system

Abstract

Provide a system. 【Solution means】 Means for collecting aircraft data and social network service data, Means for analyzing the collected data to identify important areas, Means for generating and transmitting an instruction based on the important area, A mobile terminal that starts an action based on the instruction, Means for receiving feedback from the mobile terminal and updating the instruction, Means for obtaining the user's location information, identifying and providing a safe evacuation route, Means for analyzing a disaster situation image from an aircraft or a communication satellite and providing information, Means for analyzing post data from a social network platform using natural language processing technology and evaluating its importance, A system including the above.

Description

Technical Field

[0004] , , , ,

[0005] , , , ,

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a 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 event of a disaster, rapid and effective information collection, determination of damage priorities, resource optimization, and immediate response at the scene are required. However, there is a problem that it is difficult to perform these in real time by conventional human-dependent methods. Furthermore, there is a problem that there is a lack of efficient means for analyzing a huge amount of data in a short time and generating appropriate instructions.

Means for Solving the Problems

[0005] This invention provides a system for collecting aircraft data and social network service data, and for analyzing the collected data to identify critical areas, thereby enabling a rapid and accurate response to disaster-stricken areas. Furthermore, by providing means for generating and transmitting instructions based on the critical areas, it enables on-site equipment to start acting immediately, and by receiving feedback and updating instructions, it allows for real-time adjustment of the response. This solves conventional problems and realizes an efficient and effective disaster response.

[0006] "Aircraft data" refers to images and data captured or collected by unmanned aerial vehicles or satellites.

[0007] "Social network service data" refers to posts and information shared on SNS platforms, and in the event of a disaster, it includes real-time reports from local citizens.

[0008] "Analysis tools" refer to devices that have the ability to analyze collected data using computer vision or natural language processing technologies and extract specific patterns.

[0009] A "critical area" refers to an area that is judged to have suffered significant damage from a disaster and requires priority response.

[0010] "Instruction generation means" refers to a system that has the function of formulating specific action plans and countermeasures based on analyzed data and notifying users of them.

[0011] "Equipment" refers to portable terminals and communication devices used at disaster response sites, which are tools for coordinating actions based on instructions.

[0012] "Feedback" refers to situation reports and response results sent from the field, which serve as the basis for updating the system's instructions. [Brief explanation of the drawing]

[0013] [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. [Modes for carrying out the invention]

[0014] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. 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.

[0017] In the following embodiments, the signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, the signed 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, etc.

[0019] In the following embodiments, the signed communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), etc.

[0020] 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."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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".

[0034] This invention is a system for achieving a rapid and effective response in the event of a disaster. It identifies critical areas based on the analysis of aircraft data and social network service data, and directs actions at the scene. This system is implemented through the processes of information gathering, data analysis, instruction generation, action instruction, and feedback reception.

[0035] Information gathering

[0036] The server acquires image data from unmanned aerial vehicles and satellites to monitor disaster situations in real time. It also collects posts from various social media platforms, accumulating raw information from local citizens in a database.

[0037] Data Analysis

[0038] The server analyzes image data acquired using computer vision to identify the extent and location of the damage. Simultaneously, it uses natural language processing technology to analyze social media posts and evaluate their urgency and reliability.

[0039] Instruction generation and notification

[0040] Based on the analyzed data, the server prioritizes affected areas and generates specific rescue plans and resource deployment plans. These instructions are then communicated to on-site users via terminals to help them take immediate action.

[0041] Receiving instructions and feedback

[0042] Users with terminals follow instructions received from the server to carry out rescue operations and deliver supplies in designated areas. Information gathered during the operation is sent to the server as feedback, which is then analyzed to adjust subsequent instructions.

[0043] Specific example

[0044] For example, in the event of a major earthquake, the server immediately deploys multiple unmanned aerial vehicles to capture images of the affected area. In addition, it collects social media posts from local residents to identify damage to infrastructure and disruptions to lifelines caused by the earthquake. The server identifies critical areas from the data it processes and sends priority rescue operation plans to rescue teams' terminals. This allows rescue workers (users) on the ground to check their terminals and take immediate action.

[0045] Thus, the present invention is a system that enables a rapid and accurate response to disasters and supports the early recovery of disaster-stricken areas.

[0046] The following describes the processing flow.

[0047] Step 1:

[0048] The server collects image data from the aircraft and posted data from social networking services. The unmanned aerial vehicle takes pictures of the disaster area and sends them to the server. At the same time, the server retrieves posts related to the disaster in real time using SNS APIs.

[0049] Step 2:

[0050] The server analyzes the received image data using computer vision technology to determine the extent and severity of the damage. It detects important features and damaged infrastructure within the images and stores the results in a database.

[0051] Step 3:

[0052] The server analyzes data posted from social media using natural language processing, extracting detailed disaster information, location data, and urgency levels from the text content. It filters out inaccurate information and accumulates highly reliable data.

[0053] Step 4:

[0054] The server integrates the analysis results of image data and social media data to determine the priority of critical areas. Based on this, it creates rescue operation and resource allocation plans and lists the priorities for each area.

[0055] Step 5:

[0056] The server notifies the terminal of the generated instructions. The terminal provides the user, a rescue team or aid organization, with a detailed action plan in real time, outlining specific activities to be carried out in the designated area.

[0057] Step 6:

[0058] Users follow instructions received via their terminals and carry out activities such as life-saving and supply transport at the scene. They report the situation and results of their activities to the server via their terminals.

[0059] Step 7:

[0060] The server receives user feedback and re-analyzes the situation to reflect the latest developments. This allows it to update instructions as needed and maintain the optimal response.

[0061] (Example 1)

[0062] 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."

[0063] During disasters, there is a need to collect, analyze, and issue response instructions for information quickly and efficiently. However, conventional systems have difficulty collecting information over a wide area in real time and making urgent decisions quickly, which has led to delays and confusion in on-site responses.

[0064] 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.

[0065] In this invention, the server includes means for storing high-resolution image information and information posted from social networks, means for analyzing the information using computer vision technology and natural language processing technology to identify critical areas, and means for generating rescue plans and resource allocation plans based on priorities and notifying them via communication devices. This enables rapid and appropriate information gathering and instruction generation in the event of a disaster.

[0066] "High-resolution image information" refers to image data containing detailed visual information, captured by devices such as unmanned aerial vehicles.

[0067] A "social network" is a platform on the internet for people to share information and interact with each other.

[0068] "Posted information" refers to data such as text, images, and videos that are made public by users on social networks.

[0069] "Computer vision technology" is a technology that uses computers to analyze image and video data and extract information that can be recognized by human vision.

[0070] "Natural language processing technology" is a technology that allows computers to understand, interpret, and process human language in a natural way.

[0071] A "critical area" refers to an area that requires special attention in the event of a disaster or other situation.

[0072] "Priority" refers to the order in which multiple options should be prioritized and implemented first.

[0073] A "rescue plan" is a specific action plan formulated in the event of an emergency with the aim of saving lives and mitigating damage.

[0074] A "resource allocation plan" is a plan for allocating necessary resources to the appropriate locations and utilizing them effectively.

[0075] A "communication device" is an electronic device used to send and receive information, and is usually connected to the internet or other networks.

[0076] A "portable information terminal" is an electronic device that is portable and used for inputting and outputting information and for communication.

[0077] "Information on implementation results" refers to the collective term for reports and data obtained after the execution of a specific action or process.

[0078] This invention is a digital information system designed to enable rapid and accurate responses during disasters. The main technologies used include computer vision technology for analyzing high-resolution image information and natural language processing technology for analyzing posted information collected from social networks.

[0079] The server receives high-resolution image information collected using unmanned aerial vehicles and satellites, and analyzes its geographical features and the extent of damage. Image recognition algorithms and pattern recognition models are used in this analysis. The server also collects user-submitted information from various social networking platforms on the internet. This allows for an understanding of the local situation and reports from citizens.

[0080] The analysis uses natural language processing techniques to evaluate the urgency and reliability of the posted content. This involves using an AI model to perform semantic analysis of the text. Through this series of analysis processes, the server identifies critical regions and determines whether priority action is needed for those regions.

[0081] Users with terminals receive rescue plans and resource deployment plans generated by the server. These plans include specific rescue points and detailed procedures for the activities. This allows users to quickly initiate necessary actions and efficiently carry out support activities on-site. Furthermore, users provide feedback to the server through their terminals about the results obtained during the activities. This feedback allows the server to re-evaluate the situation and continuously update instructions as needed.

[0082] Specific example

[0083] For example, in the event of a large-scale flood, the server uses unmanned aerial vehicles to photograph the affected area, analyze the images, and identify flooded zones. Simultaneously, it collects information from residents' posts on social media platforms to understand rising water levels and the need for evacuation. Based on this information, the server generates an evacuation plan and notifies the user's device. The user receives the instructions and quickly deploys evacuation support.

[0084] Example of a prompt

[0085] "Please provide a detailed explanation of the entire process in this disaster response system, from real-time image collection using drones and satellites, to data analysis and rescue plan generation by servers, notification to terminals, and finally to the user's on-site activities."

[0086] Thus, by combining advanced data analysis technology with mobile communication, the present invention can significantly improve the efficiency of disaster response.

[0087] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0088] Step 1:

[0089] The server acquires high-resolution image information in real time from unmanned aerial vehicles (UAVs) and satellites. This input data includes detailed visual information of the entire disaster area. Specifically, the server establishes communication with these vehicles and periodically retrieves image data. The output consists of tens to hundreds of high-resolution images illustrating the disaster situation.

[0090] Step 2:

[0091] The server analyzes the acquired high-resolution image information using computer vision technology. The input data includes previously acquired images. At this stage, algorithms are in operation that recognize buildings, roads, and natural terrain within the images, and identify the scale and location of damage. For example, it identifies areas with no damage and areas with significant damage, and outputs such as damage distribution maps and risk assessment reports are generated.

[0092] Step 3:

[0093] The server collects posted information from social networks. The input data for this step consists of text and image information posted by users on online platforms. Based on this, natural language processing techniques are used to evaluate the urgency and reliability of the posted content. Specifically, posts containing certain hashtags or keywords are filtered, and the output presents a list of the urgency of the information and a reliability evaluation.

[0094] Step 4:

[0095] Based on the analysis results obtained in steps 2 and 3, the server identifies and prioritizes critical areas. The input data consists of image analysis results and post analysis results. As output, the server generates a list of critical areas sorted by priority, along with corresponding rescue plans and resource deployment plans. This operation provides guidance for quickly identifying high-priority areas.

[0096] Step 5:

[0097] The server notifies local users via their terminals of the generated rescue and resource deployment plans. The input data is the plan generated in the previous step. Specifically, the server triggers the notification system and sends a message to the user's terminal. The output is that the rescue plan is communicated to each user, triggering them to begin their activities.

[0098] Step 6:

[0099] The user begins their activities on-site following instructions on their terminal. Input here consists of rescue plans and instructions received from the server. Specifically, the user makes real-time situational assessments and carries out rescue operations. Information obtained during the activity is fed back to the server via the terminal. Output includes collected information on the results of the operation, which is used to adjust instructions for the next step.

[0100] Step 7:

[0101] The server receives feedback from the user and updates instructions as needed. The input for this step is user feedback data, and the output is a revised version of the instructions or plan based on that feedback. Specific actions include re-analyzing the received information, ensuring that the server always responds optimally to the latest situation.

[0102] (Application Example 1)

[0103] 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."

[0104] In recent years, the frequency of natural disasters has increased, making rapid and effective disaster response crucial. However, quickly assessing the extent of damage on the ground and providing appropriate instructions is not easy. Furthermore, providing real-time information to those conducting on-site relief activities and flexibly allocating resources according to the situation are also challenges. This invention aims to solve these problems and provide a system for streamlining disaster relief activities.

[0105] 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.

[0106] In this invention, the server includes means for collecting aircraft data and social network service data, means for analyzing the collected data to identify critical areas, and means for generating and transmitting instructions based on the critical areas. This enables highly accurate identification of damaged areas and rapid provision of rescue instructions using information from aircraft and communication satellites.

[0107] "Aircraft data" refers to image data and location information acquired from unmanned aerial vehicles and communication satellites, and is used in disaster situations to confirm the extent of damage and identify critical areas.

[0108] "Social network service data" refers to data such as text and images posted by users on social media platforms, and is used to understand the situation in disaster-stricken areas in real time.

[0109] A "critical area" is an area where, based on the extent and urgency of the damage during a disaster, priority support and rescue operations are required.

[0110] "Means for generating and transmitting instructions" refers to a processing mechanism for creating support plans and instructions for rescue operations based on collected and analyzed data, and transmitting them to various terminals.

[0111] A "mobile terminal" is an information and communication device carried by a user, and in the event of a disaster, it is used to receive rescue instructions in real time and to provide safe evacuation routes and other information based on location data.

[0112] "Natural language processing technology" is a technology that uses computers to understand and analyze human language (natural language), and is used to evaluate the urgency and reliability of posts collected from social media platforms.

[0113] To implement this invention, it is necessary to construct a system that supports rapid assessment of damage and priority rescue operations in disaster-stricken areas. This system utilizes a cloud computing environment to acquire aircraft data from unmanned aerial vehicles and communication satellites in real time and store it on a server. This data is processed by image analysis algorithms and used to understand the current situation in the affected area. Specifically, computer vision technology is used, and the analysis is performed using models such as OpenCV or TENSORFLOW®.

[0114] The server also analyzes social networking service data collected from social media platforms using natural language processing techniques. This allows it to assess the urgency and reliability of posts and identify important regions. Generative AI models such as BERT are used for natural language processing.

[0115] A terminal is an information and communication device carried by the user that acquires location information and transmits it to a server. Based on this location information, the server generates appropriate evacuation routes and support activity information in emergencies and delivers it to the terminal as a push notification. Firebase Cloud Messaging is often used in this process.

[0116] As a concrete example, in the event of a large-scale flood, the server analyzes the damage based on image data taken by unmanned aerial vehicles and social media posts from citizens, and identifies areas that require evacuation. Each user is notified on their device with evacuation route information and other important information related to their location. An example of a prompt message might be, "Please tell me how to find a safe evacuation location and the best route during a flood."

[0117] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0118] Step 1:

[0119] The server acquires aircraft data from unmanned aerial vehicles (UAVs) and communication satellites. The acquired data is stored in the server's data storage in real time. The input is image data from UAVs and satellites, and the output is the stored raw data. This raw data is used in subsequent analysis steps.

