system

Abstract

To provide a system for preventing an accident by detecting a recognition discrepancy or an operation mistake between a controller and a pilot in real time.SOLUTION: A system comprising: means for receiving voice communication data between an air traffic controller and a pilot of an aircraft; means for converting the received voice communication data into text data; means for extracting instruction content from the converted text data; means for generating a predicted action based on the extracted instruction content; means for collecting current position data of the aircraft from a GPS; means for monitoring an actual action of the aircraft based on the collected GPS data; means for comparing the monitored action of the aircraft with the predicted action to detect an abnormality; and means for generating and notifying an alert when the abnormality is detected.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] Currently, communication between air traffic controllers and aircraft pilots is primarily conducted via voice communication, but this method carries the risk of misunderstandings and operational errors. Furthermore, as the number of air passengers increases, the frequency of flights is expected to increase, which in turn increases the risk of accidents. Effective methods are needed to reduce these risks and improve aviation safety. [Means for solving the problem]

[0005] The present invention solves these problems by providing a system that includes: means for receiving voice communication data between an air traffic controller and an aircraft pilot and converting the voice communication data into text data; means for extracting instructions from the converted text data; means for generating predicted behavior based on the extracted instructions; means for collecting current aircraft position data from a GPS; means for monitoring the actual behavior of the aircraft based on the collected GPS data; means for detecting abnormalities by comparing the monitored aircraft behavior with predicted behavior; and means for generating and notifying an alert when an abnormality is detected. This system can detect discrepancies in perception and operational errors between the air traffic controller and the pilot in real time, preventing accidents before they occur.

[0006] "Voice communication data" refers to data that refers to voice instructions and information exchanged between air traffic controllers and aircraft pilots.

[0007] "Text data" refers to data obtained by converting voice communication data into character information.

[0008] "Instruction content" refers to specific instructions from the controller to the pilot, extracted from the converted text data.

[0009] "Predicted actions" are predicted data of the actions that the aircraft should take, generated based on the instructions.

[0010] "GPS Data" means data obtained from the Global Positioning System that includes information such as an aircraft's current location, speed, and altitude.

[0011] "Monitoring measures" refer to the means of analyzing collected GPS data and observing the actual behavior of aircraft in real time.

[0012] "Comparison means" refers to the function of comparing predicted behavior with actual aircraft behavior.

[0013] "Anomaly detection" is the process of identifying discrepancies between predicted and actual behavior.

[0014] An "alert" is a warning message or signal that is generated when an abnormality is detected.

[0015] "Notification means" refers to the means for notifying controllers and pilots of generated alerts. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] To implement this invention, it is necessary to build a system that collects voice communication data between air traffic controllers and aircraft pilots in real time and converts it into text data. This system supports the safe operation of aircraft through a series of processes: extracting instructions, generating predicted behavior, collecting GPS data, monitoring behavior, detecting anomalies, and generating and notifying alerts.

[0038] Overall system flow

[0039] Receiving and converting voice communication data

[0040] The terminal receives voice communications between the controller and the pilot.

[0041] The terminal transmits this voice data to the server.

[0042] The server uses a speech recognition engine to convert the voice communication data into text data.

[0043] Extracting instruction content

[0044] The server extracts the instruction content (e.g., flight number, destination, altitude, etc.) from the converted text data.

[0045] Generating predictive behavior

[0046] The server generates a predicted flight behavior based on the extracted instructions. For example, if the instruction is "Flight 123, climb to 10,000 feet," it predicts that Flight 123 will climb from its current altitude to 10,000 feet.

[0047] GPS data collection and behavior monitoring

[0048] The terminal collects the aircraft's current GPS data and transmits it to the server.

[0049] The server analyzes this GPS data and monitors the aircraft's actual behavior (position, altitude, speed, etc.) in real time.

[0050] Anomaly detection and alert generation

[0051] The server compares the monitored aircraft behavior with the predicted behavior and checks for any anomalies.

[0052] The server immediately generates an alert message if an abnormality is detected.

[0053] The server sends the generated alert to the terminal and notifies the controller and pilot.

[0054] Specific operation examples

[0055] Example 1: Up command case

[0056] 1. The user (controller) sends the instruction "Flight 123, climb to 10,000 feet."

[0057] 2. The terminal receives this voice instruction and sends it to the server.

[0058] 3. The server uses a speech recognition engine to convert the voice into text and extract the instructions.

[0059] 4. The server generates a predicted climb to 10,000 feet for Flight 123.

[0060] 5. The terminal (aircraft side) sends the current altitude GPS data to the server.

[0061] 6. The server compares the current altitude with the predicted behavior to ensure proper ascent.

[0062] 7. The server generates an alert and sends it to the device if it does not act as instructed, for example if it stops at an altitude of 8,000 feet.

[0063] 8. The terminal alerts the controller and pilot that "Flight 123 is not climbing to 10,000 feet."

[0064] 9. The user (controller) confirms this notification and issues instructions again.

[0065] By using this system, it is possible to monitor aircraft movements in real time, detect abnormalities early, increase safety, and reduce the workload of air traffic controllers.

[0066] The processing flow will be explained below.

[0067] Step 1:

[0068] The terminal receives voice communication data between the controller and the pilot in real time.

[0069] Step 2:

[0070] The terminal converts the received voice communication data into a digital format and transmits it to the server.

[0071] Step 3:

[0072] The server uses a speech recognition engine to convert the voice communication data into text data.

[0073] Step 4:

[0074] The server analyzes the converted text data and extracts the instructions (e.g., flight number, target altitude, direction of travel, etc.).

[0075] Step 5:

[0076] The server generates a predicted action that the pilot should take based on the extracted instructions.

[0077] Step 6:

[0078] The terminal (aircraft-side device) collects the aircraft's current GPS data (altitude, position, speed, etc.) and transmits it to the server.

[0079] Step 7:

[0080] The server analyzes the received GPS data and monitors the aircraft's actual behavior in real time.

[0081] Step 8:

[0082] The server compares the monitored aircraft behavior with the predicted behavior generated in the previous step to check whether the pilot is acting as instructed.

[0083] Step 9:

[0084] The server detects an anomaly if the pilot's actions are not as instructed.

[0085] Step 10:

[0086] The server immediately generates an alert message when an abnormality is detected.

[0087] Step 11:

[0088] The server sends this alert message to the terminal.

[0089] Step 12:

[0090] The terminal (control tower equipment) receives the alert message and displays the notification on the controller's display terminal.

[0091] Step 13:

[0092] The user (controller) checks the notification and takes necessary measures.

[0093] These steps will enable misunderstandings and operational errors between controllers and pilots to be detected in real time, preventing accidents before they occur.

[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] Aircraft operations require rapid and accurate analysis of voice communication data between air traffic controllers and pilots. Conventional methods often involve manual conversion and analysis of voice data, which can lead to misunderstandings and delays. This can potentially reduce the safety of aircraft operations. To solve this problem, a system is needed that can automatically analyze voice communication data in real time and issue an immediate warning in the event of an abnormality.

[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 means for receiving voice communication data between an air traffic controller and an aircraft pilot, means for converting the received voice communication data into text data, means for extracting instructions from the converted text data, means for generating predicted behavior based on the extracted instructions, means for collecting current position data of the aircraft from a satellite positioning system, means for monitoring the actual behavior of the aircraft based on the collected position data, means for comparing the monitored behavior of the aircraft with predicted behavior and detecting abnormalities, means for generating and notifying warning information when an abnormality is detected, means for automatically analyzing instructions related to the aircraft, and means for displaying the generated warning information on a terminal. This makes it possible to automatically analyze voice communication data in real time during aircraft operation and ensure safety.

[0099] "Voice communication data" refers to the content of voice communications between air traffic controllers and aircraft pilots.

[0100] "Text data" refers to a data format in which voice communication data is converted into a string of characters.

[0101] "Instruction content" refers to specific command items such as flight number, destination, and altitude extracted from the text data.

[0102] "Predicted action" refers to the action that the aircraft is expected to take based on the instructions.

[0103] "Position Data" refers to current aircraft position information collected from satellite positioning systems.

[0104] "Satellite positioning system" refers to a general term for systems that receive signals from satellites and measure the precise location of an aircraft.

[0105] "Behavioral surveillance" refers to the process of monitoring the actual behavior of aircraft based on collected location data.

[0106] "Anomaly detection" refers to comparing monitored aircraft behavior with predicted behavior to determine whether there are any anomalies.

[0107] "Warning information" refers to a notification message that is generated when an abnormality is detected.

[0108] "Terminal" refers to a device that receives and transmits voice communication data, displays warning information, etc.

[0109] MODE FOR CARRYING OUT THE INVENTION

[0110] To implement this invention, it is necessary to build a system that collects voice communication data between air traffic controllers and aircraft pilots in real time and converts it into text data. This system supports the safe operation of aircraft through a series of processes: extraction of instruction content, generation of predicted behavior, collection of location data, behavior monitoring, anomaly detection, and generation and notification of warning information.

[0111] Receiving and converting voice communication data

[0112] The terminal receives voice communications between an air traffic controller and an aircraft pilot. The terminal collects voice data using a microphone and temporarily stores the collected voice data in local storage. The terminal then transmits the stored voice data to a server. The server converts the voice data into text data using a speech recognition engine (e.g., Google® Cloud Speech-to-Text).

[0113] For example, if a controller says, "Flight 123, climb to 10,000 feet," the device will record this audio with a microphone and send it to a server, which will then convert it into text using Google Cloud Speech-to-Text.

[0114] Extracting instruction content

[0115] The server receives the converted text data and uses an NLP model (e.g., SpaCy) to extract specific instructions, such as flight number, destination, and altitude.

[0116] In a specific example, the server extracts "Flight 123" and "climb to 10,000 feet" from the text data "Flight 123, climb to 10,000 feet."

[0117] Generating predictive behavior

[0118] The server generates a predicted flight behavior based on the extracted instructions. It uses a Python numerical calculation library (e.g., NumPy) to generate numerical data corresponding to the instructed behavior.

[0119] As a concrete example, the server generates a predicted action such as "Flight 123 will climb to 10,000 feet."

[0120] Location data collection and behavioral monitoring

[0121] The terminal collects the aircraft's current location data. This location data is obtained using a satellite positioning system (e.g., GPS). The collected location data includes latitude, longitude, altitude, etc. The terminal then transmits this location data to a server.

[0122] The server receives the transmitted position data and monitors the current aircraft behavior, a process that involves data analysis using the Pandas library.

[0123] In a specific example, the terminal uses the aircraft's GPS module to obtain information such as the current latitude, longitude, and altitude, and sends it to the server. The server confirms and records that the aircraft's current altitude is "8,000 feet."

[0124] Anomaly detection and warning information generation

[0125] The server compares predicted behavior with current behavior to check for any anomalies. If an anomaly is detected, it immediately generates a warning. The use of generative AI models improves the accuracy of anomaly detection.

[0126] As a concrete example, the server may detect that the aircraft is stuck at 8,000 feet when it should be climbing to 10,000 feet.

[0127] Warning information notification

[0128] The server sends the generated warning information to the terminal, and notifies the controller and the pilot, and the notification is displayed on the screen of the terminal, for example.

[0129] In this example, the server generates a warning message saying "Flight 123 is not climbing to 10,000 feet" and sends it to the terminal, which then displays the warning message on the controller's screen or the pilot's device.

[0130] Examples of prompt statements

[0131] The following are specific examples of prompt sentences to be input into the generative AI model.

[0132] "Please extract the instructions from the following text data: 'Flight 123, climb to 10,000 feet'"

[0133] In response to this prompt, the generative AI model will respond by extracting phrases such as "Flight 123" and "climb to 10,000 feet."

[0134] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0135] Step 1:

[0136] The terminal receives voice communications between the air traffic controller and the aircraft pilot. As input, it uses voice communication data collected through a microphone. Specifically, the terminal collects this voice data using a microphone and temporarily stores it in local storage. As output, it obtains the collected voice data.

[0137] Step 2:

[0138] The device sends the stored voice data to the server. The voice data stored in the local storage is used as input. Specifically, the device sends the collected voice files to the server via the Internet. The voice data received by the server is obtained as output.

[0139] Step 3:

[0140] The server uses a speech recognition engine to convert the received voice data into text data. The server uses the voice data it received as input. Specifically, the server calls a speech recognition engine (Google Cloud Speech-to-Text) and converts the voice data into text data such as "Flight 123, climb to 10,000 feet." The text data is obtained as output.

[0141] Step 4:

[0142] The server receives the converted text data and uses an NLP model to extract specific instructions. The text data is used as input. Specifically, the server uses an NLP model (e.g., SpaCy) to extract the instructions, such as "flight number" and "altitude instructions." The extracted instructions are obtained as output.

[0143] Step 5:

[0144] The server generates a predicted flight behavior based on the extracted instructions. The extracted instructions are used as input. Specifically, the server uses a Python mathematical library (e.g., NumPy) to generate a predicted behavior such as "the flight will climb to 10,000 feet." The generated predicted behavior is obtained as output.

[0145] Step 6:

[0146] The terminal collects the aircraft's current position data. As input, it uses the position data obtained through the GPS module. Specifically, the terminal obtains position data such as latitude, longitude, and altitude and sends it to the server. As output, it obtains the collected position data.

[0147] Step 7:

[0148] The server receives the transmitted location data and monitors the current aircraft behavior. It uses the location data transmitted from the terminal as input. Specifically, the server analyzes the collected data using the Pandas library to analyze the aircraft's current position, altitude, speed, etc. As output, it obtains the current aircraft behavior data.

[0149] Step 8:

[0150] The server compares the predicted behavior with the current behavior and checks for anomalies. As input, it uses the generated predicted behavior and the monitored behavior data. Specifically, the server performs a comparison operation to match the predicted behavior with the actual behavior and check for any discrepancies. As output, if there is an anomaly, the anomalous data is identified.

[0151] Step 9:

[0152] The server generates warning information immediately if an anomaly is detected. The server uses the anomaly data as input. Specifically, the server uses a generative AI model to generate an appropriate warning message (e.g., "Flight 123 is not climbing to 10,000 feet"). The warning information is obtained as output.

[0153] Step 10:

[0154] The server sends the generated warning information to the terminal and notifies the controller and pilot. The server uses the generated warning information as input. Specifically, the server sends the warning information to the terminal via the Internet, and the terminal displays this information on the controller's screen or the pilot's device. As output, a notification is sent.

[0155] (Application example 1)

[0156] 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."

[0157] In logistics centers, accurately managing instructions to workers and their execution status is extremely important for efficient business operations and ensuring safety. However, relying on verbal instructions is prone to human error and misunderstanding of instructions, making it difficult to grasp the situation in real time. This leads to problems such as reduced work efficiency and increased likelihood of mistakes. In addition, there are limited means to appropriately monitor the progress of work using location data, making it difficult to respond quickly when an abnormality occurs.

[0158] 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.

[0159] In this invention, the server includes means for receiving voice communication data between the controller and the operator of the vehicle, means for converting the received voice communication data into text data, means for extracting instructions from the converted text data, means for generating predicted behavior based on the extracted instructions, means for collecting current location data of the vehicle from a location information acquisition means, means for monitoring the actual behavior of the vehicle based on the collected location data, means for comparing the monitored behavior of the vehicle with the predicted behavior and detecting abnormalities, means for generating a notification when an abnormality is detected, and means for displaying the instructions and location data on the smart device. This enables real-time text conversion and analysis of voice instructions, behavior monitoring using location data, and rapid notification when an abnormality occurs.

[0160] A "controller" is a manager who gives instructions to workers and transportation means in a logistics center or transportation system.

[0161] "Vehicle" means any equipment or vehicle used to transport or move goods.

[0162] "Operator" means the worker or person in charge of operating or controlling a conveyance.

[0163] "Voice communication data" refers to data on voice instructions and reports exchanged between the controller and the pilot.

[0164] "Text data" refers to voice communication data converted into character format.

[0165] "Instruction content" refers to specific work instructions extracted from the extracted text data.

[0166] "Predicted behavior" is a model of the behavior that a vehicle should take, generated based on instructions.

[0167] "Location information acquisition means" means a device or system that collects the current location of a vehicle using technology such as GPS.

[0168] "Location data" means information regarding the current location of a vehicle.

[0169] "Behavior monitoring" is the process of comparing predicted behavior with actual behavior to monitor whether a vehicle is operating as instructed.

[0170] "Anomaly detection" is the act of detecting when predicted behavior and actual behavior do not match, or when abnormal behavior occurs.

[0171] "Notification" refers to transmitting an alert or warning to relevant parties when an abnormality is detected.

[0172] "Smart devices" refer to electronic devices such as smartphones, tablets, and wearable devices that can connect to the Internet and run various applications.

[0173] To implement this invention, it is first necessary to build a system that properly receives voice communication between the controller and the operator of the vehicle and converts it into text. Specifically, this can be realized by collaboration between a server, a terminal, and users (controller and operator).

[0174] Server Roles

[0175] The server is the central point that manages the operation of the vehicle through a number of functions. The main hardware and software used are:

[0176] Voice reception and conversion: The server uses a voice recognition engine (e.g., Google Speech Recognition API) to convert voice communication data between the controller and pilot into text data in real time.

[0177] Extracting Instructions: The text data is then analyzed and instructions are extracted using software such as Natural Language Processing (NLP) and spaCy.

[0178] Generate predictive behavior: Use a generative AI model (e.g., GPT-3®) to generate predictive behavior based on the extracted instructions.

[0179] Behavior monitoring: Receives location data of transportation vehicles from GPS modules and various sensors, and monitors the acquired data in real time.

[0180] Anomaly detection and notification: Compares monitored data with predicted behavior, and if an anomaly is detected, generates a notification and sends a quick alert to the controller or operator. Anomaly detection utilizes machine learning models and anomaly detection algorithms.

[0181] Device Role

[0182] The device (e.g., smartphone, head-mounted display) receives the information processed by the server and provides it visually and audibly to the user. The device is used as follows:

[0183] Audio reception: Receives audio communication from the controller and pilot and sends it to the server.

[0184] Location data collection: Location data is collected in real time through the GPS module and sent to the server.

[0185] Display notifications: Provides visual and audio notifications to the user of notifications and alerts sent by the server.

[0186] User Roles

[0187] The user (controller and pilot) is the main operator of the system and has the following roles:

[0188] Voice instructions: The controller issues voice instructions, which are transmitted to the server via the terminal.

[0189] Checking notifications: The pilot checks the notifications displayed on the device and takes appropriate action.

[0190] Specific examples

[0191] For example, a logistics center controller might say, "Please pick up 10 items from warehouse 1." This voice communication data is received by the terminal and sent to the server. The server uses a speech recognition engine to convert the speech into text and uses NLP technology to extract the instructions (items and quantities). Next, a generative AI model is used to generate predictive actions and monitor location data in real time. Finally, it checks whether the operator is performing the task according to the instructions, and if there is an abnormality, a notification is generated immediately to notify the operator. This series of processes improves the efficiency and safety of logistics operations.

[0192] Prompt Sentence Examples

[0193] "Give me the following instruction: Pick up 10 items from Warehouse 1. Write a Python program to retrieve this instruction and monitor its execution."

[0194] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0195] Step 1:

[0196] The terminal receives voice communication data between the controller and the pilot. The terminal uses a microphone to capture the voice and temporarily saves it as a voice data file. Then, the voice data is sent to the server.

[0197] (input)

[0198] Voice communication data between the controller and pilot.

[0199] (output)

[0200] The audio data file sent to the server.

[0201] Step 2:

[0202] The server converts the received voice data file into text data using a speech recognition engine (such as the Google Speech Recognition API). The speech recognition engine analyzes the voice data and generates corresponding text.

[0203] (input)

[0204] The audio data file sent from the device.

[0205] (output)

[0206] Text data.

[0207] Step 3:

[0208] The server extracts instructions from the generated text data. NLP techniques (e.g., spaCy) are used to identify important information in the text, such as the name of an item or quantity. The NLP model analyzes the text and outputs the instructions as structured data.

[0209] (input)

[0210] Text data converted by a speech recognition engine.

[0211] (output)

[0212] Instructions (item name, quantity, etc.).

[0213] Step 4:

[0214] The server generates a predicted action based on the extracted instructions. It uses a generative AI model (e.g., GPT-3) to predict what action is needed. The model generates an action plan based on the extracted instructions and outputs it as specific steps.

[0215] (input)

[0216] Instructions (item name, quantity, etc.).

[0217] (output)

[0218] Anticipatory behavior (action planning).

[0219] Step 5:

[0220] The terminal uses a GPS module to collect the current location data of the vehicle and transmits it to the server. The location data is collected in real time.

[0221] (input)

[0222] Real-time location of vehicles.

[0223] (output)

[0224] Location data sent to the server.

[0225] Step 6:

[0226] The server monitors the actual behavior of the vehicle based on the location data received. It compares the predicted behavior with the actual behavior to assess the data consistency. It uses a comparison algorithm to verify that each step is performed correctly.

[0227] (input)

[0228] Location data and predicted behavior sent from your device.

[0229] (output)

[0230] Behavior monitoring results (normal / abnormal).

[0231] Step 7:

[0232] The server detects anomalies based on the behavior monitoring results. If an anomaly is detected, an alert is generated immediately. Pre-defined conditions are used to generate the alert.

[0233] (input)

[0234] Behavioral monitoring results.

[0235] (output)

[0236] An alert message in case of an abnormality.

[0237] Step 8:

[0238] The server sends the generated alert to the device and notifies the user (controller and pilot). The notification is displayed on the device's display and may also sound an audio alert.

[0239] (input)

[0240] Alert message.

[0241] (output)

[0242] The notification message that appears on the device.

[0243] Prompt Sentence Examples

[0244] "Give me the following instruction: Pick up 10 items from Warehouse 1. Write a Python program to retrieve this instruction and monitor its execution."

[0245] 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.

[0246] Overall system flow

[0247] This invention is a system that improves aviation safety by not only enabling voice communication between air traffic controllers and aircraft pilots, but also recognizing the user's emotional state and detecting abnormalities early based on that data. This system includes functions for receiving and converting voice data, extracting instruction content, generating predictive actions, collecting GPS data and monitoring behavior, detecting abnormalities and generating alerts, as well as analyzing the user's emotional state using an emotion engine and providing notifications.

[0248] Receiving and converting voice communication data

[0249] The terminal receives voice communication data between the controller and the pilot in real time.

