:

[0590] Converting audio data to text

[0591] The server sends the received voice data to speech recognition software (e.g., Google Cloud Speech-to-Text API) and converts it into text data. The input is voice data, which undergoes speech recognition as data processing, and the output is the text data "Switch to autonomous driving mode."

[0592] Step 3:

[0593] Text data analysis

[0594] The server inputs the converted text data into a generative AI model (e.g., OpenAI API) and analyzes errors in the communication. The input is text data, which is analyzed by the AI ​​model as data processing and data calculation. The output is the result of whether or not an error exists. Specifically, the generative AI model is input with the prompt "Analyze the following communication for errors: 'Switch to autopilot mode.'" and the text data is analyzed.

[0595] Step 4:

[0596] Detecting errors

[0597] If an error occurs in the analysis results, the server extracts detailed information. The input is the analysis results from the generative AI model, and the server determines whether there is an error as a data calculation and identifies the part where the error occurred. The output is error information.

[0598] Step 5:

[0599] Generate a warning message

[0600] The server generates a warning message based on detailed error information. The input is the error information, and an appropriate warning text message is created by processing the data. Specifically, a warning message such as "Switching to autonomous driving mode has failed. Please continue manual operation" is output.

[0601] Step 6:

[0602] Sending and displaying warning messages

[0603] The server sends the generated warning message to the vehicle's display or head-up display (HUD) for display to the driver. The input is the warning message, and the message is sent via the communication module as data processing. The output is a warning display that the driver can check.

[0604] Through these steps, a system will be created that monitors in real time whether the driver's voice instructions are being properly reflected in the autonomous driving system, and if an error is detected, it will quickly generate a warning to notify the driver.

[0605] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0606] The present invention improves the effectiveness of error handling by combining a system that detects communication errors between pilots and air traffic controllers and provides warnings in real time with an emotion engine that recognizes user emotions. This system includes a series of processes that receive communication data, recognize voice, detect errors, generate and send warning messages, and analyze emotions.

[0607] System configuration

[0608] The system includes the following main components:

[0609] 1. Communication data receiving means

[0610] Server: Receives communication data from pilots and air traffic controllers in real time. This data is received in audio format and temporarily stored in the server's storage.

[0611] 2. Voice Recognition Method

[0612] Server: The received voice data is converted into text data using speech recognition technology, such as Google Cloud Speech-to-Text API or IBM Watson Speech to Text.

[0613] 3. Error Detection Methods

[0614] Server: The converted text data is fed into a generative AI model, which performs real-time analysis against a historical database to detect potential errors in the communication.

[0615] 4. Warning Message Generation Method

[0616] Server: If an error is detected, this information is used to generate an appropriate warning message, which will include the specific problem and a suggested solution.

[0617] 5. Means of transmission and display

[0618] Server: The generated warning messages are sent to the pilot and controller terminals via REST API.

[0619] Terminal: Receives warning messages and displays them on the user interface, allowing pilots and controllers to respond quickly.

[0620] 6. Emotion Engine

[0621] Server: Contains an emotion engine that analyzes the emotions of users (pilots and air traffic controllers) in real time from voice data. This engine uses voice analysis technology to provide emotion data to the generative AI model.

[0622] Specific examples

[0623] 1. Receiving communication data

[0624] The server receives real-time voice data from the pilot saying, "Echo 123, requesting permission to descend." This data is immediately stored in the server's storage.

[0625] 2. Voice Recognition

[0626] The server sends the received voice data to a speech recognition engine and converts it into text data. The conversion result is text data that reads, "Echo 123, requesting permission to descend."

[0627] 3. Emotion analysis

[0628] The server uses an emotion engine to analyze the user's emotions from the voice data. For example, if the pilot is anxious, the emotion engine will detect "stress."

[0629] 4. Error Detection

[0630] The server inputs text and emotion data into the generative AI model, which analyzes it for signs of error. The model compares it with past data and detects that Echo 123 was being instructed to fly at a different altitude than other aircraft.

[0631] 5. Generating Warning Messages

[0632] The server generates a warning message saying, "Echo 123 is being instructed to a different altitude. Please recheck. Pilot appears stressed."

[0633] 6. Transmission and Display

[0634] The server sends this warning message to the terminals of the pilot and the controller, and the message is displayed immediately. The user (pilot and controller) checks the warning and takes the necessary action.

[0635] Operation method

[0636] The system is designed to operate continuously while the aircraft is in operation. The server constantly receives and analyzes communication data, aiming for early detection of errors and emotions. The terminal displays an emotion-based warning message upon detecting an error, helping the user to take prompt and appropriate action.

[0637] In this way, the present invention detects pilot and air traffic controller communication errors and emotional states in real time, improving overall system safety and effective response.

[0638] The processing flow will be explained below.

[0639] Step 1: Receiving communication data

[0640] The server receives real-time communication data from pilots and air traffic controllers, which is transmitted in voice format via the TCP / IP protocol.

[0641] The server temporarily stores the received audio data in a storage device, usually in a standard audio format such as WAV or MP3.

[0642] Step 2: Preprocessing the audio data

[0643] The server performs noise reduction on the received audio data, using Python libraries (e.g., Librosa and Pydub) to remove background noise and improve the audio quality.

[0644] The server prepares the pre-processed audio data for the next step.

[0645] Step 3: Voice Recognition

[0646] The server sends the preprocessed speech data to a speech recognition engine, which can use cloud-based speech recognition services such as Google Cloud Speech-to-Text API or IBM Watson Speech to Text.

[0647] The server receives the text data returned by the speech recognition engine and stores it as input data for the generative AI model.

[0648] Step 4: Sentiment Analysis

[0649] The server inputs the preprocessed voice data or the text returned by the speech recognition engine into the emotion engine, which analyzes the user's emotions from the voice or text and identifies their emotional state, such as stress, anger, or joy.

[0650] The server converts and stores the emotion analysis results in a format that can be used by the generative AI model.

[0651] Step 5: Analyze text data and detect errors

[0652] The server inputs text and emotion data into a generative AI model, which uses natural language processing engines such as GPT-3 and BERT.

[0653] The server uses a generative AI model to analyze text data and emotional data, and compares it with a past database to detect signs of communication errors or human error.

[0654] Step 6: Generate a warning message

[0655] The server generates a warning message based on the error information and emotional information detected by the generative AI model. The warning message includes the specific details of the error, suggested countermeasures, and additional precautions according to the user's emotional state.

[0656] The server prepares the alert message for transmission.

[0657] Step 7: Sending a warning message

[0658] The server sends the generated warning messages to the pilot and air traffic controller terminals via a REST API using HTTP POST requests.

[0659] Step 8: Displaying warning messages

[0660] The terminal receives the alert messages sent by the server and visually displays them in the user interface, using a GUI library (e.g., Tkinter, JavaFX, etc.).

[0661] Users (pilots and air traffic controllers) check the displayed warning message and take necessary action, for example, rechecking and correcting the communication content in which the error was detected.

[0662] These are the specific processing steps of the system that combines the emotion engine. By linking these steps together, real-time detection of communication errors and emotional states and warnings are realized, further improving the operational safety of aircraft.

[0663] Example 2

[0664] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0665] Communications between pilots and air traffic controllers are prone to misunderstandings and miscommunications. Furthermore, the emotional state of the user during these communications (e.g., stress or impatience) can affect the detection and response to errors. While conventional systems recognize voice data and detect errors, they are unable to analyze the user's emotional state in real time and utilize it to improve response. This makes it difficult to detect errors early and improve the quality of response.

[0666] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0667] In this invention, the server includes a means for receiving communication data from pilots and air traffic controllers in real time, a speech recognition device for converting the received speech data into text data, a device for inputting the text data into a generative AI model for analysis, a device for detecting errors that have occurred and generating a warning message, a device for transmitting the warning message to a terminal and displaying it, an emotion recognition engine for analyzing user emotions in real time, and a device for inputting emotion data into the generative AI model for analysis. This makes it possible to detect errors in communication data in real time and quickly generate and provide appropriate warning messages that take the user's emotional state into consideration.

[0668] "Communication Data" means data in the form of voice exchanged between pilots and air traffic controllers.

[0669] "Speech recognition device" refers to a technology or device for converting voice data into text data.

[0670] A "generative AI model" refers to an artificial intelligence model that analyzes voice and text data based on learned past data.

[0671] "Error detection device" refers to a device that uses a generative AI model to detect potential errors in text data.

[0672] The term "warning message generating device" refers to a device that generates a warning message based on detected error information.

[0673] "Warning message transmitting device" refers to a device that transmits the generated warning messages to the terminals of pilots and air traffic controllers.

[0674] "Warning message display device" refers to a device that displays a received warning message on a user interface.

[0675] "Emotion recognition engine" refers to a technology or device that analyzes a user's emotional state from voice data.

[0676] "Emotion Data" refers to data regarding a user's emotional state analyzed by an emotion recognition engine.

[0677] Overall structure

[0678] The present invention is a system that detects communication errors between pilots and air traffic controllers and provides warnings in real time. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system enhances the effectiveness of error response. The system includes a series of processes that receive communication data, recognize voice, detect errors, generate and send warning messages, and analyze emotions.

[0679] Components

[0680] 1. Communication data receiving means:

[0681] The server receives real-time communication data from pilots and air traffic controllers. This data is received in audio format and temporarily stored in the server's storage.

[0682] 2. Voice recognition means:

[0683] The server converts the received voice data into text data using speech recognition technology, such as Google Cloud Speech-to-Text API or IBM Watson Speech to Text.

[0684] 3. Emotion Recognition Engine:

[0685] The server uses an emotion engine that analyzes the emotions of users (pilots and air traffic controllers) in real time from voice data. This engine uses voice analysis technology and provides emotion data to the generative AI model.

[0686] 4. Error detection methods:

[0687] The server then inputs the converted text and emotion data into a generative AI model, which performs real-time analysis based on a historical database to detect potential errors in communication.

[0688] 5. Warning message generation method:

[0689] If an error is detected, the server uses this information to generate an appropriate warning message, which includes the specific problem and a suggested solution.

[0690] 6. Means of transmission and display:

[0691] The server sends the generated warning messages to the pilot and controller terminals via a REST API.

[0692] The terminal receives the warning message and displays it on the user interface, allowing users (pilots and controllers) to respond quickly.

[0693] Specific examples

[0694] 1. Receiving communication data:

[0695] The server receives real-time voice data from the pilot saying, "Echo 123, requesting permission to descend." This data is immediately stored in the server's storage.

[0696] 2. Speech Recognition:

[0697] The server sends the received voice data to a speech recognition engine and converts it into text data. The conversion result is text data that reads, "Echo 123, requesting permission to descend."

[0698] 3. Emotion analysis:

[0699] The server uses an emotion engine to analyze the user's emotions from the voice data. For example, if the pilot is anxious, the emotion engine will detect "stress."

[0700] 4. Error detection:

[0701] The server inputs text data and emotion data into the generative AI model, which analyzes the error signs. The model compares it with past data and detects that Echo 123 was instructed to fly at a different altitude than other aircraft. An example prompt is "Please detect errors based on past communication data and emotion data."

[0702] 5. Generate warning messages:

[0703] The server generates a warning message saying, "Echo 123 is being instructed to a different altitude. Please recheck. Pilot appears stressed."

[0704] 6. Transmission and Display:

[0705] The server sends this warning message to the terminals of the pilot and the controller, and the message is displayed immediately. The user (pilot and controller) checks the warning and takes the necessary action.

[0706] Operation method

[0707] The system is designed to operate continuously while the aircraft is in operation. The server constantly receives and analyzes communication data, aiming for early detection of errors and emotions. The terminal displays an emotion-based warning message upon detecting an error, helping the user to take prompt and appropriate action.

[0708] In this way, the present invention detects pilot and air traffic controller communication errors and emotional states in real time, improving overall system safety and effective response.

[0709] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0710] Step 1: Receiving communication data

[0711] The server receives voice communication data transmitted in real time by pilots and air traffic controllers.

[0712] Input: Voice communication data from pilots and air traffic controllers

[0713] Specific operation: The server captures voice data via the aircraft's communication device and temporarily stores it in storage.

[0714] Output: Saved audio data

[0715] Step 2: Voice Recognition

[0716] The server sends the stored voice data to a voice recognition engine for conversion into text data.

