system

Abstract

We provide the system. [Solution] A means for integrating weather information, operational information, road surface condition information, and information on past accidents, A means for analyzing operational risks based on the aforementioned integrated information, A means for selecting appropriate safety measures based on the aforementioned risk analysis, A means of generating selected safety measures in multiple languages, Means for transmitting the generated information to the transporter or pilot, A means of proposing alternative routes in real time, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the current air traffic management system, it is difficult to effectively integrate changes in weather conditions, aircraft operation plans, runway operation status, and past accident data and analyze them in real time. As a result, in risk detection and safety measure proposals, human errors and delays in information transmission may occur, threatening the safety of air traffic. In particular, communication inconsistencies between pilots and air traffic controllers using different languages increase risks. Due to such problems, it is necessary to improve the safety and efficiency of air traffic.

Means for Solving the Problems

[0005] This invention provides a means for integrating weather information, aircraft operation information, runway operation information, and information on past accidents. It includes means for analyzing risks based on this integrated information. Furthermore, it provides means for selecting appropriate safety measures based on this risk analysis, thereby detecting potential risks and responding quickly and accurately. It also includes means for generating the selected safety measures in multiple languages ​​and transmitting them to air traffic controllers or aircraft pilots. In this way, it eliminates obstacles to communication between different languages ​​and improves the safety and efficiency of air traffic worldwide.

[0006] "Weather information" refers to data including atmospheric conditions and forecasts necessary for determining the safety and efficiency of aircraft operations.

[0007] "Aircraft operation information" refers to aircraft flight plans, schedules, routes, and other important operational data.

[0008] "Runway operation information" refers to data that includes runway usage, reservations, and maintenance information for a specific airport.

[0009] "Information on past accidents" refers to data including the history of aircraft accidents and incidents, which is useful for improving safety measures.

[0010] "Integrating" refers to the act of combining data from different formats and sources and organizing it according to certain standards.

[0011] "Risk analysis" is the process of evaluating and predicting potential dangers based on collected data.

[0012] "Selecting safety measures" means determining the most effective defensive or countermeasures for the detected risks.

[0013] "Generating in multiple languages" means translating information into one or more different languages ​​and providing it in an understandable format.

[0014] "To send" refers to the act of transferring information or data to a recipient. [Brief explanation of the drawing]

[0015] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine.

Embodiments for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0019] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0028] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0035] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0036] The system for implementing this invention is built around the roles of server, terminal, and user. First, the server collects weather information, aircraft operation information, runway operation information, and information on past accidents from various external databases and feeds. This information is acquired in real time and integrated within the server.

[0037] The server uses machine learning algorithms to analyze integrated information and assess risks. This analysis is based on historical data patterns and identifies potential risks related to aircraft operations. Based on this risk assessment, the server automatically selects the necessary safety measures. The selected safety measures are translated into multiple languages.

[0038] Next, the server sends the translated safety information to a terminal. This terminal is a device used by air traffic controllers and pilots. The terminal displays the received information appropriately and provides the user with immediate operational instructions. The air traffic controllers and pilots, as users, review the information provided through the terminal and take action as necessary.

[0039] A concrete example is when a server analyzes ground weather information and detects that a particular runway is dangerous due to strong winds. Based on this information, the server suggests an alternative runway and sends this information to the terminal in multiple languages. The pilot, as the user, checks the notification received on the terminal and follows the instructions to make a safe landing. In this way, the system can ensure the safety of air traffic inside and outside the airport and enable efficient operations.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The server periodically collects weather information, aircraft operation information, runway operation information, and historical accident information from external databases and feeds. The server retrieves data via APIs and ensures data reliability by verifying statistical data consistency.

[0043] Step 2:

[0044] The server integrates information based on the data it collects. It converts data in different formats to a standard format and stores it in an integrated database. This ensures the timeliness and consistency of the data.

[0045] Step 3:

[0046] The server initiates risk analysis using integrated data. Machine learning algorithms are used to assess similarities to past accident and incident patterns and identify potential risks. The analysis results are scored, and the risk level is expressed numerically.

[0047] Step 4:

[0048] The server selects appropriate safety measures based on the analysis results. The selection criteria include risk scores, operational status, and weather conditions, and the optimal measures are automatically determined.

[0049] Step 5:

[0050] The server translates selected security measures into multiple languages. An automatic translation system is used to generate notifications and manuals in an internationally understandable format.

[0051] Step 6:

[0052] The server sends the translated safety information to the corresponding terminal. The terminal is a device used by air traffic controllers and pilots, and after receiving the data from the server, it displays it to the user in an appropriate format.

[0053] Step 7:

[0054] Air traffic controllers and pilots, as users, review the information received via their terminals. Based on the safety measures presented, they adjust and decide on flight operations. Feedback is provided to the system as needed, leading to further improvements.

[0055] (Example 1)

[0056] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0057] In modern air traffic management, real-time information gathering and analysis regarding weather and aircraft operational status are essential. However, there is a lack of effective systems for extracting appropriate risk information from vast amounts of data and responding quickly. Therefore, there is a need for means to effectively mitigate the risk of aviation accidents. Furthermore, ensuring the accuracy of information transmission in international aircraft operations using multiple languages ​​is a major challenge.

[0058] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0059] In this invention, the server includes query means for collecting information, means for integrating and preprocessing the collected information, and means for executing a machine learning algorithm for evaluating risk based on the integrated information. This enables real-time data updates and rapid decision-making based on appropriate risk assessment. Furthermore, a multilingual translation function facilitates international information sharing.

[0060] A "querying method" refers to a communication interface used to retrieve information from external databases or information sources.

[0061] "Preprocessing" refers to functions that perform data preprocessing, such as imputing missing values ​​and removing noise, to prepare the collected data for analysis.

[0062] A "machine learning algorithm" is a computational method used to predict risk from new data based on past data patterns.

[0063] "Translation means" refers to a function for converting specific safety information into multiple languages, thereby enabling international information sharing.

[0064] "Means of communication" refers to a network interface used to transmit processed information to a receiving device or control system.

[0065] A "receiving device" refers to a device used by users such as air traffic controllers and pilots to receive and visually confirm information.

[0066] A description of the embodiment for carrying out the invention will be provided.

[0067] The primary roles in realizing this system are played by the server, terminals, and users. The server first uses query mechanisms to acquire weather information, aircraft operation information, runway operation information, and data on past accidents from external sources and databases. This process requires data client devices connected to the internet, utilizing data access points via APIs.

[0068] The server then uses methods to integrate and preprocess the collected data. Specifically, it uses programming languages ​​such as Python and the Pandas library to impute missing values ​​and remove noise. It also organizes the data into time series to ensure real-time performance.

[0069] Risk assessment utilizes a method where the server executes machine learning algorithms. Machine learning libraries such as TENSORFLOW® and scikit-learn are used to analyze past data patterns and identify risk factors. Based on this, the server calculates a risk score for each piece of information, which is then used as a basis for decision-making in the next step.

[0070] Based on the evaluation results, the server selects security measures and uses an automated translation service to translate this information into multiple languages. Using services such as Google Cloud Translation API, the selection results are translated into multiple languages ​​and made accessible to users of various languages.

[0071] The server then sends the translated information to a terminal. This terminal is typically used by air traffic controllers and pilots and usually has specialized air traffic control software installed. As a result, users can view the information provided in real time through the terminal and take the instructed actions.

[0072] As a concrete example, let's consider a scenario where a specific runway is deemed unsafe due to strong winds caused by changes in weather information. In this case, the server proposes an alternative runway, translates that information into multiple languages, and sends it to the terminal. The pilot, as the user, receives the notification via the terminal and adjusts their flight route towards a safe landing point.

[0073] An example prompt illustrating the operation of the generated AI model is, "Perform a risk assessment and propose safety measures based on weather conditions and flight information at a specific airport." Based on this prompt, the AI ​​model will perform a specific risk assessment and propose safety measures.

[0074] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0075] Step 1:

[0076] The server uses query methods to collect information. Inputs include requests for weather information, aircraft operation information, runway operation information, and information on past accidents. The server retrieves this data via external databases or APIs. The output is a set of collected raw data. Specifically, the server accesses API endpoints over the network and receives data in JSON format.

[0077] Step 2:

[0078] The server uses means to integrate and preprocess the collected data. The input is the raw dataset collected in step 1. The server organizes the data, imputes missing values, and removes noise. The output is a normalized dataset. Specifically, the server uses the Pandas library to impute missing values ​​in the data with the mean and to detect and remove outliers.

[0079] Step 3:

[0080] The server runs a machine learning algorithm to assess risk on normalized data. The input is the normalized dataset generated in step 2. The server calculates a risk score based on a model learned from historical data. The output is the risk assessment result for each aviation option. Specifically, the server uses TensorFlow to run a neural network and generate scores under specific weather conditions.

[0081] Step 4:

[0082] The server selects the necessary safety measures based on the risk assessment and translates them into multiple languages. The input is the risk assessment result from step 3. The server selects the optimal measures and translates them into multiple languages ​​via a translation service. The output is the translated safety measures information. Specifically, the server uses the Google Cloud Translation API to translate the selected information from English into other major languages.

[0083] Step 5:

[0084] The server sends the translated information to the terminal. The input is the multilingual security information generated in step 4. The server transmits this information to the user's terminal via wireless communication. The output is information in a format that can be displayed on the terminal. Specifically, the server securely pushes the data using the HTTPS protocol, triggering a notification on the terminal.

[0085] Step 6:

[0086] The user receives information provided through the terminal and takes action according to the instructions. The input is the notification received on the terminal in step 5. The user checks the information on the terminal screen and selects the necessary action. The output is the specific action based on the execution of safety measures. As a specific action, the pilot adjusts the instruments to the suggested alternative runway and ensures a safe landing path.

[0087] (Application Example 1)

[0088] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0089] Currently, a challenge in operating autonomous vehicles is the need to quickly grasp weather conditions and road surface conditions and issue operational instructions based on predicted risks. Conventional systems lack real-time information updates, making it difficult to take appropriate measures quickly. Furthermore, in situations where multilingual support is essential, information may not be translated properly, potentially compromising operational safety. As a result, the safety and efficiency of autonomous vehicles are not adequately ensured, and effective means to improve this are needed.

[0090] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0091] In this invention, the server includes means for integrating weather information, operational information, road surface condition information, and information on past accidents; means for analyzing operational risks; and means for proposing alternative routes in real time. This enables the provision of rapid and accurate safety measures and operational instructions to autonomous vehicles, resulting in safe and efficient driving.

[0092] "Weather information" refers to data related to the natural environment, such as precipitation, wind speed, and temperature, and is necessary information for evaluating the operational environment.

[0093] "Operational information" refers to traffic-related data and various status information, such as the vehicle's current location, speed, and route.

[0094] "Road surface condition information" refers to information that indicates the condition of the road and the presence or absence of obstacles, and is essential information for safe driving.

[0095] "Information regarding past accidents" refers to data that includes details of previously occurring accidents, their causes, and their impact.

[0096] "Methods for analyzing operational risks" refer to methods for identifying potential risk factors and evaluating their impact based on various collected information.

[0097] "Methods for proposing alternative routes" refer to the process of finding and proposing safe detours when the current route is deemed dangerous.

[0098] "A means of continuously updating in real time" refers to a technology that keeps ever-changing information up-to-date and reflects it immediately.

[0099] A "machine learning algorithm" is a technology that learns patterns based on past data and uses that knowledge to make predictions and classifications on new data.

[0100] "Multilingual generation methods" refer to technologies that translate information into multiple languages ​​in order to provide the same information to users who speak different languages.

[0101] This system supports the safe and efficient operation of autonomous vehicles. The server collects and integrates weather information, operational information, road surface condition information, and information on past accidents. This data is retrieved in real time from external databases and APIs and integrated within the server.

[0102] The server processes the integrated information and uses machine learning algorithms to analyze operational risks. This utilizes machine learning platforms such as TensorFlow. It learns patterns from past accident data and identifies potential risks in current operations. Based on this risk assessment, the server selects necessary safety measures and translates them into multiple languages.

[0103] Next, the server provides real-time suggestions for routes and alternative routes. Using the Google Maps API and other tools, it calculates the optimal route considering current traffic conditions. It then sends the results to the terminal, providing instructions to the autonomous vehicle.

[0104] The terminal displays received information on the vehicle's display and audio system, providing responsive operational instructions to the driver and vehicle control system. The user, either the driver or the vehicle, follows the terminal's instructions to ensure safe and optimal operation. This significantly improves the safety and efficiency of the autonomous vehicle.

[0105] For example, if a sunny day is forecast but unexpected heavy rain occurs, the system can immediately assess the risk, suggest alternative routes to avoid roads with many puddles, and display instructions to encourage drivers to slow down.

[0106] An example of a prompt sentence to input into the generating AI model would be, "Please suggest the optimal route for safely arriving at the destination in an autonomous vehicle during heavy rain."

