System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting disaster information; means for analyzing the disaster information and specifying a disaster area; means for predicting a communication demand in the disaster area and determining an optimal deployment point; means for deploying a mobile radio vehicle having an automatic driving function at the deployment point; and means for providing a communication service after the mobile radio vehicle reaches the deployment point.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] When a natural disaster occurs, communication base stations can be destroyed, cutting off communication networks over a wide area. Rapid communication restoration in such situations is crucial for supporting victims and providing relief. However, with current technology, it takes time to deploy mobile base station vehicles, making it difficult to determine optimal locations, and human resources are limited. As a result, communication restoration is delayed, hindering smooth information transmission. The present invention aims to solve these problems and provide a system that quickly and effectively restores communication networks immediately after a disaster occurs. [Means for solving the problem]

[0005] The present invention provides a system that quickly identifies affected areas by collecting and analyzing disaster information. It also provides a means for predicting communication demand within the affected area and determining optimal deployment locations. The system includes a means for autonomously deploying mobile radio vehicles with self-driving capabilities at the deployment locations. The mobile radio vehicles are equipped with image recognition AI, which analyzes road conditions and obstacles, allowing them to safely and quickly reach their destination and provide communication services at the deployment locations. Disaster information includes earthquake data, damage information, and traffic information, enabling multifaceted and highly accurate information analysis. These means enable rapid and effective communication restoration in the event of a disaster without relying on human resources.

[0006] "Disaster information" refers to information about the occurrence of a disaster and its impact, such as earthquake data, damage information, and traffic information.

[0007] "Affected area" refers to an area affected by a disaster, where there is a particular possibility of increased demand for communications.

[0008] "Communication demand" refers to the amount and frequency of communication services required by communication users in the affected area when a disaster occurs.

[0009] "Deployment point" refers to the location where a mobile radio vehicle is optimally positioned to provide communication services.

[0010] "Autonomous driving function" refers to the technology that enables a mobile radio vehicle to drive autonomously and reach its destination without human assistance.

[0011] A "mobile wireless vehicle" refers to a vehicle equipped with wireless communication equipment that travels autonomously within a disaster area to provide communication services.

[0012] "Image recognition AI" refers to artificial intelligence technology that analyzes image data obtained from cameras and sensors to recognize objects and assess situations.

[0013] "Communication services" refers to various communication means that users use through their communication terminals, such as voice calls, data communications, and Internet connections.

[0014] "Traffic information" refers to information about road traffic conditions, such as road congestion, passable routes, and traffic accident information.

[0015] "Analysis" refers to analyzing data based on collected disaster information to identify affected areas and predict communication demand. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0020] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

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

[0026] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0033] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] MODE FOR CARRYING OUT THE INVENTION

[0038] This invention relates to a system for efficiently achieving early communication restoration in the event of a disaster. This system consists of three main components: a server, a terminal (a mobile radio vehicle), and a user. The cooperation of these components enables rapid communication restoration immediately after a disaster occurs.

[0039] Server Operation

[0040] Disaster information collection and analysis

[0041] The server collects earthquake data in real time from seismometers and the Japan Meteorological Agency, receives damage information sent from local governments and various sensors, and obtains real-time traffic conditions from a traffic information database.

[0042] The server analyzes the collected data using an AI model to identify the epicenter, seismic intensity, extent of damage, etc. Using a GIS (geographic information system), this data is plotted on a map to quickly identify the affected area.

[0043] Examples:

[0044] The server uses an API to obtain earthquake information from the Japan Meteorological Agency and receives the data in JSON format. It also receives damage information from local governments as XML data and uses it for analysis.

[0045] Forecasting communication demand and determining optimal locations

[0046] After identifying affected areas, the server uses machine learning models to predict areas where communication demand will increase, taking into account the locations of important facilities such as evacuation shelters and hospitals.

[0047] The server runs an algorithm to determine the optimal locations for deploying mobile radio vehicles, thereby optimizing communication traffic during disasters.

[0048] Examples:

[0049] The server predicts that communication demand will increase in areas where evacuation shelters are concentrated, and calculates a parking lot near the center of the area as the placement location.

[0050] Sending placement instructions

[0051] The server transmits information about the determined deployment point (GPS coordinates and route information) to the mobile radio vehicle. When the mobile radio vehicle receives this information, it activates its automatic driving system and prepares to depart for the designated deployment point.

[0052] Terminal (mobile radio vehicle) operation

[0053] Autonomous driving and ensuring safety

[0054] The device uses an autonomous driving system and image recognition AI to move towards the designated location, analyzing obstacles and traffic conditions in real time while moving to ensure safe travel.

[0055] If the device detects an obstacle, it immediately recalculates the avoidance route and selects a safe path.

[0056] Examples:

[0057] When the device detects a fallen tree while driving, it automatically calculates a new, safer route based on that information and changes direction.

[0058] Arrival at deployment site and deployment of communications equipment

[0059] When the terminal arrives at the deployment site, it begins preparations for deploying its wireless communication equipment, deploying antennas and communication devices and supplying power.

[0060] The terminal starts providing communication services to surrounding communication terminals and monitors the communication status in real time.

[0061] Examples:

[0062] After arriving at the designated location, the terminal will deploy its antenna and provide communication services to smartphones and radio terminals in the affected area.

[0063] User Operation and Monitoring

[0064] Entering damage information and correcting deployment instructions

[0065] Users (e.g., disaster response personnel) can manually input disaster information and damage status into the system, allowing for immediate response to fluctuations in emergency communication demand.

[0066] The user can also modify the vehicle location instructions as needed.

[0067] Examples:

[0068] Users enter details of the damage to their building and specify areas where communication is particularly necessary.

[0069] Condition monitoring and response coordination

[0070] Users can monitor real-time status information through the system's dashboard, including communication status and the location of mobile wireless vehicles.

[0071] If necessary, orders can be given to dispatch additional mobile radio vehicles.

[0072] Examples:

[0073] The user monitors the communication status of the mobile wireless vehicle on the dashboard, and if communication traffic increases, sends an instruction to the server to dispatch an additional vehicle.

[0074] With these functions and operations, the system of the present invention can achieve rapid and effective restoration of communications in the event of a disaster, facilitating smooth information transmission in disaster-stricken areas.

[0075] The processing flow will be explained below.

[0076] Step 1:

[0077] The server collects earthquake occurrence data in real time from seismometers and the Japan Meteorological Agency, as well as damage information from local governments and various sensors, and obtains the latest traffic conditions from a traffic information database.

[0078] Step 2:

[0079] The server integrates the collected earthquake data with a GIS (geographic information system) to identify the epicenter, seismic intensity, and extent of damage, and then analyzes the damage information and plots the most affected areas on a map.

[0080] Step 3:

[0081] The server uses machine learning models to predict communication demand within the affected area, taking into account the locations of important facilities such as evacuation centers and hospitals, and identifies areas where communication demand is likely to increase.

[0082] Step 4:

[0083] The server executes an algorithm to determine the optimal deployment location of the mobile radio vehicles, which optimizes the deployment location based on the extent of damage and communication demand.

[0084] Step 5:

[0085] The server sends the GPS coordinates of the determined deployment point and route information to the mobile radio vehicle (terminal). When the terminal receives this information, it prepares to start the autonomous driving system.

[0086] Step 6:

[0087] The device activates its autonomous driving system and image recognition AI to depart for the designated location, analyzing the route to the destination in real time and proceeding safely.

[0088] Step 7:

[0089] The device uses image recognition AI to analyze road conditions and obstacles while moving, and if an obstacle is detected, it recalculates an avoidance route and selects a safe driving path.

[0090] Step 8:

[0091] When the terminal arrives at the designated deployment location, it begins preparations to deploy its wireless communication equipment, including deploying antennas and communication devices and supplying power.

[0092] Step 9:

[0093] The terminals begin providing communication services at their deployment locations, providing Wi-Fi and mobile communication services to nearby communication terminals and monitoring communication traffic in real time.

[0094] Step 10:

[0095] Users (disaster response personnel) can manually input disaster information and damage status into the system as needed, allowing for immediate response to emergency communication demands.

[0096] Step 11:

[0097] Users can monitor the real-time status information of their mobile wireless vehicles through the system's dashboard, allowing them to check the communication status and vehicle location at any time.

[0098] Step 12:

[0099] The user can issue instructions to dispatch additional mobile radio vehicles as needed, especially when communication traffic increases, by sending new instructions to the server.

[0100] Example 1

[0101] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0102] Rapid restoration of communications in the event of a disaster is extremely important for saving lives and sharing information. However, with conventional systems, identifying the extent of damage, forecasting communication demand, and optimally deploying mobile wireless vehicles were all done manually, making it difficult to respond quickly. Furthermore, the accuracy of autonomous driving and obstacle avoidance was insufficient, and ensuring the safety of mobile wireless vehicles also posed challenges. Furthermore, deploying communications equipment and providing services required human labor, making it difficult to quickly restore communications.

[0103] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0104] In this invention, the server includes means for collecting disaster information, means for analyzing the disaster information and identifying the affected area, means for predicting communication demand within the affected area using a generative AI model and determining the optimal deployment location, means for deploying mobile wireless vehicles including an automatic driving system to the deployment location, means for automatically deploying communication equipment to provide communication services after the mobile wireless vehicles reach the deployment location, and means for the user to manually input disaster information and correct the deployment instructions for the mobile wireless vehicles, thereby enabling quick and efficient communication restoration.

[0105] "Disaster information" refers to data and information related to natural disasters such as earthquakes, tsunamis, typhoons, and floods.

[0106] "Damaged area" refers to the region or area affected by a disaster.

[0107] "Communication demand" refers to the amount and necessity of communication services required in a particular region or area.

[0108] A "generative AI model" is a machine learning or artificial intelligence model used to analyze data and predict patterns.

[0109] The "optimal deployment location" refers to a location or position where a mobile radio vehicle can be deployed efficiently and achieve maximum effectiveness.

[0110] An "autonomous driving system" refers to technology and devices that enable vehicles to drive themselves and travel to designated routes and destinations.

[0111] A "mobile wireless vehicle" is a vehicle equipped with wireless communication equipment that can provide communication services while moving.

[0112] "Communications equipment" means equipment such as antennas, transmitters, and receivers used to provide communications services.

[0113] "Users" refer to the people who operate this system and those involved in disaster response.

[0114] "Deployment instructions" are instructions or orders to deploy a mobile radio vehicle at a specific location.

[0115] MODE FOR CARRYING OUT THE INVENTION

[0116] The present invention relates to a system for efficiently achieving early communication restoration in the event of a disaster. This system consists of three main components: a server, a terminal (a mobile wireless vehicle), and a user. Specific embodiments are described below.

[0117] Server Operation

[0118] Disaster information collection and analysis

[0119] The server first collects earthquake data through seismometers and the Japan Meteorological Agency's API. The collected data is sent to the server in JSON format. It then receives damage information in XML format from local governments and various sensors, and obtains real-time traffic conditions from a traffic information database. To do this, the server uses high-performance data analysis software and AI models. Specifically, it uses a GIS (geographic information system) to plot the collected data on a map and identify the affected areas.

[0120] Examples:

[0121] The server uses an API to obtain earthquake information from the Japan Meteorological Agency and receives the data in JSON format. It also receives damage information from local governments as XML data and uses GIS to quickly identify affected areas.

[0122] Forecasting communication demand and determining optimal locations

[0123] After identifying the affected areas, the server uses a generative AI model to predict areas where communication demand will increase. The predictive model takes into account past disaster data, population data, and the locations of important facilities such as evacuation centers and hospitals. The server then runs an algorithm to determine the optimal placement locations for mobile radio vehicles, thereby optimizing communication traffic.

[0124] Examples:

[0125] The server predicts that communication demand will increase in areas where evacuation shelters are concentrated, and calculates a parking lot near the center of the area as the location for deployment.

[0126] Sending placement instructions

[0127] The server transmits information about the determined deployment point (GPS coordinates and route information) to the mobile radio vehicle. When the mobile radio vehicle receives this information, it activates its automatic driving system and prepares to depart for the designated deployment point.

[0128] Terminal (mobile radio vehicle) operation

[0129] Autonomous driving and ensuring safety

[0130] The device uses an autonomous driving system and image recognition AI to move toward the designated location. During movement, it analyzes obstacles and traffic conditions in real time to ensure safe movement. If an obstacle is detected, it immediately recalculates an avoidance route and selects a safe path.

[0131] Examples:

[0132] When the device detects a fallen tree while driving, it automatically calculates a new, safer route based on that information and changes its direction of travel.

[0133] Arrival at deployment site and deployment of communications equipment

[0134] When the terminal arrives at the deployment location, it begins preparations for deploying wireless communication equipment. It deploys antennas and communication devices and supplies power. It begins providing communication services to surrounding communication terminals and monitors communication conditions in real time.

[0135] Examples:

[0136] After arriving at the designated location, the terminal will deploy its antenna and provide communication services to smartphones and radio terminals in the affected area.

[0137] User Operation and Monitoring

[0138] Manual input of damage information and correction of placement instructions

[0139] Users can manually input disaster information and damage status into the system, supplementing the information needed to respond quickly to fluctuations in emergency communication demand. It is also possible to revise mobile radio vehicle deployment instructions as needed.

[0140] Examples:

[0141] Users enter details of the damage to their building and specify areas where communication is particularly necessary.

[0142] Condition monitoring and dispatch of additional vehicles

[0143] Users can use the system dashboard to monitor the system status in real time, check communication status and vehicle location, and issue instructions to dispatch additional vehicles if necessary.

[0144] Examples:

[0145] The user monitors the communication status of the mobile wireless vehicle on the dashboard, and if communication traffic increases, sends an instruction to the server to dispatch additional vehicles.

[0146] Examples of specific prompts to input to the generative AI model

[0147] Prompt statement:

[0148] "Please explain in detail the operating procedures of the server of the communications recovery system in the event of a disaster, from real-time data collection and data analysis, to forecasting communications demand, determining the placement locations of mobile radio vehicles, and sending placement instructions."

[0149] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0150] Step 1:

[0151] The server collects earthquake data in real time from seismometers and the Japan Meteorological Agency's API. The earthquake information obtained as input is in JSON format. The server uses this data to extract information such as the time of the earthquake, epicenter, and seismic intensity. The processed earthquake information is obtained as output.

[0152] Specific behavior:

[0153] The server makes an API request, receives earthquake data in JSON format from the Japan Meteorological Agency, and analyzes it.

[0154] Step 2:

[0155] The server receives damage information in XML format from local governments and various sensors. The damage information received as input is also in XML format. The server analyzes this and extracts information on the state of building collapse and human casualties. The output is a database containing the damage information.

[0156] Specific behavior:

[0157] The server receives and analyzes the XML data and stores the damage status in a database.

[0158] Step 3:

[0159] The server obtains real-time traffic conditions from a traffic information database. The traffic information collected as input is obtained via API. The server analyzes this information and extracts road passability and congestion information. The output is the analyzed traffic information.

[0160] Specific behavior:

[0161] The server calls the traffic information API to obtain and analyze real-time traffic conditions.

[0162] Step 4:

[0163] The server uses a generative AI model to predict affected areas and communication demand based on collected earthquake data, damage information, and traffic information. The inputs are the earthquake data, damage information, and traffic information previously collected and analyzed. Using the generative AI model, information on predicted communication demand areas and damaged areas is obtained. The output is map data of the predicted damaged areas and communication demand areas.

[0164] Specific behavior:

[0165] The server inputs data into the generative AI model and plots the affected area and communication demand forecast results.

[0166] Step 5:

[0167] The server determines the optimal location for deploying mobile wireless vehicles based on the predicted communication demand area. The input is the predicted communication demand area information, and the output is the GPS coordinates of the optimal deployment location.

[0168] Specific behavior:

[0169] The server uses machine learning algorithms to calculate the optimal placement locations for points within the affected area where communication demand is high.

[0170] Step 6:

[0171] The server sends the GPS coordinates of the determined deployment point and route information to the mobile radio vehicle. The input is the GPS coordinates of the optimal deployment point and route information. The output is deployment instructions to the mobile radio vehicle.

[0172] Specific behavior:

[0173] The server generates JSON data containing GPS coordinates and route information and sends it to the mobile radio vehicle.

[0174] Step 7:

[0175] The terminal (mobile wireless vehicle) activates the autonomous driving system based on the deployment instructions received from the server. The inputs are the GPS coordinates and route information received from the server. The terminal activates the autonomous driving system and automatically moves toward the designated deployment point. The output is arrival at the deployment point.

[0176] Specific behavior:

[0177] The device will begin autonomous driving based on route information and proceed while recognizing traffic signals and road signs.