[0717] Input: Saved audio data

[0718] Specific operation: The server connects to a speech recognition engine (e.g., Google Cloud Speech-to-Text API) and uploads the voice data. The speech recognition engine analyzes the voice data and generates corresponding text data.

[0719] Output: Converted text data

[0720] Step 3: Sentiment Analysis

[0721] The server sends the voice data to an emotion recognition engine to analyze the user's emotional state.

[0722] Input: Saved audio data

[0723] How it works: The server connects to the emotion recognition engine and uploads the voice data. The emotion recognition engine analyzes the tone, rhythm, and speed of the voice and generates emotion data (e.g., "stressed," "calm").

[0724] Output: Parsed emotion data

[0725] Step 4: Error detection

[0726] The server inputs the converted text data and emotion data into a generative AI model and analyzes it for signs of error.

[0727] Input: Converted text data and emotion data

[0728] How it works: The server uses the prompt "Please detect errors based on past communication data and emotion data" to input the data into the generative AI model, which then compares it with the past database to detect anomalies and inconsistencies.

[0729] Output: Detected error data

[0730] Step 5: Generate a warning message

[0731] The server generates a warning message based on the detected error data and emotion data.

[0732] Input: Detected error data and emotion data

[0733] Specific behavior: The server uses the generated error data and emotion data to generate an appropriate warning message, including the specific problem and a suggested solution (e.g., "Echo 123 is being instructed to a different altitude. Please reconfirm. The pilot appears stressed.").

[0734] Output: Generated warning message

[0735] Step 6: Send and display warning messages

[0736] The server transmits the generated warning messages to the terminals of the pilots and the controllers, and the terminals display the received warning messages on their user interfaces.

[0737] Input: The generated warning message

[0738] Specific operation: The server sends a warning message via the REST API, and the device displays the warning message on the user interface after receiving it.

[0739] Output: The displayed warning message

[0740] Step 7: User Action

[0741] Users (pilots and controllers) check the warning message and take necessary action.

[0742] Input: The displayed warning message

[0743] Specific Action: The user reads the warning message and acts based on the indicated problem and suggested solution. For example, the pilot reconfirms the instructions and recommunicates if necessary.

[0744] Output: Corresponding results

[0745] (Application example 2)

[0746] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0747] Communication between pilots and air traffic controllers is crucial for the safe operation of aircraft, but problems can occur due to communication errors or emotional states. A system is needed to detect such communication errors and emotional states in real time and respond quickly.

[0748] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving communication data from pilots and air traffic controllers in real time, speech recognition means for converting the received voice data into text data, means for inputting the text data into a generative AI model and analyzing it, means for detecting an error that has occurred and generating a warning message, means for sending the warning message to a terminal and displaying it, emotion engine means for analyzing emotions from the voice data, and means for generating a warning message based on the emotion analysis result and the error detection result. This makes it possible to detect communication errors and the user's emotional state in real time and respond quickly and appropriately.

[0749] "Pilot" refers to a person whose job is to operate and fly an aircraft.

[0750] "Air traffic controller" refers to an official whose job is to direct and manage the course and altitude of aircraft to ensure the safety and efficiency of air traffic.

[0751] "Communications data" refers to information such as voice and text messages exchanged between pilots and air traffic controllers.

[0752] "Real-time" refers to the immediate processing and reflection of events and data occurring in the present moment.

[0753] "Server" refers to a computer system for processing, storing, and managing data over a network.

[0754] "Audio data" refers to information recorded as audio.

[0755] "Text data" refers to digital information in the form of text that has been converted from voice or other data.

[0756] "Speech recognition means" refers to technology or devices for analyzing voice data and converting it into corresponding text data.

[0757] A "generative AI model" refers to an artificial intelligence model that generates new data and analytical results based on past data.

[0758] An "emotion engine" refers to technology or software for analyzing a user's emotional state from voice data, etc.

[0759] "Error detection means" refers to technology or devices for detecting abnormalities or errors in communication data or analysis data.

[0760] "Warning message" refers to a message containing a detected error or a warning.

[0761] "Terminal" refers to a device that a user directly operates to send and receive information.

[0762] "Means of analysis" refers to the technology or equipment used to process received data and understand and judge its contents.

[0763] "Emotion analysis results" refers to information about the user's emotional state obtained using the emotion engine.

[0764] "Means for generating a warning message" refers to a technology or device that creates a warning message based on the detected error or the results of sentiment analysis.

[0765] The present invention is applied to a security service system that detects communication errors and emotional states of pilots and air traffic controllers in real time and provides warning messages. The operation mode of the system and its implementation will be described below.

[0766] Main system components

[0767] The system includes the following main components:

[0768] 1. Communication data receiving means: The server receives voice communication data from pilots and air traffic controllers in real time. This data is temporarily stored in the server's storage.

[0769] 2. Speech recognition means: The server converts the received voice data into text data using a voice recognition engine (e.g., Google Cloud Speech-to-Text API or IBM Watson Speech to Text).

[0770] 3. Error detection method: The server inputs the text data into a generative AI model for analysis. The model uses a historical database to detect errors and abnormal conditions.

[0771] 4. Emotion engine means: The server analyzes the user's emotional state from the voice data. This engine uses voice analysis technology to detect emotions such as "stress" and "anxiety."

[0772] 5. Warning message generation method: Based on the results of sentiment analysis and error detection, the server generates a warning message, which includes specific problems and suggested solutions.

[0773] 6. Warning message sending means: The server generates a warning message and sends it to the device via REST API. The device can be a smartphone or smart glasses.

[0774] 7. Display means: The terminal displays the received warning message to the user, allowing the user to take prompt action.

[0775] Program processing explanation

[0776] The server receives voice communication data from pilots and air traffic controllers in real time via a communication data receiving means. It converts the received voice data into text data using a voice recognition means, and inputs the text data into a generative AI model for analysis. It then uses an emotion engine means to analyze the user's emotional state from the voice data. Based on the emotion analysis results and the data analyzed by the generative AI model, it detects the occurrence of an error and generates a warning message. Finally, it sends this warning message to the terminal via a REST API and displays it to the user.

[0777] Specific examples

[0778] For example, if a security operator says, "An emergency has occurred, please lock the door," this voice data is sent to the server in real time. The server uses speech recognition means to convert this into text data saying, "An emergency has occurred, please lock the door," and inputs it into the generative AI model and emotion engine. The generative AI model analyzes it and detects errors, and the emotion engine detects a "stressed" state. Based on this, the server generates a warning message such as, "An emergency has occurred. The operator appears to be stressed. Please respond quickly," which is sent to the terminal and displayed to the user.

[0779] Example prompt for a generative AI model:

[0780] This audio data contains an urgent message and emotion. Convert it to text and detect the text "Emergency, please lock the doors" and the emotion of stress.

[0781] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0782] Step 1:

[0783] The server receives communication data from pilots and air traffic controllers in real time. Specifically, the server's communication module receives voice data and temporarily stores it in storage. This step includes the process of acquiring communication data (input) in real time and storing it in the server's storage (output).

[0784] Step 2:

[0785] The server converts the received voice data into text data using a voice recognition means. Specifically, it uses the server's internal voice recognition engine (Google Cloud Speech-to-Text API or IBM Watson Speech to Text) to convert the voice data into text data. In this step, the voice data (input) is converted into text data (output).

[0786] Step 3:

[0787] The server inputs the converted text data into a generative AI model for analysis. Specifically, it identifies errors and anomalies in the text data based on a historical database. This involves the process of parsing text data (input) into error data (output).

[0788] Step 4:

[0789] The server analyzes the user's emotional state from the voice data using an emotion engine. Specifically, it uses voice analysis technology to detect emotions such as "stress" and "impatience" from the voice data. This step includes processing to generate emotion analysis results (output) from the voice data (input).

[0790] Step 5:

[0791] The server generates a warning message based on the emotion analysis results and error data. Specifically, it summarizes the detected error and content according to the emotional state into a warning message. In this step, the process of creating a warning message (output) from the error data and emotion analysis results (input) is carried out.

[0792] Step 6:

[0793] The server sends the generated warning message to the terminal via the REST API. Specifically, the warning message is sent to the terminal so that it is immediately displayed in the user interface. This step includes the process of sending the warning message (input) to the terminal and displaying it (output).

[0794] Step 7:

[0795] The terminal displays the received warning message to the user. The user can check this warning message and take prompt and appropriate action. In this step, the received warning message (input) is displayed on the user interface (output).

[0796] 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.

[0797] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. 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 a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0798] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0799] [Third embodiment]

[0800] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0801] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0802] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0803] 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.

[0804] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0805] 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 surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0806] 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.

[0807] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0808] 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 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.

[0809] 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.

[0810] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0811] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0812] This invention is a system that detects communication errors between aircraft pilots and air traffic controllers in real time to prevent accidents. This system includes a series of processes that consistently perform everything from receiving communication data to detecting errors and generating and transmitting warning messages.

[0813] System configuration

[0814] The system includes the following main components:

[0815] 1. Communication data receiving means

[0816] Server: Receives communication data from pilots and air traffic controllers in real time. This data is received in audio format and temporarily stored in the server's storage.

[0817] 2. Voice Recognition Method

[0818] Server: The received voice data is converted into text data using speech recognition technology, such as Google Cloud Speech-to-Text API or IBM Watson Speech to Text.

[0819] 3. Error Detection Methods

[0820] Server: The converted text data is fed into a generative AI model, which performs real-time analysis against a historical database to detect potential errors in the communication.

[0821] 4. Warning Message Generation Method

[0822] Server: If an error is detected, this information is used to generate an appropriate warning message, which will include the specific problem and a suggested solution.

[0823] 5. Means of transmission and display

[0824] Server: The generated warning messages are sent to the pilot and controller terminals via REST API.

[0825] Terminal: Receives warning messages and displays them on the user interface, allowing pilots and controllers to respond quickly.

[0826] Specific examples

[0827] 1. Receiving communication data

[0828] The server receives real-time voice data from the pilot saying, "Echo 123, requesting permission to descend." This data is immediately stored in the server's storage.

[0829] 2. Voice Recognition

[0830] The server sends the received voice data to a speech recognition engine and converts it into text data. The conversion result is text data that reads, "Echo 123, requesting permission to descend."

[0831] 3. Error Detection

[0832] The server then feeds this text data into a generative AI model, which analyzes it for signs of error. The model uses past data to determine, for example, that Echo 123 was being instructed to fly at a different altitude than other aircraft.

[0833] 4. Generating Warning Messages

[0834] The server generates a warning message saying "Echo 123 is being instructed to a different altitude. Please recheck."

[0835] 5. Transmission and Display

[0836] The server sends this warning message to the terminals of the pilot and the controller, and the message is displayed immediately. The user (pilot and controller) checks the warning and takes the necessary action.

[0837] Operation method

[0838] The system is designed to operate continuously while the aircraft is in operation. The server constantly receives and analyzes communication data, aiming to detect errors early. The terminal displays a warning message as soon as an error is detected, helping the user to take prompt action.

[0839] In this way, the present invention detects communication errors between pilots and air traffic controllers in real time, improving the safety of the entire system.

[0840] The processing flow will be explained below.

[0841] Step 1: Receiving communication data

[0842] The server receives real-time communication data from pilots and air traffic controllers, which is transmitted in voice format via the TCP / IP protocol.

[0843] The server temporarily stores the received audio data in a storage device, usually in a standard audio format such as WAV or MP3.

[0844] Step 2: Preprocessing the audio data

[0845] The server performs noise reduction on the received audio data, using Python libraries (e.g., Librosa and Pydub) to remove background noise and improve the audio quality.

[0846] The server prepares the pre-processed audio data for the next step.

[0847] Step 3: Voice Recognition

[0848] The server sends the preprocessed speech data to a speech recognition engine, which can use cloud-based speech recognition services such as Google Cloud Speech-to-Text API or IBM Watson Speech to Text.

[0849] The server receives the text data returned by the speech recognition engine and stores it as input data for the generative AI model.

[0850] Step 4: Analyzing text data and detecting errors

[0851] The server inputs the text data into a generative AI model, which uses a natural language processing engine such as GPT-3 or BERT.

[0852] The server uses a generative AI model to analyze the text data and detect signs of communication errors or human error based on a past database.

[0853] Step 5: Generate a warning message

[0854] The server generates a warning message based on the error information detected by the generative AI model, which includes the specific details of the error and suggested countermeasures.