[0250] The terminal converts the voice data into a digital format and transmits it to the server.

[0251] Extracting instruction content

[0252] The server uses a speech recognition engine to convert the voice communication data into text data.

[0253] The server analyzes the text data, extracts the instruction content, and stores the content in a database.

[0254] Generating predictive behavior

[0255] The server generates a predicted action of the pilot based on the extracted instruction content.

[0256] For example, if you receive the command "Flight 123, climb to 10,000 feet," you would predict that Flight 123 will climb to an altitude of 10,000 feet.

[0257] GPS data collection and behavior monitoring

[0258] The terminal (on the aircraft) collects the aircraft's current GPS data (altitude, position, speed, etc.) in real time and transmits it to the server.

[0259] The server analyzes the GPS data and monitors the aircraft's actual behavior, comparing it with predicted behavior.

[0260] Anomaly detection and alert generation

[0261] Based on the comparison results, the server detects an abnormality if the pilot's actions differ from instructions.

[0262] When an abnormality is detected, the server immediately generates an alert message and sends it to the terminal.

[0263] The terminal will then notify the controller and pilot of the alert.

[0264] Emotion Engine Operation

[0265] The terminal collects voice and behavioral data from controllers and pilots and transmits it to a server.

[0266] The server uses an emotion engine to analyze this data and recognize the user's emotional state.

[0267] If the emotional state obtained from the emotion engine is determined to be abnormal, the server generates an alert message with that information.

[0268] The server also generates a message based on the abnormal emotional state, suggesting appropriate steps to take.

[0269] The terminal notifies controllers and pilots of these alert messages and response procedures.

[0270] Specific operation examples

[0271] Example 1: Up command case

[0272] 1. The user (controller) sends the instruction "Flight 123, climb to 10,000 feet."

[0273] 2. The terminal receives this voice instruction and sends it to the server.

[0274] 3. The server uses a speech recognition engine to convert the voice into text and extract the instructions.

[0275] 4. The server generates a predicted climb to 10,000 feet for Flight 123.

[0276] 5. The terminal (aircraft side) sends the current altitude GPS data to the server.

[0277] 6. The server compares the current altitude with the predicted behavior to ensure proper ascent.

[0278] 7. The server generates an alert and sends it to the device if it does not act as instructed, for example if it stops at an altitude of 8,000 feet.

[0279] 8. The terminal alerts the controller and pilot that "Flight 123 is not climbing to 10,000 feet."

[0280] 9. The user (controller) confirms this notification and issues instructions again.

[0281] Example 2: Emotional state anomaly detection case

[0282] 1. The terminal collects the pilot's voice and behavioral data in real time and sends it to the server.

[0283] 2. The server uses an emotion engine to analyze the pilot's emotional state.

[0284] 3. If the server detects abnormal stress or panic, it generates an abnormal emotion alert.

[0285] 4. The server sends this abnormal emotion alert to the terminal and notifies the controller and pilot.

[0286] 5. The device will also simultaneously send you a message suggesting ways to improve or cope with your emotional state.

[0287] The system of this invention makes it possible to detect and quickly deal with not only misunderstandings and operational errors between air traffic controllers and pilots, but also abnormalities due to emotional states in real time, which is expected to significantly improve aviation safety.

[0288] The processing flow will be explained below.

[0289] Step 1:

[0290] The terminal receives voice communication data between the controller and the pilot in real time.

[0291] Step 2:

[0292] The terminal converts the received voice communication data into a digital format and transmits it to the server.

[0293] Step 3:

[0294] The server uses a speech recognition engine to convert the voice communication data into text data.

[0295] Step 4:

[0296] The server analyzes the converted text data and extracts the instructions (e.g., flight number, target altitude, direction of travel, etc.).

[0297] Step 5:

[0298] The server generates a predicted action that the pilot should take based on the extracted instructions.

[0299] Step 6:

[0300] The terminal (aircraft-side device) collects the aircraft's current GPS data (altitude, position, speed, etc.) and transmits it to the server.

[0301] Step 7:

[0302] The server analyzes the received GPS data and monitors the aircraft's actual behavior in real time.

[0303] Step 8:

[0304] The server compares the monitored aircraft behavior with the predicted behavior generated in the previous step to check whether the pilot is acting as instructed.

[0305] Step 9:

[0306] The server detects an anomaly if the pilot's actions are not as instructed.

[0307] Step 10:

[0308] The server immediately generates an alert message when an abnormality is detected.

[0309] Step 11:

[0310] The server sends this alert message to the terminal.

[0311] Step 12:

[0312] The terminal (control tower equipment) receives the alert message and displays the notification on the controller's display terminal.

[0313] Step 13:

[0314] The user (controller) checks the notification and takes necessary measures.

[0315] Step 14:

[0316] The terminal collects voice and behavioral data from controllers and pilots and transmits it to a server.

[0317] Step 15:

[0318] The server uses an emotion engine to analyze this data and recognize the user's emotional state.

[0319] Step 16:

[0320] If the emotional state obtained from the emotion engine is determined to be abnormal, the server generates an alert message with that information.

[0321] Step 17:

[0322] The server generates a message based on the abnormal emotional state, suggesting appropriate steps to take.

[0323] Step 18:

[0324] The server sends these alert messages and troubleshooting procedures to the terminal and notifies the user.

[0325] Example 2

[0326] 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."

[0327] During aircraft operations, safety risks exist due to misunderstandings or operational errors in voice communications between air traffic controllers and pilots, as well as abnormal emotional states of pilots or controllers. A system that can detect such risks early and deal with them promptly is needed.

[0328] 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.

[0329] In this invention, the server includes a means for converting voice communication data between the controller and the pilot into text data, a means for extracting instructions from the converted text data and storing the instructions in a database, a means for analyzing collected GPS data and monitoring the aircraft's actual behavior while comparing it with predicted behavior, and a means for analyzing the voice and behavior data of the controller and the pilot using an emotion engine to recognize their emotional states. This makes it possible to detect not only misrecognition of instructions and operational errors, but also abnormal emotional states in real time and respond promptly.

[0330] "Voice communication data" refers to the voice information exchanged between air traffic controllers and pilots.

[0331] "Digital format" refers to a data format in which analog audio data is converted into a digital signal.

[0332] "Server" refers to a computer system that performs speech recognition, data analysis, and data storage.

[0333] "Text data" refers to data in the form of a character string converted from voice data.

[0334] "Instruction content" refers to the specific actions and commands extracted from text data.

[0335] "Database" refers to a structured data storage system for efficiently storing and managing data.

[0336] "Predicted actions" refers to predictions of the actions the pilot should take, generated based on the extracted instructions.

[0337] "GPS data" refers to data indicating the current location of an aircraft.

[0338] "Actual actions" refers to actions actually taken by the aircraft.

[0339] "Abnormal" refers to a state in which predicted behavior does not match actual behavior or emotional state is abnormal.

[0340] An "alert" refers to a warning message generated when the system detects an abnormality.

[0341] An "emotion engine" refers to software or algorithms that analyze voice and behavioral data to recognize emotional states.

[0342] "Terminal" refers to a device that receives, converts, transmits voice data, and notifies alerts.

[0343] "Emotional Data" refers to data regarding an emotional state analyzed using an emotion engine.

[0344] The present invention is a system that improves aviation safety by not only enabling voice communication between air traffic controllers and aircraft pilots, but also recognizing the emotional state of users and detecting abnormalities early based on that data. This system is realized using the following hardware and software.

[0345] Hardware:

[0346] Terminal (aircraft and tower): A device that receives audio, converts it into digital form, and transmits it.

[0347] Server: A computer system that processes voice data, converts text, analyzes data, runs an emotion engine, and manages the database.

[0348] GPS unit: A device used to obtain the aircraft's current position in real time.

[0349] Microphone: An acoustic device used to collect the voices of controllers and pilots.

[0350] software:

[0351] Speech recognition engine: Software that converts voice data into text data, such as the Google Speech-to-Text API.

[0352] Database management system: A database such as MySQL (registered trademark) for storing instruction content, emotional data, etc.

[0353] Natural language processing engine: Software used to analyze text data, such as NLTK.

[0354] Emotion Engine: An algorithm that recognizes emotional states from speech and behavioral data, such as IBM Watson® Tone Analyzer.

[0355] Communication protocol: TCP / IP, MQTT, or other communication protocol used to send and receive voice and GPS data.

[0356] Examples of implementation of the invention:

[0357] Example 1: Up command case

[0358] 1. The user (controller) sends a voice command: "Flight 123, climb to 10,000 feet."

[0359] 2. The device receives the voice instruction, converts it into digital form and sends it to the server.

[0360] 3. The server uses the Google Speech-to-Text API to convert the speech to text and recognizes it as "Flight 123, climb to 10,000 feet."

[0361] 4. The server uses a natural language processing engine to extract instructions from the text data and generate a predicted action for Flight 123 to climb to 10,000 feet.

[0362] 5. The terminal (aircraft side) sends real-time GPS data such as current altitude and location to the server.

[0363] 6. The server compares the current altitude data with the predicted behavior and monitors whether the ascent is proceeding properly.

[0364] 7. If the server does not act as instructed, it generates an alert saying "Flight 123 is not climbing to 10,000 feet" and sends it to the device.

[0365] 8. The terminal notifies the controller and pilot of this alert, prompting the controller to review the situation.

[0366] Example 2: Emotional state anomaly detection case

[0367] 1. The terminal collects the pilot's voice and behavioral data (e.g., operational errors and voice tremors) in real time and transmits them to the server.

[0368] 2. The server uses an emotion engine to analyze voice and behavioral data and recognize the pilot's emotional state (e.g., high stress).

[0369] 3. If the server detects an abnormal stress state, it generates an "abnormal emotion alert."

[0370] 4. The server sends this abnormal emotion alert to the terminal and notifies the controller and pilot.

[0371] 5. The device will display a message suggesting ways to improve the situation: "The pilot is under high stress. Please take a deep breath and calm down."

[0372] Example prompt sentence:

[0373] Below are some example prompts to input to the generative AI model:

[0374] "What would the system do if the controller instructed Flight 123 to climb to 10,000 feet, but it stopped below 10,000 feet?"

[0375] "Please explain specifically how the system will respond if the pilot exhibits an abnormal emotional state."

[0376] The system of this invention not only detects misunderstandings and operational errors between air traffic controllers and pilots, but also detects abnormal emotional states in real time and makes it possible to deal with them quickly, which is expected to significantly improve aviation safety.

[0377] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0378] Step 1: Receiving and converting voice communication data

[0379] The terminal receives voice communication data between the controller and the pilot in real time.

[0380] Input: Analog voice data between controller and pilot

[0381] Specific Action: Capture audio data using a microphone and receive it through a communication device.

[0382] Output: Audio data converted to digital format

[0383] The terminal converts the received voice data into a digital format and transmits it to the server.

[0384] Input: Analog audio data

[0385] Specific operation: Audio data is digitized by setting the sampling rate and bit depth, and sent to the server using the TCP / IP protocol.

[0386] Output: Digital audio data sent to the server

[0387] Step 2: Extracting instructions

[0388] The server converts the received voice data into text data using a voice recognition engine (e.g., Google Speech-to-Text API).

[0389] Input: Digital audio data

[0390] Specific operation: Passes digital voice data to a voice recognition engine and calls an API to obtain string data.

[0391] Output: Instructions converted into text data

[0392] The server analyzes the text data using a natural language processing engine, extracts the instructions, and stores them in a database.

[0393] Input: Text data

[0394] Specific operation: Parses text data using the NLTK library, extracts commands and keywords, and stores them in a database.

[0395] Output: Extracted instruction data

[0396] Step 3: Generate predicted behavior

[0397] The server generates a predicted behavior of the pilot based on the extracted instruction content.

[0398] Input: Extracted instruction data

[0399] Specific behavior: The instructions are input into the internal algorithm to generate predictive behavior. For example, if the instruction is "Flight 123, climb to 10,000 feet," it will predict that Flight 123 will climb to 10,000 feet.

[0400] Output: Generated predicted behavior data

[0401] Step 4: Collecting GPS data and monitoring behavior

[0402] The terminal (on the aircraft) collects the aircraft's current GPS data in real time and transmits it to the server.

[0403] Input: Real-time GPS data (altitude, location, speed, etc.)

[0404] Specific operation: Data is acquired from the GPS unit installed on the aircraft and sent to the server using the MQTT protocol.

[0405] Output: GPS data sent to the server

[0406] The server analyzes the received GPS data and compares it with predicted behavior to monitor behavior.

[0407] Input: Real-time GPS data, predicted behavior data

[0408] Specific operation: Using a custom algorithm implemented in Python, the received GPS data is compared with the predicted behavior data to determine whether it is normal or abnormal.

[0409] Output: Comparison results and monitoring result data

[0410] Step 5: Anomaly detection and alert generation

[0411] The server compares predicted behavior with actual behavior and detects anomalies.

[0412] Input: Comparison result data

[0413] Specific operation: If the predicted altitude does not match the actual altitude, an abnormality flag is raised.

[0414] Output: Anomaly detection flag and anomaly content data

[0415] If the server detects an abnormality, it immediately generates an alert message and sends it to the terminal.

[0416] Input: Anomaly detection flag and anomaly content data

[0417] Specific behavior: Generate an alert message containing details of the anomaly, encode it in JSON format, and send it to the terminal.

[0418] Output: The alert message sent to the terminal.

[0419] The terminal will then notify the controller and pilot of the alert.

[0420] Input: Alert message

[0421] What it does: Use the display and audio output device to provide a visual and audible alert that "Flight 123 is not climbing to 10,000 feet."

[0422] Output: Alerts sent to controllers and pilots

[0423] Step 6: Emotion Engine in Action

[0424] The terminal collects voice and behavioral data from controllers and pilots and transmits it to a server.

[0425] Input: Real-time audio and behavioral data

[0426] Specific operation: Collects voice and behavioral data through microphones and various sensors and sends it to a server.

[0427] Output: Audio and behavioral data sent to the server

[0428] The server uses an emotion engine to analyze this data and recognize the emotional state.

[0429] Input: Audio and behavioral data

[0430] Specific operation: Using emotion engines such as IBM Watson Tone Analyzer, the system analyzes voice and behavioral data to recognize emotional states.

[0431] Output: Recognized emotional state data

[0432] If the emotional state is determined to be abnormal, the server generates an alert message and notifies the user.

[0433] Input: Emotional state data

[0434] Specific operation: If an abnormal emotional state is detected, an alert message containing details is generated and sent to the device.

[0435] Output: Emotional abnormality alert message sent to the terminal

[0436] The server also generates a message based on the abnormal emotional state, suggesting appropriate steps to take.

[0437] Input: Emotional state data

[0438] Specific Action: Based on the analysis results from the emotion engine, a message is generated suggesting appropriate steps to take (e.g., "Take a deep breath and stay calm").

[0439] Output: Proposal message

[0440] The terminal notifies controllers and pilots of these alert messages and response procedures.

[0441] Input: Emotional abnormality alert message and suggested message

[0442] Specific operation: Display and play notification information using a display and audio playback device.

[0443] Output: Suggestions and emotional anomaly alerts notified to controllers and pilots

[0444] (Application example 2)

[0445] 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."

[0446] Improving the safety of autonomous vehicles is an important challenge for current technology. In particular, it is necessary to properly recognize the emotional state of driver assistants and passengers and respond quickly when an abnormality occurs. Conventional systems have had difficulty understanding passengers' emotional states in real time, detecting abnormalities, and taking countermeasures. Therefore, a new system that can analyze emotional states and support safe driving is needed.

[0447] The identification process by the identification 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 voice communication data between an air traffic controller and an aircraft pilot; means for converting the received voice communication data into text data; means for extracting instructions from the converted text data; means for generating a predicted behavior based on the extracted instructions; means for collecting current position data of the aircraft from a GPS; means for monitoring the actual behavior of the aircraft based on the collected GPS data; means for comparing the monitored behavior of the aircraft with the predicted behavior and detecting an abnormality; means for generating and notifying an alert when an abnormality is detected; means for collecting voice data and behavior data and analyzing the emotional state; and means for generating an alert and suggesting a response procedure when an abnormal emotional state is detected. This makes it possible to grasp the emotional states of the driver's assistant and passengers in real time, quickly detect abnormalities, and take appropriate measures.

[0448] A "controller" is a person whose job is to monitor and direct the operation of aircraft and vehicles.

[0449] "Aircraft" is a general term for any mechanical device that can fly.

[0450] A "pilot" is a person qualified to operate an aircraft.

[0451] "Voice communication data" means information in digital form that contains voice.

[0452] "Text data" means written information in digital form.

[0453] "Instruction content" is information for instructing a specific action.

[0454] "Predicted behavior" refers to behavior that the system generates based on the instructions it receives.

[0455] "Location Data" means geographic location information obtained using technologies such as GPS.

[0456] "GPS" is an abbreviation for Global Positioning System, a system for determining locations on Earth with high accuracy.

[0457] "Actual behavior" refers to the actions that a system or machine actually takes.

[0458] An "abnormality" is a state in which predicted behavior differs from actual behavior.

[0459] An "alert" is a warning issued when an abnormality is detected.

[0460] A "notification" is a means of conveying specific information.

[0461] "Audio data" is a general term for digital information that includes audio.

[0462] "Behavioral data" is digital information about the actions taken by a system or machine.

[0463] "Emotional state" refers to a person's emotional state.

[0464] An "abnormal emotional state" is an emotional state that is different from the normal state.

[0465] "Response procedures" refer to the actions and procedures to be taken when an abnormality occurs.

[0466] Overall system configuration

[0467] This invention is a system that analyzes voice and behavioral data in real time to detect abnormalities in order to improve the safety of autonomous vehicles. In particular, it analyzes the emotional state of the driver's assistant and passengers and provides appropriate response procedures in the event of an abnormality. It also incorporates location data collection using GPS.

[0468] Program processing explanation

[0469] The system's main hardware includes a smartphone, smart glasses, and a GPS module, while the software uses Python, the speech_recognition library, and the requests library.

[0470] Receiving and converting voice communication data

[0471] The server receives the driver's assistant's voice communication data in real time and converts it into text data. Specifically, it uses the smartphone's microphone function and a speech recognition engine (for example, the speech_recognition library) to convert the voice into text.

[0472] Extracting instruction content and generating predicted actions

[0473] The server extracts the instructions from the converted text data and generates predicted actions based on the instructions. This information is stored in a database and used for analytical processing.

[0474] GPS data collection and behavior monitoring

[0475] The terminal (on the vehicle side) collects the vehicle's current GPS data (position, speed, etc.) in real time and sends it to the server, which analyzes this GPS data and compares the actual behavior with the predicted behavior.

[0476] Anomaly detection and alert generation

[0477] The server compares predicted and actual behavior and immediately generates an alert if an abnormality is detected, which is then sent to the driver assistant via a smartphone or smart glasses.

[0478] Emotion Engine Operation

[0479] The server collects voice and behavioral data and analyzes them using an emotion engine. If the emotional state is determined to be abnormal, an alert is generated and a response procedure is proposed. This process uses a generative AI model, and the results are sent to the driver's assistant's smartphone or other device.

[0480] Specific example explanation

[0481] For example, if the driver assistant is feeling stressed, the system operates as follows:

[0482] 1. The driver assistant issues a voice command such as, "I feel the vehicle speed is a little too fast."

[0483] 2. This audio is collected through the smartphone's microphone and sent to a server.

[0484] 3. The server converts the speech into text and analyzes it using an emotion engine. The analysis results detect stress and anxiety.

[0485] 4. The server generates an alert based on this information and sends it to the smartphone.

[0486] 5. Your smartphone will display an alert such as "Driver assistant is experiencing high stress, we recommend reducing speed."

[0487] Prompt Sentence Examples

[0488] For example, a specific example of a prompt sentence to be input into a generative AI model is, "Convert this voice data into text, analyze the user's emotional state, and notify me if any abnormalities are found."

[0489] Such a system would enable autonomous vehicles to monitor the emotional state of their occupants while driving, quickly detect and respond to any abnormalities, and ultimately provide a safer driving environment.

[0490] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0491] Step 1:

[0492] The user inputs voice data using the microphone on the smartphone, and the input voice data is collected from the driver's assistant.

[0493] Step 2:

[0494] The device transmits the received voice data in real time to a server, where it is converted into a digital format and transmitted over the internet.

[0495] Step 3:

[0496] The server converts the received voice data into text data using a voice recognition engine (for example, the speech_recognition library). The input is digital voice data, and the output is text data.

[0497] Step 4:

[0498] The server extracts the instructions from the converted text data. Natural language processing technology is used to analyze the text data for specific instructions and emotional states. The input is the text data, and the output is the analysis results of the instructions and emotional states.

[0499] Step 5:

[0500] The server generates a predicted behavior based on the extracted instruction content. For example, if the instruction is "slow down," it predicts the behavior of slowing down to an appropriate speed. The input is instruction content data, and the output is predicted behavior data.

[0501] Step 6:

[0502] The terminal (vehicle side) collects current location data using a GPS module and transmits it to the server in real time. The input is GPS data, and the output is the transmitted current location data.

[0503] Step 7:

[0504] The server monitors the vehicle's actual behavior based on the collected GPS data. It compares the predicted behavior with the actual behavior and checks for any abnormalities. The inputs are the predicted behavior data and GPS data, and the output is the result of anomaly detection.

[0505] Step 8:

[0506] The server generates an alert when an anomaly is detected. The alert is generated as a specific text message. The input is the anomaly detection data, and the output is the alert message.

[0507] Step 9:

[0508] The terminal notifies the driver assistant of the generated alert message. The alert message is displayed visually or audibly using a smartphone or smart glasses. The input is the alert message, and the output is a visual or audio notification.

[0509] Step 10:

[0510] The server collects voice data and behavioral data and analyzes the emotional state using an emotion engine. The input is the voice data and behavioral data, and the output is the analysis result of the emotional state.

[0511] Step 11:

[0512] If the server detects an abnormal emotional state, it generates an alert and suggests a course of action. It uses a generative AI model to suggest an appropriate course of action. The input is emotional state data, and the output is an alert message with a course of action.

[0513] Step 12:

[0514] The terminal notifies the driver assistant of the generated alert message and the response procedures via a smartphone or smart glasses. The input is the alert message with the response procedures, and the output is a visual or audio notification.

[0515] 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.

[0516] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0517] 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.