[0178] Step 8:

[0179] As the device moves, it uses image recognition AI and sensors to detect obstacles and navigate safely. The input is real-time image data and sensor data. The device analyzes this and recalculates an avoidance route if necessary. The output is an updated safe route.

[0180] Specific behavior:

[0181] If the device detects a fallen tree or obstacle, it will automatically calculate a new route and change direction.

[0182] Step 9:

[0183] After the terminal arrives at the designated deployment point, it begins preparations to deploy wireless communication equipment. The input is arrival information for the deployment point. The terminal deploys the antenna and communication equipment and supplies power. The output is that communication is ready.

[0184] Specific behavior:

[0185] The device automatically deploys its antenna and powers on its communications equipment.

[0186] Step 10:

[0187] The terminal starts providing communication services to surrounding communication terminals and monitors the communication status in real time. The input is the request data for the communication service. The terminal analyzes this and communicates appropriately. The output is the status information of the provided communication service.

[0188] Specific behavior:

[0189] The device provides communication services to surrounding smartphones and radio devices and monitors communication conditions.

[0190] Step 11:

[0191] Users manually input disaster information and damage status into the system and modify the deployment instructions for mobile radio vehicles as necessary. The inputs are the manually entered disaster information and damage status. Based on this, the system recalculates and generates updated deployment instructions as output.

[0192] Specific behavior:

[0193] The user uses the dashboard to input information and modify the placement instructions as needed.

[0194] Step 12:

[0195] The user monitors real-time status information through the system's dashboard and issues instructions to dispatch additional mobile radio vehicles as needed. The input is real-time status information collected from the dashboard. The output is an instruction to dispatch additional vehicles.

[0196] Specific behavior:

[0197] The user monitors the communication status and location of the mobile wireless vehicles on the dashboard and issues an instruction to dispatch additional vehicles if communication traffic increases.

[0198] (Application example 1)

[0199] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0200] Conventional communication restoration systems for disaster recovery require time-consuming collection and analysis of disaster information, identification of affected areas, prediction of communication demand, and optimal deployment of mobile radios, making it difficult to quickly restore communication infrastructure. Other issues include limited real-time tracking of mobile radios and limited obstacle avoidance functions for safe operation. Furthermore, the lack of appropriate AI analysis and map display functions for emergency communication restoration makes it difficult for disaster response personnel to respond quickly.

[0201] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0202] In this invention, the server includes means for collecting disaster information, means for analyzing the disaster information to identify the affected area, means for predicting communication demand within the affected area and determining the optimal deployment location, means for deploying mobile radios with autonomous driving functions to the deployment location, means for providing communication services after the mobile radios reach the deployment location, means for tracking the progress and location information of the mobile radios in real time, and means for performing AI analysis and displaying maps to support emergency communication restoration. This enables rapid and efficient restoration of communication infrastructure, safe and reliable operation of mobile radios, and appropriate emergency response by disaster response personnel.

[0203] "Disaster information" refers to data on natural disasters such as earthquakes and typhoons, as well as information on the damage caused by these disasters.

[0204] "Affected Area" refers to the area directly or indirectly affected by a natural disaster.

[0205] "Communications demand" refers to the need for communications services at a particular time and place.

[0206] The "optimal placement point" refers to a location determined to most effectively place a mobile radio.

[0207] "Autonomous driving function" refers to the function of a mobile radio that allows it to move autonomously without human operation.

[0208] "Mobile radio" refers to communication equipment that can be moved to provide temporary communication services in the event of a disaster.

[0209] "Progress" refers to information about the location and status of the mobile radio as it progresses.

[0210] "Location information" refers to geographic coordinate data of a specific location.

[0211] "Real-time" refers to events and data processing that occur nearly simultaneously.

[0212] "Tracking" refers to the continuous monitoring of the current location and progress of a mobile radio.

[0213] "AI analytics" refers to the process of using artificial intelligence to analyze large amounts of data and derive specific goals or results.

[0214] "Map display" refers to the visual presentation of data or information on a map using a geographic information system.

[0215] "Communication services" refers to services that provide means of communication such as voice, data, and internet.

[0216] This invention relates to a system for efficiently achieving early communication restoration in the event of a disaster. This system consists of three main components: a server, a terminal (mobile radio), and a user. These components work together to enable rapid communication restoration immediately after a disaster occurs.

[0217] Server Operation

[0218] Disaster information collection and analysis

[0219] The server collects earthquake data in real time from seismometers and weather information services, receives damage information sent from local governments and various sensors, and obtains real-time traffic conditions from a traffic information database.

[0220] The server analyzes the collected data using an AI model to identify the epicenter, seismic intensity, extent of damage, etc. Using a GIS (geographic information system), this data is displayed on a map to quickly identify the affected area.

[0221] Example: The server uses an API to obtain earthquake information from a weather information service and receives the data in JSON format. It also receives damage information from local governments as XML data and uses it for analysis.

[0222] Forecasting communication demand and determining optimal locations

[0223] After identifying affected areas, the server uses machine learning models to predict areas where communication demand will increase, taking into account the locations of important facilities such as evacuation shelters and hospitals.

[0224] The system runs an algorithm to determine the optimal locations for placing mobile radios, thereby optimizing communication traffic during disasters.

[0225] Example: The server predicts that communication demand will increase in an area where evacuation shelters are concentrated, and calculates a parking lot near the center of that area as the placement point.

[0226] Sending placement instructions

[0227] The server sends information about the determined deployment point (GPS coordinates and route information) to the mobile radio. When the mobile radio receives this information, it activates the automatic driving system and prepares to depart for the designated deployment point.

[0228] Terminal (mobile radio) operation

[0229] Autonomous driving and ensuring safety

[0230] The device uses an autonomous driving system and image recognition AI to move towards the designated location, analyzing obstacles and traffic conditions in real time while moving to ensure safe travel.

[0231] If the device detects an obstacle, it immediately recalculates the avoidance route and selects a safe path.

[0232] Example: If the device detects a fallen tree while driving, it will automatically calculate a new, safer route based on that information and change direction.

[0233] Arrival at deployment site and deployment of communications equipment

[0234] When the terminal arrives at the deployment site, it begins preparations for deploying its wireless communication equipment, deploying antennas and communication devices and supplying power.

[0235] The terminal starts providing communication services to surrounding communication terminals and monitors the communication status in real time.

[0236] Example: After arriving at a designated location, the terminal deploys an antenna and provides communication services to communication terminals in the affected area.

[0237] User Operation and Monitoring

[0238] Entering damage information and correcting deployment instructions

[0239] Users (disaster response personnel) can manually input disaster information and damage status into the system, allowing for immediate response to fluctuations in emergency communication demand.

[0240] The user can also modify the mobile radio placement instructions as needed.

[0241] Example: The user inputs details of the damage situation at their facility and specifies areas where communication is particularly necessary.

[0242] Condition monitoring and response coordination

[0243] Users can monitor real-time status information through the system's dashboard, checking communication status and mobile radio location information at any time.

[0244] If necessary, instructions can be given to dispatch additional mobile radios.

[0245] Example: A user monitors the communication status of a mobile radio on the dashboard, and if communication traffic increases, sends an instruction to the server to dispatch additional vehicles.

[0246] Hardware and software used

[0247] Frontend: React Native (cross-platform development)

[0248] Backend: Node.js and Express.js (API server)

[0249] Database: MongoDB (NoSQL)

[0250] AI analysis: TensorFlow.js (machine learning model)

[0251] Map display: Google Maps API

[0252] Communication: WebSocket (real-time communication)

[0253] Prompt Sentence Examples

[0254] Examples of disaster information collection

[0255] python

[0256] import requests

[0257] def get_earthquake_data():

[0258] url = 'https: / / api.weather.jp / earthquake'

[0259] response = requests.get(url)

[0260] if response.status_code == 200:

[0261] return response.json()

[0262] else:

[0263] return None

[0264] earthquake_data = get_earthquake_data()

[0265] print(earthquake_data)

[0266] Data analysis and display examples

[0267] javascript

[0268] import as tf from '@tensorflow / tfjs';

[0269] async function analyzeEarthquakeData(data) {

[0270] const model = await tf.loadLayersModel('path / to / model.json');

[0271] const tensor = tf.tensor(data);

[0272] const predictions = model.predict(tensor).dataSync();

[0273] return predictions;

[0274] }

[0275] Example of mobile radio placement instructions

[0276] javascript

[0277] const WebSocket = require('ws');

[0278] const ws = new WebSocket('ws: / / moving_car_address');

[0279] ws.on('open', function open() {

[0280] const config = {

[0281] lat: 35.6895,

[0282] lng: 139.6917,

[0283] route: 'calculated_route_here'

[0284] };

[0285] ws.send(JSON.stringify(config));

[0286] });

[0287] Status monitoring and operation examples

[0288] javascript

[0289] import React, { useState, useEffect} from 'react';

[0290] import MapView, { Marker} from 'react-native-maps';

[0291] export default function Dashboard() {

[0292] const [cars, setCars] = useState([]);

[0293] useEffect(() => {

[0294] const fetchData = async () => {

[0295] const response = await fetch('http: / / server_address / cars');

[0296] const data = await response.json();

[0297] setCars(data);

[0298] };

[0299] fetchData();

[0300] }, []);

[0301] return (

[0302] <mapview style="{{" flex: 1}}>

[0303] {cars.map(car => (

[0304] <marker coordinate="{{" latitude: car.lat, longitude: car.lng}} / >

[0305] ))}

[0306] < / mapview>

[0307] );

[0308] }

[0309] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0310] Step 1:

[0311] Collecting disaster information

[0312] The server collects earthquake data in real time from seismometers and weather information services via API. It also receives damage information from local governments and various sensors, and obtains real-time traffic conditions from a traffic information database. Input data is mainly collected in JSON or XML format. The collected data is stored in MongoDB.

[0313] Specific behavior:

[0314] The server uses the Requests library to send requests to the earthquake data API and receives data in JSON format.

[0315] The server receives damage information in XML format from local governments and sensors via WebSocket or API.

[0316] Input: Earthquake data, damage information, traffic information

[0317] Output: Saved dataset

[0318] Step 2:

[0319] Disaster information analysis

[0320] The server analyzes the collected data using TensorFlow.js to identify the epicenter, seismic intensity, damage extent, etc. This information is displayed on a map using GIS.

[0321] Specific behavior:

[0322] The server loads the TensorFlow.js model and makes predictions using the collected data as input.

[0323] The server converts the analysis results into GeoJSON format and inputs them into a GIS to visualize the affected area.

[0324] Input: Saved dataset

[0325] Output: Map display of the affected area

[0326] Step 3:

[0327] Communications demand forecast

[0328] After identifying affected areas, the server uses machine learning models to predict areas where communication demand will increase, taking into account the locations of important facilities such as evacuation shelters and hospitals.

[0329] Specific behavior:

[0330] The server takes into account the location information of evacuation centers and hospitals and predicts communication demand using a machine learning model.

[0331] An algorithm is implemented to determine the optimum placement location of the mobile radio.

[0332] Input: Damaged area information, location information of evacuation centers and hospitals

[0333] Output: Coordinates of optimal placement point

[0334] Step 4:

[0335] Sending placement instructions

[0336] The server transmits the determined deployment location information (GPS coordinates and route information) to the mobile radio. Upon receiving this information, the mobile radio activates the automatic driving system and departs for the designated deployment location.

[0337] Specific behavior:

[0338] The server converts the GPS coordinates and route information into JSON format and sends it to the mobile radio via WebSocket.

[0339] Input: Coordinates of optimal placement point

[0340] Output: Send placement instructions

[0341] Step 5:

[0342] Autonomous driving and obstacle avoidance

[0343] The terminal (mobile radio) uses an autonomous driving system and image recognition AI to safely move towards the designated deployment point. During the journey, it analyzes obstacles and traffic conditions in real time and recalculates avoidance routes as necessary.

[0344] Specific behavior:

[0345] The mobile radio monitors road conditions using its on-board camera and sensors and performs image analysis in real time.

[0346] If an obstacle is detected, a new route is calculated and the direction of travel is changed immediately.

[0347] Input: GPS coordinates, route information, image data

[0348] Output: Safe travel route

[0349] Step 6:

[0350] Deployment of communications equipment

[0351] When the terminal (mobile radio) arrives at the deployment location, it begins preparations to deploy the wireless communication equipment, deploying antennas and communication devices and beginning to provide communication services in the affected area.

[0352] Specific behavior:

[0353] The mobile radio automatically deploys the antenna and supplies power.

[0354] We will begin providing communication services to surrounding communication terminals.

[0355] Input: Confirmation of arrival at placement point

[0356] Output: Provision of communication services

[0357] Step 7:

[0358] Condition monitoring and response coordination

[0359] Users can monitor real-time status information through the system's dashboard, check communication status and mobile radio location information at any time, and issue instructions to dispatch additional mobile radios as needed.

[0360] Specific behavior:

[0361] Users can access the dashboard through the React Native application to check communication status and mobile radio location information.

[0362] If necessary, instructions to dispatch additional mobile radios are sent to the server.

[0363] Input: Real-time status information

[0364] Output: Send dispatch instructions

[0365] Through these processing steps, rapid and efficient recovery of communication infrastructure in the event of a disaster is achieved.

[0366] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0367] MODE FOR CARRYING OUT THE INVENTION

[0368] This invention relates to a system for efficiently achieving early communication restoration in the event of a disaster. In particular, this system improves the flexibility and effectiveness of disaster response by incorporating an emotion engine that recognizes user emotions. This system consists of three main components: a server, a terminal (mobile wireless vehicle), and a user, which operate in cooperation with each other.

[0369] Server Operation

[0370] Disaster information collection and analysis

[0371] The server collects earthquake occurrence data in real time from seismometers and the Japan Meteorological Agency, receives damage information from local governments and various sensors, and obtains the latest traffic conditions from a traffic information database.

[0372] The server integrates the collected earthquake data with a GIS (geographic information system) to identify the epicenter, seismic intensity, and extent of damage, and then analyzes the damage information and plots the most affected areas on a map.

[0373] Examples:

[0374] The server uses an API to obtain earthquake information from the Japan Meteorological Agency and receives the data in JSON format. It also receives damage information from local governments as XML data and uses it for analysis.

[0375] Forecasting communication demand and determining optimal locations

[0376] After identifying affected areas, the server uses machine learning models to predict areas where communication demand will increase, taking into account the locations of important facilities such as evacuation centers and hospitals.

[0377] The server executes an algorithm to determine the optimal deployment location of the mobile radio vehicles, which optimizes the deployment location based on the extent of damage and communication demand.

[0378] Examples:

[0379] The server predicts that communication demand will increase in areas where evacuation shelters are concentrated, and calculates a parking lot near the center of the area as the placement location.

[0380] Sending placement instructions

[0381] The server sends the GPS coordinates of the determined deployment point and route information to the mobile radio vehicle (terminal). When the terminal receives this information, it activates the autonomous driving system and prepares to depart for the designated deployment point.

[0382] Terminal (mobile radio vehicle) operation

[0383] Autonomous driving and ensuring safety

[0384] The device uses an autonomous driving system and image recognition AI to move towards the designated location, analyzing obstacles and traffic conditions in real time while moving to ensure safe travel.

[0385] If the device detects an obstacle, it immediately recalculates the avoidance route and selects a safe path.

[0386] Examples:

[0387] When the device detects a fallen tree while driving, it automatically calculates a new, safer route based on that information and changes direction.

[0388] Arrival at deployment site and deployment of communications equipment

[0389] When the terminal arrives at the deployment site, it begins preparations for deploying its wireless communication equipment, deploying antennas and communication devices and supplying power.

[0390] The terminal starts providing communication services to surrounding communication terminals and monitors the communication status in real time.

[0391] Examples:

[0392] After arriving at the designated location, the terminal will deploy its antenna and provide communication services to smartphones and radio terminals in the affected area.

[0393] User interaction and emotional engine

[0394] Entering damage information and correcting deployment instructions

[0395] Users (e.g., disaster response personnel) can manually input disaster information and damage status into the system, allowing for immediate response to fluctuations in emergency communication demand.

[0396] If an emotion engine is installed, it will recognize the user's emotional state from voice input and facial expression analysis, and respond optimally based on that information.

[0397] Examples:

[0398] Users input details of the damage to their buildings and specify areas where communication is particularly necessary. If the emotion engine determines that the situation is urgent, it automatically adjusts the priority of deployment locations.

[0399] Condition monitoring and response coordination

[0400] Users can monitor the real-time status information of their mobile wireless vehicles through the system's dashboard, allowing them to check the communication status and vehicle location at any time.