[0855] The server prepares the alert message for transmission.

[0856] Step 6: Sending a warning message

[0857] The server sends the generated warning messages to the pilot and air traffic controller terminals via a REST API using HTTP POST requests.

[0858] Step 7: Displaying warning messages

[0859] The terminal receives the alert messages sent by the server and visually displays them in the user interface, using a GUI library (e.g., Tkinter, JavaFX, etc.).

[0860] Users (pilots and air traffic controllers) check the displayed warning message and take necessary action, for example, rechecking and correcting the communication content in which the error was detected.

[0861] The above is the flow of the specific processing steps of this system. Each step works in conjunction with the others to detect and warn of communication errors in real time.

[0862] Example 1

[0863] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0864] Misunderstandings and errors in communication between aircraft pilots and air traffic controllers can have a significant impact on flight safety. These errors need to be detected in real time and dealt with promptly, but current systems lack the technology to do so. Therefore, a system is needed that can detect communication errors between pilots and air traffic controllers in real time and issue immediate warnings.

[0865] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0866] In this invention, the server includes a means for receiving communication data from pilots and air traffic controllers in real time, a speech recognition means for converting the received voice data into text data, a means for inputting the text data into a generative AI model for analysis, a means for detecting an error that has occurred and generating a warning message, and a means for transmitting the warning message to a terminal for display. This enables real-time analysis of communication data, rapid detection and warning of errors, and immediate notification to pilots and air traffic controllers.

[0867] The "communication data receiving means" is a function for receiving voice communication data from pilots and air traffic controllers in real time.

[0868] The "voice recognition means" is a processing function for converting received voice data into text data.

[0869] A "generative AI model" is an artificial intelligence model that performs real-time analysis based on a past database.

[0870] The "error detection means" is a function that uses a generative AI model to analyze text data and detect communication errors.

[0871] The "warning message generating means" is a function that generates a warning message based on a detected error.

[0872] The "warning message sending means" is a function for sending the generated warning message to the terminal via the REST API.

[0873] The "warning message display means" is a function for displaying the transmitted warning message on the user interface.

[0874] The "noise removal means" is a preprocessing function for removing noise from audio data and improving sound quality.

[0875] "Real-time analysis" refers to the process of quickly analyzing received data in real time.

[0876] "Input to a generative AI model" refers to the means of supplying text data to a generative AI model and having the model analyze it.

[0877] "REST API" is a type of API (application programming interface) for exchanging warning messages between systems, and is a protocol for communication via HTTP.

[0878] The present invention is a system for detecting communication errors between aircraft pilots and air traffic controllers in real time to prevent accidents. A specific embodiment of this system is described below.

[0879] System configuration

[0880] The system includes the following main components:

[0881] 1. Communication data receiving means

[0882] The server receives communication data from pilots and air traffic controllers in real time. This communication data is received in audio format and temporarily stored in the server's storage.

[0883] 2. Voice Recognition Method

[0884] The server uses speech recognition technology to convert the received voice data into text data. Specifically, it uses services such as Google Cloud Speech-to-Text API and IBM Watson Speech to Text. The voice data is sent to the speech recognition engine and converted into text data.

[0885] 3. Error Detection Methods

[0886] The server then feeds the converted text data into a generative AI model, which performs real-time analysis based on a historical database to detect potential errors in the communication.

[0887] 4. Warning Message Generation Method

[0888] If an error is detected, the server will generate an appropriate warning message, which will include the specific problem and a recommended solution.

[0889] 5. Means of transmission and display

[0890] The server sends the generated warning messages to the pilot and air traffic controller terminals via a REST API.

[0891] The terminal receives the warning message and displays it on the user interface, allowing users (pilots and air traffic controllers) to react quickly.

[0892] Specific examples

[0893] A specific example of this system is shown below.

[0894] 1. Receiving communication data

[0895] The server receives the pilot's voice communication data in real time, such as "Echo 123, requesting permission to descend." This voice data is then stored in storage.

[0896] 2. Voice Recognition

[0897] The server uses the Google Cloud Speech-to-Text API to convert the received voice data into text data, for example, "Echo 123, requesting permission to descend."

[0898] 3. Error Detection

[0899] The server inputs this text data into a generative AI model for analysis, which uses past data to detect that Echo 123 was being instructed to fly at a different altitude than other aircraft.

[0900] 4. Generating Warning Messages

[0901] Based on the detected error information, the server generates a warning message saying "Echo 123 is being instructed to a different altitude. Please check again."

[0902] 5. Transmission and Display

[0903] The server sends this warning message to the terminals of the pilot and air traffic controller via REST API, where the users (pilot and air traffic controller) can check the warning message and take prompt action.

[0904] Examples of prompt statements

[0905] Here are some examples of specific prompts:

[0906] It receives voice data such as "Echo 123, requesting permission to descend" and specifies the prompt text that generates a warning message upon error detection.

[0907] In this way, this system will be able to detect communication errors between pilots and air traffic controllers in real time and quickly address them, which is expected to significantly improve the safety of aircraft operations.

[0908] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0909] Step 1:

[0910] Receiving communication data

[0911] The server receives voice communication data from pilots and air traffic controllers in real time. The input is the communication voice from the pilot or air traffic controller, which is temporarily stored in the server's storage. Specific operations include a process of capturing voice data through communication equipment and storing it in a storage device. The output is the voice data stored in the storage.

[0912] Step 2:

[0913] Voice Recognition

[0914] The server sends the stored voice data to the voice recognition engine. The input is the voice data stored in storage. The server converts the voice data into text data using a voice recognition service such as Google Cloud Speech-to-Text API or IBM Watson Speech to Text. Specific operations include making an API call and seamlessly converting the voice data into text. The output is text data.

[0915] Step 3:

[0916] Error Detection

[0917] The server inputs the converted text data into the generative AI model. The input is the text data generated in the speech recognition step. The server inputs this text data into the generative AI model and analyzes it in real time. Specific operations include the process of supplying text to the generative AI model and comparing it with a past database to identify errors. The output is information about the detected errors.

[0918] Step 4:

[0919] Generate a warning message

[0920] The server generates a warning message based on the error detection results. The input is the error information output in the error detection step. The server generates a warning message containing details of the error and suggests appropriate countermeasures. Specific operations include a process for dynamically generating a warning message based on the error information. The output is a warning message containing the specific problem and a suggested countermeasure.

[0921] Step 5:

[0922] Send and display

[0923] The server sends the generated warning message to the pilot's and air traffic controller's terminals via the REST API. The input is the warning message generated in the warning message generation step. The terminal displays the received warning message on its user interface. Specific operations include making a REST API call, sending a message, and displaying it on the user interface on the terminal side. The output is the warning message displayed on the terminal, which the user confirms.

[0924] (Application example 1)

[0925] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0926] In autonomous vehicles, communication errors between the driver and the system, or between vehicles, can lead to accidents or serious problems. There is a need for technology that can detect such errors in real time and warn the driver in advance. Currently, the means to detect these types of errors and respond quickly are not sufficiently developed, making improving safety a challenge.

[0927] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0928] In this invention, the server includes: means for receiving communication data from pilots and air traffic controllers in real time; speech recognition means for converting the received speech data into text data; means for inputting the text data into a generative AI model and analyzing it; means for detecting errors and generating warning messages; means for sending and displaying the warning messages on a terminal; means for monitoring voice and text communications between a driver and the autonomous driving system in real time in an autonomous driving vehicle system; means for analyzing whether the driver's instructions and the system's responses match; and means for generating warning messages and displaying them on a vehicle display or head-up display if they do not match. This enables real-time detection of communication errors and immediate warnings in autonomous driving vehicles.

[0929] A "pilot" is a person who is qualified to fly an aircraft and who actually operates the aircraft.

[0930] An "air traffic controller" is a person whose job is to monitor and direct the movements of aircraft in the air and on the ground in order to ensure the safe operation of aircraft.

[0931] "Communications Data" means information in the form of voice and text exchanged between pilots and air traffic controllers, or drivers and automated driving systems.

[0932] "Means for receiving in real time" refers to functions or devices for receiving communication data immediately without delay.

[0933] "Audio data" means information recorded or transmitted in the form of sound.

[0934] "Text data" refers to information expressed in characters and symbols.

[0935] "Speech recognition means" refers to technology or devices that convert voice data into text data.

[0936] A "generative AI model" is a model that uses artificial intelligence to analyze text data and detect errors.

[0937] An "occurring error" is an unintentional error or discrepancy that occurs in communication.

[0938] A "warning message" is information that is generated based on an error that has occurred, and that prompts attention or reconfirmation.

[0939] "Means for sending to and displaying at a terminal" refers to a function or device for sending the generated alert message to a specific device and displaying it to the user of that device.

[0940] An "autonomous vehicle system" is a vehicle system that incorporates technology and devices for automatically driving and controlling a vehicle.

[0941] The means for analyzing whether the "driver's instructions and the system's response" match refers to functions and devices for determining whether the instructions given by the driver and the response of the automated driving system match accurately.

[0942] A "display" is an electronic device for visually displaying information.

[0943] A "head-up display" is a device that displays information in front of the driver so that the driver can check it at the edge of their field of vision without having to look down.

[0944] This invention is a system that detects communication errors between the driver and the autonomous driving system in an autonomous vehicle, and between vehicles in real time, and generates and transmits warning messages. This system includes the following main components:

[0945] Hardware:

[0946] 1. Voice input system: A microphone for collecting the driver's instructions as voice data.

[0947] 2. On-board computer: A central processing unit that processes data.

[0948] 3. Display and Head-Up Display (HUD): A display device for displaying warning messages to the driver.

[0949] software:

[0950] 1. Speech recognition software: Technology that converts voice data into text data (e.g., Google Cloud Speech-to-Text API).

[0951] 2. Generative AI model: An artificial intelligence model (e.g., OpenAI API) for analyzing text data and detecting errors.

[0952] 3. Communication module: Software for sending and receiving communication data.

[0953] Server Processing

[0954] 1. Receiving audio data:

[0955] The server receives the driver's instructions as voice data from the autonomous vehicle's voice input system and temporarily stores them in storage.

[0956] 2. Audio to text conversion:

[0957] The server then sends the received audio data to speech recognition software, which converts it into text using a service like the Google Cloud Speech-to-Text API.

[0958] 3. Error detection:

[0959] The server then feeds the converted text data into a generative AI model that analyzes communication errors. The model uses a historical database and performs real-time analysis to detect potential errors.

[0960] 4. Generate a warning message:

[0961] If an error is detected, the server generates a warning message that describes the specific problem and suggests a solution.

[0962] 5. Sending and displaying warning messages:

[0963] The server sends the generated warning message to the vehicle's display or head-up display for display to the driver.

[0964] Specific examples

[0965] When the driver issues a voice command such as "Switch to autonomous driving mode," the voice data is received by the server and instantly converted into text data. The text data is then analyzed by a generative AI model to verify that the command was executed correctly. If the system's response does not match, a warning message such as "Switch to autonomous driving mode failed. Please continue manual operation" is generated and displayed on the vehicle's display.

[0966] Examples of prompts include:

[0967] Analyze the following communication for errors: "Switch to autopilot mode."

[0968] This will enable real-time detection of communication errors and immediate warnings in autonomous vehicles.

[0969] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0970] Step 1:

[0971] Receiving audio data

[0972] The server receives the driver's voice data in real time from the voice input system (microphone) of the autonomous vehicle. The input is the driver's voice command such as "switch to autonomous driving mode," and this voice data is temporarily stored in the server's storage.

[0973] Step 2:

[0974] Converting audio data to text

[0975] The server sends the received voice data to speech recognition software (e.g., Google Cloud Speech-to-Text API) and converts it into text data. The input is voice data, which undergoes speech recognition as data processing, and the output is the text data "Switch to autonomous driving mode."

[0976] Step 3:

[0977] Text data analysis

[0978] The server inputs the converted text data into a generative AI model (e.g., OpenAI API) and analyzes errors in the communication. The input is text data, which is analyzed by the AI ​​model as data processing and data calculation. The output is the result of whether or not an error exists. Specifically, the generative AI model is input with the prompt "Analyze the following communication for errors: 'Switch to autopilot mode.'" and the text data is analyzed.