[0107] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0108] Step 1:

[0109] The server collects weather information, traffic information, road surface condition information, and information on past accidents in real time from external databases and APIs. This data is obtained in JSON format and integrated in preparation for subsequent processing. It receives responses from various APIs as input and generates an integrated dataset as output.

[0110] Step 2:

[0111] The server uses an integrated dataset to analyze operational risks with machine learning algorithms based on TensorFlow. It accepts the integrated dataset as input and outputs a risk assessment score based on pattern recognition and predictive models. This identifies potential risks related to weather, traffic conditions, and road conditions.

[0112] Step 3:

[0113] The server uses the Google Maps API to calculate alternative routes based on the risk assessment score. It receives the risk assessment score and current route information as input and outputs a safe and efficient alternative route. This ensures that the vehicle is directed to a route that allows it to reach its destination more safely.

[0114] Step 4:

[0115] The server translates the selected alternative route and operational instructions into multiple languages ​​as needed. In this step, it receives alternative route information and the selected language as input and outputs multilingual operational instructions. The translated information is provided to the user in a human-readable format.

[0116] Step 5:

[0117] The terminal displays translated operational instructions received from the server and provides instructions to the user or vehicle control system via voice or display. It receives translated operational instructions as input and immediately notifies and outputs them to the user. This allows drivers to operate safely and efficiently based on the instructions.

[0118] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0119] The system for implementing this invention consists primarily of a server, terminals, users, and an emotion engine. First, the server collects and integrates weather information, aircraft operation information, runway operation information, and past accident information from various external databases. Based on this integrated information, the server uses machine learning algorithms to analyze risks and select safety measures appropriate for the specific situation.

[0120] The selected safety measures are optimized by an emotion engine based on the user's emotional state. The server evaluates the emotions of the user, such as an air traffic controller or pilot, in real time through voice analysis. Based on this emotional state, the content and presentation method of notifications are automatically adjusted and transmitted in a way that facilitates user understanding.

[0121] As a concrete example, consider a scenario where a server detects a risk to runway use due to strong winds and issues a warning. When the emotion engine detects a high level of stress from the pilot's voice, the server provides a more detailed and careful explanation in the notification. In this way, the system can respond flexibly according to the user's psychological state.

[0122] The terminal displays emotion-based notifications sent from the server, providing users with clear guidance for action. Users review the information provided through the terminal and take safety measures as needed. This feedback is evaluated by an emotion engine and used as data for future system improvements. This process allows the system to improve air traffic safety while reducing the psychological burden on users.

[0123] The following describes the processing flow.

[0124] Step 1:

[0125] The server collects weather information, aircraft operation information, runway operation information, and historical accident information from various data sources. The server integrates this data and stores it in a database, enabling real-time access.

[0126] Step 2:

[0127] The server uses the integrated data to run machine learning algorithms and initiate risk analysis. It compares current incident data with past incident data to identify potential risks in the current operational situation. Risk levels are scored and prioritized.

[0128] Step 3:

[0129] The server selects appropriate safety measures based on the results of the risk analysis. The selection criteria include the risk level and scope of impact, and the specific measures are determined and recorded.

[0130] Step 4:

[0131] The emotion engine analyzes the user's voice and behavioral data to evaluate the user's emotional state. If stress or tension is high, the emotion engine records this state and provides feedback to the server.

[0132] Step 5:

[0133] The server receives feedback from the emotion engine and adjusts the content and tone of safety alerts according to the emotional state. For example, if a high stress level is detected, detailed explanations and steps will be added to the alert.

[0134] Step 6:

[0135] The server sends optimized safety notifications to the terminal. The terminal is a device used by air traffic controllers and pilots, and it has the function to display the information from the server appropriately.

[0136] Step 7:

[0137] The user reviews the information provided through their device and takes the instructed safety measures as needed. User behavior and responses are fed back into the system to help with continuous improvement.

[0138] (Example 2)

[0139] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0140] Improving air traffic safety requires real-time information updates and accurate risk assessment, but conventional systems lacked sufficient capabilities in these areas. Furthermore, information delivery was not optimized based on the user's emotional state, creating a risk that important information might not be properly communicated.

[0141] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0142] In this invention, the server includes means for integrating weather information, aircraft operation information, air route operation information, and information on past incidents; means for analyzing risks based on the integrated information; and means for optimizing selected safety measures based on an algorithm that recognizes emotions. This enables flexible information transmission in accordance with the user's emotional state and rapid and accurate risk assessment.

[0143] "Weather information" refers to data about weather conditions, including information such as the state of the sky, temperature, humidity, wind speed, and wind direction.

[0144] "Aircraft operation information" refers to data related to the operation of aircraft, such as departure, arrival, route, speed, and altitude.

[0145] "Air route operation information" refers to information about the usage status, closure status, available times, and restrictions of air routes.

[0146] "Past incidents" refers to records of aviation-related accidents and near misses that have occurred in the past.

[0147] "Means of integrating information" refers to the process or mechanism for organizing information obtained from different data sources and combining it into a single, unified format.

[0148] "Means of risk analysis" refer to algorithms and methods for predicting and identifying potential risks based on integrated information.

[0149] "Means for selecting safety measures" refers to methods for determining the optimal response to an analyzed hazard.

[0150] An "emotion recognition algorithm" is a computational method for analyzing and recognizing emotions from a person's voice and facial expressions.

[0151] An embodiment of this invention consists of a server, a terminal, a user, and a sentiment analysis engine. The server retrieves weather information, aircraft operation information, air route operation information, and data on past incidents from an external database. This is done using the Python requests library. The server stores the collected data in a Pandas DataFrame and integrates the data using the merge function. Unnecessary data is filtered at this stage.

[0152] The server runs a machine learning model using the Scikit-learn library to analyze risks based on the integrated data. This model is pre-trained on historical data. Based on the risk assessment results, the server selects appropriate safety measures from the database, and these safety measures are optimized by a sentiment analysis engine.

[0153] The emotion analysis engine uses LibROSA for speech processing to acquire voice data from users, such as air traffic controllers and aircraft operators. The acquired voice data is analyzed through a TensorFlow deep learning model to evaluate the user's emotional state. Based on this information, the content and format of notifications are optimized.

[0154] The terminal displays optimized notifications sent from the server. The user checks the notifications on the terminal and takes specific actions. For example, if the server detects a risk of strong winds and sends a notification, the notification will appear as a pop-up on the terminal and will also be announced audibly. If the user, who is the aircraft operator, checks this notification, they will be required to adjust their actions as instructed.

[0155] User behavior and its consequences are collected via the device as feedback and stored in a server database. This feedback is used to improve the sentiment analysis engine and risk analysis model.

[0156] A concrete example of a prompt message would be: "Based on the latest weather data and aircraft operation information, please generate safety measures and suggest notification content tailored to the user's emotional state."

[0157] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0158] Step 1:

[0159] The server collects weather information, aircraft operation information, air route operation information, and past trouble information from an external database. It receives this information, obtained from an API, as input and extracts the data using the Python requests library. The output is a Pandas DataFrame containing the various types of information. Specifically, it uses asynchronous processing to quickly retrieve information and store it in the DataFrame.

[0160] Step 2:

[0161] The server runs a machine learning model to analyze risk based on information integrated into a Pandas DataFrame. The integrated data obtained in the previous step is used as input. A random forest model using Scikit-learn is applied to predict risk. The output is a list of situations where risk has been identified. The model is pre-trained and tuned using historical data.

[0162] Step 3:

[0163] The server selects appropriate safety measures from the database based on the identified risks. Using the risk analysis results as input and referencing the safety measures database, it determines the optimal measures to address the situation. The output is a list of selected safety measures. Here, a data matching algorithm is used to identify recommended measures for each risk.

[0164] Step 4:

[0165] The emotion analysis engine evaluates emotional states using user voice input. The input consists of real-time voice data from air traffic controllers and aircraft operators. Voice features are extracted using LibROSA and analyzed by an emotion recognition model built with TensorFlow. The output is a numerical evaluation of the emotional state. Here, features such as voice pitch and tempo are calculated, and the model evaluates emotions such as stress and tension.

[0166] Step 5:

[0167] The server optimizes the content and format of notifications based on an assessment of the user's emotional state. The emotional assessment obtained in the previous step is used as input. Notifications are tailored to be easily understood by the user, with particularly important information highlighted. The output is the optimized notification message. Specifically, HTML / CSS is used to modify the notification layout for better readability.

[0168] Step 6:

[0169] The terminal displays notifications sent from the server using a dedicated application. The input is an optimized notification message from the server. The notification is displayed as a pop-up on the terminal screen, and the content can also be confirmed via audio output. The output is the notification content that the user can visually confirm. A user-friendly interface is provided using a GUI framework.

[0170] Step 7:

[0171] The user takes specific actions based on the notification and provides feedback via the device. The input is the content of the notification displayed on the device. The device has a feedback input function, where the user inputs the actions taken and their results. The output is the feedback data, which is stored in the server's database and used to improve the algorithm in the future.

[0172] (Application Example 2)

[0173] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0174] In modern homes, providing optimal environmental adjustments and household support tailored to the emotional state of residents is crucial for improving their quality of life. However, conventional technologies have struggled to accurately grasp individual emotional states and automatically provide flexible responses based on them. This invention solves the problem of improving quality of life by analyzing residents' emotional states in real time and providing optimal action suggestions accordingly.

[0175] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0176] In this invention, the server includes means for integrating weather data, flight data, operational data, and historical case information; means for analyzing risks based on the integrated data; and means for analyzing the user's state and optimizing notification content. This makes it possible to accurately grasp the emotional state of residents in real time and propose optimal household support and environmental adjustments based on that.

[0177] "Weather data" refers to information related to weather, including data on environmental conditions such as temperature, humidity, and wind speed.

[0178] "Flight data" refers to information related to the operation status of aircraft and transportation services, including departure and arrival times, routes, and operational status.

[0179] "Operational data" refers to information about the usage and performance of a specific system or piece of equipment, including data on its operational status and maintenance history.

[0180] "Historical case information" refers to data about past incidents and episodes, including insights and lessons learned from past events.

[0181] "Risk analysis" is the process of evaluating potential dangers and problems based on integrated data, and analyzing their probability of occurrence and impact.

[0182] "Analyzing the user's condition" is the process of evaluating the user's emotions and psychological state using data, and then deciding on appropriate responses based on the results.

[0183] "Optimizing notification content" means adjusting the content and method of notifications provided to users based on the analyzed information, according to the situation.

[0184] The system implementing this invention consists primarily of a server, terminals, users, and an emotion engine. The system aims to analyze the emotional state of residents in real time and provide optimal support accordingly.

[0185] The server acquires data from audio and images collected within the home via smart devices. This data is analyzed using a TensorFlow-based emotion analysis model to determine the user's emotional state (stress level, relaxation level, etc.). Based on this analysis, the server utilizes an action selection module to suggest the most appropriate actions for the resident. Here, various environmental adjustments are suggested, such as playing music, adjusting lighting, and prioritizing household chores, using smart speaker technologies like Google Home® or Amazon Alexa.

[0186] The system's terminals display notifications sent from the server and present their content to residents in descending order of priority. This makes it easier for residents to select recommended actions. Simultaneously, resident feedback is collected and sent to the server, improving the accuracy of future action suggestions. This feedback data is used in real time to optimize the system's sentiment analysis model and action selection module.

[0187] For example, if the system analyzes that a resident is experiencing stress, it will automatically play relaxing music tailored to that resident's preferences. Additionally, the server uses an AI model to generate prompts such as, "This user appears to be stressed. Please suggest a relaxing action suitable for them," and uses this to select the appropriate action.

[0188] In this way, the server can comprehensively improve the quality of life for residents by enabling real-time data analysis and user-oriented notification optimization.

[0189] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0190] Step 1:

[0191] The server acquires audio and image data from smart devices within the home. Specifically, it receives input signals from smart speakers and cameras. This data serves as the source material for analyzing emotional states.

[0192] Step 2:

[0193] The server inputs the received data into an emotion analysis model using TensorFlow to analyze the residents' emotional state. Here, stress levels and emotional intensity are quantified based on factors such as voice tone and facial expression changes. Data processing includes feature extraction based on voice analysis and detection of facial expression changes through image processing.

[0194] Step 3:

[0195] Based on the analysis results, the server uses a generative AI model to generate prompt messages. Specifically, it might create instructions such as, "This user appears to be stressed. Please suggest relaxing actions suitable for them." This prompt provides the necessary context for selecting an action.

[0196] Step 4:

[0197] The device receives notifications sent from the server and displays them on the user screen. These notifications offer suggestions such as playing relaxing background music or automatically adjusting the lighting. The notifications include specific action guidelines, presented in a format that the user can intuitively understand.

[0198] Step 5:

[0199] Users provide feedback on actions suggested via their device. This feedback is provided through touch operations or voice input. The feedback data is sent to a server and used to improve the accuracy of future action suggestions.