[0401] Real-time emotional data from the emotion engine is also available on the dashboard, and if the emotional situation indicates an emergency, immediate action is required.

[0402] Examples:

[0403] The user monitors the communication status of the mobile wireless vehicle on the dashboard, and when a warning is received from the emotion engine, he or she quickly issues an instruction to dispatch an additional vehicle.

[0404] Emotion Engine Details

[0405] Emotion recognition by emotion engine

[0406] The emotion engine uses the user's voice input, facial expression analysis, and even biometric sensors to collect and analyze emotional data.

[0407] The collected emotional data is used to determine disaster response priorities and is fed back to the entire system.

[0408] Examples:

[0409] The emotion engine analyzes the user's stress level from their tone of voice and vocabulary, and automatically adjusts disaster response priorities based on the results.

[0410] In this way, the system of the present invention utilizes advanced information analysis technology combined with an emotion engine and autonomous driving technology to achieve rapid and effective communication restoration in the event of a disaster. By recognizing the user's emotional state in real time and implementing optimal disaster response measures based on that information, it is possible to facilitate the smooth transmission of information in disaster-stricken areas.

[0411] The processing flow will be explained below.

[0412] Step 1:

[0413] The server collects earthquake occurrence data in real time from seismometers and the Japan Meteorological Agency, receives damage information from local governments and various sensors, and obtains the latest traffic conditions from a traffic information database.

[0414] Step 2:

[0415] The server integrates the collected earthquake data with a GIS (geographic information system) to identify the epicenter, seismic intensity, and extent of damage, and also analyzes the damage information and maps out the most affected areas.

[0416] Examples:

[0417] The server uses an API to obtain earthquake information from the Japan Meteorological Agency and receives the data in JSON format. At the same time, it receives damage information from local governments as XML data and plots the affected areas using GIS software.

[0418] Step 3:

[0419] The server uses machine learning models to predict communication demand within the affected area, taking into account the locations of important facilities such as evacuation centers and hospitals, and identifies areas where communication demand will increase. It also determines the optimal locations for deploying mobile wireless vehicles based on the extent of damage and traffic information.

[0420] Examples:

[0421] The server predicts that communication demand will increase sharply in areas with many evacuation shelters, and calculates the location of the parking lot closest to the center of the area. If necessary, it also sets up avoidance routes based on the extent of damage and traffic conditions.

[0422] Step 4:

[0423] The server sends the GPS coordinates of the determined deployment point and route information to the mobile radio vehicle (terminal), which then begins preparations to activate the autonomous driving system.

[0424] Step 5:

[0425] Based on the deployment location information received from the server, the device activates the autonomous driving system and image recognition AI to depart for the designated deployment location. During the journey, it analyzes obstacles and traffic conditions to ensure safe travel.

[0426] Step 6:

[0427] The device uses image recognition AI to analyze road conditions and obstacles while moving, and if an obstacle is detected, it recalculates an avoidance route and selects a safe driving path.

[0428] Examples:

[0429] When the device detects a fallen tree or crack in the road while moving, it calculates a new, safer route based on camera and sensor information to avoid the obstacle.

[0430] Step 7:

[0431] When the terminal arrives at the designated deployment location, it begins preparations to deploy its wireless communication equipment, deploying antennas and communication devices and supplying power.

[0432] Step 8:

[0433] The terminals begin providing communication services at their deployment locations, providing Wi-Fi and mobile communication services to surrounding communication terminals (smartphones and radio terminals) and monitoring communication conditions in real time.

[0434] Step 9:

[0435] Users (disaster response personnel) can manually input disaster information and damage status into the system as needed, allowing for immediate response to changes in emergency communication demand.

[0436] Step 10:

[0437] Users can monitor the real-time status information of their mobile wireless vehicles through the system's dashboard, allowing them to check the communication status and vehicle location at any time.

[0438] Step 11:

[0439] The user uses an emotion engine to analyze the user's voice input and facial expressions, and adjusts the placement locations and response priorities of the mobile radio vehicles based on the emotion data.

[0440] Examples:

[0441] When a user enters detailed damage information into the system, the emotion engine analyzes the urgency of the situation from the user's tone of voice and automatically raises the priority of the deployment location if necessary.

[0442] Step 12:

[0443] The user monitors the communication status of the mobile wireless vehicle on the dashboard and receives real-time warnings from the emotion engine. If the emotion engine indicates an emergency, it will quickly dispatch additional vehicles.

[0444] Examples:

[0445] The user monitors the current communication traffic and emotional state on the dashboard, and if the communication traffic increases and the emotion engine determines that an "emergency" has occurred, it immediately sends instructions to the server to send additional vehicles.

[0446] Example 2

[0447] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0448] When a disaster occurs, rapid and effective restoration of communications in affected areas is required. However, in conventional systems, the collection of disaster information, identification of affected areas, forecasting of communication demand, optimal placement of mobile communication devices, and provision of communication services are all performed in separate processes, making efficient coordination difficult. Furthermore, prioritization of disaster response efforts does not take into account user emotions or the level of urgency, making flexible responses difficult. A system that can solve these problems is needed.

[0449] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting disaster information, means for analyzing the disaster information to identify a damaged area, means for predicting communication demand within the damaged area and determining an optimal deployment point, means for transmitting information about the determined deployment point to a mobile communication device, means for deploying a mobile communication device with an autonomous driving function to the deployment point, means for providing communication services after the mobile communication device reaches the deployment point, and means including an emotion engine that recognizes user emotions and adjusts disaster response priorities. This enables quick and efficient communication restoration in the event of a disaster and realizes flexible disaster response that takes the user's emotional state into consideration.

[0450] "Disaster information" refers to data related to disasters such as earthquakes, tsunamis, fires, and floods.

[0451] "Affected Area" refers to the area affected by a disaster.

[0452] "Communication demand" is an indicator that shows the need for communication services in a specific area.

[0453] "Deployment point" means the optimal location for placing a mobile communication device.

[0454] A "mobile communications device" is a vehicle or device with automated driving capabilities for providing communications services.

[0455] An "emotion engine" is a system or software that recognizes users' emotions, analyzes that data, and adjusts disaster response priorities.

[0456] "Autonomous driving function" refers to a technology or system that allows a vehicle or device to move automatically without human operation.

[0457] "Image recognition artificial intelligence" is a technology or system that acquires image data from cameras or sensors, analyzes it, and recognizes objects and situations.

[0458] MODE FOR CARRYING OUT THE INVENTION

[0459] The present invention is a system that utilizes advanced information analysis technology and autonomous driving technology combined with an emotion engine to achieve rapid and effective communication restoration in the event of a disaster. This system consists of three main components: a server, a terminal (mobile communication device), and a user. A specific embodiment of the system is described below.

[0460] Server Operation

[0461] Collecting disaster information

[0462] The server collects disaster information in real time from seismometers, the Japan Meteorological Agency, local governments, and various sensors. Specifically, it obtains earthquake occurrence data through the Japan Meteorological Agency's API, receives damage information in XML format from local governments, and obtains traffic conditions from a traffic information database.

[0463] Analysis of earthquake data and damage information

[0464] The server integrates the collected earthquake data with a GIS (geographic information system) to identify the epicenter, seismic intensity, and extent of damage. It also analyzes the damage information and plots the most affected areas on a map. This process uses GIS software (e.g., ArcGIS).

[0465] Communications demand forecast

[0466] The server uses machine learning models (e.g., TensorFlow) to predict areas where communication demand will increase, taking into account the locations of important facilities such as evacuation centers and hospitals.

[0467] Determining the optimal location

[0468] The server runs an algorithm to determine the location of the evacuation shelter based on the collected data, evaluating parking lots, plazas, and other locations near the shelter as candidates and selecting the optimal location.

[0469] Sending placement instructions

[0470] The server sends the GPS coordinates of the determined placement point and route information to the mobile communication device, using a communication protocol (e.g., MQTT) to transfer the data.

[0471] Terminal (mobile communication device) operation

[0472] Autonomous driving and ensuring safety

[0473] The mobile communication device moves to the designated location using an autonomous driving system and image recognition AI (e.g., Autoware). During movement, it uses cameras and Lidar sensors to analyze actual road conditions and proceed safely. If an obstacle is detected, it automatically recalculates an avoidance route.

[0474] Deployment of communications equipment

[0475] When the mobile communication device arrives at the deployment site, it begins deploying its communication equipment. It deploys the antenna and communication equipment, installs the equipment using a hydraulic system, and starts up a generator to supply power to the communication equipment. Once deployment is complete, it provides communication services to surrounding communication terminals and monitors the communication status in real time.

[0476] User interaction and emotional engine

[0477] Manual input of damage information and correction of placement instructions

[0478] Users (e.g., disaster response personnel) can manually input disaster information and damage status using a dedicated application. This allows for immediate response to changes in emergency communication demand. In addition, the emotion engine analyzes the user's voice input and facial expressions, and if it determines that the user is in a high-urgency situation, it automatically adjusts the priority of deployment locations.

[0479] Real-time monitoring and emotion engine

[0480] Users can monitor the real-time status of their mobile communication devices using a web-based dashboard. Real-time emotional data from the emotion engine is also available on the dashboard, and if the emotional situation indicates an emergency, immediate action is required.

[0481] Emotion recognition by emotion engine

[0482] The emotion engine uses deep learning models (e.g., OpenVINO) to recognize emotions by analyzing the user's tone of voice and facial expressions. This data is used to prioritize disaster response and is fed back to the entire system.

[0483] Specific examples

[0484] For example, if the server predicts that communication demand will increase in an area where evacuation shelters are concentrated and calculates a parking lot near the center of that area as the location, it will send GPS coordinates and route information to the corresponding mobile communication device. The mobile communication device will activate its autonomous driving system and reach the designated location while avoiding obstacles. After arriving, it will deploy communication equipment and provide communication services to smartphones and radio terminals in the affected area.

[0485] Prompt Sentence Examples

[0486] "Collect disaster information and plan the optimal placement of communication equipment based on that information. Also, analyze user sentiment and take appropriate action accordingly."

[0487] In this way, this system utilizes advanced information analysis technology combined with an emotion engine and autonomous driving technology to achieve rapid and effective communication restoration during disasters. By recognizing the user's emotional state in real time and implementing optimal disaster response measures based on that, it is possible to facilitate the transmission of information in disaster-stricken areas.

[0488] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0489] Step 1: Collect disaster information

[0490] Server operation: The server collects data in real time from seismometers, the Japan Meteorological Agency, local governments, traffic information databases, and various sensors. Specifically, the server obtains earthquake occurrence data using the Japan Meteorological Agency's API and receives the data in JSON format. It also receives damage information from local governments in XML format and obtains the latest traffic conditions from the traffic information database.

[0491] Input: Seismometer, Japan Meteorological Agency API, damage information from local governments, traffic information database

[0492] Output: Collected disaster information data

[0493] Specific operation: The server periodically sends API requests to receive earthquake occurrence information in JSON format, and similarly receives damage information in XML format and stores it for analysis.

[0494] Step 2: Analysis of earthquake data and damage information

[0495] Server operation: The collected earthquake data is integrated with a GIS (geographic information system) to identify the epicenter, seismic intensity, and extent of damage. The damage information is then analyzed and the affected areas are plotted on a map. This process uses GIS software (e.g., ArcGIS).

[0496] Input: Collected disaster information data

[0497] Output: Identification of epicenter, seismic intensity, and damage extent

[0498] Specific operation: The data collected by the server is imported into a GIS and visualized geographically to identify the affected area.

[0499] Step 3: Forecast communication demand

[0500] Server operation: Using machine learning models (e.g., TensorFlow), the server predicts areas where communication demand will increase, taking into account the location information of important facilities such as evacuation centers and hospitals.

[0501] Input: Epicenter, seismic intensity, damage extent identification results, and location information of important facilities

[0502] Output: Communication demand forecast results

[0503] Specific operation: The server uses a machine learning model based on past disaster data to predict areas where communication demand will increase.

[0504] Step 4: Determine the optimal location

[0505] Server operation: The algorithm determines the location of the evacuation shelter based on the analysis results. Parking lots and plazas near the shelter are evaluated as candidates, and the optimal location is selected.

[0506] Input: Communication demand forecast results

[0507] Output: Result of placement location determination

[0508] Specific operation: The server uses an algorithm to evaluate candidate locations and select the optimal placement point.

[0509] Step 5: Send placement instructions

[0510] Server operation: Sends the GPS coordinates and route information of the determined placement point to the mobile communication device. Transfers the data using a communication protocol (e.g., MQTT).

[0511] Input: Result of determining placement location

[0512] Output: Instruction data to the mobile communication device

[0513] Specific operations: The server sends the GPS coordinates and route information to the mobile communication device.

[0514] Step 6: Autonomous driving of mobile radio vehicles

[0515] Device operation: The mobile communication device moves to the designated location using an autonomous driving system and image recognition AI (e.g., Autoware). During the movement, it uses cameras and Lidar sensors to analyze the actual road conditions and proceed safely.

[0516] Input: GPS coordinates and route information from the server

[0517] Output: Mobile device location update information

[0518] How it works: The mobile device uses cameras and Lidar sensors to detect obstacles and calculates avoidance routes if necessary.

[0519] Step 7: Deploying communications equipment

[0520] Terminal operation: When the mobile communication device arrives at the deployment site, it begins deploying its communication equipment. It deploys the antenna and communication equipment, installs the equipment using the hydraulic system, and starts the generator to supply power to the communication equipment.

[0521] Input: Location information of mobile communication device

[0522] Output: Deployed communications equipment

[0523] Specific operation: The mobile communication device deploys the antenna and supplies power to the communication equipment.

[0524] Step 8: Manually enter damage information and modify deployment instructions

[0525] User behavior: The user (e.g., disaster response personnel) manually inputs disaster information and damage status using a dedicated application. The emotion engine analyzes the user's voice input and facial expressions, and if it determines that the situation is urgent, it automatically adjusts the priority of deployment locations.

[0526] Input: Disaster information, damage situation, user voice input, user facial expression data

[0527] Output: Priority adjustment result by the system

[0528] Specific operation: The user inputs information into the application, and the emotion engine performs analysis.

[0529] Step 9: Real-time monitoring and emotion engine usage

[0530] User behavior: Users can monitor the real-time status of their mobile communication devices using a web-based dashboard. They can also check real-time emotional data generated by the emotion engine and take emergency action.

[0531] Input: Status information of mobile communication device, emotion engine data

[0532] Output: Monitoring results and response instructions

[0533] Specific operation: Users monitor real-time information through the dashboard and take appropriate measures as needed.

[0534] Step 10: Emotion Recognition with the Emotion Engine

[0535] Server operation: The emotion engine uses deep learning models (e.g., OpenVINO) to recognize emotions by analyzing the user's tone of voice and facial expressions. This data is used to prioritize disaster response and is fed back to the entire system.

[0536] Input: User's voice tone, facial expression data

[0537] Output: Emotion recognition result

[0538] How it works: The emotion engine analyzes voice tone and facial expression data to assess the user's emotional state, and adjusts disaster response priorities accordingly.

[0539] Through the specific processing and operation of each step, the system of the present invention supports rapid and effective restoration of communications in the event of a disaster, and enables flexible responses that take into account the emotional state of the user.

[0540] (Application example 2)

[0541] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0542] In order to quickly and effectively restore communications during a disaster, it is essential to accurately grasp the damage situation and predict communications demand. However, conventional disaster response systems rely on fixed communications devices, making it difficult to respond flexibly. Furthermore, because they do not take into account the confusion and emotional state of users during a disaster, they are unable to prioritize responses in cases of high urgency. Therefore, the present invention aims to solve these problems by combining mobile wireless devices with emotion recognition technology, thereby realizing quick and effective communications restoration during a disaster.

[0543] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0544] In this invention, the server includes a means for collecting disaster information, a means for analyzing the disaster information to identify the affected area, and a means for predicting communication demand within the affected area and determining the optimal deployment location. This allows for accurate understanding of the damage situation and communication demand, enabling flexible and effective communication restoration. The mobile wireless device also includes a deployment means with an automatic driving function, a means for providing communication services after arriving at the deployment location, an emotion recognition means for recognizing emotions from user voice input and facial expression analysis, and a means for adjusting disaster response priorities based on the emotion data. This enables flexible response taking into account the user's urgency, achieving rapid and effective communication restoration.

[0545] "Disaster information" refers to data and reports on the occurrence of natural disasters, including information on earthquakes, floods, typhoons, etc.

[0546] "Means" refers to the methods or techniques used to achieve a certain goal.

[0547] "Damaged area" refers to the area where material and human damage has occurred due to a disaster.