[0979] Step 4:

[0980] Detecting errors

[0981] If an error occurs in the analysis results, the server extracts detailed information. The input is the analysis results from the generative AI model, and the server determines whether there is an error as a data calculation and identifies the part where the error occurred. The output is error information.

[0982] Step 5:

[0983] Generate a warning message

[0984] The server generates a warning message based on detailed error information. The input is the error information, and an appropriate warning text message is created by processing the data. Specifically, a warning message such as "Switching to autonomous driving mode has failed. Please continue manual operation" is output.

[0985] Step 6:

[0986] Sending and displaying warning messages

[0987] The server sends the generated warning message to the vehicle's display or head-up display (HUD) for display to the driver. The input is the warning message, and the message is sent via the communication module as data processing. The output is a warning display that the driver can check.

[0988] Through these steps, a system will be created that monitors in real time whether the driver's voice instructions are being properly reflected in the autonomous driving system, and if an error is detected, it will quickly generate a warning to notify the driver.

[0989] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0990] The present invention improves the effectiveness of error handling by combining a system that detects communication errors between pilots and air traffic controllers and provides warnings in real time with an emotion engine that recognizes user emotions. This system includes a series of processes that receive communication data, recognize voice, detect errors, generate and send warning messages, and analyze emotions.

[0991] System configuration

[0992] The system includes the following main components:

[0993] 1. Communication data receiving means

[0994] Server: Receives communication data from pilots and air traffic controllers in real time. This data is received in audio format and temporarily stored in the server's storage.

[0995] 2. Voice Recognition Method

[0996] Server: The received voice data is converted into text data using speech recognition technology, such as Google Cloud Speech-to-Text API or IBM Watson Speech to Text.

[0997] 3. Error Detection Methods

[0998] Server: The converted text data is fed into a generative AI model, which performs real-time analysis against a historical database to detect potential errors in the communication.

[0999] 4. Warning Message Generation Method

[1000] Server: If an error is detected, this information is used to generate an appropriate warning message, which will include the specific problem and a suggested solution.

[1001] 5. Means of transmission and display

[1002] Server: The generated warning messages are sent to the pilot and controller terminals via REST API.

[1003] Terminal: Receives warning messages and displays them on the user interface, allowing pilots and controllers to respond quickly.

[1004] 6. Emotion Engine

[1005] Server: Contains an emotion engine that analyzes the emotions of users (pilots and air traffic controllers) in real time from voice data. This engine uses voice analysis technology to provide emotion data to the generative AI model.

[1006] Specific examples

[1007] 1. Receiving communication data

[1008] The server receives real-time voice data from the pilot saying, "Echo 123, requesting permission to descend." This data is immediately stored in the server's storage.

[1009] 2. Voice Recognition

[1010] The server sends the received voice data to a speech recognition engine and converts it into text data. The conversion result is text data that reads, "Echo 123, requesting permission to descend."

[1011] 3. Emotion analysis

[1012] The server uses an emotion engine to analyze the user's emotions from the voice data. For example, if the pilot is anxious, the emotion engine will detect "stress."

[1013] 4. Error Detection

[1014] The server inputs text and emotion data into the generative AI model, which analyzes it for signs of error. The model compares it with past data and detects that Echo 123 was being instructed to fly at a different altitude than other aircraft.

[1015] 5. Generating Warning Messages

[1016] The server generates a warning message saying, "Echo 123 is being instructed to a different altitude. Please recheck. Pilot appears stressed."

[1017] 6. Transmission and Display

[1018] The server sends this warning message to the terminals of the pilot and the controller, and the message is displayed immediately. The user (pilot and controller) checks the warning and takes the necessary action.

[1019] Operation method

[1020] The system is designed to operate continuously while the aircraft is in operation. The server constantly receives and analyzes communication data, aiming for early detection of errors and emotions. The terminal displays an emotion-based warning message upon detecting an error, helping the user to take prompt and appropriate action.

[1021] In this way, the present invention detects pilot and air traffic controller communication errors and emotional states in real time, improving overall system safety and effective response.

[1022] The processing flow will be explained below.

[1023] Step 1: Receiving communication data

[1024] The server receives real-time communication data from pilots and air traffic controllers, which is transmitted in voice format via the TCP / IP protocol.

[1025] The server temporarily stores the received audio data in a storage device, usually in a standard audio format such as WAV or MP3.

[1026] Step 2: Preprocessing the audio data

[1027] The server performs noise reduction on the received audio data, using Python libraries (e.g., Librosa and Pydub) to remove background noise and improve the audio quality.

[1028] The server prepares the pre-processed audio data for the next step.

[1029] Step 3: Voice Recognition

[1030] The server sends the preprocessed speech data to a speech recognition engine, which can use cloud-based speech recognition services such as Google Cloud Speech-to-Text API or IBM Watson Speech to Text.

[1031] The server receives the text data returned by the speech recognition engine and stores it as input data for the generative AI model.

[1032] Step 4: Sentiment Analysis

[1033] The server inputs the preprocessed voice data or the text returned by the speech recognition engine into the emotion engine, which analyzes the user's emotions from the voice or text and identifies their emotional state, such as stress, anger, or joy.

[1034] The server converts and stores the emotion analysis results in a format that can be used by the generative AI model.

[1035] Step 5: Analyze text data and detect errors

[1036] The server inputs text and emotion data into a generative AI model, which uses natural language processing engines such as GPT-3 and BERT.

[1037] The server uses a generative AI model to analyze text data and emotional data, and compares it with a past database to detect signs of communication errors or human error.

[1038] Step 6: Generate a warning message

[1039] The server generates a warning message based on the error information and emotional information detected by the generative AI model. The warning message includes the specific details of the error, suggested countermeasures, and additional precautions according to the user's emotional state.

[1040] The server prepares the alert message for transmission.

[1041] Step 7: Sending a warning message

[1042] The server sends the generated warning messages to the pilot and air traffic controller terminals via a REST API using HTTP POST requests.

[1043] Step 8: Displaying warning messages

[1044] The terminal receives the alert messages sent by the server and visually displays them in the user interface, using a GUI library (e.g., Tkinter, JavaFX, etc.).

[1045] Users (pilots and air traffic controllers) check the displayed warning message and take necessary action, for example, rechecking and correcting the communication content in which the error was detected.

[1046] These are the specific processing steps of the system that combines the emotion engine. By linking these steps together, real-time detection of communication errors and emotional states and warnings are realized, further improving the operational safety of aircraft.

[1047] Example 2

[1048] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1049] Communications between pilots and air traffic controllers are prone to misunderstandings and miscommunications. Furthermore, the emotional state of the user during these communications (e.g., stress or impatience) can affect the detection and response to errors. While conventional systems recognize voice data and detect errors, they are unable to analyze the user's emotional state in real time and utilize it to improve response. This makes it difficult to detect errors early and improve the quality of response.

[1050] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1051] In this invention, the server includes a means for receiving communication data from pilots and air traffic controllers in real time, a speech recognition device for converting the received speech data into text data, a device for inputting the text data into a generative AI model for analysis, a device for detecting errors that have occurred and generating a warning message, a device for transmitting the warning message to a terminal and displaying it, an emotion recognition engine for analyzing user emotions in real time, and a device for inputting emotion data into the generative AI model for analysis. This makes it possible to detect errors in communication data in real time and quickly generate and provide appropriate warning messages that take the user's emotional state into consideration.

[1052] "Communication Data" means data in the form of voice exchanged between pilots and air traffic controllers.

[1053] "Speech recognition device" refers to a technology or device for converting voice data into text data.

[1054] A "generative AI model" refers to an artificial intelligence model that analyzes voice and text data based on learned past data.

[1055] "Error detection device" refers to a device that uses a generative AI model to detect potential errors in text data.

[1056] The term "warning message generating device" refers to a device that generates a warning message based on detected error information.

[1057] "Warning message transmitting device" refers to a device that transmits the generated warning messages to the terminals of pilots and air traffic controllers.

[1058] "Warning message display device" refers to a device that displays a received warning message on a user interface.

[1059] "Emotion recognition engine" refers to a technology or device that analyzes a user's emotional state from voice data.

[1060] "Emotion Data" refers to data regarding a user's emotional state analyzed by an emotion recognition engine.

[1061] Overall structure

[1062] The present invention is a system that detects communication errors between pilots and air traffic controllers and provides warnings in real time. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system enhances the effectiveness of error response. The system includes a series of processes that receive communication data, recognize voice, detect errors, generate and send warning messages, and analyze emotions.

[1063] Components

[1064] 1. Communication data receiving means:

[1065] The server receives real-time communication data from pilots and air traffic controllers. This data is received in audio format and temporarily stored in the server's storage.

[1066] 2. Voice recognition means:

[1067] The server converts the received voice data into text data using speech recognition technology, such as Google Cloud Speech-to-Text API or IBM Watson Speech to Text.

[1068] 3. Emotion Recognition Engine:

[1069] The server uses an emotion engine that analyzes the emotions of users (pilots and air traffic controllers) in real time from voice data. This engine uses voice analysis technology and provides emotion data to the generative AI model.

[1070] 4. Error detection methods:

[1071] The server then inputs the converted text and emotion data into a generative AI model, which performs real-time analysis based on a historical database to detect potential errors in communication.

[1072] 5. Warning message generation method:

[1073] If an error is detected, the server uses this information to generate an appropriate warning message, which includes the specific problem and a suggested solution.

[1074] 6. Means of transmission and display:

[1075] The server sends the generated warning messages to the pilot and controller terminals via a REST API.

[1076] The terminal receives the warning message and displays it on the user interface, allowing users (pilots and controllers) to respond quickly.

[1077] Specific examples

[1078] 1. Receiving communication data:

[1079] The server receives real-time voice data from the pilot saying, "Echo 123, requesting permission to descend." This data is immediately stored in the server's storage.

[1080] 2. Speech Recognition:

[1081] The server sends the received voice data to a speech recognition engine and converts it into text data. The conversion result is text data that reads, "Echo 123, requesting permission to descend."

[1082] 3. Emotion analysis:

[1083] The server uses an emotion engine to analyze the user's emotions from the voice data. For example, if the pilot is anxious, the emotion engine will detect "stress."

[1084] 4. Error detection:

[1085] The server inputs text data and emotion data into the generative AI model, which analyzes the error signs. The model compares it with past data and detects that Echo 123 was instructed to fly at a different altitude than other aircraft. An example prompt is "Please detect errors based on past communication data and emotion data."

[1086] 5. Generate warning messages:

[1087] The server generates a warning message saying, "Echo 123 is being instructed to a different altitude. Please recheck. Pilot appears stressed."

[1088] 6. Transmission and Display:

[1089] The server sends this warning message to the terminals of the pilot and the controller, and the message is displayed immediately. The user (pilot and controller) checks the warning and takes the necessary action.

[1090] Operation method

[1091] The system is designed to operate continuously while the aircraft is in operation. The server constantly receives and analyzes communication data, aiming for early detection of errors and emotions. The terminal displays an emotion-based warning message upon detecting an error, helping the user to take prompt and appropriate action.

[1092] In this way, the present invention detects pilot and air traffic controller communication errors and emotional states in real time, improving overall system safety and effective response.

[1093] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1094] Step 1: Receiving communication data

[1095] The server receives voice communication data transmitted in real time by pilots and air traffic controllers.

[1096] Input: Voice communication data from pilots and air traffic controllers

[1097] Specific operation: The server captures voice data via the aircraft's communication device and temporarily stores it in storage.

[1098] Output: Saved audio data

[1099] Step 2: Voice Recognition

[1100] The server sends the stored voice data to a voice recognition engine for conversion into text data.

[1101] Input: Saved audio data

[1102] Specific operation: The server connects to a speech recognition engine (e.g., Google Cloud Speech-to-Text API) and uploads the voice data. The speech recognition engine analyzes the voice data and generates corresponding text data.

[1103] Output: Converted text data

[1104] Step 3: Sentiment Analysis

[1105] The server sends the voice data to an emotion recognition engine to analyze the user's emotional state.

[1106] Input: Saved audio data

[1107] How it works: The server connects to the emotion recognition engine and uploads the voice data. The emotion recognition engine analyzes the tone, rhythm, and speed of the voice and generates emotion data (e.g., "stressed," "calm").

[1108] Output: Parsed emotion data

[1109] Step 4: Error detection

[1110] The server inputs the converted text data and emotion data into a generative AI model and analyzes it for signs of error.