[0518] [Second embodiment]

[0519] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0520] 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.

[0521] 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).

[0522] 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.

[0523] 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.

[0524] 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).

[0525] 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.

[0526] 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.

[0527] 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.

[0528] 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.

[0529] In the smart glasses 214, 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.

[0530] 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."

[0531] To implement this invention, it is necessary to build a system that collects voice communication data between air traffic controllers and aircraft pilots in real time and converts it into text data. This system supports the safe operation of aircraft through a series of processes: extracting instructions, generating predicted behavior, collecting GPS data, monitoring behavior, detecting anomalies, and generating and notifying alerts.

[0532] Overall system flow

[0533] Receiving and converting voice communication data

[0534] The terminal receives voice communications between the controller and the pilot.

[0535] The terminal transmits this voice data to the server.

[0536] The server uses a speech recognition engine to convert the voice communication data into text data.

[0537] Extracting instruction content

[0538] The server extracts the instruction content (e.g., flight number, destination, altitude, etc.) from the converted text data.

[0539] Generating predictive behavior

[0540] The server generates a predicted flight behavior based on the extracted instructions. For example, if the instruction is "Flight 123, climb to 10,000 feet," it predicts that Flight 123 will climb from its current altitude to 10,000 feet.

[0541] GPS data collection and behavior monitoring

[0542] The terminal collects the aircraft's current GPS data and transmits it to the server.

[0543] The server analyzes this GPS data and monitors the aircraft's actual behavior (position, altitude, speed, etc.) in real time.

[0544] Anomaly detection and alert generation

[0545] The server compares the monitored aircraft behavior with the predicted behavior and checks for any anomalies.

[0546] The server immediately generates an alert message if an abnormality is detected.

[0547] The server sends the generated alert to the terminal and notifies the controller and pilot.

[0548] Specific operation examples

[0549] Example 1: Up command case

[0550] 1. The user (controller) sends the instruction "Flight 123, climb to 10,000 feet."

[0551] 2. The terminal receives this voice instruction and sends it to the server.

[0552] 3. The server uses a speech recognition engine to convert the voice into text and extract the instructions.

[0553] 4. The server generates a predicted climb to 10,000 feet for Flight 123.

[0554] 5. The terminal (aircraft side) sends the current altitude GPS data to the server.

[0555] 6. The server compares the current altitude with the predicted behavior to ensure proper ascent.

[0556] 7. The server generates an alert and sends it to the device if it does not act as instructed, for example if it stops at an altitude of 8,000 feet.

[0557] 8. The terminal alerts the controller and pilot that "Flight 123 is not climbing to 10,000 feet."

[0558] 9. The user (controller) confirms this notification and issues instructions again.

[0559] By using this system, it is possible to monitor aircraft movements in real time, detect abnormalities early, increase safety, and reduce the workload of air traffic controllers.

[0560] The processing flow will be explained below.

[0561] Step 1:

[0562] The terminal receives voice communication data between the controller and the pilot in real time.

[0563] Step 2:

[0564] The terminal converts the received voice communication data into a digital format and transmits it to the server.

[0565] Step 3:

[0566] The server uses a speech recognition engine to convert the voice communication data into text data.

[0567] Step 4:

[0568] The server analyzes the converted text data and extracts the instructions (e.g., flight number, target altitude, direction of travel, etc.).

[0569] Step 5:

[0570] The server generates a predicted action that the pilot should take based on the extracted instructions.

[0571] Step 6:

[0572] The terminal (aircraft-side device) collects the aircraft's current GPS data (altitude, position, speed, etc.) and transmits it to the server.

[0573] Step 7:

[0574] The server analyzes the received GPS data and monitors the aircraft's actual behavior in real time.

[0575] Step 8:

[0576] The server compares the monitored aircraft behavior with the predicted behavior generated in the previous step to check whether the pilot is acting as instructed.

[0577] Step 9:

[0578] The server detects an anomaly if the pilot's actions are not as instructed.

[0579] Step 10:

[0580] The server immediately generates an alert message when an abnormality is detected.

[0581] Step 11:

[0582] The server sends this alert message to the terminal.

[0583] Step 12:

[0584] The terminal (control tower equipment) receives the alert message and displays the notification on the controller's display terminal.

[0585] Step 13:

[0586] The user (controller) checks the notification and takes necessary measures.

[0587] These steps will enable misunderstandings and operational errors between controllers and pilots to be detected in real time, preventing accidents before they occur.

[0588] Example 1

[0589] 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."

[0590] Aircraft operations require rapid and accurate analysis of voice communication data between air traffic controllers and pilots. Conventional methods often involve manual conversion and analysis of voice data, which can lead to misunderstandings and delays. This can potentially reduce the safety of aircraft operations. To solve this problem, a system is needed that can automatically analyze voice communication data in real time and issue an immediate warning in the event of an abnormality.

[0591] 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.

[0592] In this invention, the server includes means for receiving voice communication data between an air traffic controller and an aircraft pilot, means for converting the received voice communication data into text data, means for extracting instructions from the converted text data, means for generating predicted behavior based on the extracted instructions, means for collecting current position data of the aircraft from a satellite positioning system, means for monitoring the actual behavior of the aircraft based on the collected position data, means for comparing the monitored behavior of the aircraft with predicted behavior and detecting abnormalities, means for generating and notifying warning information when an abnormality is detected, means for automatically analyzing instructions related to the aircraft, and means for displaying the generated warning information on a terminal. This makes it possible to automatically analyze voice communication data in real time during aircraft operation and ensure safety.

[0593] "Voice communication data" refers to the content of voice communications between air traffic controllers and aircraft pilots.

[0594] "Text data" refers to a data format in which voice communication data is converted into a string of characters.

[0595] "Instruction content" refers to specific command items such as flight number, destination, and altitude extracted from the text data.

[0596] "Predicted action" refers to the action that the aircraft is expected to take based on the instructions.

[0597] "Position Data" refers to current aircraft position information collected from satellite positioning systems.

[0598] "Satellite positioning system" refers to a general term for systems that receive signals from satellites and measure the precise location of an aircraft.

[0599] "Behavioral surveillance" refers to the process of monitoring the actual behavior of aircraft based on collected location data.

[0600] "Anomaly detection" refers to comparing monitored aircraft behavior with predicted behavior to determine whether there are any anomalies.

[0601] "Warning information" refers to a notification message that is generated when an abnormality is detected.

[0602] "Terminal" refers to a device that receives and transmits voice communication data, displays warning information, etc.

[0603] MODE FOR CARRYING OUT THE INVENTION

[0604] To implement this invention, it is necessary to build a system that collects voice communication data between air traffic controllers and aircraft pilots in real time and converts it into text data. This system supports the safe operation of aircraft through a series of processes: extraction of instruction content, generation of predicted behavior, collection of location data, behavior monitoring, anomaly detection, and generation and notification of warning information.

[0605] Receiving and converting voice communication data

[0606] The terminal receives voice communications between the air traffic controller and the aircraft pilot. The terminal collects voice data using a microphone and temporarily stores the collected voice data in local storage. The terminal then transmits the stored voice data to a server. The server converts the voice data into text data using a speech recognition engine (e.g., Google Cloud Speech-to-Text).

[0607] For example, if a controller says, "Flight 123, climb to 10,000 feet," the device will record this audio with a microphone and send it to a server, which will then convert it into text using Google Cloud Speech-to-Text.

[0608] Extracting instruction content

[0609] The server receives the converted text data and uses an NLP model (e.g., SpaCy) to extract specific instructions, such as flight number, destination, and altitude.

[0610] In a specific example, the server extracts "Flight 123" and "climb to 10,000 feet" from the text data "Flight 123, climb to 10,000 feet."

[0611] Generating predictive behavior

[0612] The server generates a predicted flight behavior based on the extracted instructions. It uses a Python numerical calculation library (e.g., NumPy) to generate numerical data corresponding to the instructed behavior.

[0613] As a concrete example, the server generates a predicted action such as "Flight 123 will climb to 10,000 feet."

[0614] Location data collection and behavioral monitoring

[0615] The terminal collects the aircraft's current location data. This location data is obtained using a satellite positioning system (e.g., GPS). The collected location data includes latitude, longitude, altitude, etc. The terminal then transmits this location data to a server.

[0616] The server receives the transmitted position data and monitors the current aircraft behavior, a process that involves data analysis using the Pandas library.

[0617] In a specific example, the terminal uses the aircraft's GPS module to obtain information such as the current latitude, longitude, and altitude, and sends it to the server. The server confirms and records that the aircraft's current altitude is "8,000 feet."

[0618] Anomaly detection and warning information generation

[0619] The server compares predicted behavior with current behavior to check for any anomalies. If an anomaly is detected, it immediately generates a warning. The use of generative AI models improves the accuracy of anomaly detection.

[0620] As a concrete example, the server may detect that the aircraft is stuck at 8,000 feet when it should be climbing to 10,000 feet.

[0621] Warning information notification

[0622] The server sends the generated warning information to the terminal, and notifies the controller and the pilot, and the notification is displayed on the screen of the terminal, for example.

[0623] In this example, the server generates a warning message saying "Flight 123 is not climbing to 10,000 feet" and sends it to the terminal, which then displays the warning message on the controller's screen or the pilot's device.

[0624] Examples of prompt statements

[0625] The following are specific examples of prompt sentences to be input into the generative AI model.

[0626] "Please extract the instructions from the following text data: 'Flight 123, climb to 10,000 feet'"

[0627] In response to this prompt, the generative AI model will respond by extracting phrases such as "Flight 123" and "climb to 10,000 feet."

[0628] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0629] Step 1:

[0630] The terminal receives voice communications between the air traffic controller and the aircraft pilot. As input, it uses voice communication data collected through a microphone. Specifically, the terminal collects this voice data using a microphone and temporarily stores it in local storage. As output, it obtains the collected voice data.

[0631] Step 2:

[0632] The device sends the stored voice data to the server. The voice data stored in the local storage is used as input. Specifically, the device sends the collected voice files to the server via the Internet. The voice data received by the server is obtained as output.

[0633] Step 3:

[0634] The server uses a speech recognition engine to convert the received voice data into text data. The server uses the voice data it received as input. Specifically, the server calls a speech recognition engine (Google Cloud Speech-to-Text) and converts the voice data into text data such as "Flight 123, climb to 10,000 feet." The text data is obtained as output.

[0635] Step 4:

[0636] The server receives the converted text data and uses an NLP model to extract specific instructions. The text data is used as input. Specifically, the server uses an NLP model (e.g., SpaCy) to extract the instructions, such as "flight number" and "altitude instructions." The extracted instructions are obtained as output.

[0637] Step 5:

[0638] The server generates a predicted flight behavior based on the extracted instructions. The extracted instructions are used as input. Specifically, the server uses a Python mathematical library (e.g., NumPy) to generate a predicted behavior such as "the flight will climb to 10,000 feet." The generated predicted behavior is obtained as output.

[0639] Step 6:

[0640] The terminal collects the aircraft's current position data. As input, it uses the position data obtained through the GPS module. Specifically, the terminal obtains position data such as latitude, longitude, and altitude and sends it to the server. As output, it obtains the collected position data.

[0641] Step 7:

[0642] The server receives the transmitted location data and monitors the current aircraft behavior. It uses the location data transmitted from the terminal as input. Specifically, the server analyzes the collected data using the Pandas library to analyze the aircraft's current position, altitude, speed, etc. As output, it obtains the current aircraft behavior data.

[0643] Step 8:

[0644] The server compares the predicted behavior with the current behavior and checks for anomalies. As input, it uses the generated predicted behavior and the monitored behavior data. Specifically, the server performs a comparison operation to match the predicted behavior with the actual behavior and check for any discrepancies. As output, if there is an anomaly, the anomalous data is identified.

[0645] Step 9:

[0646] The server generates warning information immediately if an anomaly is detected. The server uses the anomaly data as input. Specifically, the server uses a generative AI model to generate an appropriate warning message (e.g., "Flight 123 is not climbing to 10,000 feet"). The warning information is obtained as output.

[0647] Step 10:

[0648] The server sends the generated warning information to the terminal and notifies the controller and pilot. The server uses the generated warning information as input. Specifically, the server sends the warning information to the terminal via the Internet, and the terminal displays this information on the controller's screen or the pilot's device. As output, a notification is sent.

[0649] (Application example 1)

[0650] 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."

[0651] In logistics centers, accurately managing instructions to workers and their execution status is extremely important for efficient business operations and ensuring safety. However, relying on verbal instructions is prone to human error and misunderstanding of instructions, making it difficult to grasp the situation in real time. This leads to problems such as reduced work efficiency and increased likelihood of mistakes. In addition, there are limited means to appropriately monitor the progress of work using location data, making it difficult to respond quickly when an abnormality occurs.

[0652] 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.

[0653] In this invention, the server includes means for receiving voice communication data between the controller and the operator of the vehicle, means for converting the received voice communication data into text data, means for extracting instructions from the converted text data, means for generating predicted behavior based on the extracted instructions, means for collecting current location data of the vehicle from a location information acquisition means, means for monitoring the actual behavior of the vehicle based on the collected location data, means for comparing the monitored behavior of the vehicle with the predicted behavior and detecting abnormalities, means for generating a notification when an abnormality is detected, and means for displaying the instructions and location data on the smart device. This enables real-time text conversion and analysis of voice instructions, behavior monitoring using location data, and rapid notification when an abnormality occurs.

[0654] A "controller" is a manager who gives instructions to workers and transportation means in a logistics center or transportation system.

[0655] "Vehicle" means any equipment or vehicle used to transport or move goods.

[0656] "Operator" means the worker or person in charge of operating or controlling a conveyance.

[0657] "Voice communication data" refers to data on voice instructions and reports exchanged between the controller and the pilot.

[0658] "Text data" refers to voice communication data converted into character format.

[0659] "Instruction content" refers to specific work instructions extracted from the extracted text data.

[0660] "Predicted behavior" is a model of the behavior that a vehicle should take, generated based on instructions.

[0661] "Location information acquisition means" means a device or system that collects the current location of a vehicle using technology such as GPS.

[0662] "Location data" means information regarding the current location of a vehicle.

[0663] "Behavior monitoring" is the process of comparing predicted behavior with actual behavior to monitor whether a vehicle is operating as instructed.

[0664] "Anomaly detection" is the act of detecting when predicted behavior and actual behavior do not match, or when abnormal behavior occurs.

[0665] "Notification" refers to transmitting an alert or warning to relevant parties when an abnormality is detected.

[0666] "Smart devices" refer to electronic devices such as smartphones, tablets, and wearable devices that can connect to the Internet and run various applications.

[0667] To implement this invention, it is first necessary to build a system that properly receives voice communication between the controller and the operator of the vehicle and converts it into text. Specifically, this can be realized by collaboration between a server, a terminal, and users (controller and operator).

[0668] Server Roles

[0669] The server is the central point that manages the operation of the vehicle through a number of functions. The main hardware and software used are:

[0670] Voice reception and conversion: The server uses a voice recognition engine (e.g., Google Speech Recognition API) to convert voice communication data between the controller and pilot into text data in real time.

[0671] Extracting Instructions: The text data is then analyzed and instructions are extracted using software such as Natural Language Processing (NLP) and spaCy.

[0672] Generate predictive behavior: Use a generative AI model (e.g., GPT-3) to generate predictive behavior based on the extracted instructions.

[0673] Behavior monitoring: Receives location data of transportation vehicles from GPS modules and various sensors, and monitors the acquired data in real time.

[0674] Anomaly detection and notification: Compares monitored data with predicted behavior, and if an anomaly is detected, generates a notification and sends a quick alert to the controller or operator. Anomaly detection utilizes machine learning models and anomaly detection algorithms.

[0675] Device Role

[0676] The device (e.g., smartphone, head-mounted display) receives the information processed by the server and provides it visually and audibly to the user. The device is used as follows:

[0677] Audio reception: Receives audio communication from the controller and pilot and sends it to the server.

[0678] Location data collection: Location data is collected in real time through the GPS module and sent to the server.

[0679] Display notifications: Provides visual and audio notifications to the user of notifications and alerts sent by the server.

[0680] User Roles

[0681] The user (controller and pilot) is the main operator of the system and has the following roles:

[0682] Voice instructions: The controller issues voice instructions, which are transmitted to the server via the terminal.

[0683] Checking notifications: The pilot checks the notifications displayed on the device and takes appropriate action.

[0684] Specific examples

[0685] For example, a logistics center controller might say, "Please pick up 10 items from warehouse 1." This voice communication data is received by the terminal and sent to the server. The server uses a speech recognition engine to convert the speech into text and uses NLP technology to extract the instructions (items and quantities). Next, a generative AI model is used to generate predictive actions and monitor location data in real time. Finally, it checks whether the operator is performing the task according to the instructions, and if there is an abnormality, a notification is generated immediately to notify the operator. This series of processes improves the efficiency and safety of logistics operations.

[0686] Prompt Sentence Examples

[0687] "Give me the following instruction: Pick up 10 items from Warehouse 1. Write a Python program to retrieve this instruction and monitor its execution."

[0688] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0689] Step 1:

[0690] The terminal receives voice communication data between the controller and the pilot. The terminal uses a microphone to capture the voice and temporarily saves it as a voice data file. Then, the voice data is sent to the server.

[0691] (input)

[0692] Voice communication data between the controller and pilot.

[0693] (output)

[0694] The audio data file sent to the server.

[0695] Step 2:

[0696] The server converts the received voice data file into text data using a speech recognition engine (such as the Google Speech Recognition API). The speech recognition engine analyzes the voice data and generates corresponding text.

[0697] (input)

[0698] The audio data file sent from the device.

[0699] (output)

[0700] Text data.

[0701] Step 3:

[0702] The server extracts instructions from the generated text data. NLP techniques (e.g., spaCy) are used to identify important information in the text, such as the name of an item or quantity. The NLP model analyzes the text and outputs the instructions as structured data.

[0703] (input)

[0704] Text data converted by a speech recognition engine.

[0705] (output)

[0706] Instructions (item name, quantity, etc.).

[0707] Step 4:

[0708] The server generates a predicted action based on the extracted instructions. It uses a generative AI model (e.g., GPT-3) to predict what action is needed. The model generates an action plan based on the extracted instructions and outputs it as specific steps.

[0709] (input)

[0710] Instructions (item name, quantity, etc.).

[0711] (output)

[0712] Anticipatory behavior (action planning).

[0713] Step 5:

[0714] The terminal uses a GPS module to collect the current location data of the vehicle and transmits it to the server. The location data is collected in real time.

[0715] (input)

[0716] Real-time location of vehicles.

[0717] (output)

[0718] Location data sent to the server.

[0719] Step 6:

[0720] The server monitors the actual behavior of the vehicle based on the location data received. It compares the predicted behavior with the actual behavior to assess the data consistency. It uses a comparison algorithm to verify that each step is performed correctly.

[0721] (input)

[0722] Location data and predicted behavior sent from your device.

[0723] (output)

[0724] Behavior monitoring results (normal / abnormal).

[0725] Step 7:

[0726] The server detects anomalies based on the behavior monitoring results. If an anomaly is detected, an alert is generated immediately. Pre-defined conditions are used to generate the alert.

[0727] (input)

[0728] Behavioral monitoring results.

[0729] (output)

[0730] An alert message in case of an abnormality.

[0731] Step 8:

[0732] The server sends the generated alert to the device and notifies the user (controller and pilot). The notification is displayed on the device's display and may also sound an audio alert.

[0733] (input)

[0734] Alert message.

[0735] (output)

[0736] The notification message that appears on the device.

[0737] Prompt Sentence Examples

[0738] "Give me the following instruction: Pick up 10 items from Warehouse 1. Write a Python program to retrieve this instruction and monitor its execution."

[0739] 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.

[0740] Overall system flow

[0741] This invention is a system that improves aviation safety by not only enabling voice communication between air traffic controllers and aircraft pilots, but also recognizing the user's emotional state and detecting abnormalities early based on that data. This system includes functions for receiving and converting voice data, extracting instruction content, generating predictive actions, collecting GPS data and monitoring behavior, detecting abnormalities and generating alerts, as well as analyzing the user's emotional state using an emotion engine and providing notifications.

[0742] Receiving and converting voice communication data

[0743] The terminal receives voice communication data between the controller and the pilot in real time.

[0744] The terminal converts the voice data into a digital format and transmits it to the server.

[0745] Extracting instruction content

[0746] The server uses a speech recognition engine to convert the voice communication data into text data.

[0747] The server analyzes the text data, extracts the instruction content, and stores the content in a database.

[0748] Generating predictive behavior

[0749] The server generates a predicted action of the pilot based on the extracted instruction content.

[0750] For example, if you receive the command "Flight 123, climb to 10,000 feet," you would predict that Flight 123 will climb to an altitude of 10,000 feet.

[0751] GPS data collection and behavior monitoring

[0752] The terminal (on the aircraft) collects the aircraft's current GPS data (altitude, position, speed, etc.) in real time and transmits it to the server.

[0753] The server analyzes the GPS data and monitors the aircraft's actual behavior, comparing it with predicted behavior.

[0754] Anomaly detection and alert generation

[0755] Based on the comparison results, the server detects an abnormality if the pilot's actions differ from instructions.

[0756] When an abnormality is detected, the server immediately generates an alert message and sends it to the terminal.

[0757] The terminal will then notify the controller and pilot of the alert.

[0758] Emotion Engine Operation

[0759] The terminal collects voice and behavioral data from controllers and pilots and transmits it to a server.

[0760] The server uses an emotion engine to analyze this data and recognize the user's emotional state.

[0761] If the emotional state obtained from the emotion engine is determined to be abnormal, the server generates an alert message with that information.

[0762] The server also generates a message based on the abnormal emotional state, suggesting appropriate steps to take.

[0763] The terminal notifies controllers and pilots of these alert messages and response procedures.

[0764] Specific operation examples

[0765] Example 1: Up command case

[0766] 1. The user (controller) sends the instruction "Flight 123, climb to 10,000 feet."

[0767] 2. The terminal receives this voice instruction and sends it to the server.

[0768] 3. The server uses a speech recognition engine to convert the voice into text and extract the instructions.

[0769] 4. The server generates a predicted climb to 10,000 feet for Flight 123.

[0770] 5. The terminal (aircraft side) sends the current altitude GPS data to the server.

[0771] 6. The server compares the current altitude with the predicted behavior to ensure proper ascent.