[0548] "Telecommunications demand" refers to the amount of telecommunications capacity or services required in a particular region or under particular circumstances.

[0549] "Optimal deployment location" refers to the location that is most suitable for communications equipment and facilities to achieve maximum effectiveness.

[0550] "Autonomous driving" refers to a vehicle's ability to travel autonomously without a human driver.

[0551] "Mobile wireless device" refers to a wireless communication device that can be moved from place to place as needed.

[0552] "Location" means a specific location where equipment or facilities are installed.

[0553] "Communication services" refers to services that support the exchange of information in the form of voice calls, data communications, etc.

[0554] "Emotion recognition means" refers to technology that analyzes and recognizes the user's emotional state through voice input and facial expression analysis.

[0555] "Emotion data" refers to information that represents the user's emotional state.

[0556] "Disaster response" refers to actions and measures taken to minimize damage when a disaster occurs.

[0557] "Priority" refers to the degree of importance of performing a task or action before others.

[0558] "User" refers to the people and organizations that use this system to carry out disaster prevention and communication restoration.

[0559] The present invention is a system for quickly and effectively restoring communications in the event of a disaster. This system consists of three main components: a server, a mobile wireless device (terminal), and a user, which operate in conjunction with each other. Specific embodiments of each component are described below.

[0560] Server Operation

[0561] Disaster information collection and analysis

[0562] The server uses APIs to collect earthquake occurrence data, damage information, and traffic information in real time from the Japan Meteorological Agency and other government agencies. This data is received in JSON or XML format and analyzed by the server. The analyzed data is integrated with a GIS (geographic information system) to identify the epicenter, seismic intensity, and extent of damage. Areas that are particularly affected are plotted on a map, and information is provided to users and devices as needed.

[0563] Forecasting communication demand and determining optimal locations

[0564] After identifying the affected areas, the server uses machine learning models to predict areas where communication demand will be high. Taking into account the locations of important facilities such as evacuation centers and hospitals, the server then runs an algorithm to determine the optimal locations for mobile wireless device placement. This placement decision is optimized based on the extent of damage and communication demand.

[0565] Sending placement instructions

[0566] The server then sends the GPS coordinates and route information of the determined deployment point to the mobile wireless device. Upon receiving this information, the device activates the autonomous driving system and prepares to depart for the designated deployment point.

[0567] Terminal (mobile radio device) operation

[0568] Autonomous driving and ensuring safety

[0569] The device uses an autonomous driving system and image recognition algorithms to navigate to the designated deployment location. During the journey, it analyzes obstacles and traffic conditions in real time to ensure safe travel. If an obstacle is detected, it immediately recalculates an avoidance route and selects a safe path.

[0570] Arrival at deployment site and deployment of communications equipment

[0571] When the terminal arrives at the deployment location, it begins preparations for deploying wireless communication equipment. It deploys antennas and communication devices and supplies power. It begins providing communication services to surrounding communication terminals and monitors communication conditions in real time.

[0572] User interaction and emotional engine

[0573] Entering damage information and correcting deployment instructions

[0574] Users can manually input disaster information and damage status into the system, allowing for immediate response to fluctuations in emergency communication demand. If an emotion engine is installed, it will recognize the user's emotional state from voice input and facial expression analysis, and will respond optimally based on that information.

[0575] Condition monitoring and response coordination

[0576] Users can monitor the real-time status information of their mobile wireless devices through the system's dashboard, allowing them to check communication status and vehicle location at any time. Real-time emotion data generated by the emotion engine can also be viewed on the dashboard, allowing for immediate action in the event of an emergency.

[0577] Emotion recognition by emotion engine

[0578] The emotion engine collects and analyzes emotional data using the user's voice input, facial expression analysis, and biometric sensors. The collected emotional data is used to determine disaster response priorities and is fed back to the entire system. For example, it analyzes the user's stress level from their tone of voice and vocabulary, and adjusts emergency response priorities based on the results.

[0579] Examples of specific examples and prompts

[0580] Let's take a specific scenario: a driverless autonomous vehicle arrives at a designated evacuation shelter and deploys its antenna to provide communication services. If the user yells, "Help me! The building is collapsing and I can't escape!", the emotion engine will determine that an emergency response is required and set disaster response as the highest priority.

[0581] Example prompt sentence:

[0582] User audio: "Help! My house is collapsing and I have nowhere to run!"

[0583] Expected sentiment analysis result: 'Urgent'

[0584] As described above, the system of the present invention realizes rapid and flexible communication restoration in the event of a disaster, and enables disaster response that takes into account the emotional state of the user.

[0585] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0586] Step 1: Collecting and analyzing disaster information

[0587] The server collects earthquake occurrence data, damage information, and traffic information in real time from the Japan Meteorological Agency and other government agencies via API. It sends API requests as input and receives data in JSON or XML format as output. This data is analyzed and integrated with GIS to identify the affected area, epicenter, seismic intensity, etc. Specifically, it stores the acquired data in an internal database and uses it for subsequent analysis.

[0588] Step 2: Forecasting communication demand and determining optimal deployment locations

[0589] The server uses a machine learning model based on the collected information on affected areas to predict areas where demand for communications will increase. It uses data on affected areas and location information on important facilities such as evacuation centers and hospitals as input, and calculates the optimal location for placing mobile wireless devices as output. The server then executes an algorithm to determine this location and determines the GPS coordinates of the optimal location. Specifically, it performs calculations using a model that uses this data as input, and identifies areas where demand will be concentrated.

[0590] Step 3: Send placement instructions

[0591] The server sends the GPS coordinates of the determined deployment point and route information to the mobile wireless device. The terminal receives this information and activates the autonomous driving system. The terminal receives the GPS coordinates of the deployment point and route information as input and sets this as output in the autonomous driving system. In concrete terms, the terminal activates the navigation system based on the received route information and prepares to depart for the specified location.

[0592] Step 4: Autonomous driving and safety

[0593] The device uses an autonomous driving system and image recognition algorithms to navigate to a designated deployment point. It uses real-time video and sensor data as input and calculates a safe driving route as output. It analyzes obstacles and traffic conditions in real time and recalculates an avoidance route if an obstacle is detected. Specifically, the device uses sensors and cameras to monitor its surroundings and changes direction as necessary.

[0594] Step 5: Arrival at deployment site and deployment of communications equipment

[0595] When the terminal arrives at the deployment site, it begins preparations for deploying wireless communication equipment. It uses the current location's GPS information and the deployment site settings as input, and deploys the antenna and communication equipment as output. Specifically, it deploys the equipment necessary to supply power and begin providing communication services.

[0596] Step 6: Enter damage information and modify deployment instructions

[0597] Users can manually input disaster information and damage status into the system. The system receives the disaster information and damage status entered by the user as input and updates the data within the system as output. This allows for immediate response to changes in urgent communication demand. Specifically, the system sends the information entered through the user interface to the server and recalculates the areas requiring response.

[0598] Step 7: Leverage your emotional engine

[0599] An emotion recognition means operates to recognize emotions from the user's voice input and facial expression analysis. It receives audio and video data as input and obtains emotional data as output. Disaster response priorities are adjusted based on the emotional data. Specifically, the emotion recognition algorithm performs voice analysis to detect situations with a high level of urgency. If the user's urgency is high, the priority is automatically raised within the system.

[0600] Step 8: Condition monitoring and response adjustment

[0601] The user monitors real-time status information of the mobile wireless device through the system's dashboard. Status data and communication status during autonomous driving are received as input, and this is displayed on the dashboard as output. Real-time emotion data generated by the emotion engine can also be checked, and immediate action can be taken if an emergency response is required. Specific operations include visualizing the location and communication status of the mobile wireless device on the dashboard, and issuing additional instructions as necessary.

[0602] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0603] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0604] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0605] [Second embodiment]

[0606] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0607] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0608] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0609] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0610] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0611] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0612] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0613] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0614] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0615] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0616] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0617] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0618] MODE FOR CARRYING OUT THE INVENTION

[0619] This invention relates to a system for efficiently achieving early communication restoration in the event of a disaster. This system consists of three main components: a server, a terminal (a mobile radio vehicle), and a user. The cooperation of these components enables rapid communication restoration immediately after a disaster occurs.

[0620] Server Operation

[0621] Disaster information collection and analysis

[0622] The server collects earthquake data in real time from seismometers and the Japan Meteorological Agency, receives damage information sent from local governments and various sensors, and obtains real-time traffic conditions from a traffic information database.

[0623] The server analyzes the collected data using an AI model to identify the epicenter, seismic intensity, extent of damage, etc. Using a GIS (geographic information system), this data is plotted on a map to quickly identify the affected area.

[0624] Examples:

[0625] The server uses an API to obtain earthquake information from the Japan Meteorological Agency and receives the data in JSON format. It also receives damage information from local governments as XML data and uses it for analysis.

[0626] Forecasting communication demand and determining optimal locations

[0627] After identifying affected areas, the server uses machine learning models to predict areas where communication demand will increase, taking into account the locations of important facilities such as evacuation shelters and hospitals.

[0628] The server runs an algorithm to determine the optimal locations for deploying mobile radio vehicles, thereby optimizing communication traffic during disasters.

[0629] Examples:

[0630] The server predicts that communication demand will increase in areas where evacuation shelters are concentrated, and calculates a parking lot near the center of the area as the placement location.

[0631] Sending placement instructions

[0632] The server transmits information about the determined deployment point (GPS coordinates and route information) to the mobile radio vehicle. When the mobile radio vehicle receives this information, it activates its automatic driving system and prepares to depart for the designated deployment point.

[0633] Terminal (mobile radio vehicle) operation

[0634] Autonomous driving and ensuring safety

[0635] The device uses an autonomous driving system and image recognition AI to move towards the designated location, analyzing obstacles and traffic conditions in real time while moving to ensure safe travel.

[0636] If the device detects an obstacle, it immediately recalculates the avoidance route and selects a safe path.

[0637] Examples:

[0638] When the device detects a fallen tree while driving, it automatically calculates a new, safer route based on that information and changes direction.

[0639] Arrival at deployment site and deployment of communications equipment

[0640] When the terminal arrives at the deployment site, it begins preparations for deploying its wireless communication equipment, deploying antennas and communication devices and supplying power.

[0641] The terminal starts providing communication services to surrounding communication terminals and monitors the communication status in real time.

[0642] Examples:

[0643] After arriving at the designated location, the terminal will deploy its antenna and provide communication services to smartphones and radio terminals in the affected area.

[0644] User Operation and Monitoring

[0645] Entering damage information and correcting deployment instructions

[0646] Users (e.g., disaster response personnel) can manually input disaster information and damage status into the system, allowing for immediate response to fluctuations in emergency communication demand.

[0647] The user can also modify the vehicle location instructions as needed.

[0648] Examples:

[0649] Users enter details of the damage to their building and specify areas where communication is particularly necessary.

[0650] Condition monitoring and response coordination

[0651] Users can monitor real-time status information through the system's dashboard, including communication status and the location of mobile wireless vehicles.

[0652] If necessary, orders can be given to dispatch additional mobile radio vehicles.

[0653] Examples:

[0654] The user monitors the communication status of the mobile wireless vehicle on the dashboard, and if communication traffic increases, sends an instruction to the server to dispatch an additional vehicle.

[0655] With these functions and operations, the system of the present invention can achieve rapid and effective restoration of communications in the event of a disaster, facilitating smooth information transmission in disaster-stricken areas.

[0656] The processing flow will be explained below.

[0657] Step 1:

[0658] The server collects earthquake occurrence data in real time from seismometers and the Japan Meteorological Agency, as well as damage information from local governments and various sensors, and obtains the latest traffic conditions from a traffic information database.

[0659] Step 2:

[0660] The server integrates the collected earthquake data with a GIS (geographic information system) to identify the epicenter, seismic intensity, and extent of damage, and then analyzes the damage information and plots the most affected areas on a map.

[0661] Step 3:

[0662] The server uses machine learning models to predict communication demand within the affected area, taking into account the locations of important facilities such as evacuation centers and hospitals, and identifies areas where communication demand is likely to increase.

[0663] Step 4:

[0664] The server executes an algorithm to determine the optimal deployment location of the mobile radio vehicles, which optimizes the deployment location based on the extent of damage and communication demand.

[0665] Step 5:

[0666] The server sends the GPS coordinates of the determined deployment point and route information to the mobile radio vehicle (terminal). When the terminal receives this information, it prepares to start the autonomous driving system.

[0667] Step 6:

[0668] The device activates its autonomous driving system and image recognition AI to depart for the designated location, analyzing the route to the destination in real time and proceeding safely.

[0669] Step 7:

[0670] The device uses image recognition AI to analyze road conditions and obstacles while moving, and if an obstacle is detected, it recalculates an avoidance route and selects a safe driving path.

[0671] Step 8:

[0672] When the terminal arrives at the designated deployment location, it begins preparations to deploy its wireless communication equipment, including deploying antennas and communication devices and supplying power.

[0673] Step 9:

[0674] The terminals begin providing communication services at their deployment locations, providing Wi-Fi and mobile communication services to nearby communication terminals and monitoring communication traffic in real time.

[0675] Step 10:

[0676] Users (disaster response personnel) can manually input disaster information and damage status into the system as needed, allowing for immediate response to emergency communication demands.

[0677] Step 11:

[0678] Users can monitor the real-time status information of their mobile wireless vehicles through the system's dashboard, allowing them to check the communication status and vehicle location at any time.

[0679] Step 12:

[0680] The user can issue instructions to dispatch additional mobile radio vehicles as needed, especially when communication traffic increases, by sending new instructions to the server.

[0681] Example 1

[0682] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0683] Rapid restoration of communications in the event of a disaster is extremely important for saving lives and sharing information. However, with conventional systems, identifying the extent of damage, forecasting communication demand, and optimally deploying mobile wireless vehicles were all done manually, making it difficult to respond quickly. Furthermore, the accuracy of autonomous driving and obstacle avoidance was insufficient, and ensuring the safety of mobile wireless vehicles also posed challenges. Furthermore, deploying communications equipment and providing services required human labor, making it difficult to quickly restore communications.

[0684] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0685] In this invention, the server includes means for collecting disaster information, means for analyzing the disaster information and identifying the affected area, means for predicting communication demand within the affected area using a generative AI model and determining the optimal deployment location, means for deploying mobile wireless vehicles including an automatic driving system to the deployment location, means for automatically deploying communication equipment to provide communication services after the mobile wireless vehicles reach the deployment location, and means for the user to manually input disaster information and correct the deployment instructions for the mobile wireless vehicles, thereby enabling quick and efficient communication restoration.

[0686] "Disaster information" refers to data and information related to natural disasters such as earthquakes, tsunamis, typhoons, and floods.

[0687] "Damaged area" refers to the region or area affected by a disaster.

[0688] "Communication demand" refers to the amount and necessity of communication services required in a particular region or area.

[0689] A "generative AI model" is a machine learning or artificial intelligence model used to analyze data and predict patterns.

[0690] The "optimal deployment location" refers to a location or position where a mobile radio vehicle can be deployed efficiently and achieve maximum effectiveness.

[0691] An "autonomous driving system" refers to technology and devices that enable vehicles to drive themselves and travel to designated routes and destinations.

[0692] A "mobile wireless vehicle" is a vehicle equipped with wireless communication equipment that can provide communication services while moving.

[0693] "Communications equipment" means equipment such as antennas, transmitters, and receivers used to provide communications services.

[0694] "Users" refer to the people who operate this system and those involved in disaster response.

[0695] "Deployment instructions" are instructions or orders to deploy a mobile radio vehicle at a specific location.

[0696] MODE FOR CARRYING OUT THE INVENTION

[0697] The present invention relates to a system for efficiently achieving early communication restoration in the event of a disaster. This system consists of three main components: a server, a terminal (a mobile wireless vehicle), and a user. Specific embodiments are described below.

[0698] Server Operation

[0699] Disaster information collection and analysis

[0700] The server first collects earthquake data through seismometers and the Japan Meteorological Agency's API. The collected data is sent to the server in JSON format. It then receives damage information in XML format from local governments and various sensors, and obtains real-time traffic conditions from a traffic information database. To do this, the server uses high-performance data analysis software and AI models. Specifically, it uses a GIS (geographic information system) to plot the collected data on a map and identify the affected areas.

[0701] Examples:

[0702] The server uses an API to obtain earthquake information from the Japan Meteorological Agency and receives the data in JSON format. It also receives damage information from local governments as XML data and uses GIS to quickly identify affected areas.