[1111] Input: Converted text data and emotion data

[1112] How it works: The server uses the prompt "Please detect errors based on past communication data and emotion data" to input the data into the generative AI model, which then compares it with the past database to detect anomalies and inconsistencies.

[1113] Output: Detected error data

[1114] Step 5: Generate a warning message

[1115] The server generates a warning message based on the detected error data and emotion data.

[1116] Input: Detected error data and emotion data

[1117] Specific behavior: The server uses the generated error data and emotion data to generate an appropriate warning message, including the specific problem and a suggested solution (e.g., "Echo 123 is being instructed to a different altitude. Please reconfirm. The pilot appears stressed.").

[1118] Output: Generated warning message

[1119] Step 6: Send and display warning messages

[1120] The server transmits the generated warning messages to the terminals of the pilots and the controllers, and the terminals display the received warning messages on their user interfaces.

[1121] Input: The generated warning message

[1122] Specific operation: The server sends a warning message via the REST API, and the device displays the warning message on the user interface after receiving it.

[1123] Output: The displayed warning message

[1124] Step 7: User Action

[1125] Users (pilots and controllers) check the warning message and take necessary action.

[1126] Input: The displayed warning message

[1127] Specific Action: The user reads the warning message and acts based on the indicated problem and suggested solution. For example, the pilot reconfirms the instructions and recommunicates if necessary.

[1128] Output: Corresponding results

[1129] (Application example 2)

[1130] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1131] Communication between pilots and air traffic controllers is crucial for the safe operation of aircraft, but problems can occur due to communication errors or emotional states. A system is needed to detect such communication errors and emotional states in real time and respond quickly.

[1132] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving communication data from pilots and air traffic controllers in real time, speech recognition means for converting the received voice data into text data, means for inputting the text data into a generative AI model and analyzing it, means for detecting an error that has occurred and generating a warning message, means for sending the warning message to a terminal and displaying it, emotion engine means for analyzing emotions from the voice data, and means for generating a warning message based on the emotion analysis result and the error detection result. This makes it possible to detect communication errors and the user's emotional state in real time and respond quickly and appropriately.

[1133] "Pilot" refers to a person whose job is to operate and fly an aircraft.

[1134] "Air traffic controller" refers to an official whose job is to direct and manage the course and altitude of aircraft to ensure the safety and efficiency of air traffic.

[1135] "Communications data" refers to information such as voice and text messages exchanged between pilots and air traffic controllers.

[1136] "Real-time" refers to the immediate processing and reflection of events and data occurring in the present moment.

[1137] "Server" refers to a computer system for processing, storing, and managing data over a network.

[1138] "Audio data" refers to information recorded as audio.

[1139] "Text data" refers to digital information in the form of text that has been converted from voice or other data.

[1140] "Speech recognition means" refers to technology or devices for analyzing voice data and converting it into corresponding text data.

[1141] A "generative AI model" refers to an artificial intelligence model that generates new data and analytical results based on past data.

[1142] An "emotion engine" refers to technology or software for analyzing a user's emotional state from voice data, etc.

[1143] "Error detection means" refers to technology or devices for detecting abnormalities or errors in communication data or analysis data.

[1144] "Warning message" refers to a message containing a detected error or a warning.

[1145] "Terminal" refers to a device that a user directly operates to send and receive information.

[1146] "Means of analysis" refers to the technology or equipment used to process received data and understand and judge its contents.

[1147] "Emotion analysis results" refers to information about the user's emotional state obtained using the emotion engine.

[1148] "Means for generating a warning message" refers to a technology or device that creates a warning message based on the detected error or the results of sentiment analysis.

[1149] The present invention is applied to a security service system that detects communication errors and emotional states of pilots and air traffic controllers in real time and provides warning messages. The operation mode of the system and its implementation will be described below.

[1150] Main system components

[1151] The system includes the following main components:

[1152] 1. Communication data receiving means: The server receives voice communication data from pilots and air traffic controllers in real time. This data is temporarily stored in the server's storage.

[1153] 2. Speech recognition means: The server converts the received voice data into text data using a voice recognition engine (e.g., Google Cloud Speech-to-Text API or IBM Watson Speech to Text).

[1154] 3. Error detection method: The server inputs the text data into a generative AI model for analysis. The model uses a historical database to detect errors and abnormal conditions.

[1155] 4. Emotion engine means: The server analyzes the user's emotional state from the voice data. This engine uses voice analysis technology to detect emotions such as "stress" and "anxiety."

[1156] 5. Warning message generation method: Based on the results of sentiment analysis and error detection, the server generates a warning message, which includes specific problems and suggested solutions.

[1157] 6. Warning message sending means: The server generates a warning message and sends it to the device via REST API. The device can be a smartphone or smart glasses.

[1158] 7. Display means: The terminal displays the received warning message to the user, allowing the user to take prompt action.

[1159] Program processing explanation

[1160] The server receives voice communication data from pilots and air traffic controllers in real time via a communication data receiving means. It converts the received voice data into text data using a voice recognition means, and inputs the text data into a generative AI model for analysis. It then uses an emotion engine means to analyze the user's emotional state from the voice data. Based on the emotion analysis results and the data analyzed by the generative AI model, it detects the occurrence of an error and generates a warning message. Finally, it sends this warning message to the terminal via a REST API and displays it to the user.

[1161] Specific examples

[1162] For example, if a security operator says, "An emergency has occurred, please lock the door," this voice data is sent to the server in real time. The server uses speech recognition means to convert this into text data saying, "An emergency has occurred, please lock the door," and inputs it into the generative AI model and emotion engine. The generative AI model analyzes it and detects errors, and the emotion engine detects a "stressed" state. Based on this, the server generates a warning message such as, "An emergency has occurred. The operator appears to be stressed. Please respond quickly," which is sent to the terminal and displayed to the user.

[1163] Example prompt for a generative AI model:

[1164] This audio data contains an urgent message and emotion. Convert it to text and detect the text "Emergency, please lock the doors" and the emotion of stress.

[1165] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1166] Step 1:

[1167] The server receives communication data from pilots and air traffic controllers in real time. Specifically, the server's communication module receives voice data and temporarily stores it in storage. This step includes the process of acquiring communication data (input) in real time and storing it in the server's storage (output).

[1168] Step 2:

[1169] The server converts the received voice data into text data using a voice recognition means. Specifically, it uses the server's internal voice recognition engine (Google Cloud Speech-to-Text API or IBM Watson Speech to Text) to convert the voice data into text data. In this step, the voice data (input) is converted into text data (output).

[1170] Step 3:

[1171] The server inputs the converted text data into a generative AI model for analysis. Specifically, it identifies errors and anomalies in the text data based on a historical database. This involves the process of parsing text data (input) into error data (output).

[1172] Step 4:

[1173] The server analyzes the user's emotional state from the voice data using an emotion engine. Specifically, it uses voice analysis technology to detect emotions such as "stress" and "impatience" from the voice data. This step includes processing to generate emotion analysis results (output) from the voice data (input).

[1174] Step 5:

[1175] The server generates a warning message based on the emotion analysis results and error data. Specifically, it summarizes the detected error and content according to the emotional state into a warning message. In this step, the process of creating a warning message (output) from the error data and emotion analysis results (input) is carried out.

[1176] Step 6:

[1177] The server sends the generated warning message to the terminal via the REST API. Specifically, the warning message is sent to the terminal so that it is immediately displayed in the user interface. This step includes the process of sending the warning message (input) to the terminal and displaying it (output).

[1178] Step 7:

[1179] The terminal displays the received warning message to the user. The user can check this warning message and take prompt and appropriate action. In this step, the received warning message (input) is displayed on the user interface (output).

[1180] 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.

[1181] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. 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 a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1182] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1183] [Fourth embodiment]

[1184] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1185] 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.

[1186] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1187] 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.

[1188] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1189] 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 surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1190] 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.

[1191] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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.

[1192] 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.

[1193] 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 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.

[1194] 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.

[1195] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1196] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1197] This invention is a system that detects communication errors between aircraft pilots and air traffic controllers in real time to prevent accidents. This system includes a series of processes that consistently perform everything from receiving communication data to detecting errors and generating and transmitting warning messages.

[1198] System configuration

[1199] The system includes the following main components:

[1200] 1. Communication data receiving means

[1201] Server: Receives communication data from pilots and air traffic controllers in real time. This data is received in audio format and temporarily stored in the server's storage.

[1202] 2. Voice Recognition Method

[1203] Server: The received voice data is converted into text data using speech recognition technology, such as Google Cloud Speech-to-Text API or IBM Watson Speech to Text.

[1204] 3. Error Detection Methods

[1205] Server: The converted text data is fed into a generative AI model, which performs real-time analysis against a historical database to detect potential errors in the communication.

[1206] 4. Warning Message Generation Method

[1207] Server: If an error is detected, this information is used to generate an appropriate warning message, which will include the specific problem and a suggested solution.

[1208] 5. Means of transmission and display

[1209] Server: The generated warning messages are sent to the pilot and controller terminals via REST API.

[1210] Terminal: Receives warning messages and displays them on the user interface, allowing pilots and controllers to respond quickly.

[1211] Specific examples

[1212] 1. Receiving communication data

[1213] The server receives real-time voice data from the pilot saying, "Echo 123, requesting permission to descend." This data is immediately stored in the server's storage.

[1214] 2. Voice Recognition

[1215] The server sends the received voice data to a speech recognition engine and converts it into text data. The conversion result is text data that reads, "Echo 123, requesting permission to descend."

[1216] 3. Error Detection

[1217] The server then feeds this text data into a generative AI model, which analyzes it for signs of error. The model uses past data to determine, for example, that Echo 123 was being instructed to fly at a different altitude than other aircraft.

[1218] 4. Generating Warning Messages

[1219] The server generates a warning message saying "Echo 123 is being instructed to a different altitude. Please recheck."

[1220] 5. Transmission and Display

[1221] The server sends this warning message to the terminals of the pilot and the controller, and the message is displayed immediately. The user (pilot and controller) checks the warning and takes the necessary action.

[1222] Operation method

[1223] The system is designed to operate continuously while the aircraft is in operation. The server constantly receives and analyzes communication data, aiming to detect errors early. The terminal displays a warning message as soon as an error is detected, helping the user to take prompt action.

[1224] In this way, the present invention detects communication errors between pilots and air traffic controllers in real time, improving the safety of the entire system.

[1225] The processing flow will be explained below.

[1226] Step 1: Receiving communication data

[1227] The server receives real-time communication data from pilots and air traffic controllers, which is transmitted in voice format via the TCP / IP protocol.

[1228] The server temporarily stores the received audio data in a storage device, usually in a standard audio format such as WAV or MP3.

[1229] Step 2: Preprocessing the audio data

[1230] The server performs noise reduction on the received audio data, using Python libraries (e.g., Librosa and Pydub) to remove background noise and improve the audio quality.

[1231] The server prepares the pre-processed audio data for the next step.

[1232] Step 3: Voice Recognition

[1233] The server sends the preprocessed speech data to a speech recognition engine, which can use cloud-based speech recognition services such as Google Cloud Speech-to-Text API or IBM Watson Speech to Text.

[1234] The server receives the text data returned by the speech recognition engine and stores it as input data for the generative AI model.

[1235] Step 4: Analyzing text data and detecting errors

[1236] The server inputs the text data into a generative AI model, which uses a natural language processing engine such as GPT-3 or BERT.

[1237] The server uses a generative AI model to analyze the text data and detect signs of communication errors or human error based on a past database.

[1238] Step 5: Generate a warning message

[1239] The server generates a warning message based on the error information detected by the generative AI model, which includes the specific details of the error and suggested countermeasures.

[1240] The server prepares the alert message for transmission.

[1241] Step 6: Sending a warning message

[1242] The server sends the generated warning messages to the pilot and air traffic controller terminals via a REST API using HTTP POST requests.

[1243] Step 7: Displaying warning messages

[1244] The terminal receives the alert messages sent by the server and visually displays them in the user interface, using a GUI library (e.g., Tkinter, JavaFX, etc.).

[1245] Users (pilots and air traffic controllers) check the displayed warning message and take necessary action, for example, rechecking and correcting the communication content in which the error was detected.

[1246] The above is the flow of the specific processing steps of this system. Each step works in conjunction with the others to detect and warn of communication errors in real time.