[0200] Step 6:

[0201] The server analyzes the collected feedback and updates the training datasets for the sentiment analysis model and the generative AI model. This process forms the basis for the continuous improvement of the system and for providing personalized services to users.

[0202] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0203] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0204] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0205] [Second Embodiment]

[0206] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0207] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0208] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0209] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0210] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0211] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0212] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0213] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0214] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0215] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0216] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0217] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0218] The system for implementing this invention is built around the roles of server, terminal, and user. First, the server collects weather information, aircraft operation information, runway operation information, and information on past accidents from various external databases and feeds. This information is acquired in real time and integrated within the server.

[0219] The server uses machine learning algorithms to analyze integrated information and assess risks. This analysis is based on historical data patterns and identifies potential risks related to aircraft operations. Based on this risk assessment, the server automatically selects the necessary safety measures. The selected safety measures are translated into multiple languages.

[0220] Next, the server sends the translated safety information to a terminal. This terminal is a device used by air traffic controllers and pilots. The terminal displays the received information appropriately and provides the user with immediate operational instructions. The air traffic controllers and pilots, as users, review the information provided through the terminal and take action as necessary.

[0221] A concrete example is when a server analyzes ground weather information and detects that a particular runway is dangerous due to strong winds. Based on this information, the server suggests an alternative runway and sends this information to the terminal in multiple languages. The pilot, as the user, checks the notification received on the terminal and follows the instructions to make a safe landing. In this way, the system can ensure the safety of air traffic inside and outside the airport and enable efficient operations.

[0222] The following describes the processing flow.

[0223] Step 1:

[0224] The server periodically collects weather information, aircraft operation information, runway operation information, and historical accident information from external databases and feeds. The server retrieves data via APIs and ensures data reliability by verifying statistical data consistency.

[0225] Step 2:

[0226] The server integrates information based on the data it collects. It converts data in different formats to a standard format and stores it in an integrated database. This ensures the timeliness and consistency of the data.

[0227] Step 3:

[0228] The server initiates risk analysis using integrated data. Machine learning algorithms are used to assess similarities to past accident and incident patterns and identify potential risks. The analysis results are scored, and the risk level is expressed numerically.

[0229] Step 4:

[0230] The server selects appropriate safety measures based on the analysis results. The selection criteria include risk scores, operational status, and weather conditions, and the optimal measures are automatically determined.

[0231] Step 5:

[0232] The server translates selected security measures into multiple languages. An automatic translation system is used to generate notifications and manuals in an internationally understandable format.

[0233] Step 6:

[0234] The server sends the translated safety information to the corresponding terminal. The terminal is a device used by air traffic controllers and pilots, and after receiving the data from the server, it displays it to the user in an appropriate format.

[0235] Step 7:

[0236] Air traffic controllers and pilots, as users, review the information received via their terminals. Based on the safety measures presented, they adjust and decide on flight operations. Feedback is provided to the system as needed, leading to further improvements.

[0237] (Example 1)

[0238] Next, we will describe Example 1. 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."

[0239] In modern air traffic management, real-time information gathering and analysis regarding weather and aircraft operational status are essential. However, there is a lack of effective systems for extracting appropriate risk information from vast amounts of data and responding quickly. Therefore, there is a need for means to effectively mitigate the risk of aviation accidents. Furthermore, ensuring the accuracy of information transmission in international aircraft operations using multiple languages ​​is a major challenge.

[0240] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0241] In this invention, the server includes query means for collecting information, means for integrating and preprocessing the collected information, and means for executing a machine learning algorithm for evaluating risk based on the integrated information. This enables real-time data updates and rapid decision-making based on appropriate risk assessment. Furthermore, a multilingual translation function facilitates international information sharing.

[0242] A "querying method" refers to a communication interface used to retrieve information from external databases or information sources.

[0243] "Preprocessing" refers to functions that perform data preprocessing, such as imputing missing values ​​and removing noise, to prepare the collected data for analysis.

[0244] A "machine learning algorithm" is a computational method used to predict risk from new data based on past data patterns.

[0245] "Translation means" refers to a function for converting specific safety information into multiple languages, thereby enabling international information sharing.

[0246] "Means of communication" refers to a network interface used to transmit processed information to a receiving device or control system.

[0247] A "receiving device" refers to a device used by users such as air traffic controllers and pilots to receive and visually confirm information.

[0248] A description of the embodiment for carrying out the invention will be provided.

[0249] The primary roles in realizing this system are played by the server, terminals, and users. The server first uses query mechanisms to acquire weather information, aircraft operation information, runway operation information, and data on past accidents from external sources and databases. This process requires data client devices connected to the internet, utilizing data access points via APIs.

[0250] The server then uses methods to integrate and preprocess the collected data. Specifically, it uses programming languages ​​such as Python and the Pandas library to impute missing values ​​and remove noise. It also organizes the data into time series to ensure real-time performance.

[0251] Risk assessment utilizes a method where the server executes machine learning algorithms. Machine learning libraries such as TensorFlow and scikit-learn are used to analyze past data patterns and identify risk factors. Based on this, the server calculates a risk score for each piece of information, which is then used as a basis for decision-making in the next step.

[0252] Based on the evaluation results, the server selects security measures and uses an automated translation service to translate this information into multiple languages. Using services such as the Google Cloud Translation API, the selection results are translated into multiple languages ​​and made accessible to users of various languages.

[0253] The server then sends the translated information to a terminal. This terminal is typically used by air traffic controllers and pilots and usually has specialized air traffic control software installed. As a result, users can view the information provided in real time through the terminal and take the instructed actions.

[0254] As a concrete example, let's consider a scenario where a specific runway is deemed unsafe due to strong winds caused by changes in weather information. In this case, the server proposes an alternative runway, translates that information into multiple languages, and sends it to the terminal. The pilot, as the user, receives the notification via the terminal and adjusts their flight route towards a safe landing point.

[0255] An example prompt illustrating the operation of the generated AI model is, "Perform a risk assessment and propose safety measures based on weather conditions and flight information at a specific airport." Based on this prompt, the AI ​​model will perform a specific risk assessment and propose safety measures.

[0256] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0257] Step 1:

[0258] The server uses query methods to collect information. Inputs include requests for weather information, aircraft operation information, runway operation information, and information on past accidents. The server retrieves this data via external databases or APIs. The output is a set of collected raw data. Specifically, the server accesses API endpoints over the network and receives data in JSON format.

[0259] Step 2:

[0260] The server uses means to integrate and preprocess the collected data. The input is the raw dataset collected in step 1. The server organizes the data, imputes missing values, and removes noise. The output is a normalized dataset. Specifically, the server uses the Pandas library to impute missing values ​​in the data with the mean and to detect and remove outliers.

[0261] Step 3:

[0262] The server runs a machine learning algorithm to assess risk on normalized data. The input is the normalized dataset generated in step 2. The server calculates a risk score based on a model learned from historical data. The output is the risk assessment result for each aviation option. Specifically, the server uses TensorFlow to run a neural network and generate scores under specific weather conditions.

[0263] Step 4:

[0264] The server selects the necessary safety measures based on the risk assessment and translates them into multiple languages. The input is the risk assessment result from step 3. The server selects the optimal measures and translates them into multiple languages ​​via a translation service. The output is the translated safety measures information. Specifically, the server uses the Google Cloud Translation API to translate the selected information from English into other major languages.

[0265] Step 5:

[0266] The server sends the translated information to the terminal. The input is the multilingual security information generated in step 4. The server transmits this information to the user's terminal via wireless communication. The output is information in a format that can be displayed on the terminal. Specifically, the server securely pushes the data using the HTTPS protocol, triggering a notification on the terminal.

[0267] Step 6:

[0268] The user receives information provided through the terminal and takes action according to the instructions. The input is the notification received on the terminal in step 5. The user checks the information on the terminal screen and selects the necessary action. The output is the specific action based on the execution of safety measures. As a specific action, the pilot adjusts the instruments to the suggested alternative runway and ensures a safe landing path.

[0269] (Application Example 1)

[0270] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0271] Currently, a challenge in operating autonomous vehicles is the need to quickly grasp weather conditions and road surface conditions and issue operational instructions based on predicted risks. Conventional systems lack real-time information updates, making it difficult to take appropriate measures quickly. Furthermore, in situations where multilingual support is essential, information may not be translated properly, potentially compromising operational safety. As a result, the safety and efficiency of autonomous vehicles are not adequately ensured, and effective means to improve this are needed.

[0272] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0273] In this invention, the server includes means for integrating weather information, operational information, road surface condition information, and information on past accidents; means for analyzing operational risks; and means for proposing alternative routes in real time. This enables the provision of rapid and accurate safety measures and operational instructions to autonomous vehicles, resulting in safe and efficient driving.

[0274] "Weather information" refers to data related to the natural environment, such as precipitation, wind speed, and temperature, and is necessary information for evaluating the operational environment.

[0275] "Operational information" refers to traffic-related data and various status information, such as the vehicle's current location, speed, and route.

[0276] "Road surface condition information" refers to information that indicates the condition of the road and the presence or absence of obstacles, and is essential information for safe driving.

[0277] "Information regarding past accidents" refers to data that includes details of previously occurring accidents, their causes, and their impact.

[0278] "Methods for analyzing operational risks" refer to methods for identifying potential risk factors and evaluating their impact based on various collected information.

[0279] "Methods for proposing alternative routes" refer to the process of finding and proposing safe detours when the current route is deemed dangerous.

[0280] "A means of continuously updating in real time" refers to a technology that keeps ever-changing information up-to-date and reflects it immediately.

[0281] A "machine learning algorithm" is a technology that learns patterns based on past data and uses that knowledge to make predictions and classifications on new data.

[0282] "Multilingual generation methods" refer to technologies that translate information into multiple languages ​​in order to provide the same information to users who speak different languages.

[0283] This system supports the safe and efficient operation of autonomous vehicles. The server collects and integrates weather information, operational information, road surface condition information, and information on past accidents. This data is retrieved in real time from external databases and APIs and integrated within the server.

[0284] The server processes the integrated information and analyzes the operation risks using machine learning algorithms. For this, machine learning platforms such as TensorFlow are used. It learns past accident data as patterns and identifies the risks latent in the current operation situation. Based on this risk assessment, the server selects the necessary safety measures and translates them into multiple languages.

[0285] Next, the server proposes the operation route and alternative routes in real time. Using something like the Google Maps API, it calculates the optimal route considering the current traffic situation. It sends the result to the terminal and provides instructions to the autonomous vehicle.

[0286] The terminal displays the received information on the vehicle's display and audio system, and gives immediate operation instructions to the driver and the vehicle control system. The driver or the vehicle, which is the user, follows the instructions of the terminal and conducts safe and optimal operation. Thereby, the system greatly improves the safety and efficiency of the autonomous vehicle.

[0287] As a specific example, when there was a forecast of sunny weather but unexpected heavy rain occurred, the system can immediately evaluate the risk, propose an alternative route to avoid roads with a lot of puddles, and display an instruction to prompt a reduction in the driving speed.

[0288] An example of the prompt text input to the generative AI model is in the form of "Please propose the optimal route to safely reach the destination with an autonomous vehicle in heavy rain."

[0289] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0290] Step 1:

[0291] The server collects weather information, traffic information, road surface condition information, and information on past accidents in real time from external databases and APIs. This data is obtained in JSON format and integrated in preparation for subsequent processing. It receives responses from various APIs as input and generates an integrated dataset as output.

[0292] Step 2:

[0293] The server uses an integrated dataset to analyze operational risks with machine learning algorithms based on TensorFlow. It accepts the integrated dataset as input and outputs a risk assessment score based on pattern recognition and predictive models. This identifies potential risks related to weather, traffic conditions, and road conditions.

[0294] Step 3:

[0295] The server uses the Google Maps API to calculate alternative routes based on the risk assessment score. It receives the risk assessment score and current route information as input and outputs a safe and efficient alternative route. This ensures that the vehicle is directed to a route that allows it to reach its destination more safely.

[0296] Step 4:

[0297] The server translates the selected alternative route and operational instructions into multiple languages ​​as needed. In this step, it receives alternative route information and the selected language as input and outputs multilingual operational instructions. The translated information is provided to the user in a human-readable format.

[0298] Step 5:

[0299] The terminal displays translated operational instructions received from the server and provides instructions to the user or vehicle control system via voice or display. It receives translated operational instructions as input and immediately notifies and outputs them to the user. This allows drivers to operate safely and efficiently based on the instructions.

[0300] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0301] The system for implementing this invention consists primarily of a server, terminals, users, and an emotion engine. First, the server collects and integrates weather information, aircraft operation information, runway operation information, and past accident information from various external databases. Based on this integrated information, the server uses machine learning algorithms to analyze risks and select safety measures appropriate for the specific situation.