[0703] Forecasting communication demand and determining optimal locations

[0704] After identifying the affected areas, the server uses a generative AI model to predict areas where communication demand will increase. The predictive model takes into account past disaster data, population data, and the locations of important facilities such as evacuation centers and hospitals. The server then runs an algorithm to determine the optimal placement locations for mobile radio vehicles, thereby optimizing communication traffic.

[0705] Examples:

[0706] The server predicts that communication demand will increase in areas where evacuation shelters are concentrated, and calculates a parking lot near the center of the area as the location for deployment.

[0707] Sending placement instructions

[0708] The server transmits information about the determined deployment point (GPS coordinates and route information) to the mobile radio vehicle. When the mobile radio vehicle receives this information, it activates its automatic driving system and prepares to depart for the designated deployment point.

[0709] Terminal (mobile radio vehicle) operation

[0710] Autonomous driving and ensuring safety

[0711] The device uses an autonomous driving system and image recognition AI to move toward the designated location. During movement, it analyzes obstacles and traffic conditions in real time to ensure safe movement. If an obstacle is detected, it immediately recalculates an avoidance route and selects a safe path.

[0712] Examples:

[0713] When the device detects a fallen tree while driving, it automatically calculates a new, safer route based on that information and changes its direction of travel.

[0714] Arrival at deployment site and deployment of communications equipment

[0715] When the terminal arrives at the deployment location, it begins preparations for deploying wireless communication equipment. It deploys antennas and communication devices and supplies power. It begins providing communication services to surrounding communication terminals and monitors communication conditions in real time.

[0716] Examples:

[0717] After arriving at the designated location, the terminal will deploy its antenna and provide communication services to smartphones and radio terminals in the affected area.

[0718] User Operation and Monitoring

[0719] Manual input of damage information and correction of placement instructions

[0720] Users can manually input disaster information and damage status into the system, supplementing the information needed to respond quickly to fluctuations in emergency communication demand. It is also possible to revise mobile radio vehicle deployment instructions as needed.

[0721] Examples:

[0722] Users enter details of the damage to their building and specify areas where communication is particularly necessary.

[0723] Condition monitoring and dispatch of additional vehicles

[0724] Users can use the system dashboard to monitor the system status in real time, check communication status and vehicle location, and issue instructions to dispatch additional vehicles if necessary.

[0725] Examples:

[0726] The user monitors the communication status of the mobile wireless vehicle on the dashboard, and if communication traffic increases, sends an instruction to the server to dispatch additional vehicles.

[0727] Examples of specific prompts to input to the generative AI model

[0728] Prompt statement:

[0729] "Please explain in detail the operating procedures of the server of the communications recovery system in the event of a disaster, from real-time data collection and data analysis, to forecasting communications demand, determining the placement locations of mobile radio vehicles, and sending placement instructions."

[0730] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0731] Step 1:

[0732] The server collects earthquake data in real time from seismometers and the Japan Meteorological Agency's API. The earthquake information obtained as input is in JSON format. The server uses this data to extract information such as the time of the earthquake, epicenter, and seismic intensity. The processed earthquake information is obtained as output.

[0733] Specific behavior:

[0734] The server makes an API request, receives earthquake data in JSON format from the Japan Meteorological Agency, and analyzes it.

[0735] Step 2:

[0736] The server receives damage information in XML format from local governments and various sensors. The damage information received as input is also in XML format. The server analyzes this and extracts information on the state of building collapse and human casualties. The output is a database containing the damage information.

[0737] Specific behavior:

[0738] The server receives and analyzes the XML data and stores the damage status in a database.

[0739] Step 3:

[0740] The server obtains real-time traffic conditions from a traffic information database. The traffic information collected as input is obtained via API. The server analyzes this information and extracts road passability and congestion information. The output is the analyzed traffic information.

[0741] Specific behavior:

[0742] The server calls the traffic information API to obtain and analyze real-time traffic conditions.

[0743] Step 4:

[0744] The server uses a generative AI model to predict affected areas and communication demand based on collected earthquake data, damage information, and traffic information. The inputs are the earthquake data, damage information, and traffic information previously collected and analyzed. Using the generative AI model, information on predicted communication demand areas and damaged areas is obtained. The output is map data of the predicted damaged areas and communication demand areas.

[0745] Specific behavior:

[0746] The server inputs data into the generative AI model and plots the affected area and communication demand forecast results.

[0747] Step 5:

[0748] The server determines the optimal location for deploying mobile wireless vehicles based on the predicted communication demand area. The input is the predicted communication demand area information, and the output is the GPS coordinates of the optimal deployment location.

[0749] Specific behavior:

[0750] The server uses machine learning algorithms to calculate the optimal placement locations for points within the affected area where communication demand is high.

[0751] Step 6:

[0752] The server sends the GPS coordinates of the determined deployment point and route information to the mobile radio vehicle. The input is the GPS coordinates of the optimal deployment point and route information. The output is deployment instructions to the mobile radio vehicle.

[0753] Specific behavior:

[0754] The server generates JSON data containing GPS coordinates and route information and sends it to the mobile radio vehicle.

[0755] Step 7:

[0756] The terminal (mobile wireless vehicle) activates the autonomous driving system based on the deployment instructions received from the server. The inputs are the GPS coordinates and route information received from the server. The terminal activates the autonomous driving system and automatically moves toward the designated deployment point. The output is arrival at the deployment point.

[0757] Specific behavior:

[0758] The device will begin autonomous driving based on route information and proceed while recognizing traffic signals and road signs.

[0759] Step 8:

[0760] As the device moves, it uses image recognition AI and sensors to detect obstacles and navigate safely. The input is real-time image data and sensor data. The device analyzes this and recalculates an avoidance route if necessary. The output is an updated safe route.

[0761] Specific behavior:

[0762] If the device detects a fallen tree or obstacle, it will automatically calculate a new route and change direction.

[0763] Step 9:

[0764] After the terminal arrives at the designated deployment point, it begins preparations to deploy wireless communication equipment. The input is arrival information for the deployment point. The terminal deploys the antenna and communication equipment and supplies power. The output is that communication is ready.

[0765] Specific behavior:

[0766] The device automatically deploys its antenna and powers on its communications equipment.

[0767] Step 10:

[0768] The terminal starts providing communication services to surrounding communication terminals and monitors the communication status in real time. The input is the request data for the communication service. The terminal analyzes this and communicates appropriately. The output is the status information of the provided communication service.

[0769] Specific behavior:

[0770] The device provides communication services to surrounding smartphones and radio devices and monitors communication conditions.

[0771] Step 11:

[0772] Users manually input disaster information and damage status into the system and modify the deployment instructions for mobile radio vehicles as necessary. The inputs are the manually entered disaster information and damage status. Based on this, the system recalculates and generates updated deployment instructions as output.

[0773] Specific behavior:

[0774] The user uses the dashboard to input information and modify the placement instructions as needed.

[0775] Step 12:

[0776] The user monitors real-time status information through the system's dashboard and issues instructions to dispatch additional mobile radio vehicles as needed. The input is real-time status information collected from the dashboard. The output is an instruction to dispatch additional vehicles.

[0777] Specific behavior:

[0778] The user monitors the communication status and location of the mobile wireless vehicles on the dashboard and issues an instruction to dispatch additional vehicles if communication traffic increases.

[0779] (Application example 1)

[0780] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0781] Conventional communication restoration systems for disaster recovery require time-consuming collection and analysis of disaster information, identification of affected areas, prediction of communication demand, and optimal deployment of mobile radios, making it difficult to quickly restore communication infrastructure. Other issues include limited real-time tracking of mobile radios and limited obstacle avoidance functions for safe operation. Furthermore, the lack of appropriate AI analysis and map display functions for emergency communication restoration makes it difficult for disaster response personnel to respond quickly.

[0782] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0783] In this invention, the server includes means for collecting disaster information, means for analyzing the disaster information to identify the affected area, means for predicting communication demand within the affected area and determining the optimal deployment location, means for deploying mobile radios with autonomous driving functions to the deployment location, means for providing communication services after the mobile radios reach the deployment location, means for tracking the progress and location information of the mobile radios in real time, and means for performing AI analysis and displaying maps to support emergency communication restoration. This enables rapid and efficient restoration of communication infrastructure, safe and reliable operation of mobile radios, and appropriate emergency response by disaster response personnel.

[0784] "Disaster information" refers to data on natural disasters such as earthquakes and typhoons, as well as information on the damage caused by these disasters.

[0785] "Affected Area" refers to the area directly or indirectly affected by a natural disaster.

[0786] "Communications demand" refers to the need for communications services at a particular time and place.

[0787] The "optimal placement point" refers to a location determined to most effectively place a mobile radio.

[0788] "Autonomous driving function" refers to the function of a mobile radio that allows it to move autonomously without human operation.

[0789] "Mobile radio" refers to communication equipment that can be moved to provide temporary communication services in the event of a disaster.

[0790] "Progress" refers to information about the location and status of the mobile radio as it progresses.

[0791] "Location information" refers to geographic coordinate data of a specific location.

[0792] "Real-time" refers to events and data processing that occur nearly simultaneously.

[0793] "Tracking" refers to the continuous monitoring of the current location and progress of a mobile radio.

[0794] "AI analytics" refers to the process of using artificial intelligence to analyze large amounts of data and derive specific goals or results.

[0795] "Map display" refers to the visual presentation of data or information on a map using a geographic information system.

[0796] "Communication services" refers to services that provide means of communication such as voice, data, and internet.

[0797] This invention relates to a system for efficiently achieving early communication restoration in the event of a disaster. This system consists of three main components: a server, a terminal (mobile radio), and a user. These components work together to enable rapid communication restoration immediately after a disaster occurs.

[0798] Server Operation

[0799] Disaster information collection and analysis

[0800] The server collects earthquake data in real time from seismometers and weather information services, receives damage information sent from local governments and various sensors, and obtains real-time traffic conditions from a traffic information database.

[0801] The server analyzes the collected data using an AI model to identify the epicenter, seismic intensity, extent of damage, etc. Using a GIS (geographic information system), this data is displayed on a map to quickly identify the affected area.

[0802] Example: The server uses an API to obtain earthquake information from a weather information service and receives the data in JSON format. It also receives damage information from local governments as XML data and uses it for analysis.

[0803] Forecasting communication demand and determining optimal locations

[0804] After identifying affected areas, the server uses machine learning models to predict areas where communication demand will increase, taking into account the locations of important facilities such as evacuation shelters and hospitals.

[0805] The system runs an algorithm to determine the optimal locations for placing mobile radios, thereby optimizing communication traffic during disasters.

[0806] Example: The server predicts that communication demand will increase in an area where evacuation shelters are concentrated, and calculates a parking lot near the center of that area as the placement point.

[0807] Sending placement instructions

[0808] The server sends information about the determined deployment point (GPS coordinates and route information) to the mobile radio. When the mobile radio receives this information, it activates the automatic driving system and prepares to depart for the designated deployment point.

[0809] Terminal (mobile radio) operation

[0810] Autonomous driving and ensuring safety

[0811] The device uses an autonomous driving system and image recognition AI to move towards the designated location, analyzing obstacles and traffic conditions in real time while moving to ensure safe travel.

[0812] If the device detects an obstacle, it immediately recalculates the avoidance route and selects a safe path.

[0813] Example: If the device detects a fallen tree while driving, it will automatically calculate a new, safer route based on that information and change direction.

[0814] Arrival at deployment site and deployment of communications equipment

[0815] When the terminal arrives at the deployment site, it begins preparations for deploying its wireless communication equipment, deploying antennas and communication devices and supplying power.

[0816] The terminal starts providing communication services to surrounding communication terminals and monitors the communication status in real time.

[0817] Example: After arriving at a designated location, the terminal deploys an antenna and provides communication services to communication terminals in the affected area.

[0818] User Operation and Monitoring

[0819] Entering damage information and correcting deployment instructions

[0820] Users (disaster response personnel) can manually input disaster information and damage status into the system, allowing for immediate response to fluctuations in emergency communication demand.

[0821] The user can also modify the mobile radio placement instructions as needed.

[0822] Example: The user inputs details of the damage situation at their facility and specifies areas where communication is particularly necessary.

[0823] Condition monitoring and response coordination

[0824] Users can monitor real-time status information through the system's dashboard, checking communication status and mobile radio location information at any time.

[0825] If necessary, instructions can be given to dispatch additional mobile radios.

[0826] Example: A user monitors the communication status of a mobile radio on the dashboard, and if communication traffic increases, sends an instruction to the server to dispatch additional vehicles.

[0827] Hardware and software used

[0828] Frontend: React Native (cross-platform development)

[0829] Backend: Node.js and Express.js (API server)

[0830] Database: MongoDB (NoSQL)

[0831] AI analysis: TensorFlow.js (machine learning model)

[0832] Map display: Google Maps API

[0833] Communication: WebSocket (real-time communication)

[0834] Prompt Sentence Examples

[0835] Examples of disaster information collection

[0836] python

[0837] import requests

[0838] def get_earthquake_data():

[0839] url = 'https: / / api.weather.jp / earthquake'

[0840] response = requests.get(url)

[0841] if response.status_code == 200:

[0842] return response.json()

[0843] else:

[0844] return None

[0845] earthquake_data = get_earthquake_data()

[0846] print(earthquake_data)

[0847] Data analysis and display examples

[0848] javascript

[0849] import as tf from '@tensorflow / tfjs';

[0850] async function analyzeEarthquakeData(data) {

[0851] const model = await tf.loadLayersModel('path / to / model.json');

[0852] const tensor = tf.tensor(data);

[0853] const predictions = model.predict(tensor).dataSync();

[0854] return predictions;

[0855] }

[0856] Example of mobile radio placement instructions

[0857] javascript

[0858] const WebSocket = require('ws');

[0859] const ws = new WebSocket('ws: / / moving_car_address');

[0860] ws.on('open', function open() {

[0861] const config = {

[0862] lat: 35.6895,

[0863] lng: 139.6917,

[0864] route: 'calculated_route_here'

[0865] };

[0866] ws.send(JSON.stringify(config));

[0867] });

[0868] Status monitoring and operation examples

[0869] javascript

[0870] import React, { useState, useEffect} from 'react';

[0871] import MapView, { Marker} from 'react-native-maps';

[0872] export default function Dashboard() {

[0873] const [cars, setCars] = useState([]);

[0874] useEffect(() => {

[0875] const fetchData = async () => {

[0876] const response = await fetch('http: / / server_address / cars');

[0877] const data = await response.json();

[0878] setCars(data);

[0879] };

[0880] fetchData();

[0881] }, []);

[0882] return (

[0883] <mapview style="{{" flex: 1}}>

[0884] {cars.map(car => (

[0885] <marker coordinate="{{" latitude: car.lat, longitude: car.lng}} / >

[0886] ))}

[0887] < / mapview>

[0888] );

[0889] }

[0890] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0891] Step 1:

[0892] Collecting disaster information

[0893] The server collects earthquake data in real time from seismometers and weather information services via API. It also receives damage information from local governments and various sensors, and obtains real-time traffic conditions from a traffic information database. Input data is mainly collected in JSON or XML format. The collected data is stored in MongoDB.

[0894] Specific behavior:

[0895] The server uses the Requests library to send requests to the earthquake data API and receives data in JSON format.

[0896] The server receives damage information in XML format from local governments and sensors via WebSocket or API.

[0897] Input: Earthquake data, damage information, traffic information

[0898] Output: Saved dataset

[0899] Step 2:

[0900] Disaster information analysis

[0901] The server analyzes the collected data using TensorFlow.js to identify the epicenter, seismic intensity, damage extent, etc. This information is displayed on a map using GIS.

[0902] Specific behavior:

[0903] The server loads the TensorFlow.js model and makes predictions using the collected data as input.

[0904] The server converts the analysis results into GeoJSON format and inputs them into a GIS to visualize the affected area.

[0905] Input: Saved dataset

[0906] Output: Map display of the affected area

[0907] Step 3:

[0908] Communications demand forecast

[0909] After identifying affected areas, the server uses machine learning models to predict areas where communication demand will increase, taking into account the locations of important facilities such as evacuation shelters and hospitals.

[0910] Specific behavior:

[0911] The server takes into account the location information of evacuation centers and hospitals and predicts communication demand using a machine learning model.

[0912] An algorithm is implemented to determine the optimum placement location of the mobile radio.

[0913] Input: Damaged area information, location information of evacuation centers and hospitals

[0914] Output: Coordinates of optimal placement point

[0915] Step 4:

[0916] Sending placement instructions

[0917] The server transmits the determined deployment location information (GPS coordinates and route information) to the mobile radio. Upon receiving this information, the mobile radio activates the automatic driving system and departs for the designated deployment location.

[0918] Specific behavior:

[0919] The server converts the GPS coordinates and route information into JSON format and sends it to the mobile radio via WebSocket.