[0120] Step 2:

[0121] The server performs computer vision analysis on the acquired aircraft data. Specifically, it uses OpenCV and TensorFlow to detect anomalies in the affected areas from the image data. The input is the stored image data, and the output is the analysis results identifying the affected areas. The data is classified according to the magnitude and type of damage.

[0122] Step 3:

[0123] The server collects social networking service data from social media platforms. This data consists of user posts about disasters, which are analyzed by the server using natural language processing techniques. The input is the text information of SNS posts, and the output is an evaluation of urgency and reliability. This evaluation is performed using generative AI models such as the BERT model.

[0124] Step 4:

[0125] The server identifies critical areas and generates specific support plans and evacuation routes based on the analysis results of aircraft data and social network service data. The input is the analysis results obtained in steps 2 and 3, and the output is information on evacuation routes and support plans. The generated information is distributed to users as an emergency notification.

[0126] Step 5:

[0127] The device receives notifications from the server and displays information to the user. The input is notification data sent from the server, and the output is a visual presentation of information to the user. Based on the notification, the device uses location information to display the optimal evacuation route and important alerts.

[0128] Step 6:

[0129] Users begin taking action based on evacuation routes and support information provided through their devices. Input is the information displayed on the device, and output is the user's actual actions. While evacuating, users send feedback from their devices to the server as needed.

[0130] Step 7:

[0131] The server receives feedback from the user and updates its instructions by analyzing it. The input is user feedback information, and the output is the improved instructions. The server continues to generate more appropriate instructions based on the new situation.

[0132] 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.

[0133] This invention provides a system that optimizes responses to disasters by considering the emotional state of the user, in addition to providing rapid and accurate damage response. In this configuration, priority areas are identified based on the collection and analysis of aircraft data and social network service data, and user emotions are detected, and action instructions are optimized based on these emotions.

[0134] Information gathering

[0135] The server collects image data acquired from unmanned aerial vehicles and posts from social media in real time. This makes it possible to immediately grasp the situation in disaster-stricken areas.

[0136] Data Analysis

[0137] The server analyzes the collected image data using computer vision to identify the affected areas and specific damage. Meanwhile, it analyzes text-based disaster information from social media data using natural language processing to extract important location information and urgency levels.

[0138] Emotion analysis

[0139] Through user interaction, the device's emotion engine analyzes the user's emotional state in real time based on camera footage and audio. This emotional data is used as foundational data to generate appropriate behavioral instructions.

[0140] Instruction generation and notifications that take emotions into consideration

[0141] The server generates instructions for key areas based on the analyzed data and the user's emotion recognition results. The generated instructions are then adjusted by the emotion engine according to the user's state and communicated to the device in a way that is easily accepted by the user.

[0142] Instructions and feedback

[0143] Users follow instructions received from their devices to carry out rescue operations and transport supplies at the scene. Information gathered during the activities, as well as changes in the user's emotions, are fed back to the server via the device.

[0144] Specific example

[0145] For example, in the event of a major flood, the server analyzes image data from unmanned aerial vehicles and social media posts to prioritize identifying the areas most severely affected among multiple evacuation centers. When the user's terminal, acting as a volunteer on the ground, receives the support plan for the priority area from the server, an emotion engine considers the user's fatigue and stress levels, providing instructions along with advice to reduce stress. This allows users to continue their activities efficiently and without undue strain.

[0146] This system not only enhances the effectiveness of disaster response but also reduces the mental and physical burden on users, supporting sustainable relief activities.

[0147] The following describes the processing flow.

[0148] Step 1:

[0149] The server collects image data transmitted from unmanned aerial vehicles and satellites in real time. It also continuously retrieves disaster-related posts through SNS platform APIs.

[0150] Step 2:

[0151] The server analyzes collected image data using computer vision technology to identify the extent of damage and critical areas. Simultaneously, it analyzes social media posts using natural language processing technology to extract information of high urgency.

[0152] Step 3:

[0153] The server determines priorities for identified critical areas. This involves using an algorithm that comprehensively assesses the severity and urgency of the damage.

[0154] Step 4:

[0155] Before receiving instructions from the server, the device uses its built-in camera and microphone to analyze the user's emotions using an emotion engine. This allows for real-time assessment of the user's stress level and fatigue state.

[0156] Step 5:

[0157] The server adjusts instructions to the user based on the results of the emotion engine. For example, if it determines that the user is under high stress, it may simplify the instructions or add encouraging messages.

[0158] Step 6:

[0159] The terminal notifies the user of the coordinated instructions. The user then reviews the specific rescue operation and supply delivery plan and begins work.

[0160] Step 7:

[0161] Users report new information and changes in the situation to the server via their terminals while conducting rescue operations and supply deliveries on-site. This allows feedback to be sent to the server in real time.

[0162] Step 8:

[0163] The server analyzes the feedback, updates the instructions as needed, and notifies the terminal of the results again. This allows for real-time adjustment of countermeasures and maintains optimal disaster response.

[0164] (Example 2)

[0165] 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".

[0166] There is a need for a system that enables rapid and effective damage response during disasters, and provides optimal action instructions that take into account the emotional state of users. However, conventional technologies are not sufficient for the immediate collection and analysis of on-site information in disaster-stricken areas, nor for the integration of emotional considerations to reduce the mental burden on those engaged in relief efforts.

[0167] 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.

[0168] In this invention, the server includes means for collecting aircraft information and online information sharing service data, means for analyzing the collected information to identify important locations, and means for analyzing the user's emotions. This enables rapid situation assessment and the generation and provision of appropriate and flexible action instructions that correspond to the user's emotional state.

[0169] "Aircraft information" is a general term for observational data acquired from unmanned aerial vehicles and other flying devices.

[0170] "Online information sharing service data" refers to information, including user-generated content such as text, images, and videos, that is shared on online platforms.

[0171] A "critical location" refers to an area or facility where priority action is required in disaster response and relief activities.

[0172] "Instructions" refer to guidance and instructions provided to users based on information analyzed by the system, in order to prompt them to take action.

[0173] "Emotional state" refers to an indicator of a user's psychological and physiological state, specifically including stress levels, fatigue, and tension.

[0174] "Feedback" refers to information that is returned as system data by monitoring on-site activities and user status.

[0175] This invention provides a system for implementing a rapid and effective response during disasters and for reducing the mental burden on users. The embodiments of the invention will be described in detail below.

[0176] The server collects image data acquired by unmanned aerial vehicles and posted data obtained from online information sharing service platforms. This makes it possible to grasp the real-time situation in disaster areas. The hardware used is a server computing device capable of high-performance image processing. The software utilizes TensorFlow, a commonly used machine learning framework for analyzing image data. This enables rapid identification of damage and extraction of critical locations.

[0177] The server uses natural language processing technology to analyze data obtained from online information sharing services. This involves using a library called Transformers to extract information of high urgency and location.

[0178] The device analyzes the user's emotional state in real time using its camera and microphone through interaction. To this end, it utilizes an emotion recognition API to quantify the user's state and use this information to generate appropriate action instructions.

[0179] Users receive instructions tailored based on sentiment analysis and use them to carry out on-site support activities and transportation. Instructions are provided in a way that considers the user's burden, enabling efficient and sustainable operations.

[0180] As a concrete example, in the event of a major flood, the server analyzes image data from unmanned aerial vehicles and posts from online information sharing services to identify the areas most in need of assistance. This information is then provided to local users as appropriately tailored instructions. For instance, if a user is experiencing stress, emotion analysis can be used to send a notification encouraging them to take a break.

[0181] An example of a prompt message is: "A major flood has occurred. Analyze photos of the affected area to identify areas in urgent need of assistance. Furthermore, consider the emotional state of volunteers on the ground and generate support instructions that will reduce their stress." In this way, the system takes the user's state into account, enabling a sustainable and effective disaster response.

[0182] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0183] Step 1:

[0184] The server collects data from unmanned aerial vehicles (UAVs) and online information sharing services. Specifically, it receives image data captured by UAVs and posted data obtained through the APIs of online information sharing services. This results in output that provides the latest information on the situation on the ground in disaster-stricken areas.

[0185] Step 2:

[0186] The server analyzes image data using TensorFlow. The input image data is processed through a machine learning model to detect anomalies and damage in the affected area. The output provides detailed information on identified key locations and damage.

[0187] Step 3:

[0188] The server analyzes posted data received from online information sharing services using natural language processing. It extracts important elements from the input text data using the Transformers library, identifying information of high urgency and location. This then outputs detailed information about areas in need of assistance.

[0189] Step 4:

[0190] The device uses its camera and microphone to analyze the user's emotional state in real time. User video and audio data are used as input. An emotion recognition API is used to quantify the user's stress and fatigue levels, and the current emotional state is obtained as output. This information is used to generate subsequent support instructions.

[0191] Step 5:

[0192] The server generates instructions by combining image analysis results, natural language processing results, and the user's emotional state. The analyzed data is input, and the generating AI model creates optimal action instructions. The output instructions also take the user's emotional state into consideration, providing flexible and appropriate support suggestions.

[0193] Step 6:

[0194] The device receives instructions and adjusts the content based on the emotion engine. The input consists of instruction data sent from the server, and the presentation method is adjusted based on the user's emotions. As a result, instructions are output in a way that reduces stress while promoting supportive behaviors.

[0195] Step 7:

[0196] The user begins their on-site activities based on instructions from the device. The input consists of received support instructions. The user acts accordingly and reports the information and emotional changes obtained as feedback at the end. This improves the effectiveness of the activity.

[0197] (Application Example 2)

[0198] 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".

[0199] To achieve a rapid and accurate response to disasters, it is necessary to grasp the situation on the ground in real time and optimize appropriate responses. However, existing systems make it difficult to achieve such rapid and optimized responses. Furthermore, the optimization of action instructions does not take into account the emotional state of the users, which could lead to excessive mental and physical burdens during disaster relief.

[0200] 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.

[0201] In this invention, the server includes means for collecting aircraft data and social network data, means for analyzing the collected data to identify important areas, means for generating and transmitting instructions based on the important areas, and means for detecting the user's emotional state and adjusting the instructions based on the results. This enables a rapid and accurate response in the event of a disaster, and allows for efficient and sustainable support activities while taking into account the user's emotional state.

[0202] "Aircraft data" refers to visual information acquired by unmanned aerial vehicles and is used to understand the situation during disasters.

[0203] "Social network data" refers to text and posted data obtained from social networking services on the internet, and is used to determine the urgency and location information during disasters.

[0204] "Means for analyzing and identifying critical areas" refers to methods and technologies for analyzing collected data to identify areas that are heavily affected by disaster damage.

[0205] "Means for generating and transmitting instructions" refers to a system for generating instructions to take appropriate action in identified critical areas and transmitting them to users.

[0206] "Means for detecting emotional states and adjusting instructions based on the results" refers to systems and technologies that evaluate the user's emotional state and appropriately adjust the content of instructions based on that information.

[0207] "Means of receiving feedback from the device and updating instructions" refers to a mechanism for collecting information on the results of user actions, and for reviewing and updating instructions based on that information.

[0208] The system for implementing this invention is primarily composed of a server, terminals, and users. The server has the function of identifying important areas by collecting flight data from unmanned aerial vehicles and social network data, and analyzing that data. For this purpose, it makes full use of computer vision technology and natural language processing technology. Specifically, software such as Google® Cloud Vision API and Google Cloud Natural Language are used.

[0209] The server also has an emotion recognition engine to analyze emotional feedback from the user. This enables the generation and adjustment of instructions based on the user's emotional state. It generates appropriate instructions and sends them to the user's terminal. Based on the received instructions and emotion analysis, the user's terminal initiates actions at the disaster site.

[0210] As a concrete example, consider a scenario involving a large-scale flood. The server collects visual data from unmanned aerial vehicles and text data from social media to quickly identify areas particularly severely affected by the flood. It then provides specific action instructions for relief efforts to users, such as volunteers on the ground. If users are experiencing stress or fatigue, the system provides further detailed instructions and comforting messages to reduce the burden of their relief work.

[0211] This approach enables flexible and rapid responses to diverse disaster situations, and as a result, plays a crucial role in supporting the mental and physical safety of victims and aid workers.

[0212] An example of a prompt message is: "In the following disaster scenario, please write a proposal for an app that provides optimal evacuation guidance while considering the user's stress level: Describe in detail how computer vision and natural language processing are used to understand the situation on site using data obtained from the user's smart device." By inputting this into the AI ​​model, it is possible to assist in designing disaster response plans.

[0213] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0214] Step 1:

[0215] The server acquires aircraft data from unmanned aerial vehicles (UAVs). This is high-resolution visual data, used as an aerial view of the disaster area. The server then analyzes these images using the Google Cloud Vision API to identify the affected areas. The input is image data from the UAVs, and the output is information on the identified affected areas.

[0216] Step 2:

[0217] The server collects text data posted from social networking services, including posts related to disasters. Using Google Cloud Natural Language, the server analyzes the text data using natural language processing to extract urgency and important location information. The input is text data collected from social networking services, and the output includes data with urgency and location information.

[0218] Step 3:

[0219] The server identifies critical areas requiring assistance based on the analysis results of aircraft data and information extracted from social media data. This allows for an overall assessment of the disaster situation and a decision on which areas should be prioritized for aid. The input is the damage area information and social media data analysis results processed in the previous step, and the output is the identification of critical areas.

[0220] Step 4:

[0221] The server generates appropriate action instructions for designated critical areas and sends these instructions to terminals. These instructions include information on evacuation shelters and evacuation routes. Here, a generation AI model is used to create prompt sentences and utilize them to generate the content of the instructions. The input is information on critical areas, and the output is action instructions.

[0222] Step 5:

[0223] The terminal provides the user with specific activity guidance based on instructions received from the server. In doing so, the terminal's emotion recognition engine is utilized to evaluate the user's emotional state using data acquired from the camera and microphone, and adjust the instructions accordingly. The input consists of instruction data from the server and the user's real-time emotional state, while the output is optimized action guidance.

[0224] Step 6:

[0225] The user begins on-site support activities following instructions provided by the terminal. The user can provide feedback to the server via the terminal, including information gathered during the process. This feedback includes the progress of the activities and any newly discovered problems. Input is information from the user's support activities, and output is feedback data.