[0302] The selected safety measures are optimized by an emotion engine based on the user's emotional state. The server evaluates the emotions of the user, such as an air traffic controller or pilot, in real time through voice analysis. Based on this emotional state, the content and presentation method of notifications are automatically adjusted and transmitted in a way that facilitates user understanding.

[0303] As a concrete example, consider a scenario where a server detects a risk to runway use due to strong winds and issues a warning. When the emotion engine detects a high level of stress from the pilot's voice, the server provides a more detailed and careful explanation in the notification. In this way, the system can respond flexibly according to the user's psychological state.

[0304] The terminal displays notifications based on the emotions transmitted from the server and provides clear action guidelines to the user. The user checks the information provided through the terminal and implements safety measures if necessary. This feedback is evaluated by the emotion engine and utilized as data for future system improvement. Through this process, the system can improve the safety of air traffic and reduce the psychological burden on the user.

[0305] The following describes the processing flow.

[0306] Step 1:

[0307] The server collects weather information, aircraft operation information, runway operation information, and past accident information from various data sources. The server integrates this data and stores it in a database to enable real-time access.

[0308] Step 2:

[0309] The server uses the integrated data to execute a machine learning algorithm and initiate a risk analysis. By comparing with past incident data, potential risks in the current operation situation are identified. The risk level is scored and priorities are set.

[0310] Step 3:

[0311] Based on the results of the risk analysis, the server selects appropriate safety measures. The selection criteria include the risk level and the scope of influence, and the specific content of the measures is determined and recorded.

[0312] Step 4:

[0313] The emotion engine analyzes the user's voice and behavior data and evaluates the user's emotional state. If stress or tension is high, the emotion engine records that state and provides feedback to the server.

[0314] Step 5:

[0315] The server receives feedback from the emotion engine and adjusts the content and tone of safety alerts according to the emotional state. For example, if a high stress level is detected, detailed explanations and steps will be added to the alert.

[0316] Step 6:

[0317] The server sends optimized safety notifications to the terminal. The terminal is a device used by air traffic controllers and pilots, and it has the function to display the information from the server appropriately.

[0318] Step 7:

[0319] The user reviews the information provided through their device and takes the instructed safety measures as needed. User behavior and responses are fed back into the system to help with continuous improvement.

[0320] (Example 2)

[0321] Next, we will describe Example 2. 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".

[0322] Improving air traffic safety requires real-time information updates and accurate risk assessment, but conventional systems lacked sufficient capabilities in these areas. Furthermore, information delivery was not optimized based on the user's emotional state, creating a risk that important information might not be properly communicated.

[0323] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0324] In this invention, the server includes means for integrating weather information, aircraft operation information, air route operation information, and information on past incidents; means for analyzing risks based on the integrated information; and means for optimizing selected safety measures based on an algorithm that recognizes emotions. This enables flexible information transmission in accordance with the user's emotional state and rapid and accurate risk assessment.

[0325] "Weather information" refers to data about weather conditions, including information such as the state of the sky, temperature, humidity, wind speed, and wind direction.

[0326] "Aircraft operation information" refers to data related to the operation of aircraft, such as departure, arrival, route, speed, and altitude.

[0327] "Air route operation information" refers to information about the usage status, closure status, available times, and restrictions of air routes.

[0328] "Past incidents" refers to records of aviation-related accidents and near misses that have occurred in the past.

[0329] "Means of integrating information" refers to the process or mechanism for organizing information obtained from different data sources and combining it into a single, unified format.

[0330] "Means of risk analysis" refer to algorithms and methods for predicting and identifying potential risks based on integrated information.

[0331] "Means for selecting safety measures" refers to methods for determining the optimal response to an analyzed hazard.

[0332] An "emotion recognition algorithm" is a computational method for analyzing and recognizing emotions from a person's voice and facial expressions.

[0333] An embodiment of this invention consists of a server, a terminal, a user, and a sentiment analysis engine. The server retrieves weather information, aircraft operation information, air route operation information, and data on past incidents from an external database. This is done using the Python requests library. The server stores the collected data in a Pandas DataFrame and integrates the data using the merge function. Unnecessary data is filtered at this stage.

[0334] The server runs a machine learning model using the Scikit-learn library to analyze risks based on the integrated data. This model is pre-trained on historical data. Based on the risk assessment results, the server selects appropriate safety measures from the database, and these safety measures are optimized by a sentiment analysis engine.

[0335] The emotion analysis engine uses LibROSA for speech processing to acquire voice data from users, such as air traffic controllers and aircraft operators. The acquired voice data is analyzed through a TensorFlow deep learning model to evaluate the user's emotional state. Based on this information, the content and format of notifications are optimized.

[0336] The terminal displays optimized notifications sent from the server. The user checks the notifications on the terminal and takes specific actions. For example, if the server detects a risk of strong winds and sends a notification, the notification will appear as a pop-up on the terminal and will also be announced audibly. If the user, who is the aircraft operator, checks this notification, they will be required to adjust their actions as instructed.

[0337] User behavior and its consequences are collected via the device as feedback and stored in a server database. This feedback is used to improve the sentiment analysis engine and risk analysis model.

[0338] A concrete example of a prompt message would be: "Based on the latest weather data and aircraft operation information, please generate safety measures and suggest notification content tailored to the user's emotional state."

[0339] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0340] Step 1:

[0341] The server collects weather information, aircraft operation information, air route operation information, and past trouble information from an external database. It receives this information, obtained from an API, as input and extracts the data using the Python requests library. The output is a Pandas DataFrame containing the various types of information. Specifically, it uses asynchronous processing to quickly retrieve information and store it in the DataFrame.

[0342] Step 2:

[0343] The server runs a machine learning model to analyze risk based on information integrated into a Pandas DataFrame. The integrated data obtained in the previous step is used as input. A random forest model using Scikit-learn is applied to predict risk. The output is a list of situations where risk has been identified. The model is pre-trained and tuned using historical data.

[0344] Step 3:

[0345] The server selects appropriate safety measures from the database based on the identified risks. Using the risk analysis results as input and referencing the safety measures database, it determines the optimal measures to address the situation. The output is a list of selected safety measures. Here, a data matching algorithm is used to identify recommended measures for each risk.

[0346] Step 4:

[0347] The emotion analysis engine evaluates emotional states using user voice input. The input consists of real-time voice data from air traffic controllers and aircraft operators. Voice features are extracted using LibROSA and analyzed by an emotion recognition model built with TensorFlow. The output is a numerical evaluation of the emotional state. Here, features such as voice pitch and tempo are calculated, and the model evaluates emotions such as stress and tension.

[0348] Step 5:

[0349] The server optimizes the content and format of notifications based on an assessment of the user's emotional state. The emotional assessment obtained in the previous step is used as input. Notifications are tailored to be easily understood by the user, with particularly important information highlighted. The output is the optimized notification message. Specifically, HTML / CSS is used to modify the notification layout for better readability.

[0350] Step 6:

[0351] The terminal displays notifications sent from the server using a dedicated application. The input is an optimized notification message from the server. The notification is displayed as a pop-up on the terminal screen, and the content can also be confirmed via audio output. The output is the notification content that the user can visually confirm. A user-friendly interface is provided using a GUI framework.

[0352] Step 7:

[0353] The user takes specific actions based on the notification and provides feedback via the device. The input is the content of the notification displayed on the device. The device has a feedback input function, where the user inputs the actions taken and their results. The output is the feedback data, which is stored in the server's database and used to improve the algorithm in the future.

[0354] (Application Example 2)

[0355] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0356] In modern homes, providing optimal environmental adjustments and household support tailored to the emotional state of residents is crucial for improving their quality of life. However, conventional technologies have struggled to accurately grasp individual emotional states and automatically provide flexible responses based on them. This invention solves the problem of improving quality of life by analyzing residents' emotional states in real time and providing optimal action suggestions accordingly.

[0357] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0358] In this invention, the server includes means for integrating weather data, flight data, operational data, and historical case information; means for analyzing risks based on the integrated data; and means for analyzing the user's state and optimizing notification content. This makes it possible to accurately grasp the emotional state of residents in real time and propose optimal household support and environmental adjustments based on that.

[0359] "Weather data" refers to information related to weather, including data on environmental conditions such as temperature, humidity, and wind speed.

[0360] "Flight data" refers to information related to the operation status of aircraft and transportation services, including departure and arrival times, routes, and operational status.

[0361] "Operational data" refers to information about the usage and performance of a specific system or piece of equipment, including data on its operational status and maintenance history.

[0362] "Historical case information" refers to data about past incidents and episodes, including insights and lessons learned from past events.

[0363] "Risk analysis" is the process of evaluating potential dangers and problems based on integrated data, and analyzing their probability of occurrence and impact.

[0364] "Analyzing the user's condition" is the process of evaluating the user's emotions and psychological state using data, and then deciding on appropriate responses based on the results.

[0365] "Optimizing notification content" means adjusting the content and method of notifications provided to users based on the analyzed information, according to the situation.

[0366] The system implementing this invention consists primarily of a server, terminals, users, and an emotion engine. The system aims to analyze the emotional state of residents in real time and provide optimal support accordingly.

[0367] The server acquires data from audio and images collected within the home via smart devices. This data is analyzed using a TensorFlow-based emotion analysis model to determine the user's emotional state (stress level, relaxation level, etc.). Based on this analysis, the server utilizes an action selection module to suggest the most appropriate actions for the resident. Here, various environmental adjustments are suggested, such as playing music, adjusting lighting, and prioritizing household chores, using smart speaker technologies like Google Home or Amazon Alexa.

[0368] The system's terminals display notifications sent from the server and present their content to residents in descending order of priority. This makes it easier for residents to select recommended actions. Simultaneously, resident feedback is collected and sent to the server, improving the accuracy of future action suggestions. This feedback data is used in real time to optimize the system's sentiment analysis model and action selection module.

[0369] For example, if the system analyzes that a resident is experiencing stress, it will automatically play relaxing music tailored to that resident's preferences. Additionally, the server uses an AI model to generate prompts such as, "This user appears to be stressed. Please suggest a relaxing action suitable for them," and uses this to select the appropriate action.

[0370] In this way, the server can comprehensively improve the quality of life for residents by enabling real-time data analysis and user-oriented notification optimization.

[0371] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0372] Step 1:

[0373] The server acquires audio and image data from smart devices within the home. Specifically, it receives input signals from smart speakers and cameras. This data serves as the source material for analyzing emotional states.

[0374] Step 2:

[0375] The server inputs the received data into an emotion analysis model using TensorFlow to analyze the residents' emotional state. Here, stress levels and emotional intensity are quantified based on factors such as voice tone and facial expression changes. Data processing includes feature extraction based on voice analysis and detection of facial expression changes through image processing.

[0376] Step 3:

[0377] Based on the analysis results, the server uses a generative AI model to generate prompt messages. Specifically, it might create instructions such as, "This user appears to be stressed. Please suggest relaxing actions suitable for them." This prompt provides the necessary context for selecting an action.

[0378] Step 4:

[0379] The device receives notifications sent from the server and displays them on the user screen. These notifications offer suggestions such as playing relaxing background music or automatically adjusting the lighting. The notifications include specific action guidelines, presented in a format that the user can intuitively understand.

[0380] Step 5:

[0381] Users provide feedback on actions suggested via their device. This feedback is provided through touch operations or voice input. The feedback data is sent to a server and used to improve the accuracy of future action suggestions.

[0382] Step 6:

[0383] The server analyzes the collected feedback and updates the training datasets for the sentiment analysis model and the generative AI model. This process forms the basis for the continuous improvement of the system and for providing personalized services to users.

[0384] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0385] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0386] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0387] [Third Embodiment]

[0388] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0389] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0390] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0391] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0392] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0393] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0394] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0395] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0396] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0397] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0398] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0399] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0400] The system for implementing this invention is built around the roles of server, terminal, and user. First, the server collects weather information, aircraft operation information, runway operation information, and information on past accidents from various external databases and feeds. This information is acquired in real time and integrated within the server.

[0401] The server uses machine learning algorithms to analyze integrated information and assess risks. This analysis is based on historical data patterns and identifies potential risks related to aircraft operations. Based on this risk assessment, the server automatically selects the necessary safety measures. The selected safety measures are translated into multiple languages.

[0402] Next, the server sends the translated safety information to a terminal. This terminal is a device used by air traffic controllers and pilots. The terminal displays the received information appropriately and provides the user with immediate operational instructions. The air traffic controllers and pilots, as users, review the information provided through the terminal and take action as necessary.

[0403] A concrete example is when a server analyzes ground weather information and detects that a particular runway is dangerous due to strong winds. Based on this information, the server suggests an alternative runway and sends this information to the terminal in multiple languages. The pilot, as the user, checks the notification received on the terminal and follows the instructions to make a safe landing. In this way, the system can ensure the safety of air traffic inside and outside the airport and enable efficient operations.