[1247] Example 1

[1248] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1249] Misunderstandings and errors in communication between aircraft pilots and air traffic controllers can have a significant impact on flight safety. These errors need to be detected in real time and dealt with promptly, but current systems lack the technology to do so. Therefore, a system is needed that can detect communication errors between pilots and air traffic controllers in real time and issue immediate warnings.

[1250] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1251] In this invention, the server includes a means for receiving communication data from pilots and air traffic controllers in real time, a speech recognition means for converting the received voice data into text data, a means for inputting the text data into a generative AI model for analysis, a means for detecting an error that has occurred and generating a warning message, and a means for transmitting the warning message to a terminal for display. This enables real-time analysis of communication data, rapid detection and warning of errors, and immediate notification to pilots and air traffic controllers.

[1252] The "communication data receiving means" is a function for receiving voice communication data from pilots and air traffic controllers in real time.

[1253] The "voice recognition means" is a processing function for converting received voice data into text data.

[1254] A "generative AI model" is an artificial intelligence model that performs real-time analysis based on a past database.

[1255] The "error detection means" is a function that uses a generative AI model to analyze text data and detect communication errors.

[1256] The "warning message generating means" is a function that generates a warning message based on a detected error.

[1257] The "warning message sending means" is a function for sending the generated warning message to the terminal via the REST API.

[1258] The "warning message display means" is a function for displaying the transmitted warning message on the user interface.

[1259] The "noise removal means" is a preprocessing function for removing noise from audio data and improving sound quality.

[1260] "Real-time analysis" refers to the process of quickly analyzing received data in real time.

[1261] "Input to a generative AI model" refers to the means of supplying text data to a generative AI model and having the model analyze it.

[1262] "REST API" is a type of API (application programming interface) for exchanging warning messages between systems, and is a protocol for communication via HTTP.

[1263] The present invention is a system for detecting communication errors between aircraft pilots and air traffic controllers in real time to prevent accidents. A specific embodiment of this system is described below.

[1264] System configuration

[1265] The system includes the following main components:

[1266] 1. Communication data receiving means

[1267] The server receives communication data from pilots and air traffic controllers in real time. This communication data is received in audio format and temporarily stored in the server's storage.

[1268] 2. Voice Recognition Method

[1269] The server uses speech recognition technology to convert the received voice data into text data. Specifically, it uses services such as Google Cloud Speech-to-Text API and IBM Watson Speech to Text. The voice data is sent to the speech recognition engine and converted into text data.

[1270] 3. Error Detection Methods

[1271] The server then feeds the converted text data into a generative AI model, which performs real-time analysis based on a historical database to detect potential errors in the communication.

[1272] 4. Warning Message Generation Method

[1273] If an error is detected, the server will generate an appropriate warning message, which will include the specific problem and a recommended solution.

[1274] 5. Means of transmission and display

[1275] The server sends the generated warning messages to the pilot and air traffic controller terminals via a REST API.

[1276] The terminal receives the warning message and displays it on the user interface, allowing users (pilots and air traffic controllers) to react quickly.

[1277] Specific examples

[1278] A specific example of this system is shown below.

[1279] 1. Receiving communication data

[1280] The server receives the pilot's voice communication data in real time, such as "Echo 123, requesting permission to descend." This voice data is then stored in storage.

[1281] 2. Voice Recognition

[1282] The server uses the Google Cloud Speech-to-Text API to convert the received voice data into text data, for example, "Echo 123, requesting permission to descend."

[1283] 3. Error Detection

[1284] The server inputs this text data into a generative AI model for analysis, which uses past data to detect that Echo 123 was being instructed to fly at a different altitude than other aircraft.

[1285] 4. Generating Warning Messages

[1286] Based on the detected error information, the server generates a warning message saying "Echo 123 is being instructed to a different altitude. Please check again."

[1287] 5. Transmission and Display

[1288] The server sends this warning message to the terminals of the pilot and air traffic controller via REST API, where the users (pilot and air traffic controller) can check the warning message and take prompt action.

[1289] Examples of prompt statements

[1290] Here are some examples of specific prompts:

[1291] It receives voice data such as "Echo 123, requesting permission to descend" and specifies the prompt text that generates a warning message upon error detection.

[1292] In this way, this system will be able to detect communication errors between pilots and air traffic controllers in real time and quickly address them, which is expected to significantly improve the safety of aircraft operations.

[1293] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1294] Step 1:

[1295] Receiving communication data

[1296] The server receives voice communication data from pilots and air traffic controllers in real time. The input is the communication voice from the pilot or air traffic controller, which is temporarily stored in the server's storage. Specific operations include a process of capturing voice data through communication equipment and storing it in a storage device. The output is the voice data stored in the storage.

[1297] Step 2:

[1298] Voice Recognition

[1299] The server sends the stored voice data to the voice recognition engine. The input is the voice data stored in storage. The server converts the voice data into text data using a voice recognition service such as Google Cloud Speech-to-Text API or IBM Watson Speech to Text. Specific operations include making an API call and seamlessly converting the voice data into text. The output is text data.

[1300] Step 3:

[1301] Error Detection

[1302] The server inputs the converted text data into the generative AI model. The input is the text data generated in the speech recognition step. The server inputs this text data into the generative AI model and analyzes it in real time. Specific operations include the process of supplying text to the generative AI model and comparing it with a past database to identify errors. The output is information about the detected errors.

[1303] Step 4:

[1304] Generate a warning message

[1305] The server generates a warning message based on the error detection results. The input is the error information output in the error detection step. The server generates a warning message containing details of the error and suggests appropriate countermeasures. Specific operations include a process for dynamically generating a warning message based on the error information. The output is a warning message containing the specific problem and a suggested countermeasure.

[1306] Step 5:

[1307] Send and display

[1308] The server sends the generated warning message to the pilot's and air traffic controller's terminals via the REST API. The input is the warning message generated in the warning message generation step. The terminal displays the received warning message on its user interface. Specific operations include making a REST API call, sending a message, and displaying it on the user interface on the terminal side. The output is the warning message displayed on the terminal, which the user confirms.

[1309] (Application example 1)

[1310] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1311] In autonomous vehicles, communication errors between the driver and the system, or between vehicles, can lead to accidents or serious problems. There is a need for technology that can detect such errors in real time and warn the driver in advance. Currently, the means to detect these types of errors and respond quickly are not sufficiently developed, making improving safety a challenge.

[1312] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1313] In this invention, the server includes: means for receiving communication data from pilots and air traffic controllers in real time; speech recognition means for converting the received speech data into text data; means for inputting the text data into a generative AI model and analyzing it; means for detecting errors and generating warning messages; means for sending and displaying the warning messages on a terminal; means for monitoring voice and text communications between a driver and the autonomous driving system in real time in an autonomous driving vehicle system; means for analyzing whether the driver's instructions and the system's responses match; and means for generating warning messages and displaying them on a vehicle display or head-up display if they do not match. This enables real-time detection of communication errors and immediate warnings in autonomous driving vehicles.

[1314] A "pilot" is a person who is qualified to fly an aircraft and who actually operates the aircraft.

[1315] An "air traffic controller" is a person whose job is to monitor and direct the movements of aircraft in the air and on the ground in order to ensure the safe operation of aircraft.

[1316] "Communications Data" means information in the form of voice and text exchanged between pilots and air traffic controllers, or drivers and automated driving systems.

[1317] "Means for receiving in real time" refers to functions or devices for receiving communication data immediately without delay.

[1318] "Audio data" means information recorded or transmitted in the form of sound.

[1319] "Text data" refers to information expressed in characters and symbols.

[1320] "Speech recognition means" refers to technology or devices that convert voice data into text data.

[1321] A "generative AI model" is a model that uses artificial intelligence to analyze text data and detect errors.

[1322] An "occurring error" is an unintentional error or discrepancy that occurs in communication.

[1323] A "warning message" is information that is generated based on an error that has occurred, and that prompts attention or reconfirmation.

[1324] "Means for sending to and displaying at a terminal" refers to a function or device for sending the generated alert message to a specific device and displaying it to the user of that device.

[1325] An "autonomous vehicle system" is a vehicle system that incorporates technology and devices for automatically driving and controlling a vehicle.

[1326] The means for analyzing whether the "driver's instructions and the system's response" match refers to functions and devices for determining whether the instructions given by the driver and the response of the automated driving system match accurately.

[1327] A "display" is an electronic device for visually displaying information.

[1328] A "head-up display" is a device that displays information in front of the driver so that the driver can check it at the edge of their field of vision without having to look down.

[1329] This invention is a system that detects communication errors between the driver and the autonomous driving system in an autonomous vehicle, and between vehicles in real time, and generates and transmits warning messages. This system includes the following main components:

[1330] Hardware:

[1331] 1. Voice input system: A microphone for collecting the driver's instructions as voice data.

[1332] 2. On-board computer: A central processing unit that processes data.

[1333] 3. Display and Head-Up Display (HUD): A display device for displaying warning messages to the driver.

[1334] software:

[1335] 1. Speech recognition software: Technology that converts voice data into text data (e.g., Google Cloud Speech-to-Text API).

[1336] 2. Generative AI model: An artificial intelligence model (e.g., OpenAI API) for analyzing text data and detecting errors.

[1337] 3. Communication module: Software for sending and receiving communication data.

[1338] Server Processing

[1339] 1. Receiving audio data:

[1340] The server receives the driver's instructions as voice data from the autonomous vehicle's voice input system and temporarily stores them in storage.

[1341] 2. Audio to text conversion:

[1342] The server then sends the received audio data to speech recognition software, which converts it into text using a service like the Google Cloud Speech-to-Text API.

[1343] 3. Error detection:

[1344] The server then feeds the converted text data into a generative AI model that analyzes communication errors. The model uses a historical database and performs real-time analysis to detect potential errors.

[1345] 4. Generate a warning message:

[1346] If an error is detected, the server generates a warning message that describes the specific problem and suggests a solution.

[1347] 5. Sending and displaying warning messages:

[1348] The server sends the generated warning message to the vehicle's display or head-up display for display to the driver.

[1349] Specific examples

[1350] When the driver issues a voice command such as "Switch to autonomous driving mode," the voice data is received by the server and instantly converted into text data. The text data is then analyzed by a generative AI model to verify that the command was executed correctly. If the system's response does not match, a warning message such as "Switch to autonomous driving mode failed. Please continue manual operation" is generated and displayed on the vehicle's display.

[1351] Examples of prompts include:

[1352] Analyze the following communication for errors: "Switch to autopilot mode."

[1353] This will enable real-time detection of communication errors and immediate warnings in autonomous vehicles.

[1354] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1355] Step 1:

[1356] Receiving audio data

[1357] The server receives the driver's voice data in real time from the voice input system (microphone) of the autonomous vehicle. The input is the driver's voice command such as "switch to autonomous driving mode," and this voice data is temporarily stored in the server's storage.

[1358] Step 2:

[1359] Converting audio data to text

[1360] The server sends the received voice data to speech recognition software (e.g., Google Cloud Speech-to-Text API) and converts it into text data. The input is voice data, which undergoes speech recognition as data processing, and the output is the text data "Switch to autonomous driving mode."

[1361] Step 3:

[1362] Text data analysis

[1363] The server inputs the converted text data into a generative AI model (e.g., OpenAI API) and analyzes errors in the communication. The input is text data, which is analyzed by the AI ​​model as data processing and data calculation. The output is the result of whether or not an error exists. Specifically, the generative AI model is input with the prompt "Analyze the following communication for errors: 'Switch to autopilot mode.'" and the text data is analyzed.

[1364] Step 4:

[1365] Detecting errors

[1366] If an error occurs in the analysis results, the server extracts detailed information. The input is the analysis results from the generative AI model, and the server determines whether there is an error as a data calculation and identifies the part where the error occurred. The output is error information.

[1367] Step 5:

[1368] Generate a warning message

[1369] The server generates a warning message based on detailed error information. The input is the error information, and an appropriate warning text message is created by processing the data. Specifically, a warning message such as "Switching to autonomous driving mode has failed. Please continue manual operation" is output.

[1370] Step 6:

[1371] Sending and displaying warning messages

[1372] The server sends the generated warning message to the vehicle's display or head-up display (HUD) for display to the driver. The input is the warning message, and the message is sent via the communication module as data processing. The output is a warning display that the driver can check.