[0226] Step 7:

[0227] The server analyzes user feedback data and updates instructions as needed. This enables flexible responses to changing circumstances. The input is user feedback data, and the output is updated instruction information.

[0228] 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.

[0229] 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.

[0230] 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.

[0231] [Second Embodiment]

[0232] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0233] 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.

[0234] 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).

[0235] 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.

[0236] 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.

[0237] 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).

[0238] 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.

[0239] 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.

[0240] 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.

[0241] 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.

[0242] 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.

[0243] 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".

[0244] This invention is a system for achieving a rapid and effective response in the event of a disaster. It identifies critical areas based on the analysis of aircraft data and social network service data, and directs actions at the scene. This system is implemented through the processes of information gathering, data analysis, instruction generation, action instruction, and feedback reception.

[0245] Information gathering

[0246] The server acquires image data from unmanned aerial vehicles and satellites to monitor disaster situations in real time. It also collects posts from various social media platforms, accumulating raw information from local citizens in a database.

[0247] Data Analysis

[0248] The server analyzes image data acquired using computer vision to identify the extent and location of the damage. Simultaneously, it uses natural language processing technology to analyze social media posts and evaluate their urgency and reliability.

[0249] Instruction generation and notification

[0250] Based on the analyzed data, the server prioritizes affected areas and generates specific rescue plans and resource deployment plans. These instructions are then communicated to on-site users via terminals to help them take immediate action.

[0251] Receiving instructions and feedback

[0252] Users with terminals follow instructions received from the server to carry out rescue operations and deliver supplies in designated areas. Information gathered during the operation is sent to the server as feedback, which is then analyzed to adjust subsequent instructions.

[0253] Specific example

[0254] For example, in the event of a major earthquake, the server immediately deploys multiple unmanned aerial vehicles to capture images of the affected area. In addition, it collects social media posts from local residents to identify damage to infrastructure and disruptions to lifelines caused by the earthquake. The server identifies critical areas from the data it processes and sends priority rescue operation plans to rescue teams' terminals. This allows rescue workers (users) on the ground to check their terminals and take immediate action.

[0255] Thus, the present invention is a system that enables a rapid and accurate response to disasters and supports the early recovery of disaster-stricken areas.

[0256] The following describes the processing flow.

[0257] Step 1:

[0258] The server collects image data from the aircraft and posted data from social networking services. The unmanned aerial vehicle takes pictures of the disaster area and sends them to the server. At the same time, the server retrieves posts related to the disaster in real time using SNS APIs.

[0259] Step 2:

[0260] The server analyzes the received image data using computer vision technology to determine the extent and severity of the damage. It detects important features and damaged infrastructure within the images and stores the results in a database.

[0261] Step 3:

[0262] The server analyzes data posted from social media using natural language processing, extracting detailed disaster information, location data, and urgency levels from the text content. It filters out inaccurate information and accumulates highly reliable data.

[0263] Step 4:

[0264] The server integrates the analysis results of image data and social media data to determine the priority of critical areas. Based on this, it creates rescue operation and resource allocation plans and lists the priorities for each area.

[0265] Step 5:

[0266] The server notifies the terminal of the generated instructions. The terminal provides the user, a rescue team or aid organization, with a detailed action plan in real time, outlining specific activities to be carried out in the designated area.

[0267] Step 6:

[0268] Users follow instructions received via their terminals and carry out activities such as life-saving and supply transport at the scene. They report the situation and results of their activities to the server via their terminals.

[0269] Step 7:

[0270] The server receives user feedback and re-analyzes the situation to reflect the latest developments. This allows it to update instructions as needed and maintain the optimal response.

[0271] (Example 1)

[0272] 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."

[0273] During disasters, there is a need to collect, analyze, and issue response instructions for information quickly and efficiently. However, conventional systems have difficulty collecting information over a wide area in real time and making urgent decisions quickly, which has led to delays and confusion in on-site responses.

[0274] 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.

[0275] In this invention, the server includes means for storing high-resolution image information and information posted from social networks, means for analyzing the information using computer vision technology and natural language processing technology to identify critical areas, and means for generating rescue plans and resource allocation plans based on priorities and notifying them via communication devices. This enables rapid and appropriate information gathering and instruction generation in the event of a disaster.

[0276] "High-resolution image information" refers to image data containing detailed visual information, captured by devices such as unmanned aerial vehicles.

[0277] A "social network" is a platform for people to share information and communicate on the Internet.

[0278] "Posted information" refers to data such as text, images, videos, etc. publicly released by users on a social network.

[0279] "Computer vision technology" is a technology in which a computer analyzes image and video data and extracts information that can be recognized by human vision.

[0280] "Natural language processing technology" is a technology in which a computer understands and interprets human language and processes it naturally.

[0281] "Important area" refers to an area that requires special attention in the event of a disaster or other situation.

[0282] "Priority" is an order for determining which of a number of options should be executed first relatively.

[0283] "Rescue plan" is a specific action plan formulated for the purpose of saving lives and reducing damage in an emergency.

[0284] "Resource allocation plan" is a plan for allocating necessary resources to appropriate locations and effectively utilizing them.

[0285] "Communication device" is an electronic device for transmitting and receiving information, and is usually connected to the Internet or other networks.

[0286] "Portable information terminal" is an electronic device that can be carried and is used for input / output of information and communication.

[0287] "Information on implementation results" is a general term for reports and data obtained after the execution of a specific action or process.

[0288] This invention is a digital information system designed to enable rapid and accurate responses during disasters. The main technologies used include computer vision technology for analyzing high-resolution image information and natural language processing technology for analyzing posted information collected from social networks.

[0289] The server receives high-resolution image information collected using unmanned aerial vehicles and satellites, and analyzes its geographical features and the extent of damage. Image recognition algorithms and pattern recognition models are used in this analysis. The server also collects user-submitted information from various social networking platforms on the internet. This allows for an understanding of the local situation and reports from citizens.

[0290] The analysis uses natural language processing techniques to evaluate the urgency and reliability of the posted content. This involves using an AI model to perform semantic analysis of the text. Through this series of analysis processes, the server identifies critical regions and determines whether priority action is needed for those regions.

[0291] Users with terminals receive rescue plans and resource deployment plans generated by the server. These plans include specific rescue points and detailed procedures for the activities. This allows users to quickly initiate necessary actions and efficiently carry out support activities on-site. Furthermore, users provide feedback to the server through their terminals about the results obtained during the activities. This feedback allows the server to re-evaluate the situation and continuously update instructions as needed.

[0292] Specific example

[0293] For example, in the event of a large-scale flood, the server uses unmanned aerial vehicles to photograph the affected area, analyze the images, and identify flooded zones. Simultaneously, it collects information from residents' posts on social media platforms to understand rising water levels and the need for evacuation. Based on this information, the server generates an evacuation plan and notifies the user's device. The user receives the instructions and quickly deploys evacuation support.

[0294] Example of a prompt

[0295] "Please provide a detailed explanation of the entire process in this disaster response system, from real-time image collection using drones and satellites, to data analysis and rescue plan generation by servers, notification to terminals, and finally to the user's on-site activities."

[0296] Thus, by combining advanced data analysis technology with mobile communication, the present invention can significantly improve the efficiency of disaster response.

[0297] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0298] Step 1:

[0299] The server acquires high-resolution image information in real time from unmanned aerial vehicles (UAVs) and satellites. This input data includes detailed visual information of the entire disaster area. Specifically, the server establishes communication with these vehicles and periodically retrieves image data. The output consists of tens to hundreds of high-resolution images illustrating the disaster situation.

[0300] Step 2:

[0301] The server analyzes the acquired high-resolution image information using computer vision technology. The input data includes previously acquired images. At this stage, algorithms are in operation that recognize buildings, roads, and natural terrain within the images, and identify the scale and location of damage. For example, it identifies areas with no damage and areas with significant damage, and outputs such as damage distribution maps and risk assessment reports are generated.

[0302] Step 3:

[0303] The server collects submission information from the social network. The input data for this step is the text and image information submitted by users on the online platform. Based on this, natural language processing technology is used to evaluate the urgency and reliability of the submitted content. As a specific example, submissions containing specific hashtags or keywords are filtered, and as output, a list of information urgency levels and reliability evaluations is presented.

[0304] Step 4:

[0305] Based on the analysis results obtained in Step 2 and Step 3, the server identifies important regions and assigns priorities. The input data for this is the result of image analysis and the result of submission analysis. As output, the server generates a list of important regions arranged in order of priority and a corresponding rescue plan and resource allocation plan. This operation provides a guideline for quickly identifying regions with high urgency.

[0306] Step 5:

[0307] The server notifies local users of the generated rescue plan and resource allocation plan via the terminal. The input data is the plan generated in the previous step. As a specific operation, the server triggers the notification system and sends a message to the user's terminal. As a result, the rescue plan is transmitted to each user, serving as a trigger for their activities to start.

[0308] Step 6:

[0309] Users start activities on-site according to the instructions on the terminal. The input here is the rescue plan and instructions received from the server. As a specific operation, users make real-time situation judgments and carry out rescue activities. The information obtained during the activities is fed back to the server through the terminal. As output, information on the implementation results is collected and used for adjusting instructions in the next step.

[0310] Step 7:

[0311] The server receives feedback from the user and updates instructions as needed. The input for this step is user feedback data, and the output is a revised version of the instructions or plan based on that feedback. Specific actions include re-analyzing the received information, ensuring that the server always responds optimally to the latest situation.

[0312] (Application Example 1)

[0313] 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."

[0314] In recent years, the frequency of natural disasters has increased, making rapid and effective disaster response crucial. However, quickly assessing the extent of damage on the ground and providing appropriate instructions is not easy. Furthermore, providing real-time information to those conducting on-site relief activities and flexibly allocating resources according to the situation are also challenges. This invention aims to solve these problems and provide a system for streamlining disaster relief activities.

[0315] 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.

[0316] In this invention, the server includes means for collecting aircraft data and social network service data, means for analyzing the collected data to identify critical areas, and means for generating and transmitting instructions based on the critical areas. This enables highly accurate identification of damaged areas and rapid provision of rescue instructions using information from aircraft and communication satellites.

[0317] "Aircraft data" refers to image data and location information acquired from unmanned aerial vehicles and communication satellites, and is used in disaster situations to confirm the extent of damage and identify critical areas.

[0318] "Social network service data" refers to data such as text and images posted by users on social media platforms, and is used to understand the situation in disaster-stricken areas in real time.

[0319] A "critical area" is an area where, based on the extent and urgency of the damage during a disaster, priority support and rescue operations are required.

[0320] "Means for generating and transmitting instructions" refers to a processing mechanism for creating support plans and instructions for rescue operations based on collected and analyzed data, and transmitting them to various terminals.

[0321] A "mobile terminal" is an information and communication device carried by a user, and in the event of a disaster, it is used to receive rescue instructions in real time and to provide safe evacuation routes and other information based on location data.

[0322] "Natural language processing technology" is a technology that uses computers to understand and analyze human language (natural language), and is used to evaluate the urgency and reliability of posts collected from social media platforms.

[0323] To implement this invention, it is necessary to construct a system that supports rapid damage assessment and priority rescue operations in disaster-stricken areas. This system utilizes a cloud computing environment to acquire aircraft data from unmanned aerial vehicles and communication satellites in real time and store it on a server. This data is processed by image analysis algorithms and used to understand the current situation in the affected area. Specifically, computer vision technology is used, and the analysis is performed using models such as OpenCV or TensorFlow.

[0324] The server also analyzes social networking service data collected from social media platforms using natural language processing techniques. This allows it to assess the urgency and reliability of posts and identify important regions. Generative AI models such as BERT are used for natural language processing.

[0325] A terminal is an information and communication device carried by the user that acquires location information and transmits it to a server. Based on this location information, the server generates appropriate evacuation routes and support activity information in emergencies and delivers it to the terminal as a push notification. Firebase Cloud Messaging is often used in this process.

[0326] As a concrete example, in the event of a large-scale flood, the server analyzes the damage based on image data taken by unmanned aerial vehicles and social media posts from citizens, and identifies areas that require evacuation. Each user is notified on their device with evacuation route information and other important information related to their location. An example of a prompt message might be, "Please tell me how to find a safe evacuation location and the best route during a flood."

[0327] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0328] Step 1:

[0329] The server acquires aircraft data from unmanned aerial vehicles (UAVs) and communication satellites. The acquired data is stored in the server's data storage in real time. The input is image data from UAVs and satellites, and the output is the stored raw data. This raw data is used in subsequent analysis steps.

[0330] Step 2:

[0331] The server performs computer vision analysis on the acquired aircraft data. Specifically, it uses OpenCV and TensorFlow to detect anomalies in the affected areas from the image data. The input is the stored image data, and the output is the analysis results identifying the affected areas. The data is classified according to the magnitude and type of damage.

[0332] Step 3:

[0333] The server collects social networking service data from social media platforms. This data consists of user posts about disasters, which are analyzed by the server using natural language processing techniques. The input is the text information of SNS posts, and the output is an evaluation of urgency and reliability. This evaluation is performed using generative AI models such as the BERT model.

[0334] Step 4:

[0335] The server identifies critical areas and generates specific support plans and evacuation routes based on the analysis results of aircraft data and social network service data. The input is the analysis results obtained in steps 2 and 3, and the output is information on evacuation routes and support plans. The generated information is distributed to users as an emergency notification.

[0336] Step 5:

[0337] The device receives notifications from the server and displays information to the user. The input is notification data sent from the server, and the output is a visual presentation of information to the user. Based on the notification, the device uses location information to display the optimal evacuation route and important alerts.

[0338] Step 6:

[0339] Users begin taking action based on evacuation routes and support information provided through their devices. Input is the information displayed on the device, and output is the user's actual actions. While evacuating, users send feedback from their devices to the server as needed.

[0340] Step 7:

[0341] The server receives feedback from the user and updates its instructions by analyzing it. The input is user feedback information, and the output is the improved instructions. The server continues to generate more appropriate instructions based on the new situation.

[0342] 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.

[0343] This invention provides a system that optimizes responses to disasters by considering the emotional state of the user, in addition to providing rapid and accurate damage response. In this configuration, priority areas are identified based on the collection and analysis of aircraft data and social network service data, and user emotions are detected, and action instructions are optimized based on these emotions.

[0344] Information gathering

[0345] The server collects image data acquired from unmanned aerial vehicles and posts from social media in real time. This makes it possible to immediately grasp the situation in disaster-stricken areas.