[0772] 7. The server generates an alert and sends it to the device if it does not act as instructed, for example if it stops at an altitude of 8,000 feet.

[0773] 8. The terminal alerts the controller and pilot that "Flight 123 is not climbing to 10,000 feet."

[0774] 9. The user (controller) confirms this notification and issues instructions again.

[0775] Example 2: Emotional state anomaly detection case

[0776] 1. The terminal collects the pilot's voice and behavioral data in real time and sends it to the server.

[0777] 2. The server uses an emotion engine to analyze the pilot's emotional state.

[0778] 3. If the server detects abnormal stress or panic, it generates an abnormal emotion alert.

[0779] 4. The server sends this abnormal emotion alert to the terminal and notifies the controller and pilot.

[0780] 5. The device will also simultaneously send you a message suggesting ways to improve or cope with your emotional state.

[0781] The system of this invention makes it possible to detect and quickly deal with not only misunderstandings and operational errors between air traffic controllers and pilots, but also abnormalities due to emotional states in real time, which is expected to significantly improve aviation safety.

[0782] The processing flow will be explained below.

[0783] Step 1:

[0784] The terminal receives voice communication data between the controller and the pilot in real time.

[0785] Step 2:

[0786] The terminal converts the received voice communication data into a digital format and transmits it to the server.

[0787] Step 3:

[0788] The server uses a speech recognition engine to convert the voice communication data into text data.

[0789] Step 4:

[0790] The server analyzes the converted text data and extracts the instructions (e.g., flight number, target altitude, direction of travel, etc.).

[0791] Step 5:

[0792] The server generates a predicted action that the pilot should take based on the extracted instructions.

[0793] Step 6:

[0794] The terminal (aircraft-side device) collects the aircraft's current GPS data (altitude, position, speed, etc.) and transmits it to the server.

[0795] Step 7:

[0796] The server analyzes the received GPS data and monitors the aircraft's actual behavior in real time.

[0797] Step 8:

[0798] The server compares the monitored aircraft behavior with the predicted behavior generated in the previous step to check whether the pilot is acting as instructed.

[0799] Step 9:

[0800] The server detects an anomaly if the pilot's actions are not as instructed.

[0801] Step 10:

[0802] The server immediately generates an alert message when an abnormality is detected.

[0803] Step 11:

[0804] The server sends this alert message to the terminal.

[0805] Step 12:

[0806] The terminal (control tower equipment) receives the alert message and displays the notification on the controller's display terminal.

[0807] Step 13:

[0808] The user (controller) checks the notification and takes necessary measures.

[0809] Step 14:

[0810] The terminal collects voice and behavioral data from controllers and pilots and transmits it to a server.

[0811] Step 15:

[0812] The server uses an emotion engine to analyze this data and recognize the user's emotional state.

[0813] Step 16:

[0814] If the emotional state obtained from the emotion engine is determined to be abnormal, the server generates an alert message with that information.

[0815] Step 17:

[0816] The server generates a message based on the abnormal emotional state, suggesting appropriate steps to take.

[0817] Step 18:

[0818] The server sends these alert messages and troubleshooting procedures to the terminal and notifies the user.

[0819] Example 2

[0820] 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."

[0821] During aircraft operations, safety risks exist due to misunderstandings or operational errors in voice communications between air traffic controllers and pilots, as well as abnormal emotional states of pilots or controllers. A system that can detect such risks early and deal with them promptly is needed.

[0822] 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.

[0823] In this invention, the server includes a means for converting voice communication data between the controller and the pilot into text data, a means for extracting instructions from the converted text data and storing the instructions in a database, a means for analyzing collected GPS data and monitoring the aircraft's actual behavior while comparing it with predicted behavior, and a means for analyzing the voice and behavior data of the controller and the pilot using an emotion engine to recognize their emotional states. This makes it possible to detect not only misrecognition of instructions and operational errors, but also abnormal emotional states in real time and respond promptly.

[0824] "Voice communication data" refers to the voice information exchanged between air traffic controllers and pilots.

[0825] "Digital format" refers to a data format in which analog audio data is converted into a digital signal.

[0826] "Server" refers to a computer system that performs speech recognition, data analysis, and data storage.

[0827] "Text data" refers to data in the form of a character string converted from voice data.

[0828] "Instruction content" refers to the specific actions and commands extracted from text data.

[0829] "Database" refers to a structured data storage system for efficiently storing and managing data.

[0830] "Predicted actions" refers to predictions of the actions the pilot should take, generated based on the extracted instructions.

[0831] "GPS data" refers to data indicating the current location of an aircraft.

[0832] "Actual actions" refers to actions actually taken by the aircraft.

[0833] "Abnormal" refers to a state in which predicted behavior does not match actual behavior or emotional state is abnormal.

[0834] An "alert" refers to a warning message generated when the system detects an abnormality.

[0835] An "emotion engine" refers to software or algorithms that analyze voice and behavioral data to recognize emotional states.

[0836] "Terminal" refers to a device that receives, converts, transmits voice data, and notifies alerts.

[0837] "Emotional Data" refers to data regarding an emotional state analyzed using an emotion engine.

[0838] The present invention is a system that improves aviation safety by not only enabling voice communication between air traffic controllers and aircraft pilots, but also recognizing the emotional state of users and detecting abnormalities early based on that data. This system is realized using the following hardware and software.

[0839] Hardware:

[0840] Terminal (aircraft and tower): A device that receives audio, converts it into digital form, and transmits it.

[0841] Server: A computer system that processes voice data, converts text, analyzes data, runs an emotion engine, and manages the database.

[0842] GPS unit: A device used to obtain the aircraft's current position in real time.

[0843] Microphone: An acoustic device used to collect the voices of controllers and pilots.

[0844] software:

[0845] Speech recognition engine: Software that converts voice data into text data, such as the Google Speech-to-Text API.

[0846] Database management system: A database such as MySQL for storing instructions and emotional data.

[0847] Natural language processing engine: Software used to analyze text data, such as NLTK.

[0848] Emotion engines: Algorithms that recognize emotional states from speech and behavioral data, such as IBM Watson Tone Analyzer.

[0849] Communication protocol: TCP / IP, MQTT, or other communication protocol used to send and receive voice and GPS data.

[0850] Examples of implementation of the invention:

[0851] Example 1: Up command case

[0852] 1. The user (controller) sends a voice command: "Flight 123, climb to 10,000 feet."

[0853] 2. The device receives the voice instruction, converts it into digital form and sends it to the server.

[0854] 3. The server uses the Google Speech-to-Text API to convert the speech to text and recognizes it as "Flight 123, climb to 10,000 feet."

[0855] 4. The server uses a natural language processing engine to extract instructions from the text data and generate a predicted action for Flight 123 to climb to 10,000 feet.

[0856] 5. The terminal (aircraft side) sends real-time GPS data such as current altitude and location to the server.

[0857] 6. The server compares the current altitude data with the predicted behavior and monitors whether the ascent is proceeding properly.

[0858] 7. If the server does not act as instructed, it generates an alert saying "Flight 123 is not climbing to 10,000 feet" and sends it to the device.

[0859] 8. The terminal notifies the controller and pilot of this alert, prompting the controller to review the situation.

[0860] Example 2: Emotional state anomaly detection case

[0861] 1. The terminal collects the pilot's voice and behavioral data (e.g., operational errors and voice tremors) in real time and transmits them to the server.

[0862] 2. The server uses an emotion engine to analyze voice and behavioral data and recognize the pilot's emotional state (e.g., high stress).

[0863] 3. If the server detects an abnormal stress state, it generates an "abnormal emotion alert."

[0864] 4. The server sends this abnormal emotion alert to the terminal and notifies the controller and pilot.

[0865] 5. The device will display a message suggesting ways to improve the situation: "The pilot is under high stress. Please take a deep breath and calm down."

[0866] Example prompt sentence:

[0867] Below are some example prompts to input to the generative AI model:

[0868] "What would the system do if the controller instructed Flight 123 to climb to 10,000 feet, but it stopped below 10,000 feet?"

[0869] "Please explain specifically how the system will respond if the pilot exhibits an abnormal emotional state."

[0870] The system of this invention not only detects misunderstandings and operational errors between air traffic controllers and pilots, but also detects abnormal emotional states in real time and makes it possible to deal with them quickly, which is expected to significantly improve aviation safety.

[0871] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0872] Step 1: Receiving and converting voice communication data

[0873] The terminal receives voice communication data between the controller and the pilot in real time.

[0874] Input: Analog voice data between controller and pilot

[0875] Specific Action: Capture audio data using a microphone and receive it through a communication device.

[0876] Output: Audio data converted to digital format

[0877] The terminal converts the received voice data into a digital format and transmits it to the server.

[0878] Input: Analog audio data

[0879] Specific operation: Audio data is digitized by setting the sampling rate and bit depth, and sent to the server using the TCP / IP protocol.

[0880] Output: Digital audio data sent to the server

[0881] Step 2: Extracting instructions

[0882] The server converts the received voice data into text data using a voice recognition engine (e.g., Google Speech-to-Text API).

[0883] Input: Digital audio data

[0884] Specific operation: Passes digital voice data to a voice recognition engine and calls an API to obtain string data.

[0885] Output: Instructions converted into text data

[0886] The server analyzes the text data using a natural language processing engine, extracts the instructions, and stores them in a database.

[0887] Input: Text data

[0888] Specific operation: Parses text data using the NLTK library, extracts commands and keywords, and stores them in a database.

[0889] Output: Extracted instruction data

[0890] Step 3: Generate predicted behavior

[0891] The server generates a predicted behavior of the pilot based on the extracted instruction content.

[0892] Input: Extracted instruction data

[0893] Specific behavior: The instructions are input into the internal algorithm to generate predictive behavior. For example, if the instruction is "Flight 123, climb to 10,000 feet," it will predict that Flight 123 will climb to 10,000 feet.

[0894] Output: Generated predicted behavior data

[0895] Step 4: Collecting GPS data and monitoring behavior

[0896] The terminal (on the aircraft) collects the aircraft's current GPS data in real time and transmits it to the server.

[0897] Input: Real-time GPS data (altitude, location, speed, etc.)

[0898] Specific operation: Data is acquired from the GPS unit installed on the aircraft and sent to the server using the MQTT protocol.

[0899] Output: GPS data sent to the server

[0900] The server analyzes the received GPS data and compares it with predicted behavior to monitor behavior.

[0901] Input: Real-time GPS data, predicted behavior data

[0902] Specific operation: Using a custom algorithm implemented in Python, the received GPS data is compared with the predicted behavior data to determine whether it is normal or abnormal.

[0903] Output: Comparison results and monitoring result data

[0904] Step 5: Anomaly detection and alert generation

[0905] The server compares predicted behavior with actual behavior and detects anomalies.

[0906] Input: Comparison result data

[0907] Specific operation: If the predicted altitude does not match the actual altitude, an abnormality flag is raised.

[0908] Output: Anomaly detection flag and anomaly content data

[0909] If the server detects an abnormality, it immediately generates an alert message and sends it to the terminal.

[0910] Input: Anomaly detection flag and anomaly content data

[0911] Specific behavior: Generate an alert message containing details of the anomaly, encode it in JSON format, and send it to the terminal.

[0912] Output: The alert message sent to the terminal.

[0913] The terminal will then notify the controller and pilot of the alert.

[0914] Input: Alert message

[0915] What it does: Use the display and audio output device to provide a visual and audible alert that "Flight 123 is not climbing to 10,000 feet."

[0916] Output: Alerts sent to controllers and pilots

[0917] Step 6: Emotion Engine in Action

[0918] The terminal collects voice and behavioral data from controllers and pilots and transmits it to a server.

[0919] Input: Real-time audio and behavioral data

[0920] Specific operation: Collects voice and behavioral data through microphones and various sensors and sends it to a server.

[0921] Output: Audio and behavioral data sent to the server

[0922] The server uses an emotion engine to analyze this data and recognize the emotional state.

[0923] Input: Audio and behavioral data

[0924] Specific operation: Using emotion engines such as IBM Watson Tone Analyzer, the system analyzes voice and behavioral data to recognize emotional states.

[0925] Output: Recognized emotional state data

[0926] If the emotional state is determined to be abnormal, the server generates an alert message and notifies the user.

[0927] Input: Emotional state data

[0928] Specific operation: If an abnormal emotional state is detected, an alert message containing details is generated and sent to the device.

[0929] Output: Emotional abnormality alert message sent to the terminal

[0930] The server also generates a message based on the abnormal emotional state, suggesting appropriate steps to take.

[0931] Input: Emotional state data

[0932] Specific Action: Based on the analysis results from the emotion engine, a message is generated suggesting appropriate steps to take (e.g., "Take a deep breath and stay calm").

[0933] Output: Proposal message

[0934] The terminal notifies controllers and pilots of these alert messages and response procedures.

[0935] Input: Emotional abnormality alert message and suggested message

[0936] Specific operation: Display and play notification information using a display and audio playback device.

[0937] Output: Suggestions and emotional anomaly alerts notified to controllers and pilots

[0938] (Application example 2)

[0939] 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."

[0940] Improving the safety of autonomous vehicles is an important challenge for current technology. In particular, it is necessary to properly recognize the emotional state of driver assistants and passengers and respond quickly when an abnormality occurs. Conventional systems have had difficulty understanding passengers' emotional states in real time, detecting abnormalities, and taking countermeasures. Therefore, a new system that can analyze emotional states and support safe driving is needed.

[0941] The identification process by the identification 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 voice communication data between an air traffic controller and an aircraft pilot; means for converting the received voice communication data into text data; means for extracting instructions from the converted text data; means for generating a predicted behavior based on the extracted instructions; means for collecting current position data of the aircraft from a GPS; means for monitoring the actual behavior of the aircraft based on the collected GPS data; means for comparing the monitored behavior of the aircraft with the predicted behavior and detecting an abnormality; means for generating and notifying an alert when an abnormality is detected; means for collecting voice data and behavior data and analyzing the emotional state; and means for generating an alert and suggesting a response procedure when an abnormal emotional state is detected. This makes it possible to grasp the emotional states of the driver's assistant and passengers in real time, quickly detect abnormalities, and take appropriate measures.

[0942] A "controller" is a person whose job is to monitor and direct the operation of aircraft and vehicles.

[0943] "Aircraft" is a general term for any mechanical device that can fly.

[0944] A "pilot" is a person qualified to operate an aircraft.

[0945] "Voice communication data" means information in digital form that contains voice.

[0946] "Text data" means written information in digital form.

[0947] "Instruction content" is information for instructing a specific action.

[0948] "Predicted behavior" refers to behavior that the system generates based on the instructions it receives.

[0949] "Location Data" means geographic location information obtained using technologies such as GPS.

[0950] "GPS" is an abbreviation for Global Positioning System, a system for determining locations on Earth with high accuracy.

[0951] "Actual behavior" refers to the actions that a system or machine actually takes.

[0952] An "abnormality" is a state in which predicted behavior differs from actual behavior.

[0953] An "alert" is a warning issued when an abnormality is detected.

[0954] A "notification" is a means of conveying specific information.

[0955] "Audio data" is a general term for digital information that includes audio.

[0956] "Behavioral data" is digital information about the actions taken by a system or machine.

[0957] "Emotional state" refers to a person's emotional state.

[0958] An "abnormal emotional state" is an emotional state that is different from the normal state.

[0959] "Response procedures" refer to the actions and procedures to be taken when an abnormality occurs.

[0960] Overall system configuration

[0961] This invention is a system that analyzes voice and behavioral data in real time to detect abnormalities in order to improve the safety of autonomous vehicles. In particular, it analyzes the emotional state of the driver's assistant and passengers and provides appropriate response procedures in the event of an abnormality. It also incorporates location data collection using GPS.

[0962] Program processing explanation

[0963] The system's main hardware includes a smartphone, smart glasses, and a GPS module, while the software uses Python, the speech_recognition library, and the requests library.

[0964] Receiving and converting voice communication data

[0965] The server receives the driver's assistant's voice communication data in real time and converts it into text data. Specifically, it uses the smartphone's microphone function and a speech recognition engine (for example, the speech_recognition library) to convert the voice into text.

[0966] Extracting instruction content and generating predicted actions

[0967] The server extracts the instructions from the converted text data and generates predicted actions based on the instructions. This information is stored in a database and used for analytical processing.

[0968] GPS data collection and behavior monitoring

[0969] The terminal (on the vehicle side) collects the vehicle's current GPS data (position, speed, etc.) in real time and sends it to the server, which analyzes this GPS data and compares the actual behavior with the predicted behavior.

[0970] Anomaly detection and alert generation

[0971] The server compares predicted and actual behavior and immediately generates an alert if an abnormality is detected, which is then sent to the driver assistant via a smartphone or smart glasses.

[0972] Emotion Engine Operation

[0973] The server collects voice and behavioral data and analyzes them using an emotion engine. If the emotional state is determined to be abnormal, an alert is generated and a response procedure is proposed. This process uses a generative AI model, and the results are sent to the driver's assistant's smartphone or other device.

[0974] Specific example explanation

[0975] For example, if the driver assistant is feeling stressed, the system operates as follows:

[0976] 1. The driver assistant issues a voice command such as, "I feel the vehicle speed is a little too fast."

[0977] 2. This audio is collected through the smartphone's microphone and sent to a server.

[0978] 3. The server converts the speech into text and analyzes it using an emotion engine. The analysis results detect stress and anxiety.

[0979] 4. The server generates an alert based on this information and sends it to the smartphone.

[0980] 5. Your smartphone will display an alert such as "Driver assistant is experiencing high stress, we recommend reducing speed."

[0981] Prompt Sentence Examples

[0982] For example, a specific example of a prompt sentence to be input into a generative AI model is, "Convert this voice data into text, analyze the user's emotional state, and notify me if any abnormalities are found."

[0983] Such a system would enable autonomous vehicles to monitor the emotional state of their occupants while driving, quickly detect and respond to any abnormalities, and ultimately provide a safer driving environment.

[0984] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0985] Step 1:

[0986] The user inputs voice data using the microphone on the smartphone, and the input voice data is collected from the driver's assistant.

[0987] Step 2:

[0988] The device transmits the received voice data in real time to a server, where it is converted into a digital format and transmitted over the internet.

[0989] Step 3:

[0990] The server converts the received voice data into text data using a voice recognition engine (for example, the speech_recognition library). The input is digital voice data, and the output is text data.

[0991] Step 4:

[0992] The server extracts the instructions from the converted text data. Natural language processing technology is used to analyze the text data for specific instructions and emotional states. The input is the text data, and the output is the analysis results of the instructions and emotional states.

[0993] Step 5:

[0994] The server generates a predicted behavior based on the extracted instruction content. For example, if the instruction is "slow down," it predicts the behavior of slowing down to an appropriate speed. The input is instruction content data, and the output is predicted behavior data.

[0995] Step 6:

[0996] The terminal (vehicle side) collects current location data using a GPS module and transmits it to the server in real time. The input is GPS data, and the output is the transmitted current location data.

[0997] Step 7:

[0998] The server monitors the vehicle's actual behavior based on the collected GPS data. It compares the predicted behavior with the actual behavior and checks for any abnormalities. The inputs are the predicted behavior data and GPS data, and the output is the result of anomaly detection.

[0999] Step 8:

[1000] The server generates an alert when an anomaly is detected. The alert is generated as a specific text message. The input is the anomaly detection data, and the output is the alert message.

[1001] Step 9:

[1002] The terminal notifies the driver assistant of the generated alert message. The alert message is displayed visually or audibly using a smartphone or smart glasses. The input is the alert message, and the output is a visual or audio notification.

[1003] Step 10:

[1004] The server collects voice data and behavioral data and analyzes the emotional state using an emotion engine. The input is the voice data and behavioral data, and the output is the analysis result of the emotional state.

[1005] Step 11:

[1006] If the server detects an abnormal emotional state, it generates an alert and suggests a course of action. It uses a generative AI model to suggest an appropriate course of action. The input is emotional state data, and the output is an alert message with a course of action.

[1007] Step 12:

[1008] The terminal notifies the driver assistant of the generated alert message and the response procedures via a smartphone or smart glasses. The input is the alert message with the response procedures, and the output is a visual or audio notification.

[1009] 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.

[1010] 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.

[1011] 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.

[1012] [Third embodiment]

[1013] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1014] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1015] 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).

[1016] 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.

[1017] 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.

[1018] 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).

[1019] 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.

[1020] 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.

[1021] 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.

[1022] 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.

[1023] 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.

[1024] 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."

[1025] To implement this invention, it is necessary to build a system that collects voice communication data between air traffic controllers and aircraft pilots in real time and converts it into text data. This system supports the safe operation of aircraft through a series of processes: extracting instructions, generating predicted behavior, collecting GPS data, monitoring behavior, detecting anomalies, and generating and notifying alerts.

[1026] Overall system flow

[1027] Receiving and converting voice communication data

[1028] The terminal receives voice communications between the controller and the pilot.

[1029] The terminal transmits this voice data to the server.

[1030] The server uses a speech recognition engine to convert the voice communication data into text data.

[1031] Extracting instruction content

[1032] The server extracts the instruction content (e.g., flight number, destination, altitude, etc.) from the converted text data.

[1033] Generating predictive behavior

[1034] The server generates a predicted flight behavior based on the extracted instructions. For example, if the instruction is "Flight 123, climb to 10,000 feet," it predicts that Flight 123 will climb from its current altitude to 10,000 feet.

[1035] GPS data collection and behavior monitoring

[1036] The terminal collects the aircraft's current GPS data and transmits it to the server.

[1037] The server analyzes this GPS data and monitors the aircraft's actual behavior (position, altitude, speed, etc.) in real time.

[1038] Anomaly detection and alert generation

[1039] The server compares the monitored aircraft behavior with the predicted behavior and checks for any anomalies.

[1040] The server immediately generates an alert message if an abnormality is detected.

[1041] The server sends the generated alert to the terminal and notifies the controller and pilot.

[1042] Specific operation examples

[1043] Example 1: Up command case

[1044] 1. The user (controller) sends the instruction "Flight 123, climb to 10,000 feet."

[1045] 2. The terminal receives this voice instruction and sends it to the server.

[1046] 3. The server uses a speech recognition engine to convert the voice into text and extract the instructions.

[1047] 4. The server generates a predicted climb to 10,000 feet for Flight 123.

[1048] 5. The terminal (aircraft side) sends the current altitude GPS data to the server.