[1373] Through these steps, a system will be created that monitors in real time whether the driver's voice instructions are being properly reflected in the autonomous driving system, and if an error is detected, it will quickly generate a warning to notify the driver.

[1374] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1375] The present invention improves the effectiveness of error handling by combining a system that detects communication errors between pilots and air traffic controllers and provides warnings in real time with an emotion engine that recognizes user emotions. This system includes a series of processes that receive communication data, recognize voice, detect errors, generate and send warning messages, and analyze emotions.

[1376] System configuration

[1377] The system includes the following main components:

[1378] 1. Communication data receiving means

[1379] Server: Receives communication data from pilots and air traffic controllers in real time. This data is received in audio format and temporarily stored in the server's storage.

[1380] 2. Voice Recognition Method

[1381] Server: The received voice data is converted into text data using speech recognition technology, such as Google Cloud Speech-to-Text API or IBM Watson Speech to Text.

[1382] 3. Error Detection Methods

[1383] Server: The converted text data is fed into a generative AI model, which performs real-time analysis against a historical database to detect potential errors in the communication.

[1384] 4. Warning Message Generation Method

[1385] Server: If an error is detected, this information is used to generate an appropriate warning message, which will include the specific problem and a suggested solution.

[1386] 5. Means of transmission and display

[1387] Server: The generated warning messages are sent to the pilot and controller terminals via REST API.

[1388] Terminal: Receives warning messages and displays them on the user interface, allowing pilots and controllers to respond quickly.

[1389] 6. Emotion Engine

[1390] Server: Contains an emotion engine that analyzes the emotions of users (pilots and air traffic controllers) in real time from voice data. This engine uses voice analysis technology to provide emotion data to the generative AI model.

[1391] Specific examples

[1392] 1. Receiving communication data

[1393] The server receives real-time voice data from the pilot saying, "Echo 123, requesting permission to descend." This data is immediately stored in the server's storage.

[1394] 2. Voice Recognition

[1395] The server sends the received voice data to a speech recognition engine and converts it into text data. The conversion result is text data that reads, "Echo 123, requesting permission to descend."

[1396] 3. Emotion analysis

[1397] The server uses an emotion engine to analyze the user's emotions from the voice data. For example, if the pilot is anxious, the emotion engine will detect "stress."

[1398] 4. Error Detection

[1399] The server inputs text and emotion data into the generative AI model, which analyzes it for signs of error. The model compares it with past data and detects that Echo 123 was being instructed to fly at a different altitude than other aircraft.

[1400] 5. Generating Warning Messages

[1401] The server generates a warning message saying, "Echo 123 is being instructed to a different altitude. Please recheck. Pilot appears stressed."

[1402] 6. Transmission and Display

[1403] The server sends this warning message to the terminals of the pilot and the controller, and the message is displayed immediately. The user (pilot and controller) checks the warning and takes the necessary action.

[1404] Operation method

[1405] The system is designed to operate continuously while the aircraft is in operation. The server constantly receives and analyzes communication data, aiming for early detection of errors and emotions. The terminal displays an emotion-based warning message upon detecting an error, helping the user to take prompt and appropriate action.

[1406] In this way, the present invention detects pilot and air traffic controller communication errors and emotional states in real time, improving overall system safety and effective response.

[1407] The processing flow will be explained below.

[1408] Step 1: Receiving communication data

[1409] The server receives real-time communication data from pilots and air traffic controllers, which is transmitted in voice format via the TCP / IP protocol.

[1410] The server temporarily stores the received audio data in a storage device, usually in a standard audio format such as WAV or MP3.

[1411] Step 2: Preprocessing the audio data

[1412] The server performs noise reduction on the received audio data, using Python libraries (e.g., Librosa and Pydub) to remove background noise and improve the audio quality.

[1413] The server prepares the pre-processed audio data for the next step.

[1414] Step 3: Voice Recognition

[1415] The server sends the preprocessed speech data to a speech recognition engine, which can use cloud-based speech recognition services such as Google Cloud Speech-to-Text API or IBM Watson Speech to Text.

[1416] The server receives the text data returned by the speech recognition engine and stores it as input data for the generative AI model.

[1417] Step 4: Sentiment Analysis

[1418] The server inputs the preprocessed voice data or the text returned by the speech recognition engine into the emotion engine, which analyzes the user's emotions from the voice or text and identifies their emotional state, such as stress, anger, or joy.

[1419] The server converts and stores the emotion analysis results in a format that can be used by the generative AI model.

[1420] Step 5: Analyze text data and detect errors

[1421] The server inputs text and emotion data into a generative AI model, which uses natural language processing engines such as GPT-3 and BERT.

[1422] The server uses a generative AI model to analyze text data and emotional data, and compares it with a past database to detect signs of communication errors or human error.

[1423] Step 6: Generate a warning message

[1424] The server generates a warning message based on the error information and emotional information detected by the generative AI model. The warning message includes the specific details of the error, suggested countermeasures, and additional precautions according to the user's emotional state.

[1425] The server prepares the alert message for transmission.

[1426] Step 7: Sending a warning message

[1427] The server sends the generated warning messages to the pilot and air traffic controller terminals via a REST API using HTTP POST requests.

[1428] Step 8: Displaying warning messages

[1429] The terminal receives the alert messages sent by the server and visually displays them in the user interface, using a GUI library (e.g., Tkinter, JavaFX, etc.).

[1430] Users (pilots and air traffic controllers) check the displayed warning message and take necessary action, for example, rechecking and correcting the communication content in which the error was detected.

[1431] These are the specific processing steps of the system that combines the emotion engine. By linking these steps together, real-time detection of communication errors and emotional states and warnings are realized, further improving the operational safety of aircraft.

[1432] Example 2

[1433] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1434] Communications between pilots and air traffic controllers are prone to misunderstandings and miscommunications. Furthermore, the emotional state of the user during these communications (e.g., stress or impatience) can affect the detection and response to errors. While conventional systems recognize voice data and detect errors, they are unable to analyze the user's emotional state in real time and utilize it to improve response. This makes it difficult to detect errors early and improve the quality of response.

[1435] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1436] In this invention, the server includes a means for receiving communication data from pilots and air traffic controllers in real time, a speech recognition device for converting the received speech data into text data, a device for inputting the text data into a generative AI model for analysis, a device for detecting errors that have occurred and generating a warning message, a device for transmitting the warning message to a terminal and displaying it, an emotion recognition engine for analyzing user emotions in real time, and a device for inputting emotion data into the generative AI model for analysis. This makes it possible to detect errors in communication data in real time and quickly generate and provide appropriate warning messages that take the user's emotional state into consideration.

[1437] "Communication Data" means data in the form of voice exchanged between pilots and air traffic controllers.

[1438] "Speech recognition device" refers to a technology or device for converting voice data into text data.

[1439] A "generative AI model" refers to an artificial intelligence model that analyzes voice and text data based on learned past data.

[1440] "Error detection device" refers to a device that uses a generative AI model to detect potential errors in text data.

[1441] The term "warning message generating device" refers to a device that generates a warning message based on detected error information.

[1442] "Warning message transmitting device" refers to a device that transmits the generated warning messages to the terminals of pilots and air traffic controllers.

[1443] "Warning message display device" refers to a device that displays a received warning message on a user interface.

[1444] "Emotion recognition engine" refers to a technology or device that analyzes a user's emotional state from voice data.

[1445] "Emotion Data" refers to data regarding a user's emotional state analyzed by an emotion recognition engine.

[1446] Overall structure

[1447] The present invention is a system that detects communication errors between pilots and air traffic controllers and provides warnings in real time. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, the system enhances the effectiveness of error response. The system includes a series of processes that receive communication data, recognize voice, detect errors, generate and send warning messages, and analyze emotions.

[1448] Components

[1449] 1. Communication data receiving means:

[1450] The server receives real-time communication data from pilots and air traffic controllers. This data is received in audio format and temporarily stored in the server's storage.

[1451] 2. Voice recognition means:

[1452] The server converts the received voice data into text data using speech recognition technology, such as Google Cloud Speech-to-Text API or IBM Watson Speech to Text.

[1453] 3. Emotion Recognition Engine:

[1454] The server uses an emotion engine that analyzes the emotions of users (pilots and air traffic controllers) in real time from voice data. This engine uses voice analysis technology and provides emotion data to the generative AI model.

[1455] 4. Error detection methods:

[1456] The server then inputs the converted text and emotion data into a generative AI model, which performs real-time analysis based on a historical database to detect potential errors in communication.

[1457] 5. Warning message generation method:

[1458] If an error is detected, the server uses this information to generate an appropriate warning message, which includes the specific problem and a suggested solution.

[1459] 6. Means of transmission and display:

[1460] The server sends the generated warning messages to the pilot and controller terminals via a REST API.

[1461] The terminal receives the warning message and displays it on the user interface, allowing users (pilots and controllers) to respond quickly.

[1462] Specific examples

[1463] 1. Receiving communication data:

[1464] The server receives real-time voice data from the pilot saying, "Echo 123, requesting permission to descend." This data is immediately stored in the server's storage.

[1465] 2. Speech Recognition:

[1466] The server sends the received voice data to a speech recognition engine and converts it into text data. The conversion result is text data that reads, "Echo 123, requesting permission to descend."

[1467] 3. Emotion analysis:

[1468] The server uses an emotion engine to analyze the user's emotions from the voice data. For example, if the pilot is anxious, the emotion engine will detect "stress."

[1469] 4. Error detection:

[1470] The server inputs text data and emotion data into the generative AI model, which analyzes the error signs. The model compares it with past data and detects that Echo 123 was instructed to fly at a different altitude than other aircraft. An example prompt is "Please detect errors based on past communication data and emotion data."

[1471] 5. Generate warning messages:

[1472] The server generates a warning message saying, "Echo 123 is being instructed to a different altitude. Please recheck. Pilot appears stressed."

[1473] 6. Transmission and Display:

[1474] The server sends this warning message to the terminals of the pilot and the controller, and the message is displayed immediately. The user (pilot and controller) checks the warning and takes the necessary action.

[1475] Operation method

[1476] The system is designed to operate continuously while the aircraft is in operation. The server constantly receives and analyzes communication data, aiming for early detection of errors and emotions. The terminal displays an emotion-based warning message upon detecting an error, helping the user to take prompt and appropriate action.

[1477] In this way, the present invention detects pilot and air traffic controller communication errors and emotional states in real time, improving overall system safety and effective response.

[1478] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1479] Step 1: Receiving communication data

[1480] The server receives voice communication data transmitted in real time by pilots and air traffic controllers.

[1481] Input: Voice communication data from pilots and air traffic controllers

[1482] Specific operation: The server captures voice data via the aircraft's communication device and temporarily stores it in storage.

[1483] Output: Saved audio data

[1484] Step 2: Voice Recognition

[1485] The server sends the stored voice data to a voice recognition engine for conversion into text data.

[1486] Input: Saved audio data

[1487] Specific operation: The server connects to a speech recognition engine (e.g., Google Cloud Speech-to-Text API) and uploads the voice data. The speech recognition engine analyzes the voice data and generates corresponding text data.

[1488] Output: Converted text data

[1489] Step 3: Sentiment Analysis

[1490] The server sends the voice data to an emotion recognition engine to analyze the user's emotional state.

[1491] Input: Saved audio data

[1492] How it works: The server connects to the emotion recognition engine and uploads the voice data. The emotion recognition engine analyzes the tone, rhythm, and speed of the voice and generates emotion data (e.g., "stressed," "calm").

[1493] Output: Parsed emotion data

[1494] Step 4: Error detection

[1495] The server inputs the converted text data and emotion data into a generative AI model and analyzes it for signs of error.

[1496] Input: Converted text data and emotion data

[1497] How it works: The server uses the prompt "Please detect errors based on past communication data and emotion data" to input the data into the generative AI model, which then compares it with the past database to detect anomalies and inconsistencies.

[1498] Output: Detected error data

[1499] Step 5: Generate a warning message

[1500] The server generates a warning message based on the detected error data and emotion data.

[1501] Input: Detected error data and emotion data

[1502] Specific behavior: The server uses the generated error data and emotion data to generate an appropriate warning message, including the specific problem and a suggested solution (e.g., "Echo 123 is being instructed to a different altitude. Please reconfirm. The pilot appears stressed.").