[0346] Data Analysis

[0347] The server analyzes the collected image data using computer vision to identify the affected areas and specific damage. Meanwhile, it analyzes text-based disaster information from social media data using natural language processing to extract important location information and urgency levels.

[0348] Emotion analysis

[0349] Through user interaction, the device's emotion engine analyzes the user's emotional state in real time based on camera footage and audio. This emotional data is used as foundational data to generate appropriate behavioral instructions.

[0350] Instruction generation and notifications that take emotions into consideration

[0351] The server generates instructions for key areas based on the analyzed data and the user's emotion recognition results. The generated instructions are then adjusted by the emotion engine according to the user's state and communicated to the device in a way that is easily accepted by the user.

[0352] Instructions and feedback

[0353] Users follow instructions received from their devices to carry out rescue operations and transport supplies at the scene. Information gathered during the activities, as well as changes in the user's emotions, are fed back to the server via the device.

[0354] Specific example

[0355] For example, in the event of a major flood, the server analyzes image data from unmanned aerial vehicles and social media posts to prioritize identifying the areas most severely affected among multiple evacuation centers. When the user's terminal, acting as a volunteer on the ground, receives the support plan for the priority area from the server, an emotion engine considers the user's fatigue and stress levels, providing instructions along with advice to reduce stress. This allows users to continue their activities efficiently and without undue strain.

[0356] This system not only enhances the effectiveness of disaster response but also reduces the mental and physical burden on users, supporting sustainable relief activities.

[0357] The following describes the processing flow.

[0358] Step 1:

[0359] The server collects image data transmitted from unmanned aerial vehicles and satellites in real time. It also continuously retrieves disaster-related posts through SNS platform APIs.

[0360] Step 2:

[0361] The server analyzes collected image data using computer vision technology to identify the extent of damage and critical areas. Simultaneously, it analyzes social media posts using natural language processing technology to extract information of high urgency.

[0362] Step 3:

[0363] The server determines priorities for identified critical areas. This involves using an algorithm that comprehensively assesses the severity and urgency of the damage.

[0364] Step 4:

[0365] Before receiving instructions from the server, the device uses its built-in camera and microphone to analyze the user's emotions using an emotion engine. This allows for real-time assessment of the user's stress level and fatigue state.

[0366] Step 5:

[0367] The server adjusts instructions to the user based on the results of the emotion engine. For example, if it determines that the user is under high stress, it may simplify the instructions or add encouraging messages.

[0368] Step 6:

[0369] The terminal notifies the user of the coordinated instructions. The user then reviews the specific rescue operation and supply delivery plan and begins work.

[0370] Step 7:

[0371] Users report new information and changes in the situation to the server via their terminals while conducting rescue operations and supply deliveries on-site. This allows feedback to be sent to the server in real time.

[0372] Step 8:

[0373] The server analyzes the feedback, updates the instructions as needed, and notifies the terminal of the results again. This allows for real-time adjustment of countermeasures and maintains optimal disaster response.

[0374] (Example 2)

[0375] 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".

[0376] There is a need for a system that enables rapid and effective damage response during disasters, and provides optimal action instructions that take into account the emotional state of users. However, conventional technologies are not sufficient for the immediate collection and analysis of on-site information in disaster-stricken areas, nor for the integration of emotional considerations to reduce the mental burden on those engaged in relief efforts.

[0377] 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.

[0378] In this invention, the server includes means for collecting aircraft information and online information sharing service data, means for analyzing the collected information to identify important locations, and means for analyzing the user's emotions. This enables rapid situation assessment and the generation and provision of appropriate and flexible action instructions that correspond to the user's emotional state.

[0379] "Aircraft information" is a general term for observational data acquired from unmanned aerial vehicles and other flying devices.

[0380] "Online information sharing service data" refers to information, including user-generated content such as text, images, and videos, that is shared on online platforms.

[0381] A "critical location" refers to an area or facility where priority action is required in disaster response and relief activities.

[0382] "Instructions" refer to guidance and instructions provided to users based on information analyzed by the system, in order to prompt them to take action.

[0383] "Emotional state" refers to an indicator of a user's psychological and physiological state, specifically including stress levels, fatigue, and tension.

[0384] "Feedback" refers to information that is returned as system data by monitoring on-site activities and user status.

[0385] This invention provides a system for implementing a rapid and effective response during disasters and for reducing the mental burden on users. The embodiments of the invention will be described in detail below.

[0386] The server collects image data acquired by unmanned aerial vehicles and posted data obtained from online information sharing service platforms. This makes it possible to grasp the real-time situation in disaster areas. The hardware used is a server computing device capable of high-performance image processing. The software utilizes TensorFlow, a commonly used machine learning framework for analyzing image data. This enables rapid identification of damage and extraction of critical locations.

[0387] The server uses natural language processing technology to analyze data obtained from online information sharing services. This involves using a library called Transformers to extract information of high urgency and location.

[0388] The device analyzes the user's emotional state in real time using its camera and microphone through interaction. To this end, it utilizes an emotion recognition API to quantify the user's state and use this information to generate appropriate action instructions.

[0389] Users receive instructions tailored based on sentiment analysis and use them to carry out on-site support activities and transportation. Instructions are provided in a way that considers the user's burden, enabling efficient and sustainable operations.

[0390] As a concrete example, in the event of a major flood, the server analyzes image data from unmanned aerial vehicles and posts from online information sharing services to identify the areas most in need of assistance. This information is then provided to local users as appropriately tailored instructions. For instance, if a user is experiencing stress, emotion analysis can be used to send a notification encouraging them to take a break.

[0391] An example of a prompt message is: "A major flood has occurred. Analyze photos of the affected area to identify areas in urgent need of assistance. Furthermore, consider the emotional state of volunteers on the ground and generate support instructions that will reduce their stress." In this way, the system takes the user's state into account, enabling a sustainable and effective disaster response.

[0392] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0393] Step 1:

[0394] The server collects data from unmanned aerial vehicles (UAVs) and online information sharing services. Specifically, it receives image data captured by UAVs and posted data obtained through the APIs of online information sharing services. This results in output that provides the latest information on the situation on the ground in disaster-stricken areas.

[0395] Step 2:

[0396] The server analyzes image data using TensorFlow. The input image data is processed through a machine learning model to detect anomalies and damage in the affected area. The output provides detailed information on identified key locations and damage.

[0397] Step 3:

[0398] The server analyzes posted data received from online information sharing services using natural language processing. It extracts important elements from the input text data using the Transformers library, identifying information of high urgency and location. This then outputs detailed information about areas in need of assistance.

[0399] Step 4:

[0400] The device uses its camera and microphone to analyze the user's emotional state in real time. User video and audio data are used as input. An emotion recognition API is used to quantify the user's stress and fatigue levels, and the current emotional state is obtained as output. This information is used to generate subsequent support instructions.

[0401] Step 5:

[0402] The server generates instructions by combining image analysis results, natural language processing results, and the user's emotional state. The analyzed data is input, and the generating AI model creates optimal action instructions. The output instructions also take the user's emotional state into consideration, providing flexible and appropriate support suggestions.

[0403] Step 6:

[0404] The device receives instructions and adjusts the content based on the emotion engine. The input consists of instruction data sent from the server, and the presentation method is adjusted based on the user's emotions. As a result, instructions are output in a way that reduces stress while promoting supportive behaviors.

[0405] Step 7:

[0406] The user begins their on-site activities based on instructions from the device. The input consists of received support instructions. The user acts accordingly and reports the information and emotional changes obtained as feedback at the end. This improves the effectiveness of the activity.

[0407] (Application Example 2)

[0408] 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."

[0409] To achieve a rapid and accurate response to disasters, it is necessary to grasp the situation on the ground in real time and optimize appropriate responses. However, existing systems make it difficult to achieve such rapid and optimized responses. Furthermore, the optimization of action instructions does not take into account the emotional state of the users, which could lead to excessive mental and physical burdens during disaster relief.

[0410] 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.

[0411] In this invention, the server includes means for collecting aircraft data and social network data, means for analyzing the collected data to identify important areas, means for generating and transmitting instructions based on the important areas, and means for detecting the user's emotional state and adjusting the instructions based on the results. This enables a rapid and accurate response in the event of a disaster, and allows for efficient and sustainable support activities while taking into account the user's emotional state.

[0412] "Aircraft data" refers to visual information acquired by unmanned aerial vehicles and is used to understand the situation during disasters.

[0413] "Social network data" refers to text and posted data obtained from social networking services on the internet, and is used to determine the urgency and location information during disasters.

[0414] "Means for analyzing and identifying critical areas" refers to methods and technologies for analyzing collected data to identify areas that are heavily affected by disaster damage.

[0415] "Means for generating and transmitting instructions" refers to a system for generating instructions to take appropriate action in identified critical areas and transmitting them to users.

[0416] "Means for detecting emotional states and adjusting instructions based on the results" refers to systems and technologies that evaluate the user's emotional state and appropriately adjust the content of instructions based on that information.

[0417] "Means of receiving feedback from the device and updating instructions" refers to a mechanism for collecting information on the results of user actions, and for reviewing and updating instructions based on that information.

[0418] The system for implementing this invention is primarily composed of a server, terminals, and users. The server has the function of identifying important areas by collecting flight data from unmanned aerial vehicles and social network data, and analyzing that data. For this purpose, it makes full use of computer vision technology and natural language processing technology. Specifically, software such as Google Cloud Vision API and Google Cloud Natural Language are used.

[0419] The server also has an emotion recognition engine to analyze emotional feedback from the user. This enables the generation and adjustment of instructions based on the user's emotional state. It generates appropriate instructions and sends them to the user's terminal. Based on the received instructions and emotion analysis, the user's terminal initiates actions at the disaster site.

[0420] As a concrete example, consider a scenario involving a large-scale flood. The server collects visual data from unmanned aerial vehicles and text data from social media to quickly identify areas particularly severely affected by the flood. It then provides specific action instructions for relief efforts to users, such as volunteers on the ground. If users are experiencing stress or fatigue, the system provides further detailed instructions and comforting messages to reduce the burden of their relief work.

[0421] This approach enables flexible and rapid responses to diverse disaster situations, and as a result, plays a crucial role in supporting the mental and physical safety of victims and aid workers.

[0422] An example of a prompt message is: "In the following disaster scenario, please write a proposal for an app that provides optimal evacuation guidance while considering the user's stress level: Describe in detail how computer vision and natural language processing are used to understand the situation on site using data obtained from the user's smart device." By inputting this into the AI ​​model, it is possible to assist in designing disaster response plans.

[0423] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0424] Step 1:

[0425] The server acquires aircraft data from unmanned aerial vehicles (UAVs). This is high-resolution visual data, used as an aerial view of the disaster area. The server then analyzes these images using the Google Cloud Vision API to identify the affected areas. The input is image data from the UAVs, and the output is information on the identified affected areas.

[0426] Step 2:

[0427] The server collects text data posted from social networking services, including posts related to disasters. Using Google Cloud Natural Language, the server analyzes the text data using natural language processing to extract urgency and important location information. The input is text data collected from social networking services, and the output includes data with urgency and location information.

[0428] Step 3:

[0429] The server identifies critical areas requiring assistance based on the analysis results of aircraft data and information extracted from social media data. This allows for an overall assessment of the disaster situation and a decision on which areas should be prioritized for aid. The input is the damage area information and social media data analysis results processed in the previous step, and the output is the identification of critical areas.

[0430] Step 4:

[0431] The server generates appropriate action instructions for designated critical areas and sends these instructions to terminals. These instructions include information on evacuation shelters and evacuation routes. Here, a generation AI model is used to create prompt sentences and utilize them to generate the content of the instructions. The input is information on critical areas, and the output is action instructions.

[0432] Step 5:

[0433] The terminal provides the user with specific activity guidance based on instructions received from the server. In doing so, the terminal's emotion recognition engine is utilized to evaluate the user's emotional state using data acquired from the camera and microphone, and adjust the instructions accordingly. The input consists of instruction data from the server and the user's real-time emotional state, while the output is optimized action guidance.

[0434] Step 6:

[0435] The user begins on-site support activities following instructions provided by the terminal. The user can provide feedback to the server via the terminal, including information gathered during the process. This feedback includes the progress of the activities and any newly discovered problems. Input is information from the user's support activities, and output is feedback data.

[0436] Step 7:

[0437] The server analyzes user feedback data and updates instructions as needed. This enables flexible responses to changing circumstances. The input is user feedback data, and the output is updated instruction information.

[0438] 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.

[0439] 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.

[0440] 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.

[0441] [Third Embodiment]

[0442] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0443] 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.

[0444] 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).

[0445] 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.

[0446] 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.

[0447] 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).

[0448] 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.

[0449] 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.

[0450] 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.

[0451] 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.

[0452] 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.

[0453] 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".

[0454] This invention is a system for achieving a rapid and effective response in the event of a disaster. It identifies critical areas based on the analysis of aircraft data and social network service data, and directs actions at the scene. This system is implemented through the processes of information gathering, data analysis, instruction generation, action instruction, and feedback reception.

[0455] Information gathering

[0456] The server acquires image data from unmanned aerial vehicles and satellites to monitor disaster situations in real time. It also collects posts from various social media platforms, accumulating raw information from local citizens in a database.

[0457] Data Analysis

[0458] The server analyzes image data acquired using computer vision to identify the extent and location of the damage. Simultaneously, it uses natural language processing technology to analyze social media posts and evaluate their urgency and reliability.

[0459] Instruction generation and notification

[0460] Based on the analyzed data, the server prioritizes affected areas and generates specific rescue plans and resource deployment plans. These instructions are then communicated to on-site users via terminals to help them take immediate action.

[0461] Receiving instructions and feedback

[0462] Users with terminals follow instructions received from the server to carry out rescue operations and deliver supplies in designated areas. Information gathered during the operation is sent to the server as feedback, which is then analyzed to adjust subsequent instructions.

[0463] Specific example

[0464] For example, in the event of a major earthquake, the server immediately deploys multiple unmanned aerial vehicles to capture images of the affected area. In addition, it collects social media posts from local residents to identify damage to infrastructure and disruptions to lifelines caused by the earthquake. The server identifies critical areas from the data it processes and sends priority rescue operation plans to rescue teams' terminals. This allows rescue workers (users) on the ground to check their terminals and take immediate action.