[1049] 6. The server compares the current altitude with the predicted behavior to ensure proper ascent.

[1050] 7. The server generates an alert and sends it to the device if it does not act as instructed, for example if it stops at an altitude of 8,000 feet.

[1051] 8. The terminal alerts the controller and pilot that "Flight 123 is not climbing to 10,000 feet."

[1052] 9. The user (controller) confirms this notification and issues instructions again.

[1053] By using this system, it is possible to monitor aircraft movements in real time, detect abnormalities early, increase safety, and reduce the workload of air traffic controllers.

[1054] The processing flow will be explained below.

[1055] Step 1:

[1056] The terminal receives voice communication data between the controller and the pilot in real time.

[1057] Step 2:

[1058] The terminal converts the received voice communication data into a digital format and transmits it to the server.

[1059] Step 3:

[1060] The server uses a speech recognition engine to convert the voice communication data into text data.

[1061] Step 4:

[1062] The server analyzes the converted text data and extracts the instructions (e.g., flight number, target altitude, direction of travel, etc.).

[1063] Step 5:

[1064] The server generates a predicted action that the pilot should take based on the extracted instructions.

[1065] Step 6:

[1066] The terminal (aircraft-side device) collects the aircraft's current GPS data (altitude, position, speed, etc.) and transmits it to the server.

[1067] Step 7:

[1068] The server analyzes the received GPS data and monitors the aircraft's actual behavior in real time.

[1069] Step 8:

[1070] The server compares the monitored aircraft behavior with the predicted behavior generated in the previous step to check whether the pilot is acting as instructed.

[1071] Step 9:

[1072] The server detects an anomaly if the pilot's actions are not as instructed.

[1073] Step 10:

[1074] The server immediately generates an alert message when an abnormality is detected.

[1075] Step 11:

[1076] The server sends this alert message to the terminal.

[1077] Step 12:

[1078] The terminal (control tower equipment) receives the alert message and displays the notification on the controller's display terminal.

[1079] Step 13:

[1080] The user (controller) checks the notification and takes necessary measures.

[1081] These steps will enable misunderstandings and operational errors between controllers and pilots to be detected in real time, preventing accidents before they occur.

[1082] Example 1

[1083] 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."

[1084] Aircraft operations require rapid and accurate analysis of voice communication data between air traffic controllers and pilots. Conventional methods often involve manual conversion and analysis of voice data, which can lead to misunderstandings and delays. This can potentially reduce the safety of aircraft operations. To solve this problem, a system is needed that can automatically analyze voice communication data in real time and issue an immediate warning in the event of an abnormality.

[1085] 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.

[1086] In this invention, the server includes means for receiving voice communication data between an air traffic controller and an aircraft pilot, means for converting the received voice communication data into text data, means for extracting instructions from the converted text data, means for generating predicted behavior based on the extracted instructions, means for collecting current position data of the aircraft from a satellite positioning system, means for monitoring the actual behavior of the aircraft based on the collected position data, means for comparing the monitored behavior of the aircraft with predicted behavior and detecting abnormalities, means for generating and notifying warning information when an abnormality is detected, means for automatically analyzing instructions related to the aircraft, and means for displaying the generated warning information on a terminal. This makes it possible to automatically analyze voice communication data in real time during aircraft operation and ensure safety.

[1087] "Voice communication data" refers to the content of voice communications between air traffic controllers and aircraft pilots.

[1088] "Text data" refers to a data format in which voice communication data is converted into a string of characters.

[1089] "Instruction content" refers to specific command items such as flight number, destination, and altitude extracted from the text data.

[1090] "Predicted action" refers to the action that the aircraft is expected to take based on the instructions.

[1091] "Position Data" refers to current aircraft position information collected from satellite positioning systems.

[1092] "Satellite positioning system" refers to a general term for systems that receive signals from satellites and measure the precise location of an aircraft.

[1093] "Behavioral surveillance" refers to the process of monitoring the actual behavior of aircraft based on collected location data.

[1094] "Anomaly detection" refers to comparing monitored aircraft behavior with predicted behavior to determine whether there are any anomalies.

[1095] "Warning information" refers to a notification message that is generated when an abnormality is detected.

[1096] "Terminal" refers to a device that receives and transmits voice communication data, displays warning information, etc.

[1097] MODE FOR CARRYING OUT THE INVENTION

[1098] To implement this invention, it is necessary to build a system that collects voice communication data between air traffic controllers and aircraft pilots in real time and converts it into text data. This system supports the safe operation of aircraft through a series of processes: extraction of instruction content, generation of predicted behavior, collection of location data, behavior monitoring, anomaly detection, and generation and notification of warning information.

[1099] Receiving and converting voice communication data

[1100] The terminal receives voice communications between the air traffic controller and the aircraft pilot. The terminal collects voice data using a microphone and temporarily stores the collected voice data in local storage. The terminal then transmits the stored voice data to a server. The server converts the voice data into text data using a speech recognition engine (e.g., Google Cloud Speech-to-Text).

[1101] For example, if a controller says, "Flight 123, climb to 10,000 feet," the device will record this audio with a microphone and send it to a server, which will then convert it into text using Google Cloud Speech-to-Text.

[1102] Extracting instruction content

[1103] The server receives the converted text data and uses an NLP model (e.g., SpaCy) to extract specific instructions, such as flight number, destination, and altitude.

[1104] In a specific example, the server extracts "Flight 123" and "climb to 10,000 feet" from the text data "Flight 123, climb to 10,000 feet."

[1105] Generating predictive behavior

[1106] The server generates a predicted flight behavior based on the extracted instructions. It uses a Python numerical calculation library (e.g., NumPy) to generate numerical data corresponding to the instructed behavior.

[1107] As a concrete example, the server generates a predicted action such as "Flight 123 will climb to 10,000 feet."

[1108] Location data collection and behavioral monitoring

[1109] The terminal collects the aircraft's current location data. This location data is obtained using a satellite positioning system (e.g., GPS). The collected location data includes latitude, longitude, altitude, etc. The terminal then transmits this location data to a server.

[1110] The server receives the transmitted position data and monitors the current aircraft behavior, a process that involves data analysis using the Pandas library.

[1111] In a specific example, the terminal uses the aircraft's GPS module to obtain information such as the current latitude, longitude, and altitude, and sends it to the server. The server confirms and records that the aircraft's current altitude is "8,000 feet."

[1112] Anomaly detection and warning information generation

[1113] The server compares predicted behavior with current behavior to check for any anomalies. If an anomaly is detected, it immediately generates a warning. The use of generative AI models improves the accuracy of anomaly detection.

[1114] As a concrete example, the server may detect that the aircraft is stuck at 8,000 feet when it should be climbing to 10,000 feet.

[1115] Warning information notification

[1116] The server sends the generated warning information to the terminal, and notifies the controller and the pilot, and the notification is displayed on the screen of the terminal, for example.

[1117] In this example, the server generates a warning message saying "Flight 123 is not climbing to 10,000 feet" and sends it to the terminal, which then displays the warning message on the controller's screen or the pilot's device.

[1118] Examples of prompt statements

[1119] The following are specific examples of prompt sentences to be input into the generative AI model.

[1120] "Please extract the instructions from the following text data: 'Flight 123, climb to 10,000 feet'"

[1121] In response to this prompt, the generative AI model will respond by extracting phrases such as "Flight 123" and "climb to 10,000 feet."

[1122] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1123] Step 1:

[1124] The terminal receives voice communications between the air traffic controller and the aircraft pilot. As input, it uses voice communication data collected through a microphone. Specifically, the terminal collects this voice data using a microphone and temporarily stores it in local storage. As output, it obtains the collected voice data.

[1125] Step 2:

[1126] The device sends the stored voice data to the server. The voice data stored in the local storage is used as input. Specifically, the device sends the collected voice files to the server via the Internet. The voice data received by the server is obtained as output.

[1127] Step 3:

[1128] The server uses a speech recognition engine to convert the received voice data into text data. The server uses the voice data it received as input. Specifically, the server calls a speech recognition engine (Google Cloud Speech-to-Text) and converts the voice data into text data such as "Flight 123, climb to 10,000 feet." The text data is obtained as output.

[1129] Step 4:

[1130] The server receives the converted text data and uses an NLP model to extract specific instructions. The text data is used as input. Specifically, the server uses an NLP model (e.g., SpaCy) to extract the instructions, such as "flight number" and "altitude instructions." The extracted instructions are obtained as output.

[1131] Step 5:

[1132] The server generates a predicted flight behavior based on the extracted instructions. The extracted instructions are used as input. Specifically, the server uses a Python mathematical library (e.g., NumPy) to generate a predicted behavior such as "the flight will climb to 10,000 feet." The generated predicted behavior is obtained as output.

[1133] Step 6:

[1134] The terminal collects the aircraft's current position data. As input, it uses the position data obtained through the GPS module. Specifically, the terminal obtains position data such as latitude, longitude, and altitude and sends it to the server. As output, it obtains the collected position data.

[1135] Step 7:

[1136] The server receives the transmitted location data and monitors the current aircraft behavior. It uses the location data transmitted from the terminal as input. Specifically, the server analyzes the collected data using the Pandas library to analyze the aircraft's current position, altitude, speed, etc. As output, it obtains the current aircraft behavior data.

[1137] Step 8:

[1138] The server compares the predicted behavior with the current behavior and checks for anomalies. As input, it uses the generated predicted behavior and the monitored behavior data. Specifically, the server performs a comparison operation to match the predicted behavior with the actual behavior and check for any discrepancies. As output, if there is an anomaly, the anomalous data is identified.

[1139] Step 9:

[1140] The server generates warning information immediately if an anomaly is detected. The server uses the anomaly data as input. Specifically, the server uses a generative AI model to generate an appropriate warning message (e.g., "Flight 123 is not climbing to 10,000 feet"). The warning information is obtained as output.

[1141] Step 10:

[1142] The server sends the generated warning information to the terminal and notifies the controller and pilot. The server uses the generated warning information as input. Specifically, the server sends the warning information to the terminal via the Internet, and the terminal displays this information on the controller's screen or the pilot's device. As output, a notification is sent.

[1143] (Application example 1)

[1144] 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."

[1145] In logistics centers, accurately managing instructions to workers and their execution status is extremely important for efficient business operations and ensuring safety. However, relying on verbal instructions is prone to human error and misunderstanding of instructions, making it difficult to grasp the situation in real time. This leads to problems such as reduced work efficiency and increased likelihood of mistakes. In addition, there are limited means to appropriately monitor the progress of work using location data, making it difficult to respond quickly when an abnormality occurs.

[1146] 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.

[1147] In this invention, the server includes means for receiving voice communication data between the controller and the operator of the vehicle, means for converting the received voice communication data into text data, means for extracting instructions from the converted text data, means for generating predicted behavior based on the extracted instructions, means for collecting current location data of the vehicle from a location information acquisition means, means for monitoring the actual behavior of the vehicle based on the collected location data, means for comparing the monitored behavior of the vehicle with the predicted behavior and detecting abnormalities, means for generating a notification when an abnormality is detected, and means for displaying the instructions and location data on the smart device. This enables real-time text conversion and analysis of voice instructions, behavior monitoring using location data, and rapid notification when an abnormality occurs.

[1148] A "controller" is a manager who gives instructions to workers and transportation means in a logistics center or transportation system.

[1149] "Vehicle" means any equipment or vehicle used to transport or move goods.

[1150] "Operator" means the worker or person in charge of operating or controlling a conveyance.

[1151] "Voice communication data" refers to data on voice instructions and reports exchanged between the controller and the pilot.

[1152] "Text data" refers to voice communication data converted into character format.

[1153] "Instruction content" refers to specific work instructions extracted from the extracted text data.

[1154] "Predicted behavior" is a model of the behavior that a vehicle should take, generated based on instructions.

[1155] "Location information acquisition means" means a device or system that collects the current location of a vehicle using technology such as GPS.

[1156] "Location data" means information regarding the current location of a vehicle.

[1157] "Behavior monitoring" is the process of comparing predicted behavior with actual behavior to monitor whether a vehicle is operating as instructed.

[1158] "Anomaly detection" is the act of detecting when predicted behavior and actual behavior do not match, or when abnormal behavior occurs.

[1159] "Notification" refers to transmitting an alert or warning to relevant parties when an abnormality is detected.

[1160] "Smart devices" refer to electronic devices such as smartphones, tablets, and wearable devices that can connect to the Internet and run various applications.

[1161] To implement this invention, it is first necessary to build a system that properly receives voice communication between the controller and the operator of the vehicle and converts it into text. Specifically, this can be realized by collaboration between a server, a terminal, and users (controller and operator).

[1162] Server Roles

[1163] The server is the central point that manages the operation of the vehicle through a number of functions. The main hardware and software used are:

[1164] Voice reception and conversion: The server uses a voice recognition engine (e.g., Google Speech Recognition API) to convert voice communication data between the controller and pilot into text data in real time.

[1165] Extracting Instructions: The text data is then analyzed and instructions are extracted using software such as Natural Language Processing (NLP) and spaCy.

[1166] Generate predictive behavior: Use a generative AI model (e.g., GPT-3) to generate predictive behavior based on the extracted instructions.

[1167] Behavior monitoring: Receives location data of transportation vehicles from GPS modules and various sensors, and monitors the acquired data in real time.

[1168] Anomaly detection and notification: Compares monitored data with predicted behavior, and if an anomaly is detected, generates a notification and sends a quick alert to the controller or operator. Anomaly detection utilizes machine learning models and anomaly detection algorithms.

[1169] Device Role

[1170] The device (e.g., smartphone, head-mounted display) receives the information processed by the server and provides it visually and audibly to the user. The device is used as follows:

[1171] Audio reception: Receives audio communication from the controller and pilot and sends it to the server.

[1172] Location data collection: Location data is collected in real time through the GPS module and sent to the server.

[1173] Display notifications: Provides visual and audio notifications to the user of notifications and alerts sent by the server.

[1174] User Roles

[1175] The user (controller and pilot) is the main operator of the system and has the following roles:

[1176] Voice instructions: The controller issues voice instructions, which are transmitted to the server via the terminal.

[1177] Checking notifications: The pilot checks the notifications displayed on the device and takes appropriate action.

[1178] Specific examples

[1179] For example, a logistics center controller might say, "Please pick up 10 items from warehouse 1." This voice communication data is received by the terminal and sent to the server. The server uses a speech recognition engine to convert the speech into text and uses NLP technology to extract the instructions (items and quantities). Next, a generative AI model is used to generate predictive actions and monitor location data in real time. Finally, it checks whether the operator is performing the task according to the instructions, and if there is an abnormality, a notification is generated immediately to notify the operator. This series of processes improves the efficiency and safety of logistics operations.

[1180] Prompt Sentence Examples

[1181] "Give me the following instruction: Pick up 10 items from Warehouse 1. Write a Python program to retrieve this instruction and monitor its execution."

[1182] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1183] Step 1:

[1184] The terminal receives voice communication data between the controller and the pilot. The terminal uses a microphone to capture the voice and temporarily saves it as a voice data file. Then, the voice data is sent to the server.

[1185] (input)

[1186] Voice communication data between the controller and pilot.

[1187] (output)

[1188] The audio data file sent to the server.

[1189] Step 2:

[1190] The server converts the received voice data file into text data using a speech recognition engine (such as the Google Speech Recognition API). The speech recognition engine analyzes the voice data and generates corresponding text.

[1191] (input)

[1192] The audio data file sent from the device.

[1193] (output)

[1194] Text data.

[1195] Step 3:

[1196] The server extracts instructions from the generated text data. NLP techniques (e.g., spaCy) are used to identify important information in the text, such as the name of an item or quantity. The NLP model analyzes the text and outputs the instructions as structured data.

[1197] (input)

[1198] Text data converted by a speech recognition engine.

[1199] (output)

[1200] Instructions (item name, quantity, etc.).

[1201] Step 4:

[1202] The server generates a predicted action based on the extracted instructions. It uses a generative AI model (e.g., GPT-3) to predict what action is needed. The model generates an action plan based on the extracted instructions and outputs it as specific steps.

[1203] (input)

[1204] Instructions (item name, quantity, etc.).

[1205] (output)

[1206] Anticipatory behavior (action planning).

[1207] Step 5:

[1208] The terminal uses a GPS module to collect the current location data of the vehicle and transmits it to the server. The location data is collected in real time.

[1209] (input)

[1210] Real-time location of vehicles.

[1211] (output)

[1212] Location data sent to the server.

[1213] Step 6:

[1214] The server monitors the actual behavior of the vehicle based on the location data received. It compares the predicted behavior with the actual behavior to assess the data consistency. It uses a comparison algorithm to verify that each step is performed correctly.

[1215] (input)

[1216] Location data and predicted behavior sent from your device.

[1217] (output)

[1218] Behavior monitoring results (normal / abnormal).

[1219] Step 7:

[1220] The server detects anomalies based on the behavior monitoring results. If an anomaly is detected, an alert is generated immediately. Pre-defined conditions are used to generate the alert.

[1221] (input)

[1222] Behavioral monitoring results.

[1223] (output)

[1224] An alert message in case of an abnormality.

[1225] Step 8:

[1226] The server sends the generated alert to the device and notifies the user (controller and pilot). The notification is displayed on the device's display and may also sound an audio alert.

[1227] (input)

[1228] Alert message.

[1229] (output)

[1230] The notification message that appears on the device.

[1231] Prompt Sentence Examples

[1232] "Give me the following instruction: Pick up 10 items from Warehouse 1. Write a Python program to retrieve this instruction and monitor its execution."

[1233] 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.

[1234] Overall system flow

[1235] This invention is a system that improves aviation safety by not only enabling voice communication between air traffic controllers and aircraft pilots, but also recognizing the user's emotional state and detecting abnormalities early based on that data. This system includes functions for receiving and converting voice data, extracting instruction content, generating predictive actions, collecting GPS data and monitoring behavior, detecting abnormalities and generating alerts, as well as analyzing the user's emotional state using an emotion engine and providing notifications.

[1236] Receiving and converting voice communication data

[1237] The terminal receives voice communication data between the controller and the pilot in real time.

[1238] The terminal converts the voice data into a digital format and transmits it to the server.

[1239] Extracting instruction content

[1240] The server uses a speech recognition engine to convert the voice communication data into text data.

[1241] The server analyzes the text data, extracts the instruction content, and stores the content in a database.

[1242] Generating predictive behavior

[1243] The server generates a predicted action of the pilot based on the extracted instruction content.

[1244] For example, if you receive the command "Flight 123, climb to 10,000 feet," you would predict that Flight 123 will climb to an altitude of 10,000 feet.

[1245] GPS data collection and behavior monitoring

[1246] The terminal (on the aircraft) collects the aircraft's current GPS data (altitude, position, speed, etc.) in real time and transmits it to the server.

[1247] The server analyzes the GPS data and monitors the aircraft's actual behavior, comparing it with predicted behavior.

[1248] Anomaly detection and alert generation

[1249] Based on the comparison results, the server detects an abnormality if the pilot's actions differ from instructions.

[1250] When an abnormality is detected, the server immediately generates an alert message and sends it to the terminal.

[1251] The terminal will then notify the controller and pilot of the alert.

[1252] Emotion Engine Operation

[1253] The terminal collects voice and behavioral data from controllers and pilots and transmits it to a server.

[1254] The server uses an emotion engine to analyze this data and recognize the user's emotional state.

[1255] If the emotional state obtained from the emotion engine is determined to be abnormal, the server generates an alert message with that information.

[1256] The server also generates a message based on the abnormal emotional state, suggesting appropriate steps to take.

[1257] The terminal notifies controllers and pilots of these alert messages and response procedures.

[1258] Specific operation examples

[1259] Example 1: Up command case

[1260] 1. The user (controller) sends the instruction "Flight 123, climb to 10,000 feet."

[1261] 2. The terminal receives this voice instruction and sends it to the server.

[1262] 3. The server uses a speech recognition engine to convert the voice into text and extract the instructions.

[1263] 4. The server generates a predicted climb to 10,000 feet for Flight 123.

[1264] 5. The terminal (aircraft side) sends the current altitude GPS data to the server.

[1265] 6. The server compares the current altitude with the predicted behavior to ensure proper ascent.

[1266] 7. The server generates an alert and sends it to the device if it does not act as instructed, for example if it stops at an altitude of 8,000 feet.

[1267] 8. The terminal alerts the controller and pilot that "Flight 123 is not climbing to 10,000 feet."

[1268] 9. The user (controller) confirms this notification and issues instructions again.

[1269] Example 2: Emotional state anomaly detection case

[1270] 1. The terminal collects the pilot's voice and behavioral data in real time and sends it to the server.

[1271] 2. The server uses an emotion engine to analyze the pilot's emotional state.

[1272] 3. If the server detects abnormal stress or panic, it generates an abnormal emotion alert.

[1273] 4. The server sends this abnormal emotion alert to the terminal and notifies the controller and pilot.

[1274] 5. The device will also simultaneously send you a message suggesting ways to improve or cope with your emotional state.

[1275] The system of this invention makes it possible to detect and quickly deal with not only misunderstandings and operational errors between air traffic controllers and pilots, but also abnormalities due to emotional states in real time, which is expected to significantly improve aviation safety.

[1276] The processing flow will be explained below.

[1277] Step 1:

[1278] The terminal receives voice communication data between the controller and the pilot in real time.

[1279] Step 2:

[1280] The terminal converts the received voice communication data into a digital format and transmits it to the server.

[1281] Step 3:

[1282] The server uses a speech recognition engine to convert the voice communication data into text data.

[1283] Step 4:

[1284] The server analyzes the converted text data and extracts the instructions (e.g., flight number, target altitude, direction of travel, etc.).

[1285] Step 5:

[1286] The server generates a predicted action that the pilot should take based on the extracted instructions.

[1287] Step 6:

[1288] The terminal (aircraft-side device) collects the aircraft's current GPS data (altitude, position, speed, etc.) and transmits it to the server.

[1289] Step 7:

[1290] The server analyzes the received GPS data and monitors the aircraft's actual behavior in real time.

[1291] Step 8:

[1292] The server compares the monitored aircraft behavior with the predicted behavior generated in the previous step to check whether the pilot is acting as instructed.

[1293] Step 9:

[1294] The server detects an anomaly if the pilot's actions are not as instructed.

[1295] Step 10:

[1296] The server immediately generates an alert message when an abnormality is detected.