[0920] Input: Coordinates of optimal placement point

[0921] Output: Send placement instructions

[0922] Step 5:

[0923] Autonomous driving and obstacle avoidance

[0924] The terminal (mobile radio) uses an autonomous driving system and image recognition AI to safely move towards the designated deployment point. During the journey, it analyzes obstacles and traffic conditions in real time and recalculates avoidance routes as necessary.

[0925] Specific behavior:

[0926] The mobile radio monitors road conditions using its on-board camera and sensors and performs image analysis in real time.

[0927] If an obstacle is detected, a new route is calculated and the direction of travel is changed immediately.

[0928] Input: GPS coordinates, route information, image data

[0929] Output: Safe travel route

[0930] Step 6:

[0931] Deployment of communications equipment

[0932] When the terminal (mobile radio) arrives at the deployment location, it begins preparations to deploy the wireless communication equipment, deploying antennas and communication devices and beginning to provide communication services in the affected area.

[0933] Specific behavior:

[0934] The mobile radio automatically deploys the antenna and supplies power.

[0935] We will begin providing communication services to surrounding communication terminals.

[0936] Input: Confirmation of arrival at placement point

[0937] Output: Provision of communication services

[0938] Step 7:

[0939] Condition monitoring and response coordination

[0940] Users can monitor real-time status information through the system's dashboard, check communication status and mobile radio location information at any time, and issue instructions to dispatch additional mobile radios as needed.

[0941] Specific behavior:

[0942] Users can access the dashboard through the React Native application to check communication status and mobile radio location information.

[0943] If necessary, instructions to dispatch additional mobile radios are sent to the server.

[0944] Input: Real-time status information

[0945] Output: Send dispatch instructions

[0946] Through these processing steps, rapid and efficient recovery of communication infrastructure in the event of a disaster is achieved.

[0947] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0948] MODE FOR CARRYING OUT THE INVENTION

[0949] This invention relates to a system for efficiently achieving early communication restoration in the event of a disaster. In particular, this system improves the flexibility and effectiveness of disaster response by incorporating an emotion engine that recognizes user emotions. This system consists of three main components: a server, a terminal (mobile wireless vehicle), and a user, which operate in cooperation with each other.

[0950] Server Operation

[0951] Disaster information collection and analysis

[0952] The server collects earthquake occurrence data in real time from seismometers and the Japan Meteorological Agency, receives damage information from local governments and various sensors, and obtains the latest traffic conditions from a traffic information database.

[0953] The server integrates the collected earthquake data with a GIS (geographic information system) to identify the epicenter, seismic intensity, and extent of damage, and then analyzes the damage information and plots the most affected areas on a map.

[0954] Examples:

[0955] The server uses an API to obtain earthquake information from the Japan Meteorological Agency and receives the data in JSON format. It also receives damage information from local governments as XML data and uses it for analysis.

[0956] Forecasting communication demand and determining optimal locations

[0957] After identifying affected areas, the server uses machine learning models to predict areas where communication demand will increase, taking into account the locations of important facilities such as evacuation centers and hospitals.

[0958] The server executes an algorithm to determine the optimal deployment location of the mobile radio vehicles, which optimizes the deployment location based on the extent of damage and communication demand.

[0959] Examples:

[0960] The server predicts that communication demand will increase in areas where evacuation shelters are concentrated, and calculates a parking lot near the center of the area as the placement location.

[0961] Sending placement instructions

[0962] The server sends the GPS coordinates of the determined deployment point and route information to the mobile radio vehicle (terminal). When the terminal receives this information, it activates the autonomous driving system and prepares to depart for the designated deployment point.

[0963] Terminal (mobile radio vehicle) operation

[0964] Autonomous driving and ensuring safety

[0965] The device uses an autonomous driving system and image recognition AI to move towards the designated location, analyzing obstacles and traffic conditions in real time while moving to ensure safe travel.

[0966] If the device detects an obstacle, it immediately recalculates the avoidance route and selects a safe path.

[0967] Examples:

[0968] When the device detects a fallen tree while driving, it automatically calculates a new, safer route based on that information and changes direction.

[0969] Arrival at deployment site and deployment of communications equipment

[0970] When the terminal arrives at the deployment site, it begins preparations for deploying its wireless communication equipment, deploying antennas and communication devices and supplying power.

[0971] The terminal starts providing communication services to surrounding communication terminals and monitors the communication status in real time.

[0972] Examples:

[0973] After arriving at the designated location, the terminal will deploy its antenna and provide communication services to smartphones and radio terminals in the affected area.

[0974] User interaction and emotional engine

[0975] Entering damage information and correcting deployment instructions

[0976] Users (e.g., disaster response personnel) can manually input disaster information and damage status into the system, allowing for immediate response to fluctuations in emergency communication demand.

[0977] If an emotion engine is installed, it will recognize the user's emotional state from voice input and facial expression analysis, and respond optimally based on that information.

[0978] Examples:

[0979] Users input details of the damage to their buildings and specify areas where communication is particularly necessary. If the emotion engine determines that the situation is urgent, it automatically adjusts the priority of deployment locations.

[0980] Condition monitoring and response coordination

[0981] Users can monitor the real-time status information of their mobile wireless vehicles through the system's dashboard, allowing them to check the communication status and vehicle location at any time.

[0982] Real-time emotional data from the emotion engine is also available on the dashboard, and if the emotional situation indicates an emergency, immediate action is required.

[0983] Examples:

[0984] The user monitors the communication status of the mobile wireless vehicle on the dashboard, and when a warning is received from the emotion engine, he or she quickly issues an instruction to dispatch an additional vehicle.

[0985] Emotion Engine Details

[0986] Emotion recognition by emotion engine

[0987] The emotion engine uses the user's voice input, facial expression analysis, and even biometric sensors to collect and analyze emotional data.

[0988] The collected emotional data is used to determine disaster response priorities and is fed back to the entire system.

[0989] Examples:

[0990] The emotion engine analyzes the user's stress level from their tone of voice and vocabulary, and automatically adjusts disaster response priorities based on the results.

[0991] In this way, the system of the present invention utilizes advanced information analysis technology combined with an emotion engine and autonomous driving technology to achieve rapid and effective communication restoration in the event of a disaster. By recognizing the user's emotional state in real time and implementing optimal disaster response measures based on that information, it is possible to facilitate the smooth transmission of information in disaster-stricken areas.

[0992] The processing flow will be explained below.

[0993] Step 1:

[0994] The server collects earthquake occurrence data in real time from seismometers and the Japan Meteorological Agency, receives damage information from local governments and various sensors, and obtains the latest traffic conditions from a traffic information database.

[0995] Step 2:

[0996] The server integrates the collected earthquake data with a GIS (geographic information system) to identify the epicenter, seismic intensity, and extent of damage, and also analyzes the damage information and maps out the most affected areas.

[0997] Examples:

[0998] The server uses an API to obtain earthquake information from the Japan Meteorological Agency and receives the data in JSON format. At the same time, it receives damage information from local governments as XML data and plots the affected areas using GIS software.

[0999] Step 3:

[1000] The server uses machine learning models to predict communication demand within the affected area, taking into account the locations of important facilities such as evacuation centers and hospitals, and identifies areas where communication demand will increase. It also determines the optimal locations for deploying mobile wireless vehicles based on the extent of damage and traffic information.

[1001] Examples:

[1002] The server predicts that communication demand will increase sharply in areas with many evacuation shelters, and calculates the location of the parking lot closest to the center of the area. If necessary, it also sets up avoidance routes based on the extent of damage and traffic conditions.

[1003] Step 4:

[1004] The server sends the GPS coordinates of the determined deployment point and route information to the mobile radio vehicle (terminal), which then begins preparations to activate the autonomous driving system.

[1005] Step 5:

[1006] Based on the deployment location information received from the server, the device activates the autonomous driving system and image recognition AI to depart for the designated deployment location. During the journey, it analyzes obstacles and traffic conditions to ensure safe travel.

[1007] Step 6:

[1008] The device uses image recognition AI to analyze road conditions and obstacles while moving, and if an obstacle is detected, it recalculates an avoidance route and selects a safe driving path.

[1009] Examples:

[1010] When the device detects a fallen tree or crack in the road while moving, it calculates a new, safer route based on camera and sensor information to avoid the obstacle.

[1011] Step 7:

[1012] When the terminal arrives at the designated deployment location, it begins preparations to deploy its wireless communication equipment, deploying antennas and communication devices and supplying power.

[1013] Step 8:

[1014] The terminals begin providing communication services at their deployment locations, providing Wi-Fi and mobile communication services to surrounding communication terminals (smartphones and radio terminals) and monitoring communication conditions in real time.

[1015] Step 9:

[1016] Users (disaster response personnel) can manually input disaster information and damage status into the system as needed, allowing for immediate response to changes in emergency communication demand.

[1017] Step 10:

[1018] Users can monitor the real-time status information of their mobile wireless vehicles through the system's dashboard, allowing them to check the communication status and vehicle location at any time.

[1019] Step 11:

[1020] The user uses an emotion engine to analyze the user's voice input and facial expressions, and adjusts the placement locations and response priorities of the mobile radio vehicles based on the emotion data.

[1021] Examples:

[1022] When a user enters detailed damage information into the system, the emotion engine analyzes the urgency of the situation from the user's tone of voice and automatically raises the priority of the deployment location if necessary.

[1023] Step 12:

[1024] The user monitors the communication status of the mobile wireless vehicle on the dashboard and receives real-time warnings from the emotion engine. If the emotion engine indicates an emergency, it will quickly dispatch additional vehicles.

[1025] Examples:

[1026] The user monitors the current communication traffic and emotional state on the dashboard, and if the communication traffic increases and the emotion engine determines that an "emergency" has occurred, it immediately sends instructions to the server to send additional vehicles.

[1027] Example 2

[1028] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1029] When a disaster occurs, rapid and effective restoration of communications in affected areas is required. However, in conventional systems, the collection of disaster information, identification of affected areas, forecasting of communication demand, optimal placement of mobile communication devices, and provision of communication services are all performed in separate processes, making efficient coordination difficult. Furthermore, prioritization of disaster response efforts does not take into account user emotions or the level of urgency, making flexible responses difficult. A system that can solve these problems is needed.

[1030] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting disaster information, means for analyzing the disaster information to identify a damaged area, means for predicting communication demand within the damaged area and determining an optimal deployment point, means for transmitting information about the determined deployment point to a mobile communication device, means for deploying a mobile communication device with an autonomous driving function to the deployment point, means for providing communication services after the mobile communication device reaches the deployment point, and means including an emotion engine that recognizes user emotions and adjusts disaster response priorities. This enables quick and efficient communication restoration in the event of a disaster and realizes flexible disaster response that takes the user's emotional state into consideration.

[1031] "Disaster information" refers to data related to disasters such as earthquakes, tsunamis, fires, and floods.

[1032] "Affected Area" refers to the area affected by a disaster.

[1033] "Communication demand" is an indicator that shows the need for communication services in a specific area.

[1034] "Deployment point" means the optimal location for placing a mobile communication device.

[1035] A "mobile communications device" is a vehicle or device with automated driving capabilities for providing communications services.

[1036] An "emotion engine" is a system or software that recognizes users' emotions, analyzes that data, and adjusts disaster response priorities.

[1037] "Autonomous driving function" refers to a technology or system that allows a vehicle or device to move automatically without human operation.

[1038] "Image recognition artificial intelligence" is a technology or system that acquires image data from cameras or sensors, analyzes it, and recognizes objects and situations.

[1039] MODE FOR CARRYING OUT THE INVENTION

[1040] The present invention is a system that utilizes advanced information analysis technology and autonomous driving technology combined with an emotion engine to achieve rapid and effective communication restoration in the event of a disaster. This system consists of three main components: a server, a terminal (mobile communication device), and a user. A specific embodiment of the system is described below.

[1041] Server Operation

[1042] Collecting disaster information

[1043] The server collects disaster information in real time from seismometers, the Japan Meteorological Agency, local governments, and various sensors. Specifically, it obtains earthquake occurrence data through the Japan Meteorological Agency's API, receives damage information in XML format from local governments, and obtains traffic conditions from a traffic information database.

[1044] Analysis of earthquake data and damage information

[1045] The server integrates the collected earthquake data with a GIS (geographic information system) to identify the epicenter, seismic intensity, and extent of damage. It also analyzes the damage information and plots the most affected areas on a map. This process uses GIS software (e.g., ArcGIS).

[1046] Communications demand forecast

[1047] The server uses machine learning models (e.g., TensorFlow) to predict areas where communication demand will increase, taking into account the locations of important facilities such as evacuation centers and hospitals.

[1048] Determining the optimal location

[1049] The server runs an algorithm to determine the location of the evacuation shelter based on the collected data, evaluating parking lots, plazas, and other locations near the shelter as candidates and selecting the optimal location.

[1050] Sending placement instructions

[1051] The server sends the GPS coordinates of the determined placement point and route information to the mobile communication device, using a communication protocol (e.g., MQTT) to transfer the data.

[1052] Terminal (mobile communication device) operation

[1053] Autonomous driving and ensuring safety

[1054] The mobile communication device moves to the designated location using an autonomous driving system and image recognition AI (e.g., Autoware). During movement, it uses cameras and Lidar sensors to analyze actual road conditions and proceed safely. If an obstacle is detected, it automatically recalculates an avoidance route.

[1055] Deployment of communications equipment

[1056] When the mobile communication device arrives at the deployment site, it begins deploying its communication equipment. It deploys the antenna and communication equipment, installs the equipment using a hydraulic system, and starts up a generator to supply power to the communication equipment. Once deployment is complete, it provides communication services to surrounding communication terminals and monitors the communication status in real time.

[1057] User interaction and emotional engine

[1058] Manual input of damage information and correction of placement instructions

[1059] Users (e.g., disaster response personnel) can manually input disaster information and damage status using a dedicated application. This allows for immediate response to changes in emergency communication demand. In addition, the emotion engine analyzes the user's voice input and facial expressions, and if it determines that the user is in a high-urgency situation, it automatically adjusts the priority of deployment locations.

[1060] Real-time monitoring and emotion engine

[1061] Users can monitor the real-time status of their mobile communication devices using a web-based dashboard. Real-time emotional data from the emotion engine is also available on the dashboard, and if the emotional situation indicates an emergency, immediate action is required.

[1062] Emotion recognition by emotion engine

[1063] The emotion engine uses deep learning models (e.g., OpenVINO) to recognize emotions by analyzing the user's tone of voice and facial expressions. This data is used to prioritize disaster response and is fed back to the entire system.

[1064] Specific examples

[1065] For example, if the server predicts that communication demand will increase in an area where evacuation shelters are concentrated and calculates a parking lot near the center of that area as the location, it will send GPS coordinates and route information to the corresponding mobile communication device. The mobile communication device will activate its autonomous driving system and reach the designated location while avoiding obstacles. After arriving, it will deploy communication equipment and provide communication services to smartphones and radio terminals in the affected area.

[1066] Prompt Sentence Examples

[1067] "Collect disaster information and plan the optimal placement of communication equipment based on that information. Also, analyze user sentiment and take appropriate action accordingly."

[1068] In this way, this system utilizes advanced information analysis technology combined with an emotion engine and autonomous driving technology to achieve rapid and effective communication restoration during disasters. By recognizing the user's emotional state in real time and implementing optimal disaster response measures based on that, it is possible to facilitate the transmission of information in disaster-stricken areas.

[1069] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1070] Step 1: Collect disaster information

[1071] Server operation: The server collects data in real time from seismometers, the Japan Meteorological Agency, local governments, traffic information databases, and various sensors. Specifically, the server obtains earthquake occurrence data using the Japan Meteorological Agency's API and receives the data in JSON format. It also receives damage information from local governments in XML format and obtains the latest traffic conditions from the traffic information database.

[1072] Input: Seismometer, Japan Meteorological Agency API, damage information from local governments, traffic information database

[1073] Output: Collected disaster information data

[1074] Specific operation: The server periodically sends API requests to receive earthquake occurrence information in JSON format, and similarly receives damage information in XML format and stores it for analysis.

[1075] Step 2: Analysis of earthquake data and damage information

[1076] Server operation: The collected earthquake data is integrated with a GIS (geographic information system) to identify the epicenter, seismic intensity, and extent of damage. The damage information is then analyzed and the affected areas are plotted on a map. This process uses GIS software (e.g., ArcGIS).

[1077] Input: Collected disaster information data

[1078] Output: Identification of epicenter, seismic intensity, and damage extent

[1079] Specific operation: The data collected by the server is imported into a GIS and visualized geographically to identify the affected area.