[0465] Thus, the present invention is a system that enables a rapid and accurate response to disasters and supports the early recovery of disaster-stricken areas.

[0466] The following describes the processing flow.

[0467] Step 1:

[0468] The server collects image data from the aircraft and posted data from social networking services. The unmanned aerial vehicle takes pictures of the disaster area and sends them to the server. At the same time, the server retrieves posts related to the disaster in real time using SNS APIs.

[0469] Step 2:

[0470] The server analyzes the received image data using computer vision technology to determine the extent and severity of the damage. It detects important features and damaged infrastructure within the images and stores the results in a database.

[0471] Step 3:

[0472] The server analyzes data posted from social media using natural language processing, extracting detailed disaster information, location data, and urgency levels from the text content. It filters out inaccurate information and accumulates highly reliable data.

[0473] Step 4:

[0474] The server integrates the analysis results of image data and social media data to determine the priority of critical areas. Based on this, it creates rescue operation and resource allocation plans and lists the priorities for each area.

[0475] Step 5:

[0476] The server notifies the terminal of the generated instructions. The terminal provides the user, a rescue team or aid organization, with a detailed action plan in real time, outlining specific activities to be carried out in the designated area.

[0477] Step 6:

[0478] Users follow instructions received via their terminals and carry out activities such as life-saving and supply transport at the scene. They report the situation and results of their activities to the server via their terminals.

[0479] Step 7:

[0480] The server receives user feedback and re-analyzes the situation to reflect the latest developments. This allows it to update instructions as needed and maintain the optimal response.

[0481] (Example 1)

[0482] 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."

[0483] During disasters, there is a need to collect, analyze, and issue response instructions for information quickly and efficiently. However, conventional systems have difficulty collecting information over a wide area in real time and making urgent decisions quickly, which has led to delays and confusion in on-site responses.

[0484] 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.

[0485] In this invention, the server includes means for storing high-resolution image information and information posted from social networks, means for analyzing the information using computer vision technology and natural language processing technology to identify critical areas, and means for generating rescue plans and resource allocation plans based on priorities and notifying them via communication devices. This enables rapid and appropriate information gathering and instruction generation in the event of a disaster.

[0486] "High-resolution image information" refers to image data containing detailed visual information, captured by devices such as unmanned aerial vehicles.

[0487] A "social network" is a platform on the internet for people to share information and interact with each other.

[0488] "Posted information" refers to data such as text, images, and videos that are made public by users on social networks.

[0489] "Computer vision technology" is a technology that uses computers to analyze image and video data and extract information that can be recognized by human vision.

[0490] "Natural language processing technology" is a technology that allows computers to understand, interpret, and process human language in a natural way.

[0491] A "critical area" refers to an area that requires special attention in the event of a disaster or other situation.

[0492] "Priority" refers to the order in which multiple options should be prioritized and implemented first.

[0493] A "rescue plan" is a specific action plan formulated in the event of an emergency with the aim of saving lives and mitigating damage.

[0494] A "resource allocation plan" is a plan for allocating necessary resources to the appropriate locations and utilizing them effectively.

[0495] A "communication device" is an electronic device used to send and receive information, and is usually connected to the internet or other networks.

[0496] A "portable information terminal" is an electronic device that is portable and used for inputting and outputting information and for communication.

[0497] "Information on implementation results" refers to the collective term for reports and data obtained after the execution of a specific action or process.

[0498] This invention is a digital information system designed to enable rapid and accurate responses during disasters. The main technologies used include computer vision technology for analyzing high-resolution image information and natural language processing technology for analyzing posted information collected from social networks.

[0499] The server receives high-resolution image information collected using unmanned aerial vehicles and satellites, and analyzes its geographical features and the extent of damage. Image recognition algorithms and pattern recognition models are used in this analysis. The server also collects user-submitted information from various social networking platforms on the internet. This allows for an understanding of the local situation and reports from citizens.

[0500] The analysis uses natural language processing techniques to evaluate the urgency and reliability of the posted content. This involves using an AI model to perform semantic analysis of the text. Through this series of analysis processes, the server identifies critical regions and determines whether priority action is needed for those regions.

[0501] Users with terminals receive rescue plans and resource deployment plans generated by the server. These plans include specific rescue points and detailed procedures for the activities. This allows users to quickly initiate necessary actions and efficiently carry out support activities on-site. Furthermore, users provide feedback to the server through their terminals about the results obtained during the activities. This feedback allows the server to re-evaluate the situation and continuously update instructions as needed.

[0502] Specific example

[0503] For example, in the event of a large-scale flood, the server uses unmanned aerial vehicles to photograph the affected area, analyze the images, and identify flooded zones. Simultaneously, it collects information from residents' posts on social media platforms to understand rising water levels and the need for evacuation. Based on this information, the server generates an evacuation plan and notifies the user's device. The user receives the instructions and quickly deploys evacuation support.

[0504] Example of a prompt

[0505] "Please provide a detailed explanation of the entire process in this disaster response system, from real-time image collection using drones and satellites, to data analysis and rescue plan generation by servers, notification to terminals, and finally to the user's on-site activities."

[0506] Thus, by combining advanced data analysis technology with mobile communication, the present invention can significantly improve the efficiency of disaster response.

[0507] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0508] Step 1:

[0509] The server acquires high-resolution image information in real time from unmanned aerial vehicles (UAVs) and satellites. This input data includes detailed visual information of the entire disaster area. Specifically, the server establishes communication with these vehicles and periodically retrieves image data. The output consists of tens to hundreds of high-resolution images illustrating the disaster situation.

[0510] Step 2:

[0511] The server analyzes the acquired high-resolution image information using computer vision technology. The input data includes previously acquired images. At this stage, algorithms are in operation that recognize buildings, roads, and natural terrain within the images, and identify the scale and location of damage. For example, it identifies areas with no damage and areas with significant damage, and outputs such as damage distribution maps and risk assessment reports are generated.

[0512] Step 3:

[0513] The server collects posted information from social networks. The input data for this step consists of text and image information posted by users on online platforms. Based on this, natural language processing techniques are used to evaluate the urgency and reliability of the posted content. Specifically, posts containing certain hashtags or keywords are filtered, and the output presents a list of the urgency of the information and a reliability evaluation.

[0514] Step 4:

[0515] Based on the analysis results obtained in steps 2 and 3, the server identifies and prioritizes critical areas. The input data consists of image analysis results and post analysis results. As output, the server generates a list of critical areas sorted by priority, along with corresponding rescue plans and resource deployment plans. This operation provides guidance for quickly identifying high-priority areas.

[0516] Step 5:

[0517] The server notifies local users via their terminals of the generated rescue and resource deployment plans. The input data is the plan generated in the previous step. Specifically, the server triggers the notification system and sends a message to the user's terminal. The output is that the rescue plan is communicated to each user, triggering them to begin their activities.

[0518] Step 6:

[0519] The user begins their activities on-site following instructions on their terminal. Input here consists of rescue plans and instructions received from the server. Specifically, the user makes real-time situational assessments and carries out rescue operations. Information obtained during the activity is fed back to the server via the terminal. Output includes collected information on the results of the operation, which is used to adjust instructions for the next step.

[0520] Step 7:

[0521] The server receives feedback from the user and updates instructions as needed. The input for this step is user feedback data, and the output is a revised version of the instructions or plan based on that feedback. Specific actions include re-analyzing the received information, ensuring that the server always responds optimally to the latest situation.

[0522] (Application Example 1)

[0523] 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."

[0524] In recent years, the frequency of natural disasters has increased, making rapid and effective disaster response crucial. However, quickly assessing the extent of damage on the ground and providing appropriate instructions is not easy. Furthermore, providing real-time information to those conducting on-site relief activities and flexibly allocating resources according to the situation are also challenges. This invention aims to solve these problems and provide a system for streamlining disaster relief activities.

[0525] 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.

[0526] In this invention, the server includes means for collecting aircraft data and social network service data, means for analyzing the collected data to identify critical areas, and means for generating and transmitting instructions based on the critical areas. This enables highly accurate identification of damaged areas and rapid provision of rescue instructions using information from aircraft and communication satellites.

[0527] "Aircraft data" refers to image data and location information acquired from unmanned aerial vehicles and communication satellites, and is used in disaster situations to confirm the extent of damage and identify critical areas.

[0528] "Social network service data" refers to data such as text and images posted by users on social media platforms, and is used to understand the situation in disaster-stricken areas in real time.

[0529] A "critical area" is an area where, based on the extent and urgency of the damage during a disaster, priority support and rescue operations are required.

[0530] "Means for generating and transmitting instructions" refers to a processing mechanism for creating support plans and instructions for rescue operations based on collected and analyzed data, and transmitting them to various terminals.

[0531] A "mobile terminal" is an information and communication device carried by a user, and in the event of a disaster, it is used to receive rescue instructions in real time and to provide safe evacuation routes and other information based on location data.

[0532] "Natural language processing technology" is a technology that uses computers to understand and analyze human language (natural language), and is used to evaluate the urgency and reliability of posts collected from social media platforms.

[0533] To implement this invention, it is necessary to construct a system that supports rapid damage assessment and priority rescue operations in disaster-stricken areas. This system utilizes a cloud computing environment to acquire aircraft data from unmanned aerial vehicles and communication satellites in real time and store it on a server. This data is processed by image analysis algorithms and used to understand the current situation in the affected area. Specifically, computer vision technology is used, and the analysis is performed using models such as OpenCV or TensorFlow.

[0534] The server also analyzes social networking service data collected from social media platforms using natural language processing techniques. This allows it to assess the urgency and reliability of posts and identify important regions. Generative AI models such as BERT are used for natural language processing.

[0535] A terminal is an information and communication device carried by the user that acquires location information and transmits it to a server. Based on this location information, the server generates appropriate evacuation routes and support activity information in emergencies and delivers it to the terminal as a push notification. Firebase Cloud Messaging is often used in this process.

[0536] As a concrete example, in the event of a large-scale flood, the server analyzes the damage based on image data taken by unmanned aerial vehicles and social media posts from citizens, and identifies areas that require evacuation. Each user is notified on their device with evacuation route information and other important information related to their location. An example of a prompt message might be, "Please tell me how to find a safe evacuation location and the best route during a flood."

[0537] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0538] Step 1:

[0539] The server acquires aircraft data from unmanned aerial vehicles (UAVs) and communication satellites. The acquired data is stored in the server's data storage in real time. The input is image data from UAVs and satellites, and the output is the stored raw data. This raw data is used in subsequent analysis steps.

[0540] Step 2:

[0541] The server performs computer vision analysis on the acquired aircraft data. Specifically, it uses OpenCV and TensorFlow to detect anomalies in the affected areas from the image data. The input is the stored image data, and the output is the analysis results identifying the affected areas. The data is classified according to the magnitude and type of damage.

[0542] Step 3:

[0543] The server collects social networking service data from social media platforms. This data consists of user posts about disasters, which are analyzed by the server using natural language processing techniques. The input is the text information of SNS posts, and the output is an evaluation of urgency and reliability. This evaluation is performed using generative AI models such as the BERT model.

[0544] Step 4:

[0545] The server identifies critical areas and generates specific support plans and evacuation routes based on the analysis results of aircraft data and social network service data. The input is the analysis results obtained in steps 2 and 3, and the output is information on evacuation routes and support plans. The generated information is distributed to users as an emergency notification.

[0546] Step 5:

[0547] The device receives notifications from the server and displays information to the user. The input is notification data sent from the server, and the output is a visual presentation of information to the user. Based on the notification, the device uses location information to display the optimal evacuation route and important alerts.

[0548] Step 6:

[0549] Users begin taking action based on evacuation routes and support information provided through their devices. Input is the information displayed on the device, and output is the user's actual actions. While evacuating, users send feedback from their devices to the server as needed.

[0550] Step 7:

[0551] The server receives feedback from the user and updates its instructions by analyzing it. The input is user feedback information, and the output is the improved instructions. The server continues to generate more appropriate instructions based on the new situation.

[0552] 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.

[0553] This invention provides a system that optimizes responses to disasters by considering the emotional state of the user, in addition to providing rapid and accurate damage response. In this configuration, priority areas are identified based on the collection and analysis of aircraft data and social network service data, and user emotions are detected, and action instructions are optimized based on these emotions.

[0554] Information gathering

[0555] The server collects image data acquired from unmanned aerial vehicles and posts from social media in real time. This makes it possible to immediately grasp the situation in disaster-stricken areas.

[0556] Data Analysis

[0557] The server analyzes the collected image data using computer vision to identify the affected areas and specific damage. Meanwhile, it analyzes text-based disaster information from social media data using natural language processing to extract important location information and urgency levels.

[0558] Emotion analysis

[0559] Through user interaction, the device's emotion engine analyzes the user's emotional state in real time based on camera footage and audio. This emotional data is used as foundational data to generate appropriate behavioral instructions.

[0560] Instruction generation and notifications that take emotions into consideration

[0561] The server generates instructions for key areas based on the analyzed data and the user's emotion recognition results. The generated instructions are then adjusted by the emotion engine according to the user's state and communicated to the device in a way that is easily accepted by the user.

[0562] Instructions and feedback

[0563] Users follow instructions received from their devices to carry out rescue operations and transport supplies at the scene. Information gathered during the activities, as well as changes in the user's emotions, are fed back to the server via the device.

[0564] Specific example

[0565] For example, in the event of a major flood, the server analyzes image data from unmanned aerial vehicles and social media posts to prioritize identifying the areas most severely affected among multiple evacuation centers. When the user's terminal, acting as a volunteer on the ground, receives the support plan for the priority area from the server, an emotion engine considers the user's fatigue and stress levels, providing instructions along with advice to reduce stress. This allows users to continue their activities efficiently and without undue strain.

[0566] This system not only enhances the effectiveness of disaster response but also reduces the mental and physical burden on users, supporting sustainable relief activities.

[0567] The following describes the processing flow.

[0568] Step 1:

[0569] The server collects image data transmitted from unmanned aerial vehicles and satellites in real time. It also continuously retrieves disaster-related posts through SNS platform APIs.

[0570] Step 2:

[0571] The server analyzes collected image data using computer vision technology to identify the extent of damage and critical areas. Simultaneously, it analyzes social media posts using natural language processing technology to extract information of high urgency.