[1297] Step 11:

[1298] The server sends this alert message to the terminal.

[1299] Step 12:

[1300] The terminal (control tower equipment) receives the alert message and displays the notification on the controller's display terminal.

[1301] Step 13:

[1302] The user (controller) checks the notification and takes necessary measures.

[1303] Step 14:

[1304] The terminal collects voice and behavioral data from controllers and pilots and transmits it to a server.

[1305] Step 15:

[1306] The server uses an emotion engine to analyze this data and recognize the user's emotional state.

[1307] Step 16:

[1308] If the emotional state obtained from the emotion engine is determined to be abnormal, the server generates an alert message with that information.

[1309] Step 17:

[1310] The server generates a message based on the abnormal emotional state, suggesting appropriate steps to take.

[1311] Step 18:

[1312] The server sends these alert messages and troubleshooting procedures to the terminal and notifies the user.

[1313] Example 2

[1314] 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."

[1315] During aircraft operations, safety risks exist due to misunderstandings or operational errors in voice communications between air traffic controllers and pilots, as well as abnormal emotional states of pilots or controllers. A system that can detect such risks early and deal with them promptly is needed.

[1316] 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.

[1317] In this invention, the server includes a means for converting voice communication data between the controller and the pilot into text data, a means for extracting instructions from the converted text data and storing the instructions in a database, a means for analyzing collected GPS data and monitoring the aircraft's actual behavior while comparing it with predicted behavior, and a means for analyzing the voice and behavior data of the controller and the pilot using an emotion engine to recognize their emotional states. This makes it possible to detect not only misrecognition of instructions and operational errors, but also abnormal emotional states in real time and respond promptly.

[1318] "Voice communication data" refers to the voice information exchanged between air traffic controllers and pilots.

[1319] "Digital format" refers to a data format in which analog audio data is converted into a digital signal.

[1320] "Server" refers to a computer system that performs speech recognition, data analysis, and data storage.

[1321] "Text data" refers to data in the form of a character string converted from voice data.

[1322] "Instruction content" refers to the specific actions and commands extracted from text data.

[1323] "Database" refers to a structured data storage system for efficiently storing and managing data.

[1324] "Predicted actions" refers to predictions of the actions the pilot should take, generated based on the extracted instructions.

[1325] "GPS data" refers to data indicating the current location of an aircraft.

[1326] "Actual actions" refers to actions actually taken by the aircraft.

[1327] "Abnormal" refers to a state in which predicted behavior does not match actual behavior or emotional state is abnormal.

[1328] An "alert" refers to a warning message generated when the system detects an abnormality.

[1329] An "emotion engine" refers to software or algorithms that analyze voice and behavioral data to recognize emotional states.

[1330] "Terminal" refers to a device that receives, converts, transmits voice data, and notifies alerts.

[1331] "Emotional Data" refers to data regarding an emotional state analyzed using an emotion engine.

[1332] The present invention is a system that improves aviation safety by not only enabling voice communication between air traffic controllers and aircraft pilots, but also recognizing the emotional state of users and detecting abnormalities early based on that data. This system is realized using the following hardware and software.

[1333] Hardware:

[1334] Terminal (aircraft and tower): A device that receives audio, converts it into digital form, and transmits it.

[1335] Server: A computer system that processes voice data, converts text, analyzes data, runs an emotion engine, and manages the database.

[1336] GPS unit: A device used to obtain the aircraft's current position in real time.

[1337] Microphone: An acoustic device used to collect the voices of controllers and pilots.

[1338] software:

[1339] Speech recognition engine: Software that converts voice data into text data, such as the Google Speech-to-Text API.

[1340] Database management system: A database such as MySQL for storing instructions and emotional data.

[1341] Natural language processing engine: Software used to analyze text data, such as NLTK.

[1342] Emotion engines: Algorithms that recognize emotional states from speech and behavioral data, such as IBM Watson Tone Analyzer.

[1343] Communication protocol: TCP / IP, MQTT, or other communication protocol used to send and receive voice and GPS data.

[1344] Examples of implementation of the invention:

[1345] Example 1: Up command case

[1346] 1. The user (controller) sends a voice command: "Flight 123, climb to 10,000 feet."

[1347] 2. The device receives the voice instruction, converts it into digital form and sends it to the server.

[1348] 3. The server uses the Google Speech-to-Text API to convert the speech to text and recognizes it as "Flight 123, climb to 10,000 feet."

[1349] 4. The server uses a natural language processing engine to extract instructions from the text data and generate a predicted action for Flight 123 to climb to 10,000 feet.

[1350] 5. The terminal (aircraft side) sends real-time GPS data such as current altitude and location to the server.

[1351] 6. The server compares the current altitude data with the predicted behavior and monitors whether the ascent is proceeding properly.

[1352] 7. If the server does not act as instructed, it generates an alert saying "Flight 123 is not climbing to 10,000 feet" and sends it to the device.

[1353] 8. The terminal notifies the controller and pilot of this alert, prompting the controller to review the situation.

[1354] Example 2: Emotional state anomaly detection case

[1355] 1. The terminal collects the pilot's voice and behavioral data (e.g., operational errors and voice tremors) in real time and transmits them to the server.

[1356] 2. The server uses an emotion engine to analyze voice and behavioral data and recognize the pilot's emotional state (e.g., high stress).

[1357] 3. If the server detects an abnormal stress state, it generates an "abnormal emotion alert."

[1358] 4. The server sends this abnormal emotion alert to the terminal and notifies the controller and pilot.

[1359] 5. The device will display a message suggesting ways to improve the situation: "The pilot is under high stress. Please take a deep breath and calm down."

[1360] Example prompt sentence:

[1361] Below are some example prompts to input to the generative AI model:

[1362] "What would the system do if the controller instructed Flight 123 to climb to 10,000 feet, but it stopped below 10,000 feet?"

[1363] "Please explain specifically how the system will respond if the pilot exhibits an abnormal emotional state."

[1364] The system of this invention not only detects misunderstandings and operational errors between air traffic controllers and pilots, but also detects abnormal emotional states in real time and makes it possible to deal with them quickly, which is expected to significantly improve aviation safety.

[1365] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1366] Step 1: Receiving and converting voice communication data

[1367] The terminal receives voice communication data between the controller and the pilot in real time.

[1368] Input: Analog voice data between controller and pilot

[1369] Specific Action: Capture audio data using a microphone and receive it through a communication device.

[1370] Output: Audio data converted to digital format

[1371] The terminal converts the received voice data into a digital format and transmits it to the server.

[1372] Input: Analog audio data

[1373] Specific operation: Audio data is digitized by setting the sampling rate and bit depth, and sent to the server using the TCP / IP protocol.

[1374] Output: Digital audio data sent to the server

[1375] Step 2: Extracting instructions

[1376] The server converts the received voice data into text data using a voice recognition engine (e.g., Google Speech-to-Text API).

[1377] Input: Digital audio data

[1378] Specific operation: Passes digital voice data to a voice recognition engine and calls an API to obtain string data.

[1379] Output: Instructions converted into text data

[1380] The server analyzes the text data using a natural language processing engine, extracts the instructions, and stores them in a database.

[1381] Input: Text data

[1382] Specific operation: Parses text data using the NLTK library, extracts commands and keywords, and stores them in a database.

[1383] Output: Extracted instruction data

[1384] Step 3: Generate predicted behavior

[1385] The server generates a predicted behavior of the pilot based on the extracted instruction content.

[1386] Input: Extracted instruction data

[1387] Specific behavior: The instructions are input into the internal algorithm to generate predictive behavior. For example, if the instruction is "Flight 123, climb to 10,000 feet," it will predict that Flight 123 will climb to 10,000 feet.

[1388] Output: Generated predicted behavior data

[1389] Step 4: Collecting GPS data and monitoring behavior

[1390] The terminal (on the aircraft) collects the aircraft's current GPS data in real time and transmits it to the server.

[1391] Input: Real-time GPS data (altitude, location, speed, etc.)

[1392] Specific operation: Data is acquired from the GPS unit installed on the aircraft and sent to the server using the MQTT protocol.

[1393] Output: GPS data sent to the server

[1394] The server analyzes the received GPS data and compares it with predicted behavior to monitor behavior.

[1395] Input: Real-time GPS data, predicted behavior data

[1396] Specific operation: Using a custom algorithm implemented in Python, the received GPS data is compared with the predicted behavior data to determine whether it is normal or abnormal.

[1397] Output: Comparison results and monitoring result data

[1398] Step 5: Anomaly detection and alert generation

[1399] The server compares predicted behavior with actual behavior and detects anomalies.

[1400] Input: Comparison result data

[1401] Specific operation: If the predicted altitude does not match the actual altitude, an abnormality flag is raised.

[1402] Output: Anomaly detection flag and anomaly content data

[1403] If the server detects an abnormality, it immediately generates an alert message and sends it to the terminal.

[1404] Input: Anomaly detection flag and anomaly content data

[1405] Specific behavior: Generate an alert message containing details of the anomaly, encode it in JSON format, and send it to the terminal.

[1406] Output: The alert message sent to the terminal.

[1407] The terminal will then notify the controller and pilot of the alert.

[1408] Input: Alert message

[1409] What it does: Use the display and audio output device to provide a visual and audible alert that "Flight 123 is not climbing to 10,000 feet."

[1410] Output: Alerts sent to controllers and pilots

[1411] Step 6: Emotion Engine in Action

[1412] The terminal collects voice and behavioral data from controllers and pilots and transmits it to a server.

[1413] Input: Real-time audio and behavioral data

[1414] Specific operation: Collects voice and behavioral data through microphones and various sensors and sends it to a server.

[1415] Output: Audio and behavioral data sent to the server

[1416] The server uses an emotion engine to analyze this data and recognize the emotional state.

[1417] Input: Audio and behavioral data

[1418] Specific operation: Using emotion engines such as IBM Watson Tone Analyzer, the system analyzes voice and behavioral data to recognize emotional states.

[1419] Output: Recognized emotional state data

[1420] If the emotional state is determined to be abnormal, the server generates an alert message and notifies the user.

[1421] Input: Emotional state data

[1422] Specific operation: If an abnormal emotional state is detected, an alert message containing details is generated and sent to the device.

[1423] Output: Emotional abnormality alert message sent to the terminal

[1424] The server also generates a message based on the abnormal emotional state, suggesting appropriate steps to take.

[1425] Input: Emotional state data

[1426] Specific Action: Based on the analysis results from the emotion engine, a message is generated suggesting appropriate steps to take (e.g., "Take a deep breath and stay calm").

[1427] Output: Proposal message

[1428] The terminal notifies controllers and pilots of these alert messages and response procedures.

[1429] Input: Emotional abnormality alert message and suggested message

[1430] Specific operation: Display and play notification information using a display and audio playback device.

[1431] Output: Suggestions and emotional anomaly alerts notified to controllers and pilots

[1432] (Application example 2)

[1433] 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."

[1434] Improving the safety of autonomous vehicles is an important challenge for current technology. In particular, it is necessary to properly recognize the emotional state of driver assistants and passengers and respond quickly when an abnormality occurs. Conventional systems have had difficulty understanding passengers' emotional states in real time, detecting abnormalities, and taking countermeasures. Therefore, a new system that can analyze emotional states and support safe driving is needed.

[1435] The identification process by the identification 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 voice communication data between an air traffic controller and an aircraft pilot; means for converting the received voice communication data into text data; means for extracting instructions from the converted text data; means for generating a predicted behavior based on the extracted instructions; means for collecting current position data of the aircraft from a GPS; means for monitoring the actual behavior of the aircraft based on the collected GPS data; means for comparing the monitored behavior of the aircraft with the predicted behavior and detecting an abnormality; means for generating and notifying an alert when an abnormality is detected; means for collecting voice data and behavior data and analyzing the emotional state; and means for generating an alert and suggesting a response procedure when an abnormal emotional state is detected. This makes it possible to grasp the emotional states of the driver's assistant and passengers in real time, quickly detect abnormalities, and take appropriate measures.

[1436] A "controller" is a person whose job is to monitor and direct the operation of aircraft and vehicles.

[1437] "Aircraft" is a general term for any mechanical device that can fly.

[1438] A "pilot" is a person qualified to operate an aircraft.

[1439] "Voice communication data" means information in digital form that contains voice.

[1440] "Text data" means written information in digital form.

[1441] "Instruction content" is information for instructing a specific action.

[1442] "Predicted behavior" refers to behavior that the system generates based on the instructions it receives.

[1443] "Location Data" means geographic location information obtained using technologies such as GPS.

[1444] "GPS" is an abbreviation for Global Positioning System, a system for determining locations on Earth with high accuracy.

[1445] "Actual behavior" refers to the actions that a system or machine actually takes.

[1446] An "abnormality" is a state in which predicted behavior differs from actual behavior.

[1447] An "alert" is a warning issued when an abnormality is detected.

[1448] A "notification" is a means of conveying specific information.

[1449] "Audio data" is a general term for digital information that includes audio.

[1450] "Behavioral data" is digital information about the actions taken by a system or machine.

[1451] "Emotional state" refers to a person's emotional state.

[1452] An "abnormal emotional state" is an emotional state that is different from the normal state.

[1453] "Response procedures" refer to the actions and procedures to be taken when an abnormality occurs.

[1454] Overall system configuration

[1455] This invention is a system that analyzes voice and behavioral data in real time to detect abnormalities in order to improve the safety of autonomous vehicles. In particular, it analyzes the emotional state of the driver's assistant and passengers and provides appropriate response procedures in the event of an abnormality. It also incorporates location data collection using GPS.

[1456] Program processing explanation

[1457] The system's main hardware includes a smartphone, smart glasses, and a GPS module, while the software uses Python, the speech_recognition library, and the requests library.

[1458] Receiving and converting voice communication data

[1459] The server receives the driver's assistant's voice communication data in real time and converts it into text data. Specifically, it uses the smartphone's microphone function and a speech recognition engine (for example, the speech_recognition library) to convert the voice into text.

[1460] Extracting instruction content and generating predicted actions

[1461] The server extracts the instructions from the converted text data and generates predicted actions based on the instructions. This information is stored in a database and used for analytical processing.

[1462] GPS data collection and behavior monitoring

[1463] The terminal (on the vehicle side) collects the vehicle's current GPS data (position, speed, etc.) in real time and sends it to the server, which analyzes this GPS data and compares the actual behavior with the predicted behavior.

[1464] Anomaly detection and alert generation

[1465] The server compares predicted and actual behavior and immediately generates an alert if an abnormality is detected, which is then sent to the driver assistant via a smartphone or smart glasses.

[1466] Emotion Engine Operation

[1467] The server collects voice and behavioral data and analyzes them using an emotion engine. If the emotional state is determined to be abnormal, an alert is generated and a response procedure is proposed. This process uses a generative AI model, and the results are sent to the driver's assistant's smartphone or other device.

[1468] Specific example explanation

[1469] For example, if the driver assistant is feeling stressed, the system operates as follows:

[1470] 1. The driver assistant issues a voice command such as, "I feel the vehicle speed is a little too fast."

[1471] 2. This audio is collected through the smartphone's microphone and sent to a server.

[1472] 3. The server converts the speech into text and analyzes it using an emotion engine. The analysis results detect stress and anxiety.

[1473] 4. The server generates an alert based on this information and sends it to the smartphone.

[1474] 5. Your smartphone will display an alert such as "Driver assistant is experiencing high stress, we recommend reducing speed."

[1475] Prompt Sentence Examples

[1476] For example, a specific example of a prompt sentence to be input into a generative AI model is, "Convert this voice data into text, analyze the user's emotional state, and notify me if any abnormalities are found."

[1477] Such a system would enable autonomous vehicles to monitor the emotional state of their occupants while driving, quickly detect and respond to any abnormalities, and ultimately provide a safer driving environment.

[1478] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1479] Step 1:

[1480] The user inputs voice data using the microphone on the smartphone, and the input voice data is collected from the driver's assistant.

[1481] Step 2:

[1482] The device transmits the received voice data in real time to a server, where it is converted into a digital format and transmitted over the internet.

[1483] Step 3:

[1484] The server converts the received voice data into text data using a voice recognition engine (for example, the speech_recognition library). The input is digital voice data, and the output is text data.

[1485] Step 4:

[1486] The server extracts the instructions from the converted text data. Natural language processing technology is used to analyze the text data for specific instructions and emotional states. The input is the text data, and the output is the analysis results of the instructions and emotional states.

[1487] Step 5:

[1488] The server generates a predicted behavior based on the extracted instruction content. For example, if the instruction is "slow down," it predicts the behavior of slowing down to an appropriate speed. The input is instruction content data, and the output is predicted behavior data.

[1489] Step 6:

[1490] The terminal (vehicle side) collects current location data using a GPS module and transmits it to the server in real time. The input is GPS data, and the output is the transmitted current location data.

[1491] Step 7:

[1492] The server monitors the vehicle's actual behavior based on the collected GPS data. It compares the predicted behavior with the actual behavior and checks for any abnormalities. The inputs are the predicted behavior data and GPS data, and the output is the result of anomaly detection.

[1493] Step 8:

[1494] The server generates an alert when an anomaly is detected. The alert is generated as a specific text message. The input is the anomaly detection data, and the output is the alert message.

[1495] Step 9:

[1496] The terminal notifies the driver assistant of the generated alert message. The alert message is displayed visually or audibly using a smartphone or smart glasses. The input is the alert message, and the output is a visual or audio notification.

[1497] Step 10:

[1498] The server collects voice data and behavioral data and analyzes the emotional state using an emotion engine. The input is the voice data and behavioral data, and the output is the analysis result of the emotional state.

[1499] Step 11:

[1500] If the server detects an abnormal emotional state, it generates an alert and suggests a course of action. It uses a generative AI model to suggest an appropriate course of action. The input is emotional state data, and the output is an alert message with a course of action.

[1501] Step 12:

[1502] The terminal notifies the driver assistant of the generated alert message and the response procedures via a smartphone or smart glasses. The input is the alert message with the response procedures, and the output is a visual or audio notification.

[1503] 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.

[1504] 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.

[1505] 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.

[1506] [Fourth embodiment]

[1507] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1508] 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.

[1509] 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).

[1510] 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.

[1511] 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.

[1512] 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).

[1513] 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.

[1514] 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.

[1515] 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.

[1516] 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.

[1517] 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.

[1518] 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.

[1519] 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."

[1520] To implement this invention, it is necessary to build a system that collects voice communication data between air traffic controllers and aircraft pilots in real time and converts it into text data. This system supports the safe operation of aircraft through a series of processes: extracting instructions, generating predicted behavior, collecting GPS data, monitoring behavior, detecting anomalies, and generating and notifying alerts.

[1521] Overall system flow

[1522] Receiving and converting voice communication data

[1523] The terminal receives voice communications between the controller and the pilot.

[1524] The terminal transmits this voice data to the server.

[1525] The server uses a speech recognition engine to convert the voice communication data into text data.

[1526] Extracting instruction content

[1527] The server extracts the instruction content (e.g., flight number, destination, altitude, etc.) from the converted text data.

[1528] Generating predictive behavior

[1529] The server generates a predicted flight behavior based on the extracted instructions. For example, if the instruction is "Flight 123, climb to 10,000 feet," it predicts that Flight 123 will climb from its current altitude to 10,000 feet.

[1530] GPS data collection and behavior monitoring

[1531] The terminal collects the aircraft's current GPS data and transmits it to the server.

[1532] The server analyzes this GPS data and monitors the aircraft's actual behavior (position, altitude, speed, etc.) in real time.

[1533] Anomaly detection and alert generation

[1534] The server compares the monitored aircraft behavior with the predicted behavior and checks for any anomalies.

[1535] The server immediately generates an alert message if an abnormality is detected.

[1536] The server sends the generated alert to the terminal and notifies the controller and pilot.

[1537] Specific operation examples

[1538] Example 1: Up command case

[1539] 1. The user (controller) sends the instruction "Flight 123, climb to 10,000 feet."

[1540] 2. The terminal receives this voice instruction and sends it to the server.

[1541] 3. The server uses a speech recognition engine to convert the voice into text and extract the instructions.

[1542] 4. The server generates a predicted climb to 10,000 feet for Flight 123.

[1543] 5. The terminal (aircraft side) sends the current altitude GPS data to the server.

[1544] 6. The server compares the current altitude with the predicted behavior to ensure proper ascent.

[1545] 7. The server generates an alert and sends it to the device if it does not act as instructed, for example if it stops at an altitude of 8,000 feet.

[1546] 8. The terminal alerts the controller and pilot that "Flight 123 is not climbing to 10,000 feet."

[1547] 9. The user (controller) confirms this notification and issues instructions again.

[1548] By using this system, it is possible to monitor aircraft movements in real time, detect abnormalities early, increase safety, and reduce the workload of air traffic controllers.

[1549] The processing flow will be explained below.

[1550] Step 1:

[1551] The terminal receives voice communication data between the controller and the pilot in real time.

[1552] Step 2:

[1553] The terminal converts the received voice communication data into a digital format and transmits it to the server.

[1554] Step 3:

[1555] The server uses a speech recognition engine to convert the voice communication data into text data.

[1556] Step 4:

[1557] The server analyzes the converted text data and extracts the instructions (e.g., flight number, target altitude, direction of travel, etc.).

[1558] Step 5:

[1559] The server generates a predicted action that the pilot should take based on the extracted instructions.

[1560] Step 6:

[1561] The terminal (aircraft-side device) collects the aircraft's current GPS data (altitude, position, speed, etc.) and transmits it to the server.

[1562] Step 7:

[1563] The server analyzes the received GPS data and monitors the aircraft's actual behavior in real time.

[1564] Step 8:

[1565] The server compares the monitored aircraft behavior with the predicted behavior generated in the previous step to check whether the pilot is acting as instructed.

[1566] Step 9:

[1567] The server detects an anomaly if the pilot's actions are not as instructed.

[1568] Step 10:

[1569] The server immediately generates an alert message when an abnormality is detected.

[1570] Step 11:

[1571] The server sends this alert message to the terminal.

[1572] Step 12:

[1573] The terminal (control tower equipment) receives the alert message and displays the notification on the controller's display terminal.

[1574] Step 13:

[1575] The user (controller) checks the notification and takes necessary measures.

[1576] These steps will enable misunderstandings and operational errors between controllers and pilots to be detected in real time, preventing accidents before they occur.

[1577] Example 1

[1578] 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."