[0404] The following describes the processing flow.

[0405] Step 1:

[0406] The server periodically collects weather information, aircraft operation information, runway operation information, and historical accident information from external databases and feeds. The server retrieves data via APIs and ensures data reliability by verifying statistical data consistency.

[0407] Step 2:

[0408] The server integrates information based on the data it collects. It converts data in different formats to a standard format and stores it in an integrated database. This ensures the timeliness and consistency of the data.

[0409] Step 3:

[0410] The server initiates risk analysis using integrated data. Machine learning algorithms are used to assess similarities to past accident and incident patterns and identify potential risks. The analysis results are scored, and the risk level is expressed numerically.

[0411] Step 4:

[0412] The server selects appropriate safety measures based on the analysis results. The selection criteria include risk scores, operational status, and weather conditions, and the optimal measures are automatically determined.

[0413] Step 5:

[0414] The server translates selected security measures into multiple languages. An automatic translation system is used to generate notifications and manuals in an internationally understandable format.

[0415] Step 6:

[0416] The server sends the translated safety information to the corresponding terminal. The terminal is a device used by air traffic controllers and pilots, and after receiving the data from the server, it displays it to the user in an appropriate format.

[0417] Step 7:

[0418] Air traffic controllers and pilots, as users, review the information received via their terminals. Based on the safety measures presented, they adjust and decide on flight operations. Feedback is provided to the system as needed, leading to further improvements.

[0419] (Example 1)

[0420] Next, we will describe Example 1. 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."

[0421] In modern air traffic management, real-time information gathering and analysis regarding weather and aircraft operational status are essential. However, there is a lack of effective systems for extracting appropriate risk information from vast amounts of data and responding quickly. Therefore, there is a need for means to effectively mitigate the risk of aviation accidents. Furthermore, ensuring the accuracy of information transmission in international aircraft operations using multiple languages ​​is a major challenge.

[0422] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0423] In this invention, the server includes query means for collecting information, means for integrating and preprocessing the collected information, and means for executing a machine learning algorithm for evaluating risk based on the integrated information. This enables real-time data updates and rapid decision-making based on appropriate risk assessment. Furthermore, a multilingual translation function facilitates international information sharing.

[0424] A "querying method" refers to a communication interface used to retrieve information from external databases or information sources.

[0425] "Preprocessing" refers to functions that perform data preprocessing, such as imputing missing values ​​and removing noise, to prepare the collected data for analysis.

[0426] A "machine learning algorithm" is a computational method used to predict risk from new data based on past data patterns.

[0427] "Translation means" refers to a function for converting specific safety information into multiple languages, thereby enabling international information sharing.

[0428] "Means of communication" refers to a network interface used to transmit processed information to a receiving device or control system.

[0429] A "receiving device" refers to a device used by users such as air traffic controllers and pilots to receive and visually confirm information.

[0430] A description of the embodiment for carrying out the invention will be provided.

[0431] The primary roles in realizing this system are played by the server, terminals, and users. The server first uses query mechanisms to acquire weather information, aircraft operation information, runway operation information, and data on past accidents from external sources and databases. This process requires data client devices connected to the internet, utilizing data access points via APIs.

[0432] The server then uses methods to integrate and preprocess the collected data. Specifically, it uses programming languages ​​such as Python and the Pandas library to impute missing values ​​and remove noise. It also organizes the data into time series to ensure real-time performance.

[0433] Risk assessment utilizes a method where the server executes machine learning algorithms. Machine learning libraries such as TensorFlow and scikit-learn are used to analyze past data patterns and identify risk factors. Based on this, the server calculates a risk score for each piece of information, which is then used as a basis for decision-making in the next step.

[0434] Based on the evaluation results, the server selects security measures and uses an automated translation service to translate this information into multiple languages. Using services such as the Google Cloud Translation API, the selection results are translated into multiple languages ​​and made accessible to users of various languages.

[0435] The server then sends the translated information to a terminal. This terminal is typically used by air traffic controllers and pilots and usually has specialized air traffic control software installed. As a result, users can view the information provided in real time through the terminal and take the instructed actions.

[0436] As a concrete example, let's consider a scenario where a specific runway is deemed unsafe due to strong winds caused by changes in weather information. In this case, the server proposes an alternative runway, translates that information into multiple languages, and sends it to the terminal. The pilot, as the user, receives the notification via the terminal and adjusts their flight route towards a safe landing point.

[0437] An example prompt illustrating the operation of the generated AI model is, "Perform a risk assessment and propose safety measures based on weather conditions and flight information at a specific airport." Based on this prompt, the AI ​​model will perform a specific risk assessment and propose safety measures.

[0438] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0439] Step 1:

[0440] The server uses query methods to collect information. Inputs include requests for weather information, aircraft operation information, runway operation information, and information on past accidents. The server retrieves this data via external databases or APIs. The output is a set of collected raw data. Specifically, the server accesses API endpoints over the network and receives data in JSON format.

[0441] Step 2:

[0442] The server uses means to integrate and preprocess the collected data. The input is the raw dataset collected in step 1. The server organizes the data, imputes missing values, and removes noise. The output is a normalized dataset. Specifically, the server uses the Pandas library to impute missing values ​​in the data with the mean and to detect and remove outliers.

[0443] Step 3:

[0444] The server runs a machine learning algorithm to assess risk on normalized data. The input is the normalized dataset generated in step 2. The server calculates a risk score based on a model learned from historical data. The output is the risk assessment result for each aviation option. Specifically, the server uses TensorFlow to run a neural network and generate scores under specific weather conditions.

[0445] Step 4:

[0446] The server selects the necessary safety measures based on the risk assessment and translates them into multiple languages. The input is the risk assessment result from step 3. The server selects the optimal measures and translates them into multiple languages ​​via a translation service. The output is the translated safety measures information. Specifically, the server uses the Google Cloud Translation API to translate the selected information from English into other major languages.

[0447] Step 5:

[0448] The server sends the translated information to the terminal. The input is the multilingual security information generated in step 4. The server transmits this information to the user's terminal via wireless communication. The output is information in a format that can be displayed on the terminal. Specifically, the server securely pushes the data using the HTTPS protocol, triggering a notification on the terminal.

[0449] Step 6:

[0450] The user receives information provided through the terminal and takes action according to the instructions. The input is the notification received on the terminal in step 5. The user checks the information on the terminal screen and selects the necessary action. The output is the specific action based on the execution of safety measures. As a specific action, the pilot adjusts the instruments to the suggested alternative runway and ensures a safe landing path.

[0451] (Application Example 1)

[0452] Next, we will explain Application Example 1. In the following explanation, 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."

[0453] Currently, a challenge in operating autonomous vehicles is the need to quickly grasp weather conditions and road surface conditions and issue operational instructions based on predicted risks. Conventional systems lack real-time information updates, making it difficult to take appropriate measures quickly. Furthermore, in situations where multilingual support is essential, information may not be translated properly, potentially compromising operational safety. As a result, the safety and efficiency of autonomous vehicles are not adequately ensured, and effective means to improve this are needed.

[0454] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0455] In this invention, the server includes means for integrating weather information, operational information, road surface condition information, and information on past accidents; means for analyzing operational risks; and means for proposing alternative routes in real time. This enables the provision of rapid and accurate safety measures and operational instructions to autonomous vehicles, resulting in safe and efficient driving.

[0456] "Weather information" refers to data related to the natural environment, such as precipitation, wind speed, and temperature, and is necessary information for evaluating the operational environment.

[0457] "Operational information" refers to traffic-related data and various status information, such as the vehicle's current location, speed, and route.

[0458] "Road surface condition information" refers to information that indicates the condition of the road and the presence or absence of obstacles, and is essential information for safe driving.

[0459] "Information regarding past accidents" refers to data that includes details of previously occurring accidents, their causes, and their impact.

[0460] "Methods for analyzing operational risks" refer to methods for identifying potential risk factors and evaluating their impact based on various collected information.

[0461] "Methods for proposing alternative routes" refer to the process of finding and proposing safe detours when the current route is deemed dangerous.

[0462] "A means of continuously updating in real time" refers to a technology that keeps ever-changing information up-to-date and reflects it immediately.

[0463] A "machine learning algorithm" is a technology that learns patterns based on past data and uses that knowledge to make predictions and classifications on new data.

[0464] "Multilingual generation methods" refer to technologies that translate information into multiple languages ​​in order to provide the same information to users who speak different languages.

[0465] This system supports the safe and efficient operation of autonomous vehicles. The server collects and integrates weather information, operational information, road surface condition information, and information on past accidents. This data is retrieved in real time from external databases and APIs and integrated within the server.

[0466] The server processes the integrated information and uses machine learning algorithms to analyze operational risks. This utilizes machine learning platforms such as TensorFlow. It learns patterns from past accident data and identifies potential risks in current operations. Based on this risk assessment, the server selects necessary safety measures and translates them into multiple languages.

[0467] Next, the server provides real-time suggestions for routes and alternative routes. Using the Google Maps API and other tools, it calculates the optimal route considering current traffic conditions. It then sends the results to the terminal, providing instructions to the autonomous vehicle.

[0468] The terminal displays received information on the vehicle's display and audio system, providing responsive operational instructions to the driver and vehicle control system. The user, either the driver or the vehicle, follows the terminal's instructions to ensure safe and optimal operation. This significantly improves the safety and efficiency of the autonomous vehicle.

[0469] For example, if a sunny day is forecast but unexpected heavy rain occurs, the system can immediately assess the risk, suggest alternative routes to avoid roads with many puddles, and display instructions to encourage drivers to slow down.

[0470] An example of a prompt sentence to input into the generating AI model would be, "Please suggest the optimal route for safely arriving at the destination in an autonomous vehicle during heavy rain."

[0471] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0472] Step 1:

[0473] The server collects weather information, traffic information, road surface condition information, and information on past accidents in real time from external databases and APIs. This data is obtained in JSON format and integrated in preparation for subsequent processing. It receives responses from various APIs as input and generates an integrated dataset as output.

[0474] Step 2:

[0475] The server uses an integrated dataset to analyze operational risks with machine learning algorithms based on TensorFlow. It accepts the integrated dataset as input and outputs a risk assessment score based on pattern recognition and predictive models. This identifies potential risks related to weather, traffic conditions, and road conditions.

[0476] Step 3:

[0477] The server uses the Google Maps API to calculate alternative routes based on the risk assessment score. It receives the risk assessment score and current route information as input and outputs a safe and efficient alternative route. This ensures that the vehicle is directed to a route that allows it to reach its destination more safely.

[0478] Step 4:

[0479] The server translates the selected alternative route and operational instructions into multiple languages ​​as needed. In this step, it receives alternative route information and the selected language as input and outputs multilingual operational instructions. The translated information is provided to the user in a human-readable format.

[0480] Step 5:

[0481] The terminal displays translated operational instructions received from the server and provides instructions to the user or vehicle control system via voice or display. It receives translated operational instructions as input and immediately notifies and outputs them to the user. This allows drivers to operate safely and efficiently based on the instructions.

[0482] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0483] The system for implementing this invention consists primarily of a server, terminals, users, and an emotion engine. First, the server collects and integrates weather information, aircraft operation information, runway operation information, and past accident information from various external databases. Based on this integrated information, the server uses machine learning algorithms to analyze risks and select safety measures appropriate for the specific situation.

[0484] The selected safety measures are optimized by an emotion engine based on the user's emotional state. The server evaluates the emotions of the user, such as an air traffic controller or pilot, in real time through voice analysis. Based on this emotional state, the content and presentation method of notifications are automatically adjusted and transmitted in a way that facilitates user understanding.

[0485] As a concrete example, consider a scenario where a server detects a risk to runway use due to strong winds and issues a warning. When the emotion engine detects a high level of stress from the pilot's voice, the server provides a more detailed and careful explanation in the notification. In this way, the system can respond flexibly according to the user's psychological state.

[0486] The terminal displays emotion-based notifications sent from the server, providing users with clear guidance for action. Users review the information provided through the terminal and take safety measures as needed. This feedback is evaluated by an emotion engine and used as data for future system improvements. This process allows the system to improve air traffic safety while reducing the psychological burden on users.

[0487] The following describes the processing flow.

[0488] Step 1:

[0489] The server collects weather information, aircraft operation information, runway operation information, and historical accident information from various data sources. The server integrates this data and stores it in a database, enabling real-time access.

[0490] Step 2:

[0491] The server uses the integrated data to run machine learning algorithms and initiate risk analysis. It compares current incident data with past incident data to identify potential risks in the current operational situation. Risk levels are scored and prioritized.

[0492] Step 3:

[0493] The server selects appropriate safety measures based on the results of the risk analysis. The selection criteria include the risk level and scope of impact, and the specific measures are determined and recorded.

[0494] Step 4:

[0495] The emotion engine analyzes the user's voice and behavioral data to evaluate the user's emotional state. If stress or tension is high, the emotion engine records this state and provides feedback to the server.