[0572] Step 3:

[0573] The server determines priorities for identified critical areas. This involves using an algorithm that comprehensively assesses the severity and urgency of the damage.

[0574] Step 4:

[0575] Before receiving instructions from the server, the device uses its built-in camera and microphone to analyze the user's emotions using an emotion engine. This allows for real-time assessment of the user's stress level and fatigue state.

[0576] Step 5:

[0577] The server adjusts instructions to the user based on the results of the emotion engine. For example, if it determines that the user is under high stress, it may simplify the instructions or add encouraging messages.

[0578] Step 6:

[0579] The terminal notifies the user of the coordinated instructions. The user then reviews the specific rescue operation and supply delivery plan and begins work.

[0580] Step 7:

[0581] Users report new information and changes in the situation to the server via their terminals while conducting rescue operations and supply deliveries on-site. This allows feedback to be sent to the server in real time.

[0582] Step 8:

[0583] The server analyzes the feedback, updates the instructions as needed, and notifies the terminal of the results again. This allows for real-time adjustment of countermeasures and maintains optimal disaster response.

[0584] (Example 2)

[0585] 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."

[0586] There is a need for a system that enables rapid and effective damage response during disasters, and provides optimal action instructions that take into account the emotional state of users. However, conventional technologies are not sufficient for the immediate collection and analysis of on-site information in disaster-stricken areas, nor for the integration of emotional considerations to reduce the mental burden on those engaged in relief efforts.

[0587] 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.

[0588] In this invention, the server includes means for collecting aircraft information and online information sharing service data, means for analyzing the collected information to identify important locations, and means for analyzing the user's emotions. This enables rapid situation assessment and the generation and provision of appropriate and flexible action instructions that correspond to the user's emotional state.

[0589] "Aircraft information" is a general term for observational data acquired from unmanned aerial vehicles and other flying devices.

[0590] "Online information sharing service data" refers to information, including user-generated content such as text, images, and videos, that is shared on online platforms.

[0591] A "critical location" refers to an area or facility where priority action is required in disaster response and relief activities.

[0592] "Instructions" refer to guidance and instructions provided to users based on information analyzed by the system, in order to prompt them to take action.

[0593] "Emotional state" refers to an indicator of a user's psychological and physiological state, specifically including stress levels, fatigue, and tension.

[0594] "Feedback" refers to information that is returned as system data by monitoring on-site activities and user status.

[0595] This invention provides a system for implementing a rapid and effective response during disasters and for reducing the mental burden on users. The embodiments of the invention will be described in detail below.

[0596] The server collects image data acquired by unmanned aerial vehicles and posted data obtained from online information sharing service platforms. This makes it possible to grasp the real-time situation in disaster areas. The hardware used is a server computing device capable of high-performance image processing. The software utilizes TensorFlow, a commonly used machine learning framework for analyzing image data. This enables rapid identification of damage and extraction of critical locations.

[0597] The server uses natural language processing technology to analyze data obtained from online information sharing services. This involves using a library called Transformers to extract information of high urgency and location.

[0598] The device analyzes the user's emotional state in real time using its camera and microphone through interaction. To this end, it utilizes an emotion recognition API to quantify the user's state and use this information to generate appropriate action instructions.

[0599] Users receive instructions tailored based on sentiment analysis and use them to carry out on-site support activities and transportation. Instructions are provided in a way that considers the user's burden, enabling efficient and sustainable operations.

[0600] As a concrete example, in the event of a major flood, the server analyzes image data from unmanned aerial vehicles and posts from online information sharing services to identify the areas most in need of assistance. This information is then provided to local users as appropriately tailored instructions. For instance, if a user is experiencing stress, emotion analysis can be used to send a notification encouraging them to take a break.

[0601] An example of a prompt message is: "A major flood has occurred. Analyze photos of the affected area to identify areas in urgent need of assistance. Furthermore, consider the emotional state of volunteers on the ground and generate support instructions that will reduce their stress." In this way, the system takes the user's state into account, enabling a sustainable and effective disaster response.

[0602] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0603] Step 1:

[0604] The server collects data from unmanned aerial vehicles (UAVs) and online information sharing services. Specifically, it receives image data captured by UAVs and posted data obtained through the APIs of online information sharing services. This results in output that provides the latest information on the situation on the ground in disaster-stricken areas.

[0605] Step 2:

[0606] The server analyzes image data using TensorFlow. The input image data is processed through a machine learning model to detect anomalies and damage in the affected area. The output provides detailed information on identified key locations and damage.

[0607] Step 3:

[0608] The server analyzes posted data received from online information sharing services using natural language processing. It extracts important elements from the input text data using the Transformers library, identifying information of high urgency and location. This then outputs detailed information about areas in need of assistance.

[0609] Step 4:

[0610] The device uses its camera and microphone to analyze the user's emotional state in real time. User video and audio data are used as input. An emotion recognition API is used to quantify the user's stress and fatigue levels, and the current emotional state is obtained as output. This information is used to generate subsequent support instructions.

[0611] Step 5:

[0612] The server generates instructions by combining image analysis results, natural language processing results, and the user's emotional state. The analyzed data is input, and the generating AI model creates optimal action instructions. The output instructions also take the user's emotional state into consideration, providing flexible and appropriate support suggestions.

[0613] Step 6:

[0614] The device receives instructions and adjusts the content based on the emotion engine. The input consists of instruction data sent from the server, and the presentation method is adjusted based on the user's emotions. As a result, instructions are output in a way that reduces stress while promoting supportive behaviors.

[0615] Step 7:

[0616] The user begins their on-site activities based on instructions from the device. The input consists of received support instructions. The user acts accordingly and reports the information and emotional changes obtained as feedback at the end. This improves the effectiveness of the activity.

[0617] (Application Example 2)

[0618] 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."

[0619] To achieve a rapid and accurate response to disasters, it is necessary to grasp the situation on the ground in real time and optimize appropriate responses. However, existing systems make it difficult to achieve such rapid and optimized responses. Furthermore, the optimization of action instructions does not take into account the emotional state of the users, which could lead to excessive mental and physical burdens during disaster relief.

[0620] 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.

[0621] In this invention, the server includes means for collecting aircraft data and social network data, means for analyzing the collected data to identify important areas, means for generating and transmitting instructions based on the important areas, and means for detecting the user's emotional state and adjusting the instructions based on the results. This enables a rapid and accurate response in the event of a disaster, and allows for efficient and sustainable support activities while taking into account the user's emotional state.

[0622] "Aircraft data" refers to visual information acquired by unmanned aerial vehicles and is used to understand the situation during disasters.

[0623] "Social network data" refers to text and posted data obtained from social networking services on the internet, and is used to determine the urgency and location information during disasters.

[0624] "Means for analyzing and identifying critical areas" refers to methods and technologies for analyzing collected data to identify areas that are heavily affected by disaster damage.

[0625] "Means for generating and transmitting instructions" refers to a system for generating instructions to take appropriate action in identified critical areas and transmitting them to users.

[0626] "Means for detecting emotional states and adjusting instructions based on the results" refers to systems and technologies that evaluate the user's emotional state and appropriately adjust the content of instructions based on that information.

[0627] "Means of receiving feedback from the device and updating instructions" refers to a mechanism for collecting information on the results of user actions, and for reviewing and updating instructions based on that information.

[0628] The system for implementing this invention is primarily composed of a server, terminals, and users. The server has the function of identifying important areas by collecting flight data from unmanned aerial vehicles and social network data, and analyzing that data. For this purpose, it makes full use of computer vision technology and natural language processing technology. Specifically, software such as Google Cloud Vision API and Google Cloud Natural Language are used.

[0629] The server also has an emotion recognition engine to analyze emotional feedback from the user. This enables the generation and adjustment of instructions based on the user's emotional state. It generates appropriate instructions and sends them to the user's terminal. Based on the received instructions and emotion analysis, the user's terminal initiates actions at the disaster site.

[0630] As a concrete example, consider a scenario involving a large-scale flood. The server collects visual data from unmanned aerial vehicles and text data from social media to quickly identify areas particularly severely affected by the flood. It then provides specific action instructions for relief efforts to users, such as volunteers on the ground. If users are experiencing stress or fatigue, the system provides further detailed instructions and comforting messages to reduce the burden of their relief work.

[0631] This approach enables flexible and rapid responses to diverse disaster situations, and as a result, plays a crucial role in supporting the mental and physical safety of victims and aid workers.

[0632] An example of a prompt message is: "In the following disaster scenario, please write a proposal for an app that provides optimal evacuation guidance while considering the user's stress level: Describe in detail how computer vision and natural language processing are used to understand the situation on site using data obtained from the user's smart device." By inputting this into the AI ​​model, it is possible to assist in designing disaster response plans.

[0633] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0634] Step 1:

[0635] The server acquires aircraft data from unmanned aerial vehicles (UAVs). This is high-resolution visual data, used as an aerial view of the disaster area. The server then analyzes these images using the Google Cloud Vision API to identify the affected areas. The input is image data from the UAVs, and the output is information on the identified affected areas.

[0636] Step 2:

[0637] The server collects text data posted from social networking services, including posts related to disasters. Using Google Cloud Natural Language, the server analyzes the text data using natural language processing to extract urgency and important location information. The input is text data collected from social networking services, and the output includes data with urgency and location information.

[0638] Step 3:

[0639] The server identifies critical areas requiring assistance based on the analysis results of aircraft data and information extracted from social media data. This allows for an overall assessment of the disaster situation and a decision on which areas should be prioritized for aid. The input is the damage area information and social media data analysis results processed in the previous step, and the output is the identification of critical areas.

[0640] Step 4:

[0641] The server generates appropriate action instructions for designated critical areas and sends these instructions to terminals. These instructions include information on evacuation shelters and evacuation routes. Here, a generation AI model is used to create prompt sentences and utilize them to generate the content of the instructions. The input is information on critical areas, and the output is action instructions.

[0642] Step 5:

[0643] The terminal provides the user with specific activity guidance based on instructions received from the server. In doing so, the terminal's emotion recognition engine is utilized to evaluate the user's emotional state using data acquired from the camera and microphone, and adjust the instructions accordingly. The input consists of instruction data from the server and the user's real-time emotional state, while the output is optimized action guidance.

[0644] Step 6:

[0645] The user begins on-site support activities following instructions provided by the terminal. The user can provide feedback to the server via the terminal, including information gathered during the process. This feedback includes the progress of the activities and any newly discovered problems. Input is information from the user's support activities, and output is feedback data.

[0646] Step 7:

[0647] The server analyzes user feedback data and updates instructions as needed. This enables flexible responses to changing circumstances. The input is user feedback data, and the output is updated instruction information.

[0648] 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.

[0649] 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.

[0650] 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.

[0651] [Fourth Embodiment]

[0652] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0653] 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.

[0654] 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).

[0655] 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.

[0656] 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.

[0657] 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).

[0658] 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.

[0659] 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.

[0660] 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.

[0661] 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.

[0662] 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.

[0663] 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.

[0664] 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".

[0665] This invention is a system for achieving a rapid and effective response in the event of a disaster. It identifies critical areas based on the analysis of aircraft data and social network service data, and directs actions at the scene. This system is implemented through the processes of information gathering, data analysis, instruction generation, action instruction, and feedback reception.

[0666] Information gathering

[0667] The server acquires image data from unmanned aerial vehicles and satellites to monitor disaster situations in real time. It also collects posts from various social media platforms, accumulating raw information from local citizens in a database.

[0668] Data Analysis

[0669] The server analyzes image data acquired using computer vision to identify the extent and location of the damage. Simultaneously, it uses natural language processing technology to analyze social media posts and evaluate their urgency and reliability.

[0670] Instruction generation and notification

[0671] Based on the analyzed data, the server prioritizes affected areas and generates specific rescue plans and resource deployment plans. These instructions are then communicated to on-site users via terminals to help them take immediate action.

[0672] Receiving instructions and feedback

[0673] Users with terminals follow instructions received from the server to carry out rescue operations and deliver supplies in designated areas. Information gathered during the operation is sent to the server as feedback, which is then analyzed to adjust subsequent instructions.

[0674] Specific example

[0675] For example, in the event of a major earthquake, the server immediately deploys multiple unmanned aerial vehicles to capture images of the affected area. In addition, it collects social media posts from local residents to identify damage to infrastructure and disruptions to lifelines caused by the earthquake. The server identifies critical areas from the data it processes and sends priority rescue operation plans to rescue teams' terminals. This allows rescue workers (users) on the ground to check their terminals and take immediate action.

[0676] Thus, the present invention is a system that enables a rapid and accurate response to disasters and supports the early recovery of disaster-stricken areas.

[0677] The following describes the processing flow.

[0678] Step 1:

[0679] The server collects image data from the aircraft and posted data from social networking services. The unmanned aerial vehicle takes pictures of the disaster area and sends them to the server. At the same time, the server retrieves posts related to the disaster in real time using SNS APIs.

[0680] Step 2:

[0681] The server analyzes the received image data using computer vision technology to determine the extent and severity of the damage. It detects important features and damaged infrastructure within the images and stores the results in a database.

[0682] Step 3:

[0683] The server analyzes data posted from social media using natural language processing, extracting detailed disaster information, location data, and urgency levels from the text content. It filters out inaccurate information and accumulates highly reliable data.

[0684] Step 4:

[0685] The server integrates the analysis results of image data and social media data to determine the priority of critical areas. Based on this, it creates rescue operation and resource allocation plans and lists the priorities for each area.

[0686] Step 5:

[0687] The server notifies the terminal of the generated instructions. The terminal provides the user, a rescue team or aid organization, with a detailed action plan in real time, outlining specific activities to be carried out in the designated area.

[0688] Step 6:

[0689] Users follow instructions received via their terminals and carry out activities such as life-saving and supply transport at the scene. They report the situation and results of their activities to the server via their terminals.

[0690] Step 7:

[0691] The server receives user feedback and re-analyzes the situation to reflect the latest developments. This allows it to update instructions as needed and maintain the optimal response.

[0692] (Example 1)

[0693] 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".

[0694] During disasters, there is a need to collect, analyze, and issue response instructions for information quickly and efficiently. However, conventional systems have difficulty collecting information over a wide area in real time and making urgent decisions quickly, which has led to delays and confusion in on-site responses.

[0695] 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.