[1579] Aircraft operations require rapid and accurate analysis of voice communication data between air traffic controllers and pilots. Conventional methods often involve manual conversion and analysis of voice data, which can lead to misunderstandings and delays. This can potentially reduce the safety of aircraft operations. To solve this problem, a system is needed that can automatically analyze voice communication data in real time and issue an immediate warning in the event of an abnormality.

[1580] 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.

[1581] In this invention, the server includes means for receiving voice communication data between an air traffic controller and an aircraft pilot, means for converting the received voice communication data into text data, means for extracting instructions from the converted text data, means for generating predicted behavior based on the extracted instructions, means for collecting current position data of the aircraft from a satellite positioning system, means for monitoring the actual behavior of the aircraft based on the collected position data, means for comparing the monitored behavior of the aircraft with predicted behavior and detecting abnormalities, means for generating and notifying warning information when an abnormality is detected, means for automatically analyzing instructions related to the aircraft, and means for displaying the generated warning information on a terminal. This makes it possible to automatically analyze voice communication data in real time during aircraft operation and ensure safety.

[1582] "Voice communication data" refers to the content of voice communications between air traffic controllers and aircraft pilots.

[1583] "Text data" refers to a data format in which voice communication data is converted into a string of characters.

[1584] "Instruction content" refers to specific command items such as flight number, destination, and altitude extracted from the text data.

[1585] "Predicted action" refers to the action that the aircraft is expected to take based on the instructions.

[1586] "Position Data" refers to current aircraft position information collected from satellite positioning systems.

[1587] "Satellite positioning system" refers to a general term for systems that receive signals from satellites and measure the precise location of an aircraft.

[1588] "Behavioral surveillance" refers to the process of monitoring the actual behavior of aircraft based on collected location data.

[1589] "Anomaly detection" refers to comparing monitored aircraft behavior with predicted behavior to determine whether there are any anomalies.

[1590] "Warning information" refers to a notification message that is generated when an abnormality is detected.

[1591] "Terminal" refers to a device that receives and transmits voice communication data, displays warning information, etc.

[1592] MODE FOR CARRYING OUT THE INVENTION

[1593] To implement this invention, it is necessary to build a system that collects voice communication data between air traffic controllers and aircraft pilots in real time and converts it into text data. This system supports the safe operation of aircraft through a series of processes: extraction of instruction content, generation of predicted behavior, collection of location data, behavior monitoring, anomaly detection, and generation and notification of warning information.

[1594] Receiving and converting voice communication data

[1595] The terminal receives voice communications between the air traffic controller and the aircraft pilot. The terminal collects voice data using a microphone and temporarily stores the collected voice data in local storage. The terminal then transmits the stored voice data to a server. The server converts the voice data into text data using a speech recognition engine (e.g., Google Cloud Speech-to-Text).

[1596] For example, if a controller says, "Flight 123, climb to 10,000 feet," the device will record this audio with a microphone and send it to a server, which will then convert it into text using Google Cloud Speech-to-Text.

[1597] Extracting instruction content

[1598] The server receives the converted text data and uses an NLP model (e.g., SpaCy) to extract specific instructions, such as flight number, destination, and altitude.

[1599] In a specific example, the server extracts "Flight 123" and "climb to 10,000 feet" from the text data "Flight 123, climb to 10,000 feet."

[1600] Generating predictive behavior

[1601] The server generates a predicted flight behavior based on the extracted instructions. It uses a Python numerical calculation library (e.g., NumPy) to generate numerical data corresponding to the instructed behavior.

[1602] As a concrete example, the server generates a predicted action such as "Flight 123 will climb to 10,000 feet."

[1603] Location data collection and behavioral monitoring

[1604] The terminal collects the aircraft's current location data. This location data is obtained using a satellite positioning system (e.g., GPS). The collected location data includes latitude, longitude, altitude, etc. The terminal then transmits this location data to a server.

[1605] The server receives the transmitted position data and monitors the current aircraft behavior, a process that involves data analysis using the Pandas library.

[1606] In a specific example, the terminal uses the aircraft's GPS module to obtain information such as the current latitude, longitude, and altitude, and sends it to the server. The server confirms and records that the aircraft's current altitude is "8,000 feet."

[1607] Anomaly detection and warning information generation

[1608] The server compares predicted behavior with current behavior to check for any anomalies. If an anomaly is detected, it immediately generates a warning. The use of generative AI models improves the accuracy of anomaly detection.

[1609] As a concrete example, the server may detect that the aircraft is stuck at 8,000 feet when it should be climbing to 10,000 feet.

[1610] Warning information notification

[1611] The server sends the generated warning information to the terminal, and notifies the controller and the pilot, and the notification is displayed on the screen of the terminal, for example.

[1612] In this example, the server generates a warning message saying "Flight 123 is not climbing to 10,000 feet" and sends it to the terminal, which then displays the warning message on the controller's screen or the pilot's device.

[1613] Examples of prompt statements

[1614] The following are specific examples of prompt sentences to be input into the generative AI model.

[1615] "Please extract the instructions from the following text data: 'Flight 123, climb to 10,000 feet'"

[1616] In response to this prompt, the generative AI model will respond by extracting phrases such as "Flight 123" and "climb to 10,000 feet."

[1617] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1618] Step 1:

[1619] The terminal receives voice communications between the air traffic controller and the aircraft pilot. As input, it uses voice communication data collected through a microphone. Specifically, the terminal collects this voice data using a microphone and temporarily stores it in local storage. As output, it obtains the collected voice data.

[1620] Step 2:

[1621] The device sends the stored voice data to the server. The voice data stored in the local storage is used as input. Specifically, the device sends the collected voice files to the server via the Internet. The voice data received by the server is obtained as output.

[1622] Step 3:

[1623] The server uses a speech recognition engine to convert the received voice data into text data. The server uses the voice data it received as input. Specifically, the server calls a speech recognition engine (Google Cloud Speech-to-Text) and converts the voice data into text data such as "Flight 123, climb to 10,000 feet." The text data is obtained as output.

[1624] Step 4:

[1625] The server receives the converted text data and uses an NLP model to extract specific instructions. The text data is used as input. Specifically, the server uses an NLP model (e.g., SpaCy) to extract the instructions, such as "flight number" and "altitude instructions." The extracted instructions are obtained as output.

[1626] Step 5:

[1627] The server generates a predicted flight behavior based on the extracted instructions. The extracted instructions are used as input. Specifically, the server uses a Python mathematical library (e.g., NumPy) to generate a predicted behavior such as "the flight will climb to 10,000 feet." The generated predicted behavior is obtained as output.

[1628] Step 6:

[1629] The terminal collects the aircraft's current position data. As input, it uses the position data obtained through the GPS module. Specifically, the terminal obtains position data such as latitude, longitude, and altitude and sends it to the server. As output, it obtains the collected position data.

[1630] Step 7:

[1631] The server receives the transmitted location data and monitors the current aircraft behavior. It uses the location data transmitted from the terminal as input. Specifically, the server analyzes the collected data using the Pandas library to analyze the aircraft's current position, altitude, speed, etc. As output, it obtains the current aircraft behavior data.

[1632] Step 8:

[1633] The server compares the predicted behavior with the current behavior and checks for anomalies. As input, it uses the generated predicted behavior and the monitored behavior data. Specifically, the server performs a comparison operation to match the predicted behavior with the actual behavior and check for any discrepancies. As output, if there is an anomaly, the anomalous data is identified.

[1634] Step 9:

[1635] The server generates warning information immediately if an anomaly is detected. The server uses the anomaly data as input. Specifically, the server uses a generative AI model to generate an appropriate warning message (e.g., "Flight 123 is not climbing to 10,000 feet"). The warning information is obtained as output.

[1636] Step 10:

[1637] The server sends the generated warning information to the terminal and notifies the controller and pilot. The server uses the generated warning information as input. Specifically, the server sends the warning information to the terminal via the Internet, and the terminal displays this information on the controller's screen or the pilot's device. As output, a notification is sent.

[1638] (Application example 1)

[1639] 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."

[1640] In logistics centers, accurately managing instructions to workers and their execution status is extremely important for efficient business operations and ensuring safety. However, relying on verbal instructions is prone to human error and misunderstanding of instructions, making it difficult to grasp the situation in real time. This leads to problems such as reduced work efficiency and increased likelihood of mistakes. In addition, there are limited means to appropriately monitor the progress of work using location data, making it difficult to respond quickly when an abnormality occurs.

[1641] 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.

[1642] In this invention, the server includes means for receiving voice communication data between the controller and the operator of the vehicle, means for converting the received voice communication data into text data, means for extracting instructions from the converted text data, means for generating predicted behavior based on the extracted instructions, means for collecting current location data of the vehicle from a location information acquisition means, means for monitoring the actual behavior of the vehicle based on the collected location data, means for comparing the monitored behavior of the vehicle with the predicted behavior and detecting abnormalities, means for generating a notification when an abnormality is detected, and means for displaying the instructions and location data on the smart device. This enables real-time text conversion and analysis of voice instructions, behavior monitoring using location data, and rapid notification when an abnormality occurs.

[1643] A "controller" is a manager who gives instructions to workers and transportation means in a logistics center or transportation system.

[1644] "Vehicle" means any equipment or vehicle used to transport or move goods.

[1645] "Operator" means the worker or person in charge of operating or controlling a conveyance.

[1646] "Voice communication data" refers to data on voice instructions and reports exchanged between the controller and the pilot.

[1647] "Text data" refers to voice communication data converted into character format.

[1648] "Instruction content" refers to specific work instructions extracted from the extracted text data.

[1649] "Predicted behavior" is a model of the behavior that a vehicle should take, generated based on instructions.

[1650] "Location information acquisition means" means a device or system that collects the current location of a vehicle using technology such as GPS.

[1651] "Location data" means information regarding the current location of a vehicle.

[1652] "Behavior monitoring" is the process of comparing predicted behavior with actual behavior to monitor whether a vehicle is operating as instructed.

[1653] "Anomaly detection" is the act of detecting when predicted behavior and actual behavior do not match, or when abnormal behavior occurs.

[1654] "Notification" refers to transmitting an alert or warning to relevant parties when an abnormality is detected.

[1655] "Smart devices" refer to electronic devices such as smartphones, tablets, and wearable devices that can connect to the Internet and run various applications.

[1656] To implement this invention, it is first necessary to build a system that properly receives voice communication between the controller and the operator of the vehicle and converts it into text. Specifically, this can be realized by collaboration between a server, a terminal, and users (controller and operator).

[1657] Server Roles

[1658] The server is the central point that manages the operation of the vehicle through a number of functions. The main hardware and software used are:

[1659] Voice reception and conversion: The server uses a voice recognition engine (e.g., Google Speech Recognition API) to convert voice communication data between the controller and pilot into text data in real time.

[1660] Extracting Instructions: The text data is then analyzed and instructions are extracted using software such as Natural Language Processing (NLP) and spaCy.

[1661] Generate predictive behavior: Use a generative AI model (e.g., GPT-3) to generate predictive behavior based on the extracted instructions.

[1662] Behavior monitoring: Receives location data of transportation vehicles from GPS modules and various sensors, and monitors the acquired data in real time.

[1663] Anomaly detection and notification: Compares monitored data with predicted behavior, and if an anomaly is detected, generates a notification and sends a quick alert to the controller or operator. Anomaly detection utilizes machine learning models and anomaly detection algorithms.

[1664] Device Role

[1665] The device (e.g., smartphone, head-mounted display) receives the information processed by the server and provides it visually and audibly to the user. The device is used as follows:

[1666] Audio reception: Receives audio communication from the controller and pilot and sends it to the server.

[1667] Location data collection: Location data is collected in real time through the GPS module and sent to the server.

[1668] Display notifications: Provides visual and audio notifications to the user of notifications and alerts sent by the server.

[1669] User Roles

[1670] The user (controller and pilot) is the main operator of the system and has the following roles:

[1671] Voice instructions: The controller issues voice instructions, which are transmitted to the server via the terminal.

[1672] Checking notifications: The pilot checks the notifications displayed on the device and takes appropriate action.

[1673] Specific examples

[1674] For example, a logistics center controller might say, "Please pick up 10 items from warehouse 1." This voice communication data is received by the terminal and sent to the server. The server uses a speech recognition engine to convert the speech into text and uses NLP technology to extract the instructions (items and quantities). Next, a generative AI model is used to generate predictive actions and monitor location data in real time. Finally, it checks whether the operator is performing the task according to the instructions, and if there is an abnormality, a notification is generated immediately to notify the operator. This series of processes improves the efficiency and safety of logistics operations.

[1675] Prompt Sentence Examples

[1676] "Give me the following instruction: Pick up 10 items from Warehouse 1. Write a Python program to retrieve this instruction and monitor its execution."

[1677] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1678] Step 1:

[1679] The terminal receives voice communication data between the controller and the pilot. The terminal uses a microphone to capture the voice and temporarily saves it as a voice data file. Then, the voice data is sent to the server.

[1680] (input)

[1681] Voice communication data between the controller and pilot.

[1682] (output)

[1683] The audio data file sent to the server.

[1684] Step 2:

[1685] The server converts the received voice data file into text data using a speech recognition engine (such as the Google Speech Recognition API). The speech recognition engine analyzes the voice data and generates corresponding text.

[1686] (input)

[1687] The audio data file sent from the device.

[1688] (output)

[1689] Text data.

[1690] Step 3:

[1691] The server extracts instructions from the generated text data. NLP techniques (e.g., spaCy) are used to identify important information in the text, such as the name of an item or quantity. The NLP model analyzes the text and outputs the instructions as structured data.

[1692] (input)

[1693] Text data converted by a speech recognition engine.

[1694] (output)

[1695] Instructions (item name, quantity, etc.).

[1696] Step 4:

[1697] The server generates a predicted action based on the extracted instructions. It uses a generative AI model (e.g., GPT-3) to predict what action is needed. The model generates an action plan based on the extracted instructions and outputs it as specific steps.

[1698] (input)

[1699] Instructions (item name, quantity, etc.).

[1700] (output)

[1701] Anticipatory behavior (action planning).

[1702] Step 5:

[1703] The terminal uses a GPS module to collect the current location data of the vehicle and transmits it to the server. The location data is collected in real time.

[1704] (input)

[1705] Real-time location of vehicles.

[1706] (output)

[1707] Location data sent to the server.

[1708] Step 6:

[1709] The server monitors the actual behavior of the vehicle based on the location data received. It compares the predicted behavior with the actual behavior to assess the data consistency. It uses a comparison algorithm to verify that each step is performed correctly.

[1710] (input)

[1711] Location data and predicted behavior sent from your device.

[1712] (output)

[1713] Behavior monitoring results (normal / abnormal).

[1714] Step 7:

[1715] The server detects anomalies based on the behavior monitoring results. If an anomaly is detected, an alert is generated immediately. Pre-defined conditions are used to generate the alert.

[1716] (input)

[1717] Behavioral monitoring results.

[1718] (output)

[1719] An alert message in case of an abnormality.

[1720] Step 8:

[1721] The server sends the generated alert to the device and notifies the user (controller and pilot). The notification is displayed on the device's display and may also sound an audio alert.

[1722] (input)

[1723] Alert message.

[1724] (output)

[1725] The notification message that appears on the device.

[1726] Prompt Sentence Examples

[1727] "Give me the following instruction: Pick up 10 items from Warehouse 1. Write a Python program to retrieve this instruction and monitor its execution."

[1728] 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.

[1729] Overall system flow

[1730] This invention is a system that improves aviation safety by not only enabling voice communication between air traffic controllers and aircraft pilots, but also recognizing the user's emotional state and detecting abnormalities early based on that data. This system includes functions for receiving and converting voice data, extracting instruction content, generating predictive actions, collecting GPS data and monitoring behavior, detecting abnormalities and generating alerts, as well as analyzing the user's emotional state using an emotion engine and providing notifications.

[1731] Receiving and converting voice communication data

[1732] The terminal receives voice communication data between the controller and the pilot in real time.

[1733] The terminal converts the voice data into a digital format and transmits it to the server.

[1734] Extracting instruction content

[1735] The server uses a speech recognition engine to convert the voice communication data into text data.

[1736] The server analyzes the text data, extracts the instruction content, and stores the content in a database.

[1737] Generating predictive behavior

[1738] The server generates a predicted action of the pilot based on the extracted instruction content.

[1739] For example, if you receive the command "Flight 123, climb to 10,000 feet," you would predict that Flight 123 will climb to an altitude of 10,000 feet.

[1740] GPS data collection and behavior monitoring

[1741] The terminal (on the aircraft) collects the aircraft's current GPS data (altitude, position, speed, etc.) in real time and transmits it to the server.

[1742] The server analyzes the GPS data and monitors the aircraft's actual behavior, comparing it with predicted behavior.

[1743] Anomaly detection and alert generation

[1744] Based on the comparison results, the server detects an abnormality if the pilot's actions differ from instructions.

[1745] When an abnormality is detected, the server immediately generates an alert message and sends it to the terminal.

[1746] The terminal will then notify the controller and pilot of the alert.

[1747] Emotion Engine Operation

[1748] The terminal collects voice and behavioral data from controllers and pilots and transmits it to a server.

[1749] The server uses an emotion engine to analyze this data and recognize the user's emotional state.

[1750] If the emotional state obtained from the emotion engine is determined to be abnormal, the server generates an alert message with that information.

[1751] The server also generates a message based on the abnormal emotional state, suggesting appropriate steps to take.

[1752] The terminal notifies controllers and pilots of these alert messages and response procedures.

[1753] Specific operation examples

[1754] Example 1: Up command case

[1755] 1. The user (controller) sends the instruction "Flight 123, climb to 10,000 feet."

[1756] 2. The terminal receives this voice instruction and sends it to the server.

[1757] 3. The server uses a speech recognition engine to convert the voice into text and extract the instructions.

[1758] 4. The server generates a predicted climb to 10,000 feet for Flight 123.

[1759] 5. The terminal (aircraft side) sends the current altitude GPS data to the server.

[1760] 6. The server compares the current altitude with the predicted behavior to ensure proper ascent.

[1761] 7. The server generates an alert and sends it to the device if it does not act as instructed, for example if it stops at an altitude of 8,000 feet.

[1762] 8. The terminal alerts the controller and pilot that "Flight 123 is not climbing to 10,000 feet."

[1763] 9. The user (controller) confirms this notification and issues instructions again.

[1764] Example 2: Emotional state anomaly detection case

[1765] 1. The terminal collects the pilot's voice and behavioral data in real time and sends it to the server.

[1766] 2. The server uses an emotion engine to analyze the pilot's emotional state.

[1767] 3. If the server detects abnormal stress or panic, it generates an abnormal emotion alert.

[1768] 4. The server sends this abnormal emotion alert to the terminal and notifies the controller and pilot.

[1769] 5. The device will also simultaneously send you a message suggesting ways to improve or cope with your emotional state.

[1770] The system of this invention makes it possible to detect and quickly deal with not only misunderstandings and operational errors between air traffic controllers and pilots, but also abnormalities due to emotional states in real time, which is expected to significantly improve aviation safety.

[1771] The processing flow will be explained below.

[1772] Step 1:

[1773] The terminal receives voice communication data between the controller and the pilot in real time.

[1774] Step 2:

[1775] The terminal converts the received voice communication data into a digital format and transmits it to the server.

[1776] Step 3:

[1777] The server uses a speech recognition engine to convert the voice communication data into text data.

[1778] Step 4:

[1779] The server analyzes the converted text data and extracts the instructions (e.g., flight number, target altitude, direction of travel, etc.).

[1780] Step 5:

[1781] The server generates a predicted action that the pilot should take based on the extracted instructions.

[1782] Step 6:

[1783] The terminal (aircraft-side device) collects the aircraft's current GPS data (altitude, position, speed, etc.) and transmits it to the server.

[1784] Step 7:

[1785] The server analyzes the received GPS data and monitors the aircraft's actual behavior in real time.

[1786] Step 8:

[1787] The server compares the monitored aircraft behavior with the predicted behavior generated in the previous step to check whether the pilot is acting as instructed.

[1788] Step 9:

[1789] The server detects an anomaly if the pilot's actions are not as instructed.

[1790] Step 10:

[1791] The server immediately generates an alert message when an abnormality is detected.

[1792] Step 11:

[1793] The server sends this alert message to the terminal.

[1794] Step 12:

[1795] The terminal (control tower equipment) receives the alert message and displays the notification on the controller's display terminal.

[1796] Step 13:

[1797] The user (controller) checks the notification and takes necessary measures.

[1798] Step 14:

[1799] The terminal collects voice and behavioral data from controllers and pilots and transmits it to a server.

[1800] Step 15:

[1801] The server uses an emotion engine to analyze this data and recognize the user's emotional state.

[1802] Step 16:

[1803] If the emotional state obtained from the emotion engine is determined to be abnormal, the server generates an alert message with that information.

[1804] Step 17:

[1805] The server generates a message based on the abnormal emotional state, suggesting appropriate steps to take.

[1806] Step 18:

[1807] The server sends these alert messages and troubleshooting procedures to the terminal and notifies the user.

[1808] Example 2

[1809] 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."

[1810] During aircraft operations, safety risks exist due to misunderstandings or operational errors in voice communications between air traffic controllers and pilots, as well as abnormal emotional states of pilots or controllers. A system that can detect such risks early and deal with them promptly is needed.

[1811] 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.

[1812] In this invention, the server includes a means for converting voice communication data between the controller and the pilot into text data, a means for extracting instructions from the converted text data and storing the instructions in a database, a means for analyzing collected GPS data and monitoring the aircraft's actual behavior while comparing it with predicted behavior, and a means for analyzing the voice and behavior data of the controller and the pilot using an emotion engine to recognize their emotional states. This makes it possible to detect not only misrecognition of instructions and operational errors, but also abnormal emotional states in real time and respond promptly.

[1813] "Voice communication data" refers to the voice information exchanged between air traffic controllers and pilots.

[1814] "Digital format" refers to a data format in which analog audio data is converted into a digital signal.

[1815] "Server" refers to a computer system that performs speech recognition, data analysis, and data storage.

[1816] "Text data" refers to data in the form of a character string converted from voice data.

[1817] "Instruction content" refers to the specific actions and commands extracted from text data.

[1818] "Database" refers to a structured data storage system for efficiently storing and managing data.

[1819] "Predicted actions" refers to predictions of the actions the pilot should take, generated based on the extracted instructions.