[0496] Step 5:

[0497] The server receives feedback from the emotion engine and adjusts the content and tone of safety alerts according to the emotional state. For example, if a high stress level is detected, detailed explanations and steps will be added to the alert.

[0498] Step 6:

[0499] The server sends optimized safety notifications to the terminal. The terminal is a device used by air traffic controllers and pilots, and it has the function to display the information from the server appropriately.

[0500] Step 7:

[0501] The user reviews the information provided through their device and takes the instructed safety measures as needed. User behavior and responses are fed back into the system to help with continuous improvement.

[0502] (Example 2)

[0503] Next, we will describe Example 2. 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."

[0504] Improving air traffic safety requires real-time information updates and accurate risk assessment, but conventional systems lacked sufficient capabilities in these areas. Furthermore, information delivery was not optimized based on the user's emotional state, creating a risk that important information might not be properly communicated.

[0505] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0506] In this invention, the server includes means for integrating weather information, aircraft operation information, air route operation information, and information on past incidents; means for analyzing risks based on the integrated information; and means for optimizing selected safety measures based on an algorithm that recognizes emotions. This enables flexible information transmission in accordance with the user's emotional state and rapid and accurate risk assessment.

[0507] "Weather information" refers to data about weather conditions, including information such as the state of the sky, temperature, humidity, wind speed, and wind direction.

[0508] "Aircraft operation information" refers to data related to the operation of aircraft, such as departure, arrival, route, speed, and altitude.

[0509] "Air route operation information" refers to information about the usage status, closure status, available times, and restrictions of air routes.

[0510] "Past incidents" refers to records of aviation-related accidents and near misses that have occurred in the past.

[0511] "Means of integrating information" refers to the process or mechanism for organizing information obtained from different data sources and combining it into a single, unified format.

[0512] "Means of risk analysis" refer to algorithms and methods for predicting and identifying potential risks based on integrated information.

[0513] "Means for selecting safety measures" refers to methods for determining the optimal response to an analyzed hazard.

[0514] An "emotion recognition algorithm" is a computational method for analyzing and recognizing emotions from a person's voice and facial expressions.

[0515] An embodiment of this invention consists of a server, a terminal, a user, and a sentiment analysis engine. The server retrieves weather information, aircraft operation information, air route operation information, and data on past incidents from an external database. This is done using the Python requests library. The server stores the collected data in a Pandas DataFrame and integrates the data using the merge function. Unnecessary data is filtered at this stage.

[0516] The server runs a machine learning model using the Scikit-learn library to analyze risks based on the integrated data. This model is pre-trained on historical data. Based on the risk assessment results, the server selects appropriate safety measures from the database, and these safety measures are optimized by a sentiment analysis engine.

[0517] The emotion analysis engine uses LibROSA for speech processing to acquire voice data from users, such as air traffic controllers and aircraft operators. The acquired voice data is analyzed through a TensorFlow deep learning model to evaluate the user's emotional state. Based on this information, the content and format of notifications are optimized.

[0518] The terminal displays optimized notifications sent from the server. The user checks the notifications on the terminal and takes specific actions. For example, if the server detects a risk of strong winds and sends a notification, the notification will appear as a pop-up on the terminal and will also be announced audibly. If the user, who is the aircraft operator, checks this notification, they will be required to adjust their actions as instructed.

[0519] User behavior and its consequences are collected via the device as feedback and stored in a server database. This feedback is used to improve the sentiment analysis engine and risk analysis model.

[0520] A concrete example of a prompt message would be: "Based on the latest weather data and aircraft operation information, please generate safety measures and suggest notification content tailored to the user's emotional state."

[0521] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0522] Step 1:

[0523] The server collects weather information, aircraft operation information, air route operation information, and past trouble information from an external database. It receives this information, obtained from an API, as input and extracts the data using the Python requests library. The output is a Pandas DataFrame containing the various types of information. Specifically, it uses asynchronous processing to quickly retrieve information and store it in the DataFrame.

[0524] Step 2:

[0525] The server runs a machine learning model to analyze risk based on information integrated into a Pandas DataFrame. The integrated data obtained in the previous step is used as input. A random forest model using Scikit-learn is applied to predict risk. The output is a list of situations where risk has been identified. The model is pre-trained and tuned using historical data.

[0526] Step 3:

[0527] The server selects appropriate safety measures from the database based on the identified risks. Using the risk analysis results as input and referencing the safety measures database, it determines the optimal measures to address the situation. The output is a list of selected safety measures. Here, a data matching algorithm is used to identify recommended measures for each risk.

[0528] Step 4:

[0529] The emotion analysis engine evaluates emotional states using user voice input. The input consists of real-time voice data from air traffic controllers and aircraft operators. Voice features are extracted using LibROSA and analyzed by an emotion recognition model built with TensorFlow. The output is a numerical evaluation of the emotional state. Here, features such as voice pitch and tempo are calculated, and the model evaluates emotions such as stress and tension.

[0530] Step 5:

[0531] The server optimizes the content and format of notifications based on an assessment of the user's emotional state. The emotional assessment obtained in the previous step is used as input. Notifications are tailored to be easily understood by the user, with particularly important information highlighted. The output is the optimized notification message. Specifically, HTML / CSS is used to modify the notification layout for better readability.

[0532] Step 6:

[0533] The terminal displays notifications sent from the server using a dedicated application. The input is an optimized notification message from the server. The notification is displayed as a pop-up on the terminal screen, and the content can also be confirmed via audio output. The output is the notification content that the user can visually confirm. A user-friendly interface is provided using a GUI framework.

[0534] Step 7:

[0535] The user takes specific actions based on the notification and provides feedback via the device. The input is the content of the notification displayed on the device. The device has a feedback input function, where the user inputs the actions taken and their results. The output is the feedback data, which is stored in the server's database and used to improve the algorithm in the future.

[0536] (Application Example 2)

[0537] Next, we will explain application example 2. In the following explanation, 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."

[0538] In modern homes, providing optimal environmental adjustments and household support tailored to the emotional state of residents is crucial for improving their quality of life. However, conventional technologies have struggled to accurately grasp individual emotional states and automatically provide flexible responses based on them. This invention solves the problem of improving quality of life by analyzing residents' emotional states in real time and providing optimal action suggestions accordingly.

[0539] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0540] In this invention, the server includes means for integrating weather data, flight data, operational data, and historical case information; means for analyzing risks based on the integrated data; and means for analyzing the user's state and optimizing notification content. This makes it possible to accurately grasp the emotional state of residents in real time and propose optimal household support and environmental adjustments based on that.

[0541] "Weather data" refers to information related to weather, including data on environmental conditions such as temperature, humidity, and wind speed.

[0542] "Flight data" refers to information related to the operation status of aircraft and transportation services, including departure and arrival times, routes, and operational status.

[0543] "Operational data" refers to information about the usage and performance of a specific system or piece of equipment, including data on its operational status and maintenance history.

[0544] "Historical case information" refers to data about past incidents and episodes, including insights and lessons learned from past events.

[0545] "Risk analysis" is the process of evaluating potential dangers and problems based on integrated data, and analyzing their probability of occurrence and impact.

[0546] "Analyzing the user's condition" is the process of evaluating the user's emotions and psychological state using data, and then deciding on appropriate responses based on the results.

[0547] "Optimizing notification content" means adjusting the content and method of notifications provided to users based on the analyzed information, according to the situation.

[0548] The system implementing this invention consists primarily of a server, terminals, users, and an emotion engine. The system aims to analyze the emotional state of residents in real time and provide optimal support accordingly.

[0549] The server acquires data from audio and images collected within the home via smart devices. This data is analyzed using a TensorFlow-based emotion analysis model to determine the user's emotional state (stress level, relaxation level, etc.). Based on this analysis, the server utilizes an action selection module to suggest the most appropriate actions for the resident. Here, various environmental adjustments are suggested, such as playing music, adjusting lighting, and prioritizing household chores, using smart speaker technologies like Google Home or Amazon Alexa.

[0550] The system's terminals display notifications sent from the server and present their content to residents in descending order of priority. This makes it easier for residents to select recommended actions. Simultaneously, resident feedback is collected and sent to the server, improving the accuracy of future action suggestions. This feedback data is used in real time to optimize the system's sentiment analysis model and action selection module.

[0551] For example, if the system analyzes that a resident is experiencing stress, it will automatically play relaxing music tailored to that resident's preferences. Additionally, the server uses an AI model to generate prompts such as, "This user appears to be stressed. Please suggest a relaxing action suitable for them," and uses this to select the appropriate action.

[0552] In this way, the server can comprehensively improve the quality of life for residents by enabling real-time data analysis and user-oriented notification optimization.

[0553] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0554] Step 1:

[0555] The server acquires audio and image data from smart devices within the home. Specifically, it receives input signals from smart speakers and cameras. This data serves as the source material for analyzing emotional states.

[0556] Step 2:

[0557] The server inputs the received data into an emotion analysis model using TensorFlow to analyze the residents' emotional state. Here, stress levels and emotional intensity are quantified based on factors such as voice tone and facial expression changes. Data processing includes feature extraction based on voice analysis and detection of facial expression changes through image processing.

[0558] Step 3:

[0559] Based on the analysis results, the server uses a generative AI model to generate prompt messages. Specifically, it might create instructions such as, "This user appears to be stressed. Please suggest relaxing actions suitable for them." This prompt provides the necessary context for selecting an action.

[0560] Step 4:

[0561] The device receives notifications sent from the server and displays them on the user screen. These notifications offer suggestions such as playing relaxing background music or automatically adjusting the lighting. The notifications include specific action guidelines, presented in a format that the user can intuitively understand.

[0562] Step 5:

[0563] Users provide feedback on actions suggested via their device. This feedback is provided through touch operations or voice input. The feedback data is sent to a server and used to improve the accuracy of future action suggestions.

[0564] Step 6:

[0565] The server analyzes the collected feedback and updates the training datasets for the sentiment analysis model and the generative AI model. This process forms the basis for the continuous improvement of the system and for providing personalized services to users.

[0566] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0567] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0568] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0569] [Fourth Embodiment]

[0570] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0571] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0572] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0573] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0574] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0575] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0576] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0577] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0578] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0579] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0580] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0581] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0582] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0583] The system for implementing this invention is built around the roles of server, terminal, and user. First, the server collects weather information, aircraft operation information, runway operation information, and information on past accidents from various external databases and feeds. This information is acquired in real time and integrated within the server.

[0584] The server uses machine learning algorithms to analyze integrated information and assess risks. This analysis is based on historical data patterns and identifies potential risks related to aircraft operations. Based on this risk assessment, the server automatically selects the necessary safety measures. The selected safety measures are translated into multiple languages.

[0585] Next, the server sends the translated safety information to a terminal. This terminal is a device used by air traffic controllers and pilots. The terminal displays the received information appropriately and provides the user with immediate operational instructions. The air traffic controllers and pilots, as users, review the information provided through the terminal and take action as necessary.

[0586] A concrete example is when a server analyzes ground weather information and detects that a particular runway is dangerous due to strong winds. Based on this information, the server suggests an alternative runway and sends this information to the terminal in multiple languages. The pilot, as the user, checks the notification received on the terminal and follows the instructions to make a safe landing. In this way, the system can ensure the safety of air traffic inside and outside the airport and enable efficient operations.

[0587] The following describes the processing flow.

[0588] Step 1:

[0589] The server periodically collects weather information, aircraft operation information, runway operation information, and historical accident information from external databases and feeds. The server retrieves data via APIs and ensures data reliability by verifying statistical data consistency.

[0590] Step 2:

[0591] The server integrates information based on the data it collects. It converts data in different formats to a standard format and stores it in an integrated database. This ensures the timeliness and consistency of the data.

[0592] Step 3:

[0593] The server initiates risk analysis using integrated data. Machine learning algorithms are used to assess similarities to past accident and incident patterns and identify potential risks. The analysis results are scored, and the risk level is expressed numerically.

[0594] Step 4:

[0595] The server selects appropriate safety measures based on the analysis results. The selection criteria include risk scores, operational status, and weather conditions, and the optimal measures are automatically determined.

[0596] Step 5:

[0597] The server translates selected security measures into multiple languages. An automatic translation system is used to generate notifications and manuals in an internationally understandable format.

[0598] Step 6:

[0599] The server sends the translated safety information to the corresponding terminal. The terminal is a device used by air traffic controllers and pilots, and after receiving the data from the server, it displays it to the user in an appropriate format.

[0600] Step 7:

[0601] Air traffic controllers and pilots, as users, review the information received via their terminals. Based on the safety measures presented, they adjust and decide on flight operations. Feedback is provided to the system as needed, leading to further improvements.