[0696] In this invention, the server includes means for storing high-resolution image information and information posted from social networks, means for analyzing the information using computer vision technology and natural language processing technology to identify critical areas, and means for generating rescue plans and resource allocation plans based on priorities and notifying them via communication devices. This enables rapid and appropriate information gathering and instruction generation in the event of a disaster.

[0697] "High-resolution image information" refers to image data containing detailed visual information, captured by devices such as unmanned aerial vehicles.

[0698] A "social network" is a platform on the internet for people to share information and interact with each other.

[0699] "Posted information" refers to data such as text, images, and videos that are made public by users on social networks.

[0700] "Computer vision technology" is a technology that uses computers to analyze image and video data and extract information that can be recognized by human vision.

[0701] "Natural language processing technology" is a technology that allows computers to understand, interpret, and process human language in a natural way.

[0702] A "critical area" refers to an area that requires special attention in the event of a disaster or other situation.

[0703] "Priority" refers to the order in which multiple options should be prioritized and implemented first.

[0704] A "rescue plan" is a specific action plan formulated in the event of an emergency with the aim of saving lives and mitigating damage.

[0705] A "resource allocation plan" is a plan for allocating necessary resources to the appropriate locations and utilizing them effectively.

[0706] A "communication device" is an electronic device used to send and receive information, and is usually connected to the internet or other networks.

[0707] A "portable information terminal" is an electronic device that is portable and used for inputting and outputting information and for communication.

[0708] "Information on implementation results" refers to the collective term for reports and data obtained after the execution of a specific action or process.

[0709] This invention is a digital information system designed to enable rapid and accurate responses during disasters. The main technologies used include computer vision technology for analyzing high-resolution image information and natural language processing technology for analyzing posted information collected from social networks.

[0710] The server receives high-resolution image information collected using unmanned aerial vehicles and satellites, and analyzes its geographical features and the extent of damage. Image recognition algorithms and pattern recognition models are used in this analysis. The server also collects user-submitted information from various social networking platforms on the internet. This allows for an understanding of the local situation and reports from citizens.

[0711] The analysis uses natural language processing techniques to evaluate the urgency and reliability of the posted content. This involves using an AI model to perform semantic analysis of the text. Through this series of analysis processes, the server identifies critical regions and determines whether priority action is needed for those regions.

[0712] Users with terminals receive rescue plans and resource deployment plans generated by the server. These plans include specific rescue points and detailed procedures for the activities. This allows users to quickly initiate necessary actions and efficiently carry out support activities on-site. Furthermore, users provide feedback to the server through their terminals about the results obtained during the activities. This feedback allows the server to re-evaluate the situation and continuously update instructions as needed.

[0713] Specific example

[0714] For example, in the event of a large-scale flood, the server uses unmanned aerial vehicles to photograph the affected area, analyze the images, and identify flooded zones. Simultaneously, it collects information from residents' posts on social media platforms to understand rising water levels and the need for evacuation. Based on this information, the server generates an evacuation plan and notifies the user's device. The user receives the instructions and quickly deploys evacuation support.

[0715] Example of a prompt

[0716] "Please provide a detailed explanation of the entire process in this disaster response system, from real-time image collection using drones and satellites, to data analysis and rescue plan generation by servers, notification to terminals, and finally to the user's on-site activities."

[0717] Thus, by combining advanced data analysis technology with mobile communication, the present invention can significantly improve the efficiency of disaster response.

[0718] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0719] Step 1:

[0720] The server acquires high-resolution image information in real time from unmanned aerial vehicles (UAVs) and satellites. This input data includes detailed visual information of the entire disaster area. Specifically, the server establishes communication with these vehicles and periodically retrieves image data. The output consists of tens to hundreds of high-resolution images illustrating the disaster situation.

[0721] Step 2:

[0722] The server analyzes the acquired high-resolution image information using computer vision technology. The input data includes previously acquired images. At this stage, algorithms are in operation that recognize buildings, roads, and natural terrain within the images, and identify the scale and location of damage. For example, it identifies areas with no damage and areas with significant damage, and outputs such as damage distribution maps and risk assessment reports are generated.

[0723] Step 3:

[0724] The server collects posted information from social networks. The input data for this step consists of text and image information posted by users on online platforms. Based on this, natural language processing techniques are used to evaluate the urgency and reliability of the posted content. Specifically, posts containing certain hashtags or keywords are filtered, and the output presents a list of the urgency of the information and a reliability evaluation.

[0725] Step 4:

[0726] Based on the analysis results obtained in steps 2 and 3, the server identifies and prioritizes critical areas. The input data consists of image analysis results and post analysis results. As output, the server generates a list of critical areas sorted by priority, along with corresponding rescue plans and resource deployment plans. This operation provides guidance for quickly identifying high-priority areas.

[0727] Step 5:

[0728] The server notifies local users via their terminals of the generated rescue and resource deployment plans. The input data is the plan generated in the previous step. Specifically, the server triggers the notification system and sends a message to the user's terminal. The output is that the rescue plan is communicated to each user, triggering them to begin their activities.

[0729] Step 6:

[0730] The user begins their activities on-site following instructions on their terminal. Input here consists of rescue plans and instructions received from the server. Specifically, the user makes real-time situational assessments and carries out rescue operations. Information obtained during the activity is fed back to the server via the terminal. Output includes collected information on the results of the operation, which is used to adjust instructions for the next step.

[0731] Step 7:

[0732] The server receives feedback from the user and updates instructions as needed. The input for this step is user feedback data, and the output is a revised version of the instructions or plan based on that feedback. Specific actions include re-analyzing the received information, ensuring that the server always responds optimally to the latest situation.

[0733] (Application Example 1)

[0734] 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".

[0735] In recent years, the frequency of natural disasters has increased, making rapid and effective disaster response crucial. However, quickly assessing the extent of damage on the ground and providing appropriate instructions is not easy. Furthermore, providing real-time information to those conducting on-site relief activities and flexibly allocating resources according to the situation are also challenges. This invention aims to solve these problems and provide a system for streamlining disaster relief activities.

[0736] 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.

[0737] In this invention, the server includes means for collecting aircraft data and social network service data, means for analyzing the collected data to identify critical areas, and means for generating and transmitting instructions based on the critical areas. This enables highly accurate identification of damaged areas and rapid provision of rescue instructions using information from aircraft and communication satellites.

[0738] "Aircraft data" refers to image data and location information acquired from unmanned aerial vehicles and communication satellites, and is used in disaster situations to confirm the extent of damage and identify critical areas.

[0739] "Social network service data" refers to data such as text and images posted by users on social media platforms, and is used to understand the situation in disaster-stricken areas in real time.

[0740] A "critical area" is an area where, based on the extent and urgency of the damage during a disaster, priority support and rescue operations are required.

[0741] "Means for generating and transmitting instructions" refers to a processing mechanism for creating support plans and instructions for rescue operations based on collected and analyzed data, and transmitting them to various terminals.

[0742] A "mobile terminal" is an information and communication device carried by a user, and in the event of a disaster, it is used to receive rescue instructions in real time and to provide safe evacuation routes and other information based on location data.

[0743] "Natural language processing technology" is a technology that uses computers to understand and analyze human language (natural language), and is used to evaluate the urgency and reliability of posts collected from social media platforms.

[0744] To implement this invention, it is necessary to construct a system that supports rapid damage assessment and priority rescue operations in disaster-stricken areas. This system utilizes a cloud computing environment to acquire aircraft data from unmanned aerial vehicles and communication satellites in real time and store it on a server. This data is processed by image analysis algorithms and used to understand the current situation in the affected area. Specifically, computer vision technology is used, and the analysis is performed using models such as OpenCV or TensorFlow.

[0745] The server also analyzes social networking service data collected from social media platforms using natural language processing techniques. This allows it to assess the urgency and reliability of posts and identify important regions. Generative AI models such as BERT are used for natural language processing.

[0746] A terminal is an information and communication device carried by the user that acquires location information and transmits it to a server. Based on this location information, the server generates appropriate evacuation routes and support activity information in emergencies and delivers it to the terminal as a push notification. Firebase Cloud Messaging is often used in this process.

[0747] As a concrete example, in the event of a large-scale flood, the server analyzes the damage based on image data taken by unmanned aerial vehicles and social media posts from citizens, and identifies areas that require evacuation. Each user is notified on their device with evacuation route information and other important information related to their location. An example of a prompt message might be, "Please tell me how to find a safe evacuation location and the best route during a flood."

[0748] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0749] Step 1:

[0750] The server acquires aircraft data from unmanned aerial vehicles (UAVs) and communication satellites. The acquired data is stored in the server's data storage in real time. The input is image data from UAVs and satellites, and the output is the stored raw data. This raw data is used in subsequent analysis steps.

[0751] Step 2:

[0752] The server performs computer vision analysis on the acquired aircraft data. Specifically, it uses OpenCV and TensorFlow to detect anomalies in the affected areas from the image data. The input is the stored image data, and the output is the analysis results identifying the affected areas. The data is classified according to the magnitude and type of damage.

[0753] Step 3:

[0754] The server collects social networking service data from social media platforms. This data consists of user posts about disasters, which are analyzed by the server using natural language processing techniques. The input is the text information of SNS posts, and the output is an evaluation of urgency and reliability. This evaluation is performed using generative AI models such as the BERT model.

[0755] Step 4:

[0756] The server identifies critical areas and generates specific support plans and evacuation routes based on the analysis results of aircraft data and social network service data. The input is the analysis results obtained in steps 2 and 3, and the output is information on evacuation routes and support plans. The generated information is distributed to users as an emergency notification.

[0757] Step 5:

[0758] The device receives notifications from the server and displays information to the user. The input is notification data sent from the server, and the output is a visual presentation of information to the user. Based on the notification, the device uses location information to display the optimal evacuation route and important alerts.

[0759] Step 6:

[0760] Users begin taking action based on evacuation routes and support information provided through their devices. Input is the information displayed on the device, and output is the user's actual actions. While evacuating, users send feedback from their devices to the server as needed.

[0761] Step 7:

[0762] The server receives feedback from the user and updates its instructions by analyzing it. The input is user feedback information, and the output is the improved instructions. The server continues to generate more appropriate instructions based on the new situation.

[0763] 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.

[0764] This invention provides a system that optimizes responses to disasters by considering the emotional state of the user, in addition to providing rapid and accurate damage response. In this configuration, priority areas are identified based on the collection and analysis of aircraft data and social network service data, and user emotions are detected, and action instructions are optimized based on these emotions.

[0765] Information gathering

[0766] The server collects image data acquired from unmanned aerial vehicles and posts from social media in real time. This makes it possible to immediately grasp the situation in disaster-stricken areas.

[0767] Data Analysis

[0768] The server analyzes the collected image data using computer vision to identify the affected areas and specific damage. Meanwhile, it analyzes text-based disaster information from social media data using natural language processing to extract important location information and urgency levels.

[0769] Emotion analysis

[0770] Through user interaction, the device's emotion engine analyzes the user's emotional state in real time based on camera footage and audio. This emotional data is used as foundational data to generate appropriate behavioral instructions.

[0771] Instruction generation and notifications that take emotions into consideration

[0772] The server generates instructions for key areas based on the analyzed data and the user's emotion recognition results. The generated instructions are then adjusted by the emotion engine according to the user's state and communicated to the device in a way that is easily accepted by the user.

[0773] Instructions and feedback

[0774] Users follow instructions received from their devices to carry out rescue operations and transport supplies at the scene. Information gathered during the activities, as well as changes in the user's emotions, are fed back to the server via the device.

[0775] Specific example

[0776] For example, in the event of a major flood, the server analyzes image data from unmanned aerial vehicles and social media posts to prioritize identifying the areas most severely affected among multiple evacuation centers. When the user's terminal, acting as a volunteer on the ground, receives the support plan for the priority area from the server, an emotion engine considers the user's fatigue and stress levels, providing instructions along with advice to reduce stress. This allows users to continue their activities efficiently and without undue strain.

[0777] This system not only enhances the effectiveness of disaster response but also reduces the mental and physical burden on users, supporting sustainable relief activities.

[0778] The following describes the processing flow.

[0779] Step 1:

[0780] The server collects image data transmitted from unmanned aerial vehicles and satellites in real time. It also continuously retrieves disaster-related posts through SNS platform APIs.

[0781] Step 2:

[0782] The server analyzes collected image data using computer vision technology to identify the extent of damage and critical areas. Simultaneously, it analyzes social media posts using natural language processing technology to extract information of high urgency.

[0783] Step 3:

[0784] The server determines priorities for identified critical areas. This involves using an algorithm that comprehensively assesses the severity and urgency of the damage.

[0785] Step 4:

[0786] Before receiving instructions from the server, the device uses its built-in camera and microphone to analyze the user's emotions using an emotion engine. This allows for real-time assessment of the user's stress level and fatigue state.

[0787] Step 5:

[0788] The server adjusts instructions to the user based on the results of the emotion engine. For example, if it determines that the user is under high stress, it may simplify the instructions or add encouraging messages.

[0789] Step 6:

[0790] The terminal notifies the user of the coordinated instructions. The user then reviews the specific rescue operation and supply delivery plan and begins work.

[0791] Step 7:

[0792] Users report new information and changes in the situation to the server via their terminals while conducting rescue operations and supply deliveries on-site. This allows feedback to be sent to the server in real time.

[0793] Step 8:

[0794] The server analyzes the feedback, updates the instructions as needed, and notifies the terminal of the results again. This allows for real-time adjustment of countermeasures and maintains optimal disaster response.

[0795] (Example 2)

[0796] 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".

[0797] There is a need for a system that enables rapid and effective damage response during disasters, and provides optimal action instructions that take into account the emotional state of users. However, conventional technologies are not sufficient for the immediate collection and analysis of on-site information in disaster-stricken areas, nor for the integration of emotional considerations to reduce the mental burden on those engaged in relief efforts.

[0798] 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.

[0799] In this invention, the server includes means for collecting aircraft information and online information sharing service data, means for analyzing the collected information to identify important locations, and means for analyzing the user's emotions. This enables rapid situation assessment and the generation and provision of appropriate and flexible action instructions that correspond to the user's emotional state.

[0800] "Aircraft information" is a general term for observational data acquired from unmanned aerial vehicles and other flying devices.

[0801] "Online information sharing service data" refers to information, including user-generated content such as text, images, and videos, that is shared on online platforms.

[0802] A "critical location" refers to an area or facility where priority action is required in disaster response and relief activities.