[1503] Output: Generated warning message

[1504] Step 6: Send and display warning messages

[1505] The server transmits the generated warning messages to the terminals of the pilots and the controllers, and the terminals display the received warning messages on their user interfaces.

[1506] Input: The generated warning message

[1507] Specific operation: The server sends a warning message via the REST API, and the device displays the warning message on the user interface after receiving it.

[1508] Output: The displayed warning message

[1509] Step 7: User Action

[1510] Users (pilots and controllers) check the warning message and take necessary action.

[1511] Input: The displayed warning message

[1512] Specific Action: The user reads the warning message and acts based on the indicated problem and suggested solution. For example, the pilot reconfirms the instructions and recommunicates if necessary.

[1513] Output: Corresponding results

[1514] (Application example 2)

[1515] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1516] Communication between pilots and air traffic controllers is crucial for the safe operation of aircraft, but problems can occur due to communication errors or emotional states. A system is needed to detect such communication errors and emotional states in real time and respond quickly.

[1517] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving communication data from pilots and air traffic controllers in real time, speech recognition means for converting the received voice data into text data, means for inputting the text data into a generative AI model and analyzing it, means for detecting an error that has occurred and generating a warning message, means for sending the warning message to a terminal and displaying it, emotion engine means for analyzing emotions from the voice data, and means for generating a warning message based on the emotion analysis result and the error detection result. This makes it possible to detect communication errors and the user's emotional state in real time and respond quickly and appropriately.

[1518] "Pilot" refers to a person whose job is to operate and fly an aircraft.

[1519] "Air traffic controller" refers to an official whose job is to direct and manage the course and altitude of aircraft to ensure the safety and efficiency of air traffic.

[1520] "Communications data" refers to information such as voice and text messages exchanged between pilots and air traffic controllers.

[1521] "Real-time" refers to the immediate processing and reflection of events and data occurring in the present moment.

[1522] "Server" refers to a computer system for processing, storing, and managing data over a network.

[1523] "Audio data" refers to information recorded as audio.

[1524] "Text data" refers to digital information in the form of text that has been converted from voice or other data.

[1525] "Speech recognition means" refers to technology or devices for analyzing voice data and converting it into corresponding text data.

[1526] A "generative AI model" refers to an artificial intelligence model that generates new data and analytical results based on past data.

[1527] An "emotion engine" refers to technology or software for analyzing a user's emotional state from voice data, etc.

[1528] "Error detection means" refers to technology or devices for detecting abnormalities or errors in communication data or analysis data.

[1529] "Warning message" refers to a message containing a detected error or a warning.

[1530] "Terminal" refers to a device that a user directly operates to send and receive information.

[1531] "Means of analysis" refers to the technology or equipment used to process received data and understand and judge its contents.

[1532] "Emotion analysis results" refers to information about the user's emotional state obtained using the emotion engine.

[1533] "Means for generating a warning message" refers to a technology or device that creates a warning message based on the detected error or the results of sentiment analysis.

[1534] The present invention is applied to a security service system that detects communication errors and emotional states of pilots and air traffic controllers in real time and provides warning messages. The operation mode of the system and its implementation will be described below.

[1535] Main system components

[1536] The system includes the following main components:

[1537] 1. Communication data receiving means: The server receives voice communication data from pilots and air traffic controllers in real time. This data is temporarily stored in the server's storage.

[1538] 2. Speech recognition means: The server converts the received voice data into text data using a voice recognition engine (e.g., Google Cloud Speech-to-Text API or IBM Watson Speech to Text).

[1539] 3. Error detection method: The server inputs the text data into a generative AI model for analysis. The model uses a historical database to detect errors and abnormal conditions.

[1540] 4. Emotion engine means: The server analyzes the user's emotional state from the voice data. This engine uses voice analysis technology to detect emotions such as "stress" and "anxiety."

[1541] 5. Warning message generation method: Based on the results of sentiment analysis and error detection, the server generates a warning message, which includes specific problems and suggested solutions.

[1542] 6. Warning message sending means: The server generates a warning message and sends it to the device via REST API. The device can be a smartphone or smart glasses.

[1543] 7. Display means: The terminal displays the received warning message to the user, allowing the user to take prompt action.

[1544] Program processing explanation

[1545] The server receives voice communication data from pilots and air traffic controllers in real time via a communication data receiving means. It converts the received voice data into text data using a voice recognition means, and inputs the text data into a generative AI model for analysis. It then uses an emotion engine means to analyze the user's emotional state from the voice data. Based on the emotion analysis results and the data analyzed by the generative AI model, it detects the occurrence of an error and generates a warning message. Finally, it sends this warning message to the terminal via a REST API and displays it to the user.

[1546] Specific examples

[1547] For example, if a security operator says, "An emergency has occurred, please lock the door," this voice data is sent to the server in real time. The server uses speech recognition means to convert this into text data saying, "An emergency has occurred, please lock the door," and inputs it into the generative AI model and emotion engine. The generative AI model analyzes it and detects errors, and the emotion engine detects a "stressed" state. Based on this, the server generates a warning message such as, "An emergency has occurred. The operator appears to be stressed. Please respond quickly," which is sent to the terminal and displayed to the user.

[1548] Example prompt for a generative AI model:

[1549] This audio data contains an urgent message and emotion. Convert it to text and detect the text "Emergency, please lock the doors" and the emotion of stress.

[1550] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1551] Step 1:

[1552] The server receives communication data from pilots and air traffic controllers in real time. Specifically, the server's communication module receives voice data and temporarily stores it in storage. This step includes the process of acquiring communication data (input) in real time and storing it in the server's storage (output).

[1553] Step 2:

[1554] The server converts the received voice data into text data using a voice recognition means. Specifically, it uses the server's internal voice recognition engine (Google Cloud Speech-to-Text API or IBM Watson Speech to Text) to convert the voice data into text data. In this step, the voice data (input) is converted into text data (output).

[1555] Step 3:

[1556] The server inputs the converted text data into a generative AI model for analysis. Specifically, it identifies errors and anomalies in the text data based on a historical database. This involves the process of parsing text data (input) into error data (output).

[1557] Step 4:

[1558] The server analyzes the user's emotional state from the voice data using an emotion engine. Specifically, it uses voice analysis technology to detect emotions such as "stress" and "impatience" from the voice data. This step includes processing to generate emotion analysis results (output) from the voice data (input).

[1559] Step 5:

[1560] The server generates a warning message based on the emotion analysis results and error data. Specifically, it summarizes the detected error and content according to the emotional state into a warning message. In this step, the process of creating a warning message (output) from the error data and emotion analysis results (input) is carried out.

[1561] Step 6:

[1562] The server sends the generated warning message to the terminal via the REST API. Specifically, the warning message is sent to the terminal so that it is immediately displayed in the user interface. This step includes the process of sending the warning message (input) to the terminal and displaying it (output).

[1563] Step 7:

[1564] The terminal displays the received warning message to the user. The user can check this warning message and take prompt and appropriate action. In this step, the received warning message (input) is displayed on the user interface (output).

[1565] 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.

[1566] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. 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 a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1567] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1568] 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.

[1569] 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 includes both affect 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.

[1570] 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.

[1571] 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).

[1572] 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 indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, 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 indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1573] 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."

[1574] 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.

[1575] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1576] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1577] 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.

[1578] 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.

[1579] 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.

[1580] The hardware resource for executing a specific process can be any of the following processors: An example of a processor 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. Another example of a processor is 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.

[1581] The hardware resource that executes the specific processing 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 processing may be a single processor.

[1582] 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.

[1583] 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.

[1584] 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.

[1585] 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.

[1586] The following is further disclosed regarding the above embodiment.

[1587] (Claim 1)

[1588] means for receiving communication data from pilots and air traffic controllers in real time;

[1589] a speech recognition means for converting received speech data into text data;

[1590] A means of inputting text data into a generative AI model for analysis;

[1591] means for detecting any errors that occur and generating warning messages;

[1592] means for sending and displaying a warning message on a terminal;

[1593] A system including:

[1594] (Claim 2)

[1595] 10. The system of claim 1, further comprising pre-processing means for noise reduction and sound quality improvement.

[1596] (Claim 3)

[1597] 10. The system of claim 1, further comprising means for the generative AI model to perform analysis using a historical database.

[1598] "Example 1"

[1599] (Claim 1)

[1600] means for receiving communication data from pilots and air traffic controllers in real time;

[1601] a speech recognition means for converting received speech data into text data;

[1602] A means of inputting text data into a generative AI model for analysis;

[1603] means for detecting any errors that occur and generating warning messages;

[1604] means for sending and displaying a warning message on a terminal;

[1605] A system including:

[1606] (Claim 2)

[1607] 10. The system of claim 1, further comprising pre-processing means for noise reduction and sound quality improvement.

[1608] (Claim 3)

[1609] 10. The system of claim 1, further comprising means for the generative AI model to perform analysis using a historical database.

[1610] (Claim 4)

[1611] 10. The system of claim 1, further comprising: means for inputting the generated text data to a generative AI model in real time for error detection.

[1612] (Claim 5)

[1613] 10. The system of claim 1, further comprising: means for transmitting the generated warning message to the terminal through a REST API and displaying it on a user interface.

[1614] (Claim 6)

[1615] 10. The system of claim 1, further comprising: means for generating a warning message upon detecting an error, the warning message including a specific problem and a suggested solution.

[1616] "Application Example 1"

[1617] (Claim 1)

[1618] means for receiving communication data from pilots and air traffic controllers in real time;

[1619] a speech recognition means for converting received speech data into text data;

[1620] A means of inputting text data into a generative AI model for analysis;

[1621] means for detecting any errors that occur and generating warning messages;

[1622] means for sending and displaying a warning message on a terminal;

[1623] A means for monitoring voice and text communications between a driver and an automated driving system in real time in an automated driving vehicle system;

[1624] A means of analyzing whether the driver's instructions and the system's response are consistent;

[1625] means for generating a warning message in the event of a mismatch and displaying the warning message on a vehicle display or head-up display;

[1626] A system including:

[1627] (Claim 2)

[1628] 10. The system of claim 1, further comprising pre-processing means for noise reduction and sound quality improvement.

[1629] (Claim 3)

[1630] 10. The system of claim 1, further comprising means for the generative AI model to perform analysis using a historical database.

[1631] "Example 2: Combining Emotion Engines"

[1632] (Claim 1)

[1633] means for receiving communication data from pilots and air traffic controllers in real time;

[1634] a voice recognition device that converts received voice data into text data;

[1635] A device that inputs text data into a generative AI model for analysis;

[1636] a device for detecting errors that occur and generating warning messages;

[1637] a device for transmitting and displaying a warning message on a terminal;

[1638] An emotion recognition engine that analyzes user emotions in real time,

[1639] A device that inputs emotion data into a generative AI model for analysis;

[1640] A system including:

[1641] (Claim 2)

[1642] 10. The system of claim 1, further comprising pre-processing means for noise reduction and sound quality improvement.

[1643] (Claim 3)

[1644] 10. The system of claim 1, further comprising means for the generative AI model to perform analysis using a historical database.

[1645] "Application example 2 when combining emotion engines"

[1646] (Claim 1)

[1647] means for receiving communication data from pilots and air traffic controllers in real time;

[1648] a speech recognition means for converting received speech data into text data;

[1649] A means of inputting text data into a generative AI model for analysis;

[1650] means for detecting any errors that occur and generating warning messages;

[1651] means for sending and displaying a warning message on a terminal;

[1652] emotion engine means for analyzing emotions from voice data;

[1653] means for generating a warning message based on the sentiment analysis result and the error detection result;

[1654] A system including:

[1655] (Claim 2)

[1656] 10. The system of claim 1, further comprising pre-processing means for noise reduction and sound quality improvement.

[1657] (Claim 3)

[1658] 10. The system of claim 1, further comprising means for the generative AI model to perform analysis using a historical database. [Explanation of symbols]

[1659] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving communication data from pilots and air traffic controllers in real time; a speech recognition means for converting received speech data into text data; A means of inputting text data into a generative AI model for analysis; means for detecting any errors that occur and generating warning messages; means for sending and displaying a warning message on a terminal; A system including:

2. 10. The system of claim 1, further comprising pre-processing means for noise reduction and sound quality improvement.

3. 10. The system of claim 1, further comprising means for the generative AI model to perform analysis using a historical database.

Images