[0602] (Example 1)

[0603] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0604] In modern air traffic management, real-time information gathering and analysis regarding weather and aircraft operational status are essential. However, there is a lack of effective systems for extracting appropriate risk information from vast amounts of data and responding quickly. Therefore, there is a need for means to effectively mitigate the risk of aviation accidents. Furthermore, ensuring the accuracy of information transmission in international aircraft operations using multiple languages ​​is a major challenge.

[0605] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0606] In this invention, the server includes query means for collecting information, means for integrating and preprocessing the collected information, and means for executing a machine learning algorithm for evaluating risk based on the integrated information. This enables real-time data updates and rapid decision-making based on appropriate risk assessment. Furthermore, a multilingual translation function facilitates international information sharing.

[0607] A "querying method" refers to a communication interface used to retrieve information from external databases or information sources.

[0608] "Preprocessing" refers to functions that perform data preprocessing, such as imputing missing values ​​and removing noise, to prepare the collected data for analysis.

[0609] A "machine learning algorithm" is a computational method used to predict risk from new data based on past data patterns.

[0610] "Translation means" refers to a function for converting specific safety information into multiple languages, thereby enabling international information sharing.

[0611] "Means of communication" refers to a network interface used to transmit processed information to a receiving device or control system.

[0612] A "receiving device" refers to a device used by users such as air traffic controllers and pilots to receive and visually confirm information.

[0613] A description of the embodiment for carrying out the invention will be provided.

[0614] The primary roles in realizing this system are played by the server, terminals, and users. The server first uses query mechanisms to acquire weather information, aircraft operation information, runway operation information, and data on past accidents from external sources and databases. This process requires data client devices connected to the internet, utilizing data access points via APIs.

[0615] The server then uses methods to integrate and preprocess the collected data. Specifically, it uses programming languages ​​such as Python and the Pandas library to impute missing values ​​and remove noise. It also organizes the data into time series to ensure real-time performance.

[0616] Risk assessment utilizes a method where the server executes machine learning algorithms. Machine learning libraries such as TensorFlow and scikit-learn are used to analyze past data patterns and identify risk factors. Based on this, the server calculates a risk score for each piece of information, which is then used as a basis for decision-making in the next step.

[0617] Based on the evaluation results, the server selects security measures and uses an automated translation service to translate this information into multiple languages. Using services such as the Google Cloud Translation API, the selection results are translated into multiple languages ​​and made accessible to users of various languages.

[0618] The server then sends the translated information to a terminal. This terminal is typically used by air traffic controllers and pilots and usually has specialized air traffic control software installed. As a result, users can view the information provided in real time through the terminal and take the instructed actions.

[0619] As a concrete example, let's consider a scenario where a specific runway is deemed unsafe due to strong winds caused by changes in weather information. In this case, the server proposes an alternative runway, translates that information into multiple languages, and sends it to the terminal. The pilot, as the user, receives the notification via the terminal and adjusts their flight route towards a safe landing point.

[0620] An example prompt illustrating the operation of the generated AI model is, "Perform a risk assessment and propose safety measures based on weather conditions and flight information at a specific airport." Based on this prompt, the AI ​​model will perform a specific risk assessment and propose safety measures.

[0621] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0622] Step 1:

[0623] The server uses query methods to collect information. Inputs include requests for weather information, aircraft operation information, runway operation information, and information on past accidents. The server retrieves this data via external databases or APIs. The output is a set of collected raw data. Specifically, the server accesses API endpoints over the network and receives data in JSON format.

[0624] Step 2:

[0625] The server uses means to integrate and preprocess the collected data. The input is the raw dataset collected in step 1. The server organizes the data, imputes missing values, and removes noise. The output is a normalized dataset. Specifically, the server uses the Pandas library to impute missing values ​​in the data with the mean and to detect and remove outliers.

[0626] Step 3:

[0627] The server runs a machine learning algorithm to assess risk on normalized data. The input is the normalized dataset generated in step 2. The server calculates a risk score based on a model learned from historical data. The output is the risk assessment result for each aviation option. Specifically, the server uses TensorFlow to run a neural network and generate scores under specific weather conditions.

[0628] Step 4:

[0629] The server selects the necessary safety measures based on the risk assessment and translates them into multiple languages. The input is the risk assessment result from step 3. The server selects the optimal measures and translates them into multiple languages ​​via a translation service. The output is the translated safety measures information. Specifically, the server uses the Google Cloud Translation API to translate the selected information from English into other major languages.

[0630] Step 5:

[0631] The server sends the translated information to the terminal. The input is the multilingual security information generated in step 4. The server transmits this information to the user's terminal via wireless communication. The output is information in a format that can be displayed on the terminal. Specifically, the server securely pushes the data using the HTTPS protocol, triggering a notification on the terminal.

[0632] Step 6:

[0633] The user receives information provided through the terminal and takes action according to the instructions. The input is the notification received on the terminal in step 5. The user checks the information on the terminal screen and selects the necessary action. The output is the specific action based on the execution of safety measures. As a specific action, the pilot adjusts the instruments to the suggested alternative runway and ensures a safe landing path.

[0634] (Application Example 1)

[0635] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0636] Currently, a challenge in operating autonomous vehicles is the need to quickly grasp weather conditions and road surface conditions and issue operational instructions based on predicted risks. Conventional systems lack real-time information updates, making it difficult to take appropriate measures quickly. Furthermore, in situations where multilingual support is essential, information may not be translated properly, potentially compromising operational safety. As a result, the safety and efficiency of autonomous vehicles are not adequately ensured, and effective means to improve this are needed.

[0637] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0638] In this invention, the server includes means for integrating weather information, operational information, road surface condition information, and information on past accidents; means for analyzing operational risks; and means for proposing alternative routes in real time. This enables the provision of rapid and accurate safety measures and operational instructions to autonomous vehicles, resulting in safe and efficient driving.

[0639] "Weather information" refers to data related to the natural environment, such as precipitation, wind speed, and temperature, and is necessary information for evaluating the operational environment.

[0640] "Operational information" refers to traffic-related data and various status information, such as the vehicle's current location, speed, and route.

[0641] "Road surface condition information" refers to information that indicates the condition of the road and the presence or absence of obstacles, and is essential information for safe driving.

[0642] "Information regarding past accidents" refers to data that includes details of previously occurring accidents, their causes, and their impact.

[0643] "Methods for analyzing operational risks" refer to methods for identifying potential risk factors and evaluating their impact based on various collected information.

[0644] "Methods for proposing alternative routes" refer to the process of finding and proposing safe detours when the current route is deemed dangerous.

[0645] "A means of continuously updating in real time" refers to a technology that keeps ever-changing information up-to-date and reflects it immediately.

[0646] A "machine learning algorithm" is a technology that learns patterns based on past data and uses that knowledge to make predictions and classifications on new data.

[0647] "Multilingual generation methods" refer to technologies that translate information into multiple languages ​​in order to provide the same information to users who speak different languages.

[0648] This system supports the safe and efficient operation of autonomous vehicles. The server collects and integrates weather information, operational information, road surface condition information, and information on past accidents. This data is retrieved in real time from external databases and APIs and integrated within the server.

[0649] The server processes the integrated information and uses machine learning algorithms to analyze operational risks. This utilizes machine learning platforms such as TensorFlow. It learns patterns from past accident data and identifies potential risks in current operations. Based on this risk assessment, the server selects necessary safety measures and translates them into multiple languages.

[0650] Next, the server provides real-time suggestions for routes and alternative routes. Using the Google Maps API and other tools, it calculates the optimal route considering current traffic conditions. It then sends the results to the terminal, providing instructions to the autonomous vehicle.

[0651] The terminal displays received information on the vehicle's display and audio system, providing responsive operational instructions to the driver and vehicle control system. The user, either the driver or the vehicle, follows the terminal's instructions to ensure safe and optimal operation. This significantly improves the safety and efficiency of the autonomous vehicle.

[0652] For example, if a sunny day is forecast but unexpected heavy rain occurs, the system can immediately assess the risk, suggest alternative routes to avoid roads with many puddles, and display instructions to encourage drivers to slow down.

[0653] An example of a prompt sentence to input into the generating AI model would be, "Please suggest the optimal route for safely arriving at the destination in an autonomous vehicle during heavy rain."

[0654] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0655] Step 1:

[0656] The server collects weather information, traffic information, road surface condition information, and information on past accidents in real time from external databases and APIs. This data is obtained in JSON format and integrated in preparation for subsequent processing. It receives responses from various APIs as input and generates an integrated dataset as output.

[0657] Step 2:

[0658] The server uses an integrated dataset to analyze operational risks with machine learning algorithms based on TensorFlow. It accepts the integrated dataset as input and outputs a risk assessment score based on pattern recognition and predictive models. This identifies potential risks related to weather, traffic conditions, and road conditions.

[0659] Step 3:

[0660] The server uses the Google Maps API to calculate alternative routes based on the risk assessment score. It receives the risk assessment score and current route information as input and outputs a safe and efficient alternative route. This ensures that the vehicle is directed to a route that allows it to reach its destination more safely.

[0661] Step 4:

[0662] The server translates the selected alternative route and operational instructions into multiple languages ​​as needed. In this step, it receives alternative route information and the selected language as input and outputs multilingual operational instructions. The translated information is provided to the user in a human-readable format.

[0663] Step 5:

[0664] The terminal displays translated operational instructions received from the server and provides instructions to the user or vehicle control system via voice or display. It receives translated operational instructions as input and immediately notifies and outputs them to the user. This allows drivers to operate safely and efficiently based on the instructions.

[0665] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0666] The system for implementing this invention consists primarily of a server, terminals, users, and an emotion engine. First, the server collects and integrates weather information, aircraft operation information, runway operation information, and past accident information from various external databases. Based on this integrated information, the server uses machine learning algorithms to analyze risks and select safety measures appropriate for the specific situation.

[0667] The selected safety measures are optimized by an emotion engine based on the user's emotional state. The server evaluates the emotions of the user, such as an air traffic controller or pilot, in real time through voice analysis. Based on this emotional state, the content and presentation method of notifications are automatically adjusted and transmitted in a way that facilitates user understanding.

[0668] As a concrete example, consider a scenario where a server detects a risk to runway use due to strong winds and issues a warning. When the emotion engine detects a high level of stress from the pilot's voice, the server provides a more detailed and careful explanation in the notification. In this way, the system can respond flexibly according to the user's psychological state.

[0669] The terminal displays emotion-based notifications sent from the server, providing users with clear guidance for action. Users review the information provided through the terminal and take safety measures as needed. This feedback is evaluated by an emotion engine and used as data for future system improvements. This process allows the system to improve air traffic safety while reducing the psychological burden on users.

[0670] The following describes the processing flow.

[0671] Step 1:

[0672] The server collects weather information, aircraft operation information, runway operation information, and historical accident information from various data sources. The server integrates this data and stores it in a database, enabling real-time access.

[0673] Step 2:

[0674] The server uses the integrated data to run machine learning algorithms and initiate risk analysis. It compares current incident data with past incident data to identify potential risks in the current operational situation. Risk levels are scored and prioritized.

[0675] Step 3:

[0676] The server selects appropriate safety measures based on the results of the risk analysis. The selection criteria include the risk level and scope of impact, and the specific measures are determined and recorded.

[0677] Step 4:

[0678] The emotion engine analyzes the user's voice and behavioral data to evaluate the user's emotional state. If stress or tension is high, the emotion engine records this state and provides feedback to the server.

[0679] Step 5:

[0680] The server receives feedback from the emotion engine and adjusts the content and tone of safety alerts according to the emotional state. For example, if a high stress level is detected, detailed explanations and steps will be added to the alert.

[0681] Step 6:

[0682] The server sends optimized safety notifications to the terminal. The terminal is a device used by air traffic controllers and pilots, and it has the function to display the information from the server appropriately.

[0683] Step 7:

[0684] The user reviews the information provided through their device and takes the instructed safety measures as needed. User behavior and responses are fed back into the system to help with continuous improvement.

[0685] (Example 2)

[0686] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0687] Improving air traffic safety requires real-time information updates and accurate risk assessment, but conventional systems lacked sufficient capabilities in these areas. Furthermore, information delivery was not optimized based on the user's emotional state, creating a risk that important information might not be properly communicated.

[0688] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0689] In this invention, the server includes means for integrating weather information, aircraft operation information, air route operation information, and information on past incidents; means for analyzing risks based on the integrated information; and means for optimizing selected safety measures based on an algorithm that recognizes emotions. This enables flexible information transmission in accordance with the user's emotional state and rapid and accurate risk assessment.

[0690] "Weather information" refers to data about weather conditions, including information such as the state of the sky, temperature, humidity, wind speed, and wind direction.

[0691] "Aircraft operation information" refers to data related to the operation of aircraft, such as departure, arrival, route, speed, and altitude.

[0692] "Air route operation information" refers to information about the usage status, closure status, available times, and restrictions of air routes.

[0693] "Past incidents" refers to records of aviation-related accidents and near misses that have occurred in the past.