[1080] Step 3: Forecast communication demand

[1081] Server operation: Using machine learning models (e.g., TensorFlow), the server predicts areas where communication demand will increase, taking into account the location information of important facilities such as evacuation centers and hospitals.

[1082] Input: Epicenter, seismic intensity, damage extent identification results, and location information of important facilities

[1083] Output: Communication demand forecast results

[1084] Specific operation: The server uses a machine learning model based on past disaster data to predict areas where communication demand will increase.

[1085] Step 4: Determine the optimal location

[1086] Server operation: The algorithm determines the location of the evacuation shelter based on the analysis results. Parking lots and plazas near the shelter are evaluated as candidates, and the optimal location is selected.

[1087] Input: Communication demand forecast results

[1088] Output: Result of placement location determination

[1089] How it works: The server uses an algorithm to evaluate candidate locations and select the optimal placement point.

[1090] Step 5: Send placement instructions

[1091] Server operation: Sends the GPS coordinates and route information of the determined placement point to the mobile communication device. Transfers the data using a communication protocol (e.g., MQTT).

[1092] Input: Result of determining placement location

[1093] Output: Instruction data to the mobile communication device

[1094] Specific operations: The server sends the GPS coordinates and route information to the mobile communication device.

[1095] Step 6: Autonomous driving of mobile radio vehicles

[1096] Device operation: The mobile communication device moves to the designated location using an autonomous driving system and image recognition AI (e.g., Autoware). During the movement, it uses cameras and Lidar sensors to analyze the actual road conditions and proceed safely.

[1097] Input: GPS coordinates and route information from the server

[1098] Output: Mobile device location update information

[1099] How it works: The mobile device uses cameras and Lidar sensors to detect obstacles and calculates avoidance routes if necessary.

[1100] Step 7: Deploying communications equipment

[1101] Terminal operation: When the mobile communication device arrives at the deployment site, it begins deploying its communication equipment. It deploys the antenna and communication equipment, installs the equipment using the hydraulic system, and starts the generator to supply power to the communication equipment.

[1102] Input: Location information of mobile communication device

[1103] Output: Deployed communications equipment

[1104] Specific operation: The mobile communication device deploys the antenna and supplies power to the communication equipment.

[1105] Step 8: Manually enter damage information and modify deployment instructions

[1106] User behavior: The user (e.g., disaster response personnel) manually inputs disaster information and damage status using a dedicated application. The emotion engine analyzes the user's voice input and facial expressions, and if it determines that the situation is urgent, it automatically adjusts the priority of deployment locations.

[1107] Input: Disaster information, damage situation, user voice input, user facial expression data

[1108] Output: Priority adjustment result by the system

[1109] Specific operation: The user inputs information into the application, and the emotion engine performs analysis.

[1110] Step 9: Real-time monitoring and emotion engine usage

[1111] User behavior: Users can monitor the real-time status of their mobile communication devices using a web-based dashboard. They can also check real-time emotional data generated by the emotion engine and take emergency action.

[1112] Input: Status information of mobile communication device, emotion engine data

[1113] Output: Monitoring results and response instructions

[1114] Specific operation: Users monitor real-time information through the dashboard and take appropriate measures as needed.

[1115] Step 10: Emotion Recognition with the Emotion Engine

[1116] Server operation: The emotion engine uses deep learning models (e.g., OpenVINO) to recognize emotions by analyzing the user's tone of voice and facial expressions. This data is used to prioritize disaster response and is fed back to the entire system.

[1117] Input: User's voice tone, facial expression data

[1118] Output: Emotion recognition result

[1119] How it works: The emotion engine analyzes voice tone and facial expression data to assess the user's emotional state, and adjusts disaster response priorities accordingly.

[1120] Through the specific processing and operation of each step, the system of the present invention supports rapid and effective restoration of communications in the event of a disaster, and enables flexible responses that take into account the emotional state of the user.

[1121] (Application example 2)

[1122] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1123] In order to quickly and effectively restore communications during a disaster, it is essential to accurately grasp the damage situation and predict communications demand. However, conventional disaster response systems rely on fixed communications devices, making it difficult to respond flexibly. Furthermore, because they do not take into account the confusion and emotional state of users during a disaster, they are unable to prioritize responses in cases of high urgency. Therefore, the present invention aims to solve these problems by combining mobile wireless devices with emotion recognition technology, thereby realizing quick and effective communications restoration during a disaster.

[1124] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1125] In this invention, the server includes a means for collecting disaster information, a means for analyzing the disaster information to identify the affected area, and a means for predicting communication demand within the affected area and determining the optimal deployment location. This allows for accurate understanding of the damage situation and communication demand, enabling flexible and effective communication restoration. The mobile wireless device also includes a deployment means with an automatic driving function, a means for providing communication services after arriving at the deployment location, an emotion recognition means for recognizing emotions from user voice input and facial expression analysis, and a means for adjusting disaster response priorities based on the emotion data. This enables flexible response taking into account the user's urgency, achieving rapid and effective communication restoration.

[1126] "Disaster information" refers to data and reports on the occurrence of natural disasters, including information on earthquakes, floods, typhoons, etc.

[1127] "Means" refers to the methods or techniques used to achieve a certain goal.

[1128] "Damaged area" refers to the area where material and human damage has occurred due to a disaster.

[1129] "Telecommunications demand" refers to the amount of telecommunications capacity or services required in a particular region or under particular circumstances.

[1130] "Optimal deployment location" refers to the location that is most suitable for communications equipment and facilities to achieve maximum effectiveness.

[1131] "Autonomous driving" refers to a vehicle's ability to travel autonomously without a human driver.

[1132] "Mobile wireless device" refers to a wireless communication device that can be moved from place to place as needed.

[1133] "Location" means a specific location where equipment or facilities are installed.

[1134] "Communication services" refers to services that support the exchange of information in the form of voice calls, data communications, etc.

[1135] "Emotion recognition means" refers to technology that analyzes and recognizes the user's emotional state through voice input and facial expression analysis.

[1136] "Emotion data" refers to information that represents the user's emotional state.

[1137] "Disaster response" refers to actions and measures taken to minimize damage when a disaster occurs.

[1138] "Priority" refers to the degree of importance of performing a task or action before others.

[1139] "User" refers to the people and organizations that use this system to carry out disaster prevention and communication restoration.

[1140] The present invention is a system for quickly and effectively restoring communications in the event of a disaster. This system consists of three main components: a server, a mobile wireless device (terminal), and a user, which operate in conjunction with each other. Specific embodiments of each component are described below.

[1141] Server Operation

[1142] Disaster information collection and analysis

[1143] The server uses APIs to collect earthquake occurrence data, damage information, and traffic information in real time from the Japan Meteorological Agency and other government agencies. This data is received in JSON or XML format and analyzed by the server. The analyzed data is integrated with a GIS (geographic information system) to identify the epicenter, seismic intensity, and extent of damage. Areas that are particularly affected are plotted on a map, and information is provided to users and devices as needed.

[1144] Forecasting communication demand and determining optimal locations

[1145] After identifying the affected areas, the server uses machine learning models to predict areas where communication demand will be high. Taking into account the locations of important facilities such as evacuation centers and hospitals, the server then runs an algorithm to determine the optimal locations for mobile wireless device placement. This placement decision is optimized based on the extent of damage and communication demand.

[1146] Sending placement instructions

[1147] The server then sends the GPS coordinates and route information of the determined deployment point to the mobile wireless device. Upon receiving this information, the device activates the autonomous driving system and prepares to depart for the designated deployment point.

[1148] Terminal (mobile radio device) operation

[1149] Autonomous driving and ensuring safety

[1150] The device uses an autonomous driving system and image recognition algorithms to navigate to the designated deployment location. During the journey, it analyzes obstacles and traffic conditions in real time to ensure safe travel. If an obstacle is detected, it immediately recalculates an avoidance route and selects a safe path.

[1151] Arrival at deployment site and deployment of communications equipment

[1152] When the terminal arrives at the deployment location, it begins preparations for deploying wireless communication equipment. It deploys antennas and communication devices and supplies power. It begins providing communication services to surrounding communication terminals and monitors communication conditions in real time.

[1153] User interaction and emotional engine

[1154] Entering damage information and correcting deployment instructions

[1155] Users can manually input disaster information and damage status into the system, allowing for immediate response to fluctuations in emergency communication demand. If an emotion engine is installed, it will recognize the user's emotional state from voice input and facial expression analysis, and will respond optimally based on that information.

[1156] Condition monitoring and response coordination

[1157] Users can monitor the real-time status information of their mobile wireless devices through the system's dashboard, allowing them to check communication status and vehicle location at any time. Real-time emotion data generated by the emotion engine can also be viewed on the dashboard, allowing for immediate action in the event of an emergency.

[1158] Emotion recognition by emotion engine

[1159] The emotion engine collects and analyzes emotional data using the user's voice input, facial expression analysis, and biometric sensors. The collected emotional data is used to determine disaster response priorities and is fed back to the entire system. For example, it analyzes the user's stress level from their tone of voice and vocabulary, and adjusts emergency response priorities based on the results.

[1160] Examples of specific examples and prompts

[1161] Let's take a specific scenario: a driverless autonomous vehicle arrives at a designated evacuation shelter and deploys its antenna to provide communication services. If the user yells, "Help me! The building is collapsing and I can't escape!", the emotion engine will determine that an emergency response is required and set disaster response as the highest priority.

[1162] Example prompt sentence:

[1163] User audio: "Help! My house is collapsing and I have nowhere to run!"

[1164] Expected sentiment analysis result: 'Urgent'

[1165] As described above, the system of the present invention realizes rapid and flexible communication restoration in the event of a disaster, and enables disaster response that takes into account the emotional state of the user.

[1166] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1167] Step 1: Collecting and analyzing disaster information

[1168] The server collects earthquake occurrence data, damage information, and traffic information in real time from the Japan Meteorological Agency and other government agencies via API. It sends API requests as input and receives data in JSON or XML format as output. This data is analyzed and integrated with GIS to identify the affected area, epicenter, seismic intensity, etc. Specifically, it stores the acquired data in an internal database and uses it for subsequent analysis.

[1169] Step 2: Forecasting communication demand and determining optimal deployment locations

[1170] The server uses a machine learning model based on the collected information on affected areas to predict areas where demand for communications will increase. It uses data on affected areas and location information on important facilities such as evacuation centers and hospitals as input, and calculates the optimal location for placing mobile wireless devices as output. The server then executes an algorithm to determine this location and determines the GPS coordinates of the optimal location. Specifically, it performs calculations using a model that uses this data as input, and identifies areas where demand will be concentrated.

[1171] Step 3: Send placement instructions

[1172] The server sends the GPS coordinates of the determined deployment point and route information to the mobile wireless device. The terminal receives this information and activates the autonomous driving system. The terminal receives the GPS coordinates of the deployment point and route information as input and sets this as output in the autonomous driving system. In concrete terms, the terminal activates the navigation system based on the received route information and prepares to depart for the specified location.

[1173] Step 4: Autonomous driving and safety

[1174] The device uses an autonomous driving system and image recognition algorithms to navigate to a designated deployment point. It uses real-time video and sensor data as input and calculates a safe driving route as output. It analyzes obstacles and traffic conditions in real time and recalculates an avoidance route if an obstacle is detected. Specifically, the device uses sensors and cameras to monitor its surroundings and changes direction as necessary.

[1175] Step 5: Arrival at deployment site and deployment of communications equipment

[1176] When the terminal arrives at the deployment site, it begins preparations for deploying wireless communication equipment. It uses the current location's GPS information and the deployment site settings as input, and deploys the antenna and communication equipment as output. Specifically, it deploys the equipment necessary to supply power and begin providing communication services.

[1177] Step 6: Enter damage information and modify deployment instructions

[1178] Users can manually input disaster information and damage status into the system. The system receives the disaster information and damage status entered by the user as input and updates the data within the system as output. This allows for immediate response to changes in urgent communication demand. Specifically, the system sends the information entered through the user interface to the server and recalculates the areas requiring response.

[1179] Step 7: Leverage your emotional engine

[1180] An emotion recognition means operates to recognize emotions from the user's voice input and facial expression analysis. It receives audio and video data as input and obtains emotional data as output. Disaster response priorities are adjusted based on the emotional data. Specifically, the emotion recognition algorithm performs voice analysis to detect situations with a high level of urgency. If the user's urgency is high, the priority is automatically raised within the system.

[1181] Step 8: Condition monitoring and response adjustment

[1182] The user monitors real-time status information of the mobile wireless device through the system's dashboard. Status data and communication status during autonomous driving are received as input, and this is displayed on the dashboard as output. Real-time emotion data generated by the emotion engine can also be checked, and immediate action can be taken if an emergency response is required. Specific operations include visualizing the location and communication status of the mobile wireless device on the dashboard, and issuing additional instructions as necessary.

[1183] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1184] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1185] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1186] [Third embodiment]

[1187] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1188] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1189] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1190] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1191] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1192] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1193] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1194] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1195] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1196] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1197] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1198] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[1199] MODE FOR CARRYING OUT THE INVENTION

[1200] This invention relates to a system for efficiently achieving early communication restoration in the event of a disaster. This system consists of three main components: a server, a terminal (a mobile radio vehicle), and a user. The cooperation of these components enables rapid communication restoration immediately after a disaster occurs.

[1201] Server Operation

[1202] Disaster information collection and analysis

[1203] The server collects earthquake data in real time from seismometers and the Japan Meteorological Agency, receives damage information sent from local governments and various sensors, and obtains real-time traffic conditions from a traffic information database.

[1204] The server analyzes the collected data using an AI model to identify the epicenter, seismic intensity, extent of damage, etc. Using a GIS (geographic information system), this data is plotted on a map to quickly identify the affected area.

[1205] Examples:

[1206] The server uses an API to obtain earthquake information from the Japan Meteorological Agency and receives the data in JSON format. It also receives damage information from local governments as XML data and uses it for analysis.

[1207] Forecasting communication demand and determining optimal locations

[1208] After identifying affected areas, the server uses machine learning models to predict areas where communication demand will increase, taking into account the locations of important facilities such as evacuation shelters and hospitals.

[1209] The server runs an algorithm to determine the optimal locations for deploying mobile radio vehicles, thereby optimizing communication traffic during disasters.

[1210] Examples:

[1211] The server predicts that communication demand will increase in areas where evacuation shelters are concentrated, and calculates a parking lot near the center of the area as the placement location.

[1212] Sending placement instructions

[1213] The server transmits information about the determined deployment point (GPS coordinates and route information) to the mobile radio vehicle. When the mobile radio vehicle receives this information, it activates its automatic driving system and prepares to depart for the designated deployment point.

[1214] Terminal (mobile radio vehicle) operation

[1215] Autonomous driving and ensuring safety

[1216] The device uses an autonomous driving system and image recognition AI to move towards the designated location, analyzing obstacles and traffic conditions in real time while moving to ensure safe travel.

[1217] If the device detects an obstacle, it immediately recalculates the avoidance route and selects a safe path.

[1218] Examples:

[1219] When the device detects a fallen tree while driving, it automatically calculates a new, safer route based on that information and changes direction.

[1220] Arrival at deployment site and deployment of communications equipment

[1221] When the terminal arrives at the deployment site, it begins preparations for deploying its wireless communication equipment, deploying antennas and communication devices and supplying power.

[1222] The terminal starts providing communication services to surrounding communication terminals and monitors the communication status in real time.

[1223] Examples:

[1224] After arriving at the designated location, the terminal will deploy its antenna and provide communication services to smartphones and radio terminals in the affected area.

[1225] User Operation and Monitoring

[1226] Entering damage information and correcting deployment instructions

[1227] Users (e.g., disaster response personnel) can manually input disaster information and damage status into the system, allowing for immediate response to fluctuations in emergency communication demand.

[1228] The user can also modify the vehicle location instructions as needed.

[1229] Examples:

[1230] Users enter details of the damage to their building and specify areas where communication is particularly necessary.

[1231] Condition monitoring and response coordination

[1232] Users can monitor real-time status information through the system's dashboard, including communication status and the location of mobile wireless vehicles.

[1233] If necessary, orders can be given to dispatch additional mobile radio vehicles.

[1234] Examples:

[1235] The user monitors the communication status of the mobile wireless vehicle on the dashboard, and if communication traffic increases, sends an instruction to the server to dispatch an additional vehicle.

[1236] With these functions and operations, the system of the present invention can achieve rapid and effective restoration of communications in the event of a disaster, facilitating smooth information transmission in disaster-stricken areas.

[1237] The processing flow will be explained below.