[1820] "GPS data" refers to data indicating the current location of an aircraft.

[1821] "Actual actions" refers to actions actually taken by the aircraft.

[1822] "Abnormal" refers to a state in which predicted behavior does not match actual behavior or emotional state is abnormal.

[1823] An "alert" refers to a warning message generated when the system detects an abnormality.

[1824] An "emotion engine" refers to software or algorithms that analyze voice and behavioral data to recognize emotional states.

[1825] "Terminal" refers to a device that receives, converts, transmits voice data, and notifies alerts.

[1826] "Emotional Data" refers to data regarding an emotional state analyzed using an emotion engine.

[1827] The present invention is a system that improves aviation safety by not only enabling voice communication between air traffic controllers and aircraft pilots, but also recognizing the emotional state of users and detecting abnormalities early based on that data. This system is realized using the following hardware and software.

[1828] Hardware:

[1829] Terminal (aircraft and tower): A device that receives audio, converts it into digital form, and transmits it.

[1830] Server: A computer system that processes voice data, converts text, analyzes data, runs an emotion engine, and manages the database.

[1831] GPS unit: A device used to obtain the aircraft's current position in real time.

[1832] Microphone: An acoustic device used to collect the voices of controllers and pilots.

[1833] software:

[1834] Speech recognition engine: Software that converts voice data into text data, such as the Google Speech-to-Text API.

[1835] Database management system: A database such as MySQL for storing instructions and emotional data.

[1836] Natural language processing engine: Software used to analyze text data, such as NLTK.

[1837] Emotion engines: Algorithms that recognize emotional states from speech and behavioral data, such as IBM Watson Tone Analyzer.

[1838] Communication protocol: TCP / IP, MQTT, or other communication protocol used to send and receive voice and GPS data.

[1839] Examples of implementation of the invention:

[1840] Example 1: Up command case

[1841] 1. The user (controller) sends a voice command: "Flight 123, climb to 10,000 feet."

[1842] 2. The device receives the voice instruction, converts it into digital form and sends it to the server.

[1843] 3. The server uses the Google Speech-to-Text API to convert the speech to text and recognizes it as "Flight 123, climb to 10,000 feet."

[1844] 4. The server uses a natural language processing engine to extract instructions from the text data and generate a predicted action for Flight 123 to climb to 10,000 feet.

[1845] 5. The terminal (aircraft side) sends real-time GPS data such as current altitude and location to the server.

[1846] 6. The server compares the current altitude data with the predicted behavior and monitors whether the ascent is proceeding properly.

[1847] 7. If the server does not act as instructed, it generates an alert saying "Flight 123 is not climbing to 10,000 feet" and sends it to the device.

[1848] 8. The terminal notifies the controller and pilot of this alert, prompting the controller to review the situation.

[1849] Example 2: Emotional state anomaly detection case

[1850] 1. The terminal collects the pilot's voice and behavioral data (e.g., operational errors and voice tremors) in real time and transmits them to the server.

[1851] 2. The server uses an emotion engine to analyze voice and behavioral data and recognize the pilot's emotional state (e.g., high stress).

[1852] 3. If the server detects an abnormal stress state, it generates an "abnormal emotion alert."

[1853] 4. The server sends this abnormal emotion alert to the terminal and notifies the controller and pilot.

[1854] 5. The device will display a message suggesting ways to improve the situation: "The pilot is under high stress. Please take a deep breath and calm down."

[1855] Example prompt sentence:

[1856] Below are some example prompts to input to the generative AI model:

[1857] "What would the system do if the controller instructed Flight 123 to climb to 10,000 feet, but it stopped below 10,000 feet?"

[1858] "Please explain specifically how the system will respond if the pilot exhibits an abnormal emotional state."

[1859] The system of this invention not only detects misunderstandings and operational errors between air traffic controllers and pilots, but also detects abnormal emotional states in real time and makes it possible to deal with them quickly, which is expected to significantly improve aviation safety.

[1860] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1861] Step 1: Receiving and converting voice communication data

[1862] The terminal receives voice communication data between the controller and the pilot in real time.

[1863] Input: Analog voice data between controller and pilot

[1864] Specific Action: Capture audio data using a microphone and receive it through a communication device.

[1865] Output: Audio data converted to digital format

[1866] The terminal converts the received voice data into a digital format and transmits it to the server.

[1867] Input: Analog audio data

[1868] Specific operation: Audio data is digitized by setting the sampling rate and bit depth, and sent to the server using the TCP / IP protocol.

[1869] Output: Digital audio data sent to the server

[1870] Step 2: Extracting instructions

[1871] The server converts the received voice data into text data using a voice recognition engine (e.g., Google Speech-to-Text API).

[1872] Input: Digital audio data

[1873] Specific operation: Passes digital voice data to a voice recognition engine and calls an API to obtain string data.

[1874] Output: Instructions converted into text data

[1875] The server analyzes the text data using a natural language processing engine, extracts the instructions, and stores them in a database.

[1876] Input: Text data

[1877] Specific operation: Parses text data using the NLTK library, extracts commands and keywords, and stores them in a database.

[1878] Output: Extracted instruction data

[1879] Step 3: Generate predicted behavior

[1880] The server generates a predicted behavior of the pilot based on the extracted instruction content.

[1881] Input: Extracted instruction data

[1882] Specific behavior: The instructions are input into the internal algorithm to generate predictive behavior. For example, if the instruction is "Flight 123, climb to 10,000 feet," it will predict that Flight 123 will climb to 10,000 feet.

[1883] Output: Generated predicted behavior data

[1884] Step 4: Collecting GPS data and monitoring behavior

[1885] The terminal (on the aircraft) collects the aircraft's current GPS data in real time and transmits it to the server.

[1886] Input: Real-time GPS data (altitude, location, speed, etc.)

[1887] Specific operation: Data is acquired from the GPS unit installed on the aircraft and sent to the server using the MQTT protocol.

[1888] Output: GPS data sent to the server

[1889] The server analyzes the received GPS data and compares it with predicted behavior to monitor behavior.

[1890] Input: Real-time GPS data, predicted behavior data

[1891] Specific operation: Using a custom algorithm implemented in Python, the received GPS data is compared with the predicted behavior data to determine whether it is normal or abnormal.

[1892] Output: Comparison results and monitoring result data

[1893] Step 5: Anomaly detection and alert generation

[1894] The server compares predicted behavior with actual behavior and detects anomalies.

[1895] Input: Comparison result data

[1896] Specific operation: If the predicted altitude does not match the actual altitude, an abnormality flag is raised.

[1897] Output: Anomaly detection flag and anomaly content data

[1898] If the server detects an abnormality, it immediately generates an alert message and sends it to the terminal.

[1899] Input: Anomaly detection flag and anomaly content data

[1900] Specific behavior: Generate an alert message containing details of the anomaly, encode it in JSON format, and send it to the terminal.

[1901] Output: The alert message sent to the terminal.

[1902] The terminal will then notify the controller and pilot of the alert.

[1903] Input: Alert message

[1904] What it does: Use the display and audio output device to provide a visual and audible alert that "Flight 123 is not climbing to 10,000 feet."

[1905] Output: Alerts sent to controllers and pilots

[1906] Step 6: Emotion Engine in Action

[1907] The terminal collects voice and behavioral data from controllers and pilots and transmits it to a server.

[1908] Input: Real-time audio and behavioral data

[1909] Specific operation: Collects voice and behavioral data through microphones and various sensors and sends it to a server.

[1910] Output: Audio and behavioral data sent to the server

[1911] The server uses an emotion engine to analyze this data and recognize the emotional state.

[1912] Input: Audio and behavioral data

[1913] Specific operation: Using emotion engines such as IBM Watson Tone Analyzer, the system analyzes voice and behavioral data to recognize emotional states.

[1914] Output: Recognized emotional state data

[1915] If the emotional state is determined to be abnormal, the server generates an alert message and notifies the user.

[1916] Input: Emotional state data

[1917] Specific operation: If an abnormal emotional state is detected, an alert message containing details is generated and sent to the device.

[1918] Output: Emotional abnormality alert message sent to the terminal

[1919] The server also generates a message based on the abnormal emotional state, suggesting appropriate steps to take.

[1920] Input: Emotional state data

[1921] Specific Action: Based on the analysis results from the emotion engine, a message is generated suggesting appropriate steps to take (e.g., "Take a deep breath and stay calm").

[1922] Output: Proposal message

[1923] The terminal notifies controllers and pilots of these alert messages and response procedures.

[1924] Input: Emotional abnormality alert message and suggested message

[1925] Specific operation: Display and play notification information using a display and audio playback device.

[1926] Output: Suggestions and emotional anomaly alerts notified to controllers and pilots

[1927] (Application example 2)

[1928] 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."

[1929] Improving the safety of autonomous vehicles is an important challenge for current technology. In particular, it is necessary to properly recognize the emotional state of driver assistants and passengers and respond quickly when an abnormality occurs. Conventional systems have had difficulty understanding passengers' emotional states in real time, detecting abnormalities, and taking countermeasures. Therefore, a new system that can analyze emotional states and support safe driving is needed.

[1930] The identification process by the identification 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 voice communication data between an air traffic controller and an aircraft pilot; means for converting the received voice communication data into text data; means for extracting instructions from the converted text data; means for generating a predicted behavior based on the extracted instructions; means for collecting current position data of the aircraft from a GPS; means for monitoring the actual behavior of the aircraft based on the collected GPS data; means for comparing the monitored behavior of the aircraft with the predicted behavior and detecting an abnormality; means for generating and notifying an alert when an abnormality is detected; means for collecting voice data and behavior data and analyzing the emotional state; and means for generating an alert and suggesting a response procedure when an abnormal emotional state is detected. This makes it possible to grasp the emotional states of the driver's assistant and passengers in real time, quickly detect abnormalities, and take appropriate measures.

[1931] A "controller" is a person whose job is to monitor and direct the operation of aircraft and vehicles.

[1932] "Aircraft" is a general term for any mechanical device that can fly.

[1933] A "pilot" is a person qualified to operate an aircraft.

[1934] "Voice communication data" means information in digital form that contains voice.

[1935] "Text data" means written information in digital form.

[1936] "Instruction content" is information for instructing a specific action.

[1937] "Predicted behavior" refers to behavior that the system generates based on the instructions it receives.

[1938] "Location Data" means geographic location information obtained using technologies such as GPS.

[1939] "GPS" is an abbreviation for Global Positioning System, a system for determining locations on Earth with high accuracy.

[1940] "Actual behavior" refers to the actions that a system or machine actually takes.

[1941] An "abnormality" is a state in which predicted behavior differs from actual behavior.

[1942] An "alert" is a warning issued when an abnormality is detected.

[1943] A "notification" is a means of conveying specific information.

[1944] "Audio data" is a general term for digital information that includes audio.

[1945] "Behavioral data" is digital information about the actions taken by a system or machine.

[1946] "Emotional state" refers to a person's emotional state.

[1947] An "abnormal emotional state" is an emotional state that is different from the normal state.

[1948] "Response procedures" refer to the actions and procedures to be taken when an abnormality occurs.

[1949] Overall system configuration

[1950] This invention is a system that analyzes voice and behavioral data in real time to detect abnormalities in order to improve the safety of autonomous vehicles. In particular, it analyzes the emotional state of the driver's assistant and passengers and provides appropriate response procedures in the event of an abnormality. It also incorporates location data collection using GPS.

[1951] Program processing explanation

[1952] The system's main hardware includes a smartphone, smart glasses, and a GPS module, while the software uses Python, the speech_recognition library, and the requests library.

[1953] Receiving and converting voice communication data

[1954] The server receives the driver's assistant's voice communication data in real time and converts it into text data. Specifically, it uses the smartphone's microphone function and a speech recognition engine (for example, the speech_recognition library) to convert the voice into text.

[1955] Extracting instruction content and generating predicted actions

[1956] The server extracts the instructions from the converted text data and generates predicted actions based on the instructions. This information is stored in a database and used for analytical processing.

[1957] GPS data collection and behavior monitoring

[1958] The terminal (on the vehicle side) collects the vehicle's current GPS data (position, speed, etc.) in real time and sends it to the server, which analyzes this GPS data and compares the actual behavior with the predicted behavior.

[1959] Anomaly detection and alert generation

[1960] The server compares predicted and actual behavior and immediately generates an alert if an abnormality is detected, which is then sent to the driver assistant via a smartphone or smart glasses.

[1961] Emotion Engine Operation

[1962] The server collects voice and behavioral data and analyzes them using an emotion engine. If the emotional state is determined to be abnormal, an alert is generated and a response procedure is proposed. This process uses a generative AI model, and the results are sent to the driver's assistant's smartphone or other device.

[1963] Specific example explanation

[1964] For example, if the driver assistant is feeling stressed, the system operates as follows:

[1965] 1. The driver assistant issues a voice command such as, "I feel the vehicle speed is a little too fast."

[1966] 2. This audio is collected through the smartphone's microphone and sent to a server.

[1967] 3. The server converts the speech into text and analyzes it using an emotion engine. The analysis results detect stress and anxiety.

[1968] 4. The server generates an alert based on this information and sends it to the smartphone.

[1969] 5. Your smartphone will display an alert such as "Driver assistant is experiencing high stress, we recommend reducing speed."

[1970] Prompt Sentence Examples

[1971] For example, a specific example of a prompt sentence to be input into a generative AI model is, "Convert this voice data into text, analyze the user's emotional state, and notify me if any abnormalities are found."

[1972] Such a system would enable autonomous vehicles to monitor the emotional state of their occupants while driving, quickly detect and respond to any abnormalities, and ultimately provide a safer driving environment.

[1973] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1974] Step 1:

[1975] The user inputs voice data using the microphone on the smartphone, and the input voice data is collected from the driver's assistant.

[1976] Step 2:

[1977] The device transmits the received voice data in real time to a server, where it is converted into a digital format and transmitted over the internet.

[1978] Step 3:

[1979] The server converts the received voice data into text data using a voice recognition engine (for example, the speech_recognition library). The input is digital voice data, and the output is text data.

[1980] Step 4:

[1981] The server extracts the instructions from the converted text data. Natural language processing technology is used to analyze the text data for specific instructions and emotional states. The input is the text data, and the output is the analysis results of the instructions and emotional states.

[1982] Step 5:

[1983] The server generates a predicted behavior based on the extracted instruction content. For example, if the instruction is "slow down," it predicts the behavior of slowing down to an appropriate speed. The input is instruction content data, and the output is predicted behavior data.

[1984] Step 6:

[1985] The terminal (vehicle side) collects current location data using a GPS module and transmits it to the server in real time. The input is GPS data, and the output is the transmitted current location data.

[1986] Step 7:

[1987] The server monitors the vehicle's actual behavior based on the collected GPS data. It compares the predicted behavior with the actual behavior and checks for any abnormalities. The inputs are the predicted behavior data and GPS data, and the output is the result of anomaly detection.

[1988] Step 8:

[1989] The server generates an alert when an anomaly is detected. The alert is generated as a specific text message. The input is the anomaly detection data, and the output is the alert message.

[1990] Step 9:

[1991] The terminal notifies the driver assistant of the generated alert message. The alert message is displayed visually or audibly using a smartphone or smart glasses. The input is the alert message, and the output is a visual or audio notification.

[1992] Step 10:

[1993] The server collects voice data and behavioral data and analyzes the emotional state using an emotion engine. The input is the voice data and behavioral data, and the output is the analysis result of the emotional state.

[1994] Step 11:

[1995] If the server detects an abnormal emotional state, it generates an alert and suggests a course of action. It uses a generative AI model to suggest an appropriate course of action. The input is emotional state data, and the output is an alert message with a course of action.

[1996] Step 12:

[1997] The terminal notifies the driver assistant of the generated alert message and the response procedures via a smartphone or smart glasses. The input is the alert message with the response procedures, and the output is a visual or audio notification.

[1998] 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.

[1999] 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.

[2000] 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 robot 414.

[2001] 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.

[2002] FIG. 9 is a diagram illustrating 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 actions 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.

[2003] 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.

[2004] 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).

[2005] 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.

[2006] 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."

[2007] 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.

[2008] 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).

[2009] 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.

[2010] 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.

[2011] 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.

[2012] 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.

[2013] 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.

[2014] 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.

[2015] 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.

[2016] 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.

[2017] 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.

[2018] 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.

[2019] The following is further disclosed regarding the above embodiment.

[2020] (Claim 1)

[2021] means for receiving voice communication data between the air traffic controller and the pilot of the aircraft;

[2022] means for converting received voice communication data into text data;

[2023] means for extracting instruction content from the converted text data;

[2024] A means for generating a predicted behavior based on the extracted instruction content;

[2025] means for collecting current aircraft position data from a GPS;

[2026] A means of monitoring the actual behavior of aircraft based on the collected GPS data; and

[2027] means for comparing monitored aircraft behavior with predicted behavior to detect anomalies; and

[2028] A means for generating and notifying an alert when an abnormality is detected;

[2029] A system including:

[2030] (Claim 2)

[2031] 10. The system of claim 1, wherein the voice communication data is received, converted, and analyzed in real time.

[2032] (Claim 3)

[2033] The system of claim 1, wherein the comparison of the predicted behavior with the monitored aircraft behavior utilizes generative AI.

[2034] "Example 1"

[2035] (Claim 1)

[2036] means for receiving voice communication data between the air traffic controller and the pilot of the aircraft;

[2037] means for converting received voice communication data into text data;

[2038] means for extracting instruction content from the converted text data;

[2039] A means for generating a predicted behavior based on the extracted instruction content;

[2040] means for collecting current position data of the aircraft from a satellite positioning system;

[2041] a means for monitoring the actual behavior of the aircraft based on the collected location data;

[2042] means for comparing monitored aircraft behavior with predicted behavior to detect anomalies; and

[2043] means for generating and notifying warning information when an abnormality is detected;

[2044] means for automatically analyzing aircraft instructions;

[2045] means for displaying the generated warning information on a terminal;

[2046] A system including:

[2047] (Claim 2)

[2048] 10. The system of claim 1, wherein the voice communication data is received, converted, and analyzed in real time.

[2049] (Claim 3)

[2050] 10. The system of claim 1, wherein the comparison of the predicted behavior to the monitored aircraft behavior uses a generative AI model.

[2051] "Application Example 1"

[2052] (Claim 1)

[2053] means for receiving voice communication data between the controller and the operator of the vehicle;

[2054] means for converting received voice communication data into text data;

[2055] means for extracting instruction content from the converted text data;

[2056] A means for generating a predicted behavior based on the extracted instruction content;

[2057] means for collecting current location data of the vehicle from the location information acquisition means;

[2058] means for monitoring the actual behavior of the conveyance based on the collected location data;

[2059] means for comparing monitored vehicle behavior with predicted behavior to detect anomalies;

[2060] means for generating a notification when an anomaly is detected;

[2061] means for displaying the instruction content and location data on the smart device;

[2062] A system including:

[2063] (Claim 2)

[2064] 10. The system of claim 1, wherein the voice communication data is received, converted, and analyzed in real time.

[2065] (Claim 3)

[2066] 10. The system of claim 1, wherein the comparison of the predicted behavior to the monitored vehicle behavior utilizes generative AI.

[2067] "Example 2: Combining Emotion Engines"

[2068] (Claim 1)

[2069] means for receiving voice communication data between the air traffic controller and the pilot of the aircraft;

[2070] means for converting the received voice communication data into a digital format and transmitting the digital data to a server;

[2071] A means for converting voice communication data into text data by a server;

[2072] means for extracting instruction content from the converted text data and storing the content in a database;

[2073] A means for generating a predicted behavior based on the extracted instruction content;

[2074] means for collecting the current position of the aircraft from the GPS and transmitting the same to a server;

[2075] A server analyzes the collected GPS data and monitors actual behavior by comparing it with predicted behavior;

[2076] means for detecting anomalies when monitored aircraft behavior differs from predicted behavior;

[2077] When an abnormality is detected, an alert is generated and notified to the terminal.

[2078] A means for analyzing voice and behavioral data of controllers and pilots using an emotion engine to recognize their emotional states;

[2079] a means for generating and notifying an alert when an abnormal emotional state is detected;

[2080] A means for suggesting appropriate coping procedures based on the abnormal emotional state;

[2081] A system including:

[2082] (Claim 2)

[2083] 10. The system of claim 1, wherein the system receives, converts, and analyzes voice communication data and emotion data in real time.

[2084] (Claim 3)

[2085] 10. The system of claim 1, wherein the system uses generative AI when comparing predicted behavior to monitored aircraft behavior.

[2086] "Application example 2 when combining emotion engines"

[2087] (Claim 1)

[2088] means for receiving voice communication data between the air traffic controller and the pilot of the aircraft;

[2089] means for converting received voice communication data into text data;

[2090] means for extracting instruction content from the converted text data;

[2091] A means for generating a predicted behavior based on the extracted instruction content;

[2092] means for collecting current aircraft position data from a GPS;

[2093] A means of monitoring the actual behavior of aircraft based on the collected GPS data; and

[2094] means for comparing monitored aircraft behavior with predicted behavior to detect anomalies; and

[2095] A means for generating and notifying an alert when an abnormality is detected;

[2096] means for collecting voice data and behavioral data and analyzing emotional states;

[2097] A means for generating an alert and suggesting a procedure for dealing with an abnormal emotional state when such an abnormal emotional state is detected;

[2098] A system including:

[2099] (Claim 2)

[2100] 10. The system of claim 1, wherein the voice communication data and emotional state are received, transformed, and analyzed in real time.

[2101] (Claim 3)

[2102] The system of claim 1, wherein the comparison of the predicted behavior with the monitored aircraft behavior utilizes generative AI. [Explanation of symbols]

[2103] 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 voice communication data between the air traffic controller and the pilot of the aircraft; means for converting received voice communication data into text data; means for extracting instruction content from the converted text data; A means for generating a predicted behavior based on the extracted instruction content; means for collecting current aircraft position data from a GPS; A means of monitoring the actual behavior of aircraft based on the collected GPS data; and means for comparing monitored aircraft behavior with predicted behavior to detect anomalies; and A means for generating and notifying an alert when an abnormality is detected; A system including:

2. 10. The system of claim 1, wherein said voice communication data is received, converted, and analyzed in real time.

3. The system of claim 1 , wherein the comparison of the predicted behavior with the monitored aircraft behavior utilizes generative AI.

Images