[0694] "Means of integrating information" refers to the process or mechanism for organizing information obtained from different data sources and combining it into a single, unified format.

[0695] "Means of risk analysis" refer to algorithms and methods for predicting and identifying potential risks based on integrated information.

[0696] "Means for selecting safety measures" refers to methods for determining the optimal response to an analyzed hazard.

[0697] An "emotion recognition algorithm" is a computational method for analyzing and recognizing emotions from a person's voice and facial expressions.

[0698] An embodiment of this invention consists of a server, a terminal, a user, and a sentiment analysis engine. The server retrieves weather information, aircraft operation information, air route operation information, and data on past incidents from an external database. This is done using the Python requests library. The server stores the collected data in a Pandas DataFrame and integrates the data using the merge function. Unnecessary data is filtered at this stage.

[0699] The server runs a machine learning model using the Scikit-learn library to analyze risks based on the integrated data. This model is pre-trained on historical data. Based on the risk assessment results, the server selects appropriate safety measures from the database, and these safety measures are optimized by a sentiment analysis engine.

[0700] The emotion analysis engine uses LibROSA for speech processing to acquire voice data from users, such as air traffic controllers and aircraft operators. The acquired voice data is analyzed through a TensorFlow deep learning model to evaluate the user's emotional state. Based on this information, the content and format of notifications are optimized.

[0701] The terminal displays optimized notifications sent from the server. The user checks the notifications on the terminal and takes specific actions. For example, if the server detects a risk of strong winds and sends a notification, the notification will appear as a pop-up on the terminal and will also be announced audibly. If the user, who is the aircraft operator, checks this notification, they will be required to adjust their actions as instructed.

[0702] User behavior and its consequences are collected via the device as feedback and stored in a server database. This feedback is used to improve the sentiment analysis engine and risk analysis model.

[0703] A concrete example of a prompt message would be: "Based on the latest weather data and aircraft operation information, please generate safety measures and suggest notification content tailored to the user's emotional state."

[0704] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0705] Step 1:

[0706] The server collects weather information, aircraft operation information, air route operation information, and past trouble information from an external database. It receives this information, obtained from an API, as input and extracts the data using the Python requests library. The output is a Pandas DataFrame containing the various types of information. Specifically, it uses asynchronous processing to quickly retrieve information and store it in the DataFrame.

[0707] Step 2:

[0708] The server runs a machine learning model to analyze risk based on information integrated into a Pandas DataFrame. The integrated data obtained in the previous step is used as input. A random forest model using Scikit-learn is applied to predict risk. The output is a list of situations where risk has been identified. The model is pre-trained and tuned using historical data.

[0709] Step 3:

[0710] The server selects appropriate safety measures from the database based on the identified risks. Using the risk analysis results as input and referencing the safety measures database, it determines the optimal measures to address the situation. The output is a list of selected safety measures. Here, a data matching algorithm is used to identify recommended measures for each risk.

[0711] Step 4:

[0712] The emotion analysis engine evaluates emotional states using user voice input. The input consists of real-time voice data from air traffic controllers and aircraft operators. Voice features are extracted using LibROSA and analyzed by an emotion recognition model built with TensorFlow. The output is a numerical evaluation of the emotional state. Here, features such as voice pitch and tempo are calculated, and the model evaluates emotions such as stress and tension.

[0713] Step 5:

[0714] The server optimizes the content and format of notifications based on an assessment of the user's emotional state. The emotional assessment obtained in the previous step is used as input. Notifications are tailored to be easily understood by the user, with particularly important information highlighted. The output is the optimized notification message. Specifically, HTML / CSS is used to modify the notification layout for better readability.

[0715] Step 6:

[0716] The terminal displays notifications sent from the server using a dedicated application. The input is an optimized notification message from the server. The notification is displayed as a pop-up on the terminal screen, and the content can also be confirmed via audio output. The output is the notification content that the user can visually confirm. A user-friendly interface is provided using a GUI framework.

[0717] Step 7:

[0718] The user takes specific actions based on the notification and provides feedback via the device. The input is the content of the notification displayed on the device. The device has a feedback input function, where the user inputs the actions taken and their results. The output is the feedback data, which is stored in the server's database and used to improve the algorithm in the future.

[0719] (Application Example 2)

[0720] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0721] In modern homes, providing optimal environmental adjustments and household support tailored to the emotional state of residents is crucial for improving their quality of life. However, conventional technologies have struggled to accurately grasp individual emotional states and automatically provide flexible responses based on them. This invention solves the problem of improving quality of life by analyzing residents' emotional states in real time and providing optimal action suggestions accordingly.

[0722] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0723] In this invention, the server includes means for integrating weather data, flight data, operational data, and historical case information; means for analyzing risks based on the integrated data; and means for analyzing the user's state and optimizing notification content. This makes it possible to accurately grasp the emotional state of residents in real time and propose optimal household support and environmental adjustments based on that.

[0724] "Weather data" refers to information related to weather, including data on environmental conditions such as temperature, humidity, and wind speed.

[0725] "Flight data" refers to information related to the operation status of aircraft and transportation services, including departure and arrival times, routes, and operational status.

[0726] "Operational data" refers to information about the usage and performance of a specific system or piece of equipment, including data on its operational status and maintenance history.

[0727] "Historical case information" refers to data about past incidents and episodes, including insights and lessons learned from past events.

[0728] "Risk analysis" is the process of evaluating potential dangers and problems based on integrated data, and analyzing their probability of occurrence and impact.

[0729] "Analyzing the user's condition" is the process of evaluating the user's emotions and psychological state using data, and then deciding on appropriate responses based on the results.

[0730] "Optimizing notification content" means adjusting the content and method of notifications provided to users based on the analyzed information, according to the situation.

[0731] The system implementing this invention consists primarily of a server, terminals, users, and an emotion engine. The system aims to analyze the emotional state of residents in real time and provide optimal support accordingly.

[0732] The server acquires data from audio and images collected within the home via smart devices. This data is analyzed using a TensorFlow-based emotion analysis model to determine the user's emotional state (stress level, relaxation level, etc.). Based on this analysis, the server utilizes an action selection module to suggest the most appropriate actions for the resident. Here, various environmental adjustments are suggested, such as playing music, adjusting lighting, and prioritizing household chores, using smart speaker technologies like Google Home or Amazon Alexa.

[0733] The system's terminals display notifications sent from the server and present their content to residents in descending order of priority. This makes it easier for residents to select recommended actions. Simultaneously, resident feedback is collected and sent to the server, improving the accuracy of future action suggestions. This feedback data is used in real time to optimize the system's sentiment analysis model and action selection module.

[0734] For example, if the system analyzes that a resident is experiencing stress, it will automatically play relaxing music tailored to that resident's preferences. Additionally, the server uses an AI model to generate prompts such as, "This user appears to be stressed. Please suggest a relaxing action suitable for them," and uses this to select the appropriate action.

[0735] In this way, the server can comprehensively improve the quality of life for residents by enabling real-time data analysis and user-oriented notification optimization.

[0736] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0737] Step 1:

[0738] The server acquires audio and image data from smart devices within the home. Specifically, it receives input signals from smart speakers and cameras. This data serves as the source material for analyzing emotional states.

[0739] Step 2:

[0740] The server inputs the received data into an emotion analysis model using TensorFlow to analyze the residents' emotional state. Here, stress levels and emotional intensity are quantified based on factors such as voice tone and facial expression changes. Data processing includes feature extraction based on voice analysis and detection of facial expression changes through image processing.

[0741] Step 3:

[0742] Based on the analysis results, the server uses a generative AI model to generate prompt messages. Specifically, it might create instructions such as, "This user appears to be stressed. Please suggest relaxing actions suitable for them." This prompt provides the necessary context for selecting an action.

[0743] Step 4:

[0744] The device receives notifications sent from the server and displays them on the user screen. These notifications offer suggestions such as playing relaxing background music or automatically adjusting the lighting. The notifications include specific action guidelines, presented in a format that the user can intuitively understand.

[0745] Step 5:

[0746] Users provide feedback on actions suggested via their device. This feedback is provided through touch operations or voice input. The feedback data is sent to a server and used to improve the accuracy of future action suggestions.

[0747] Step 6:

[0748] The server analyzes the collected feedback and updates the training datasets for the sentiment analysis model and the generative AI model. This process forms the basis for the continuous improvement of the system and for providing personalized services to users.

[0749] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0750] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0751] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0752] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0753] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0754] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0755] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0756] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0757] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0758] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0759] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0760] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0761] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0762] 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.

[0763] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0764] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0765] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0766] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0767] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0768] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0769] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0770] The following is further disclosed regarding the embodiments described above.

[0771] (Claim 1)

[0772] A means for integrating weather information, aircraft operation information, runway operation information, and information on past accidents,

[0773] A means for analyzing risk based on the aforementioned integrated information,

[0774] A means for selecting appropriate safety measures based on the aforementioned risk analysis,

[0775] A means of generating selected safety measures in multiple languages,

[0776] Means for transmitting the generated information to air traffic controllers or aircraft pilots,

[0777] A system that includes this.

[0778] (Claim 2)

[0779] The system according to claim 1, comprising means for continuously updating the integrated information in real time.

[0780] (Claim 3)

[0781] The system according to claim 1, wherein the risk analysis means includes means for executing a machine learning algorithm using past incident data.

[0782] "Example 1"

[0783] (Claim 1)

[0784] Inquiry methods for gathering information,

[0785] Means for integrating and preprocessing the collected information,

[0786] A means for executing a machine learning algorithm to assess risk based on the aforementioned integrated information,

[0787] A means for selecting necessary safety measures based on the aforementioned risk assessment,

[0788] A means for translating the selected safety measures into multiple languages,

[0789] Means for communicating the translated information to the control system,

[0790] A means comprising a receiving device that displays operating procedures in accordance with the aforementioned information,

[0791] A system that includes this.

[0792] (Claim 2)

[0793] The system according to claim 1, comprising means for updating and dynamically reflecting the aforementioned information in real time.

[0794] (Claim 3)

[0795] The system according to claim 1, wherein the risk assessment means includes means for applying a descriptive algorithm considering existing event data.

[0796] "Application Example 1"

[0797] (Claim 1)

[0798] A means for integrating weather information, operational information, road surface condition information, and information on past accidents,

[0799] A means for analyzing operational risks based on the aforementioned integrated information,

[0800] A means for selecting appropriate safety measures based on the aforementioned risk analysis,

[0801] A means of generating selected safety measures in multiple languages,

[0802] Means for transmitting the generated information to the transporter or pilot,

[0803] A means of proposing alternative routes in real time,

[0804] A system that includes this.

[0805] (Claim 2)

[0806] The system according to claim 1, comprising means for continuously updating the integrated information and safety measures in real time.

[0807] (Claim 3)

[0808] The system according to claim 1, wherein the risk analysis means includes means for executing a machine learning algorithm using past incident data.

[0809] "Example 2 of combining an emotion engine"

[0810] (Claim 1)

[0811] A means for integrating weather information, aircraft operation information, air route operation information, and information on past incidents,

[0812] A means for analyzing the risks based on the aforementioned integrated information,

[0813] A means for selecting appropriate safety measures based on the aforementioned risk analysis,

[0814] A means of optimizing selected safety measures based on an algorithm that recognizes emotions,

[0815] Means for transmitting the generated information to an air traffic controller or aircraft operator,

[0816] A system that includes this.

[0817] (Claim 2)

[0818] The system according to claim 1, comprising means for continuously updating the integrated information in real time.

[0819] (Claim 3)

[0820] The system according to claim 1, wherein the risk analysis means includes means for executing a machine learning algorithm using past case data and evaluating emotional states.

[0821] "Application example 2 when combining with an emotional engine"

[0822] (Claim 1)

[0823] A means of integrating weather data, flight data, operational data, and historical case information,

[0824] A means for analyzing risk based on the aforementioned integrated data,

[0825] A means for determining appropriate safety measures based on the aforementioned risk analysis,

[0826] A means to analyze the user's status and optimize notification content,

[0827] Means for presenting optimized information to users in multiple ways,

[0828] A system that includes this.

[0829] (Claim 2)

[0830] The system according to claim 1, comprising means for continuously updating the integrated data in real time.

[0831] (Claim 3)

[0832] The system according to claim 1, wherein the risk analysis means comprises means for executing an algorithm using historical data. [Explanation of Symbols]

[0833] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for integrating weather information, operational information, road surface condition information, and information on past accidents, A means for analyzing operational risks based on the aforementioned integrated information, A means for selecting appropriate safety measures based on the aforementioned risk analysis, A means of generating selected safety measures in multiple languages, Means for transmitting the generated information to the transporter or pilot, A means of proposing alternative routes in real time, A system that includes this.

2. The system according to claim 1, comprising means for continuously updating the integrated information and safety measures in real time.

3. The system according to claim 1, wherein the risk analysis means includes means for executing a machine learning algorithm using past incident data.

Images