[0803] "Instructions" refer to guidance and instructions provided to users based on information analyzed by the system, in order to prompt them to take action.

[0804] "Emotional state" refers to an indicator of a user's psychological and physiological state, specifically including stress levels, fatigue, and tension.

[0805] "Feedback" refers to information that is returned as system data by monitoring on-site activities and user status.

[0806] This invention provides a system for implementing a rapid and effective response during disasters and for reducing the mental burden on users. The embodiments of the invention will be described in detail below.

[0807] The server collects image data acquired by unmanned aerial vehicles and posted data obtained from online information sharing service platforms. This makes it possible to grasp the real-time situation in disaster areas. The hardware used is a server computing device capable of high-performance image processing. The software utilizes TensorFlow, a commonly used machine learning framework for analyzing image data. This enables rapid identification of damage and extraction of critical locations.

[0808] The server uses natural language processing technology to analyze data obtained from online information sharing services. This involves using a library called Transformers to extract information of high urgency and location.

[0809] The device analyzes the user's emotional state in real time using its camera and microphone through interaction. To this end, it utilizes an emotion recognition API to quantify the user's state and use this information to generate appropriate action instructions.

[0810] Users receive instructions tailored based on sentiment analysis and use them to carry out on-site support activities and transportation. Instructions are provided in a way that considers the user's burden, enabling efficient and sustainable operations.

[0811] As a concrete example, in the event of a major flood, the server analyzes image data from unmanned aerial vehicles and posts from online information sharing services to identify the areas most in need of assistance. This information is then provided to local users as appropriately tailored instructions. For instance, if a user is experiencing stress, emotion analysis can be used to send a notification encouraging them to take a break.

[0812] An example of a prompt message is: "A major flood has occurred. Analyze photos of the affected area to identify areas in urgent need of assistance. Furthermore, consider the emotional state of volunteers on the ground and generate support instructions that will reduce their stress." In this way, the system takes the user's state into account, enabling a sustainable and effective disaster response.

[0813] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0814] Step 1:

[0815] The server collects data from unmanned aerial vehicles (UAVs) and online information sharing services. Specifically, it receives image data captured by UAVs and posted data obtained through the APIs of online information sharing services. This results in output that provides the latest information on the situation on the ground in disaster-stricken areas.

[0816] Step 2:

[0817] The server analyzes image data using TensorFlow. The input image data is processed through a machine learning model to detect anomalies and damage in the affected area. The output provides detailed information on identified key locations and damage.

[0818] Step 3:

[0819] The server analyzes posted data received from online information sharing services using natural language processing. It extracts important elements from the input text data using the Transformers library, identifying information of high urgency and location. This then outputs detailed information about areas in need of assistance.

[0820] Step 4:

[0821] The device uses its camera and microphone to analyze the user's emotional state in real time. User video and audio data are used as input. An emotion recognition API is used to quantify the user's stress and fatigue levels, and the current emotional state is obtained as output. This information is used to generate subsequent support instructions.

[0822] Step 5:

[0823] The server generates instructions by combining image analysis results, natural language processing results, and the user's emotional state. The analyzed data is input, and the generating AI model creates optimal action instructions. The output instructions also take the user's emotional state into consideration, providing flexible and appropriate support suggestions.

[0824] Step 6:

[0825] The device receives instructions and adjusts the content based on the emotion engine. The input consists of instruction data sent from the server, and the presentation method is adjusted based on the user's emotions. As a result, instructions are output in a way that reduces stress while promoting supportive behaviors.

[0826] Step 7:

[0827] The user begins their on-site activities based on instructions from the device. The input consists of received support instructions. The user acts accordingly and reports the information and emotional changes obtained as feedback at the end. This improves the effectiveness of the activity.

[0828] (Application Example 2)

[0829] 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".

[0830] To achieve a rapid and accurate response to disasters, it is necessary to grasp the situation on the ground in real time and optimize appropriate responses. However, existing systems make it difficult to achieve such rapid and optimized responses. Furthermore, the optimization of action instructions does not take into account the emotional state of the users, which could lead to excessive mental and physical burdens during disaster relief.

[0831] 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.

[0832] In this invention, the server includes means for collecting aircraft data and social network data, means for analyzing the collected data to identify important areas, means for generating and transmitting instructions based on the important areas, and means for detecting the user's emotional state and adjusting the instructions based on the results. This enables a rapid and accurate response in the event of a disaster, and allows for efficient and sustainable support activities while taking into account the user's emotional state.

[0833] "Aircraft data" refers to visual information acquired by unmanned aerial vehicles and is used to understand the situation during disasters.

[0834] "Social network data" refers to text and posted data obtained from social networking services on the internet, and is used to determine the urgency and location information during disasters.

[0835] "Means for analyzing and identifying critical areas" refers to methods and technologies for analyzing collected data to identify areas that are heavily affected by disaster damage.

[0836] "Means for generating and transmitting instructions" refers to a system for generating instructions to take appropriate action in identified critical areas and transmitting them to users.

[0837] "Means for detecting emotional states and adjusting instructions based on the results" refers to systems and technologies that evaluate the user's emotional state and appropriately adjust the content of instructions based on that information.

[0838] "Means of receiving feedback from the device and updating instructions" refers to a mechanism for collecting information on the results of user actions, and for reviewing and updating instructions based on that information.

[0839] The system for implementing this invention is primarily composed of a server, terminals, and users. The server has the function of identifying important areas by collecting flight data from unmanned aerial vehicles and social network data, and analyzing that data. For this purpose, it makes full use of computer vision technology and natural language processing technology. Specifically, software such as Google Cloud Vision API and Google Cloud Natural Language are used.

[0840] The server also has an emotion recognition engine to analyze emotional feedback from the user. This enables the generation and adjustment of instructions based on the user's emotional state. It generates appropriate instructions and sends them to the user's terminal. Based on the received instructions and emotion analysis, the user's terminal initiates actions at the disaster site.

[0841] As a concrete example, consider a scenario involving a large-scale flood. The server collects visual data from unmanned aerial vehicles and text data from social media to quickly identify areas particularly severely affected by the flood. It then provides specific action instructions for relief efforts to users, such as volunteers on the ground. If users are experiencing stress or fatigue, the system provides further detailed instructions and comforting messages to reduce the burden of their relief work.

[0842] This approach enables flexible and rapid responses to diverse disaster situations, and as a result, plays a crucial role in supporting the mental and physical safety of victims and aid workers.

[0843] An example of a prompt message is: "In the following disaster scenario, please write a proposal for an app that provides optimal evacuation guidance while considering the user's stress level: Describe in detail how computer vision and natural language processing are used to understand the situation on site using data obtained from the user's smart device." By inputting this into the AI ​​model, it is possible to assist in designing disaster response plans.

[0844] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0845] Step 1:

[0846] The server acquires aircraft data from unmanned aerial vehicles (UAVs). This is high-resolution visual data, used as an aerial view of the disaster area. The server then analyzes these images using the Google Cloud Vision API to identify the affected areas. The input is image data from the UAVs, and the output is information on the identified affected areas.

[0847] Step 2:

[0848] The server collects text data posted from social networking services, including posts related to disasters. Using Google Cloud Natural Language, the server analyzes the text data using natural language processing to extract urgency and important location information. The input is text data collected from social networking services, and the output includes data with urgency and location information.

[0849] Step 3:

[0850] The server identifies critical areas requiring assistance based on the analysis results of aircraft data and information extracted from social media data. This allows for an overall assessment of the disaster situation and a decision on which areas should be prioritized for aid. The input is the damage area information and social media data analysis results processed in the previous step, and the output is the identification of critical areas.

[0851] Step 4:

[0852] The server generates appropriate action instructions for designated critical areas and sends these instructions to terminals. These instructions include information on evacuation shelters and evacuation routes. Here, a generation AI model is used to create prompt sentences and utilize them to generate the content of the instructions. The input is information on critical areas, and the output is action instructions.

[0853] Step 5:

[0854] The terminal provides the user with specific activity guidance based on instructions received from the server. In doing so, the terminal's emotion recognition engine is utilized to evaluate the user's emotional state using data acquired from the camera and microphone, and adjust the instructions accordingly. The input consists of instruction data from the server and the user's real-time emotional state, while the output is optimized action guidance.

[0855] Step 6:

[0856] The user begins on-site support activities following instructions provided by the terminal. The user can provide feedback to the server via the terminal, including information gathered during the process. This feedback includes the progress of the activities and any newly discovered problems. Input is information from the user's support activities, and output is feedback data.

[0857] Step 7:

[0858] The server analyzes user feedback data and updates instructions as needed. This enables flexible responses to changing circumstances. The input is user feedback data, and the output is updated instruction information.

[0859] 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.

[0860] 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.

[0861] 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.

[0862] 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.

[0863] 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.

[0864] 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.

[0865] 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.

[0866] 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.

[0867] 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."

[0868] 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.

[0869] 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.

[0870] 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.

[0871] 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.

[0872] 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.

[0873] 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.

[0874] 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.

[0875] 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.

[0876] 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.

[0877] 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.

[0878] 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.

[0879] 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.

[0880] The following is further disclosed regarding the embodiments described above.

[0881] (Claim 1)

[0882] Means for collecting aircraft data and social network service data,

[0883] A means for analyzing the collected data to identify important areas,

[0884] Means for generating and transmitting instructions based on the aforementioned important areas,

[0885] A device that initiates action based on the aforementioned instructions,

[0886] A means for receiving feedback from the aforementioned device and updating the instructions,

[0887] A system that includes this.

[0888] (Claim 2)

[0889] The system according to claim 1, characterized in that the aforementioned aircraft data is image data captured by an unmanned aerial vehicle.

[0890] (Claim 3)

[0891] The system according to claim 1, characterized in that the device is a portable terminal for persons who carry out on-site support activities and material delivery.

[0892] "Example 1"

[0893] (Claim 1)

[0894] A means for accumulating high-resolution image information acquired by an aircraft and posted information collected from social networks,

[0895] A means for identifying important regions by analyzing the acquired high-resolution image information using computer vision technology and further evaluating the posted information using natural language processing technology,

[0896] A means for generating rescue plans and resource deployment plans based on the prioritization of the identified critical areas, and for notifying the plans via a communication device,

[0897] Upon receiving the aforementioned notification, a person with a portable information terminal who begins rescue or resupply operations at the scene,

[0898] A means for receiving information on the results of the implementation from the aforementioned portable information terminal and updating the notification content in a timely manner,

[0899] A system that includes this.

[0900] (Claim 2)

[0901] The system according to claim 1, characterized in that the high-resolution image information is information collected by an unmanned aerial vehicle.

[0902] (Claim 3)

[0903] The system according to claim 1, characterized in that the portable information terminal is a means of carrying out on-site support activities and material delivery by a person.

[0904] "Application Example 1"

[0905] (Claim 1)

[0906] Means for collecting aircraft data and social network service data,

[0907] A means for analyzing the collected data to identify important areas,

[0908] Means for generating and transmitting instructions based on the aforementioned important areas,

[0909] A mobile terminal that initiates action based on the aforementioned instructions,

[0910] A means for receiving feedback from the aforementioned mobile terminal and updating instructions,

[0911] A means of obtaining the user's location information, identifying and providing safe evacuation routes,

[0912] A means of providing information by analyzing images of the damage situation from aircraft and communication satellites,

[0913] A method for analyzing posted data from social networking platforms using natural language processing technology and evaluating its importance,

[0914] A system that includes this.

[0915] (Claim 2)

[0916] The system according to claim 1, characterized in that the aforementioned aircraft data is image data captured by an unmanned aerial vehicle, and further characterized in that computer vision technology is used when analyzing said image data.

[0917] (Claim 3)

[0918] The system according to claim 1, wherein the mobile terminal is a portable information and communication terminal for persons performing on-site support activities and material delivery, and further receives and provides emergency notifications based on location information to the user.

[0919] "Example 2 of combining an emotion engine"

[0920] (Claim 1)

[0921] Means for collecting aircraft information and online information sharing service data,

[0922] A means for analyzing the collected information to identify important locations,

[0923] Means for generating and transmitting instructions based on the aforementioned important locations,

[0924] A means of analyzing user emotions,

[0925] A means for adjusting and transmitting the aforementioned instructions according to the user's emotional state,

[0926] A device that initiates action based on the aforementioned instructions,

[0927] A means for receiving feedback from the aforementioned device and updating the instructions,

[0928] A system that includes this.

[0929] (Claim 2)

[0930] The system according to claim 1, characterized in that the aforementioned aircraft information is image data captured by an unmanned aerial vehicle.

[0931] (Claim 3)

[0932] The system according to claim 1, characterized in that the device is a communication terminal for persons performing on-site support work and material transport.

[0933] "Application example 2 of combining emotional engines"

[0934] (Claim 1)

[0935] Means for collecting aircraft data and social network data,

[0936] A means for analyzing the collected data to identify important areas,

[0937] Means for generating and transmitting instructions based on the aforementioned important areas,

[0938] A means for detecting the user's emotional state and adjusting instructions based on the results,

[0939] A device that initiates action based on the aforementioned instructions,

[0940] A means for receiving feedback from the aforementioned device and updating the instructions,

[0941] A system that includes this.

[0942] (Claim 2)

[0943] The system according to claim 1, characterized in that the aforementioned aircraft data is visual data acquired by an unmanned aerial vehicle.

[0944] (Claim 3)

[0945] The system according to claim 1, characterized in that the device is a portable information terminal for persons who perform on-site support activities and resource delivery. [Explanation of Symbols]

[0946] 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. Means for collecting aircraft data and social network service data, A means for analyzing the collected data to identify important areas, Means for generating and transmitting instructions based on the aforementioned important areas, A mobile terminal that initiates action based on the aforementioned instructions, A means for receiving feedback from the aforementioned mobile terminal and updating instructions, A means of obtaining the user's location information, identifying and providing safe evacuation routes, A means of providing information by analyzing images of the damage situation from aircraft and communication satellites, A method for analyzing posted data from social networking platforms using natural language processing technology and evaluating its importance, A system that includes this.

2. The system according to claim 1, characterized in that the aforementioned aircraft data is image data captured by an unmanned aerial vehicle, and further characterized in that computer vision technology is used when analyzing said image data.

3. The system according to claim 1, wherein the mobile terminal is a portable information and communication terminal for persons performing on-site support activities and material delivery, and further receives and provides emergency notifications based on location information to the user.

Images