[1238] Step 1:

[1239] The server collects earthquake occurrence data in real time from seismometers and the Japan Meteorological Agency, as well as damage information from local governments and various sensors, and obtains the latest traffic conditions from a traffic information database.

[1240] Step 2:

[1241] The server integrates the collected earthquake data with a GIS (geographic information system) to identify the epicenter, seismic intensity, and extent of damage, and then analyzes the damage information and plots the most affected areas on a map.

[1242] Step 3:

[1243] The server uses machine learning models to predict communication demand within the affected area, taking into account the locations of important facilities such as evacuation centers and hospitals, and identifies areas where communication demand is likely to increase.

[1244] Step 4:

[1245] The server executes an algorithm to determine the optimal deployment location of the mobile radio vehicles, which optimizes the deployment location based on the extent of damage and communication demand.

[1246] Step 5:

[1247] The server sends the GPS coordinates of the determined deployment point and route information to the mobile radio vehicle (terminal). When the terminal receives this information, it prepares to start the autonomous driving system.

[1248] Step 6:

[1249] The device activates its autonomous driving system and image recognition AI to depart for the designated location, analyzing the route to the destination in real time and proceeding safely.

[1250] Step 7:

[1251] The device uses image recognition AI to analyze road conditions and obstacles while moving, and if an obstacle is detected, it recalculates an avoidance route and selects a safe driving path.

[1252] Step 8:

[1253] When the terminal arrives at the designated deployment location, it begins preparations to deploy its wireless communication equipment, including deploying antennas and communication devices and supplying power.

[1254] Step 9:

[1255] The terminals begin providing communication services at their deployment locations, providing Wi-Fi and mobile communication services to nearby communication terminals and monitoring communication traffic in real time.

[1256] Step 10:

[1257] Users (disaster response personnel) can manually input disaster information and damage status into the system as needed, allowing for immediate response to emergency communication demands.

[1258] Step 11:

[1259] Users can monitor the real-time status information of their mobile wireless vehicles through the system's dashboard, allowing them to check the communication status and vehicle location at any time.

[1260] Step 12:

[1261] The user can issue instructions to dispatch additional mobile radio vehicles as needed, especially when communication traffic increases, by sending new instructions to the server.

[1262] Example 1

[1263] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1264] Rapid restoration of communications in the event of a disaster is extremely important for saving lives and sharing information. However, with conventional systems, identifying the extent of damage, forecasting communication demand, and optimally deploying mobile wireless vehicles were all done manually, making it difficult to respond quickly. Furthermore, the accuracy of autonomous driving and obstacle avoidance was insufficient, and ensuring the safety of mobile wireless vehicles also posed challenges. Furthermore, deploying communications equipment and providing services required human labor, making it difficult to quickly restore communications.

[1265] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1266] In this invention, the server includes means for collecting disaster information, means for analyzing the disaster information and identifying the affected area, means for predicting communication demand within the affected area using a generative AI model and determining the optimal deployment location, means for deploying mobile wireless vehicles including an automatic driving system to the deployment location, means for automatically deploying communication equipment to provide communication services after the mobile wireless vehicles reach the deployment location, and means for the user to manually input disaster information and correct the deployment instructions for the mobile wireless vehicles, thereby enabling quick and efficient communication restoration.

[1267] "Disaster information" refers to data and information related to natural disasters such as earthquakes, tsunamis, typhoons, and floods.

[1268] "Damaged area" refers to the region or area affected by a disaster.

[1269] "Communication demand" refers to the amount and necessity of communication services required in a particular region or area.

[1270] A "generative AI model" is a machine learning or artificial intelligence model used to analyze data and predict patterns.

[1271] The "optimal deployment location" refers to a location or position where a mobile radio vehicle can be deployed efficiently and achieve maximum effectiveness.

[1272] An "autonomous driving system" refers to technology and devices that enable vehicles to drive themselves and travel to designated routes and destinations.

[1273] A "mobile wireless vehicle" is a vehicle equipped with wireless communication equipment that can provide communication services while moving.

[1274] "Communications equipment" means equipment such as antennas, transmitters, and receivers used to provide communications services.

[1275] "Users" refer to the people who operate this system and those involved in disaster response.

[1276] "Deployment instructions" are instructions or orders to deploy a mobile radio vehicle at a specific location.

[1277] MODE FOR CARRYING OUT THE INVENTION

[1278] The present invention relates to a system for efficiently achieving early communication restoration in the event of a disaster. This system consists of three main components: a server, a terminal (a mobile wireless vehicle), and a user. Specific embodiments are described below.

[1279] Server Operation

[1280] Disaster information collection and analysis

[1281] The server first collects earthquake data through seismometers and the Japan Meteorological Agency's API. The collected data is sent to the server in JSON format. It then receives damage information in XML format from local governments and various sensors, and obtains real-time traffic conditions from a traffic information database. To do this, the server uses high-performance data analysis software and AI models. Specifically, it uses a GIS (geographic information system) to plot the collected data on a map and identify the affected areas.

[1282] Examples:

[1283] The server uses an API to obtain earthquake information from the Japan Meteorological Agency and receives the data in JSON format. It also receives damage information from local governments as XML data and uses GIS to quickly identify affected areas.

[1284] Forecasting communication demand and determining optimal locations

[1285] After identifying the affected areas, the server uses a generative AI model to predict areas where communication demand will increase. The predictive model takes into account past disaster data, population data, and the locations of important facilities such as evacuation centers and hospitals. The server then runs an algorithm to determine the optimal placement locations for mobile radio vehicles, thereby optimizing communication traffic.

[1286] Examples:

[1287] The server predicts that communication demand will increase in areas where evacuation shelters are concentrated, and calculates a parking lot near the center of the area as the location for deployment.

[1288] Sending placement instructions

[1289] The server transmits information about the determined deployment point (GPS coordinates and route information) to the mobile radio vehicle. When the mobile radio vehicle receives this information, it activates its automatic driving system and prepares to depart for the designated deployment point.

[1290] Terminal (mobile radio vehicle) operation

[1291] Autonomous driving and ensuring safety

[1292] The device uses an autonomous driving system and image recognition AI to move toward the designated location. During movement, it analyzes obstacles and traffic conditions in real time to ensure safe movement. If an obstacle is detected, it immediately recalculates an avoidance route and selects a safe path.

[1293] Examples:

[1294] When the device detects a fallen tree while driving, it automatically calculates a new, safer route based on that information and changes its direction of travel.

[1295] Arrival at deployment site and deployment of communications equipment

[1296] When the terminal arrives at the deployment location, it begins preparations for deploying wireless communication equipment. It deploys antennas and communication devices and supplies power. It begins providing communication services to surrounding communication terminals and monitors communication conditions in real time.

[1297] Examples:

[1298] After arriving at the designated location, the terminal will deploy its antenna and provide communication services to smartphones and radio terminals in the affected area.

[1299] User Operation and Monitoring

[1300] Manual input of damage information and correction of placement instructions

[1301] Users can manually input disaster information and damage status into the system, supplementing the information needed to respond quickly to fluctuations in emergency communication demand. It is also possible to revise mobile radio vehicle deployment instructions as needed.

[1302] Examples:

[1303] Users enter details of the damage to their building and specify areas where communication is particularly necessary.

[1304] Condition monitoring and dispatch of additional vehicles

[1305] Users can use the system dashboard to monitor the system status in real time, check communication status and vehicle location, and issue instructions to dispatch additional vehicles if necessary.

[1306] Examples:

[1307] The user monitors the communication status of the mobile wireless vehicle on the dashboard, and if communication traffic increases, sends an instruction to the server to dispatch additional vehicles.

[1308] Examples of specific prompts to input to the generative AI model

[1309] Prompt statement:

[1310] "Please explain in detail the operating procedures of the server of the communications recovery system in the event of a disaster, from real-time data collection and data analysis, to forecasting communications demand, determining the placement locations of mobile radio vehicles, and sending placement instructions."

[1311] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1312] Step 1:

[1313] The server collects earthquake data in real time from seismometers and the Japan Meteorological Agency's API. The earthquake information obtained as input is in JSON format. The server uses this data to extract information such as the time of the earthquake, epicenter, and seismic intensity. The processed earthquake information is obtained as output.

[1314] Specific behavior:

[1315] The server makes an API request, receives earthquake data in JSON format from the Japan Meteorological Agency, and analyzes it.

[1316] Step 2:

[1317] The server receives damage information in XML format from local governments and various sensors. The damage information received as input is also in XML format. The server analyzes this and extracts information on the state of building collapse and human casualties. The output is a database containing the damage information.

[1318] Specific behavior:

[1319] The server receives and analyzes the XML data and stores the damage status in a database.

[1320] Step 3:

[1321] The server obtains real-time traffic conditions from a traffic information database. The traffic information collected as input is obtained via API. The server analyzes this information and extracts road passability and congestion information. The output is the analyzed traffic information.

[1322] Specific behavior:

[1323] The server calls the traffic information API to obtain and analyze real-time traffic conditions.

[1324] Step 4:

[1325] The server uses a generative AI model to predict affected areas and communication demand based on collected earthquake data, damage information, and traffic information. The inputs are the earthquake data, damage information, and traffic information previously collected and analyzed. Using the generative AI model, information on predicted communication demand areas and damaged areas is obtained. The output is map data of the predicted damaged areas and communication demand areas.

[1326] Specific behavior:

[1327] The server inputs data into the generative AI model and plots the affected area and communication demand forecast results.

[1328] Step 5:

[1329] The server determines the optimal location for deploying mobile wireless vehicles based on the predicted communication demand area. The input is the predicted communication demand area information, and the output is the GPS coordinates of the optimal deployment location.

[1330] Specific behavior:

[1331] The server uses machine learning algorithms to calculate the optimal placement locations for points within the affected area where communication demand is high.

[1332] Step 6:

[1333] The server sends the GPS coordinates of the determined deployment point and route information to the mobile radio vehicle. The input is the GPS coordinates of the optimal deployment point and route information. The output is deployment instructions to the mobile radio vehicle.

[1334] Specific behavior:

[1335] The server generates JSON data containing GPS coordinates and route information and sends it to the mobile radio vehicle.

[1336] Step 7:

[1337] The terminal (mobile wireless vehicle) activates the autonomous driving system based on the deployment instructions received from the server. The inputs are the GPS coordinates and route information received from the server. The terminal activates the autonomous driving system and automatically moves toward the designated deployment point. The output is arrival at the deployment point.

[1338] Specific behavior:

[1339] The device will begin autonomous driving based on route information and proceed while recognizing traffic signals and road signs.

[1340] Step 8:

[1341] As the device moves, it uses image recognition AI and sensors to detect obstacles and navigate safely. The input is real-time image data and sensor data. The device analyzes this and recalculates an avoidance route if necessary. The output is an updated safe route.

[1342] Specific behavior:

[1343] If the device detects a fallen tree or obstacle, it will automatically calculate a new route and change direction.

[1344] Step 9:

[1345] After the terminal arrives at the designated deployment point, it begins preparations to deploy wireless communication equipment. The input is arrival information for the deployment point. The terminal deploys the antenna and communication equipment and supplies power. The output is that communication is ready.

[1346] Specific behavior:

[1347] The device automatically deploys its antenna and powers on its communications equipment.

[1348] Step 10:

[1349] The terminal starts providing communication services to surrounding communication terminals and monitors the communication status in real time. The input is the request data for the communication service. The terminal analyzes this and communicates appropriately. The output is the status information of the provided communication service.

[1350] Specific behavior:

[1351] The device provides communication services to surrounding smartphones and radio devices and monitors communication conditions.

[1352] Step 11:

[1353] Users manually input disaster information and damage status into the system and modify the deployment instructions for mobile radio vehicles as necessary. The inputs are the manually entered disaster information and damage status. Based on this, the system recalculates and generates updated deployment instructions as output.

[1354] Specific behavior:

[1355] The user uses the dashboard to input information and modify the placement instructions as needed.

[1356] Step 12:

[1357] The user monitors real-time status information through the system's dashboard and issues instructions to dispatch additional mobile radio vehicles as needed. The input is real-time status information collected from the dashboard. The output is an instruction to dispatch additional vehicles.

[1358] Specific behavior:

[1359] The user monitors the communication status and location of the mobile wireless vehicles on the dashboard and issues an instruction to dispatch additional vehicles if communication traffic increases.

[1360] (Application example 1)

[1361] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1362] Conventional communication restoration systems for disaster recovery require time-consuming collection and analysis of disaster information, identification of affected areas, prediction of communication demand, and optimal deployment of mobile radios, making it difficult to quickly restore communication infrastructure. Other issues include limited real-time tracking of mobile radios and limited obstacle avoidance functions for safe operation. Furthermore, the lack of appropriate AI analysis and map display functions for emergency communication restoration makes it difficult for disaster response personnel to respond quickly.

[1363] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1364] In this invention, the server includes means for collecting disaster information, means for analyzing the disaster information to identify the affected area, means for predicting communication demand within the affected area and determining the optimal deployment location, means for deploying mobile radios with autonomous driving functions to the deployment location, means for providing communication services after the mobile radios reach the deployment location, means for tracking the progress and location information of the mobile radios in real time, and means for performing AI analysis and displaying maps to support emergency communication restoration. This enables rapid and efficient restoration of communication infrastructure, safe and reliable operation of mobile radios, and appropriate emergency response by disaster response personnel.

[1365] "Disaster information" refers to data on natural disasters such as earthquakes and typhoons, as well as information on the damage caused by these disasters.

[1366] "Affected Area" refers to the area directly or indirectly affected by a natural disaster.

[1367] "Communications demand" refers to the need for communications services at a particular time and place.

[1368] The "optimal placement point" refers to a location determined to most effectively place a mobile radio.

[1369] "Autonomous driving function" refers to the function of a mobile radio that allows it to move autonomously without human operation.

[1370] "Mobile radio" refers to communication equipment that can be moved to provide temporary communication services in the event of a disaster.

[1371] "Progress" refers to information about the location and status of the mobile radio as it progresses.

[1372] "Location information" refers to geographic coordinate data of a specific location.

[1373] "Real-time" refers to events and data processing that occur nearly simultaneously.

[1374] "Tracking" refers to the continuous monitoring of the current location and progress of a mobile radio.

[1375] "AI analytics" refers to the process of using artificial intelligence to analyze large amounts of data and derive specific goals or results.

[1376] "Map display" refers to the visual presentation of data or information on a map using a geographic information system.

[1377] "Communication services" refers to services that provide means of communication such as voice, data, and internet.

[1378] This invention relates to a system for efficiently achieving early communication restoration in the event of a disaster. This system consists of three main components: a server, a terminal (mobile radio), and a user. These components work together to enable rapid communication restoration immediately after a disaster occurs.

[1379] Server Operation

[1380] Disaster information collection and analysis

[1381] The server collects earthquake data in real time from seismometers and weather information services, receives damage information sent from local governments and various sensors, and obtains real-time traffic conditions from a traffic information database.

[1382] The server analyzes the collected data using an AI model to identify the epicenter, seismic intensity, extent of damage, etc. Using a GIS (geographic information system), this data is displayed on a map to quickly identify the affected area.

[1383] Example: The server uses an API to obtain earthquake information from a weather information service and receives the data in JSON format. It also receives damage information from local governments as XML data and uses it for analysis.

[1384] Forecasting communication demand and determining optimal locations

[1385] After identifying affected areas, the server uses machine learning models to predict areas where communication demand will increase, taking into account the locations of important facilities such as evacuation shelters and hospitals.

[1386] The system runs an algorithm to determine the optimal locations for placing mobile radios, thereby optimizing communication traffic during disasters.

[1387] Example: The server predicts that communication demand will increase in an area where evacuation shelters are concentrated, and calculates a parking lot near the center of that area as the placement point.

[1388] Sending placement instructions

[1389] The server sends information about the determined deployment point (GPS coordinates and route information) to the mobile radio. When the mobile radio receives this information, it activates the automatic driving system and prepares to depart for the designated deployment point.

[1390] Terminal (mobile radio) operation

[1391] Autonomous driving and ensuring safety

[1392] The device uses an autonomous driving system and image recognition AI to move towards the designated location, analyzing obstacles and traffic conditions in real time while moving to ensure safe travel.

[1393] If the device detects an obstacle, it immediately recalculates the avoidance route and selects a safe path.

[1394] Example: If the device detects a fallen tree while driving, it will automatically calculate a new, safer route based on that information and change direction.

[1395] Arrival at deployment site and deployment of communications equipment

[1396] When the terminal arrives at the deployment site, it begins preparations for deploying its wireless communication equipment, deploying antennas and communication devices and supplying power.

[1397] The terminal starts providing communication services to surrounding communication terminals and monitors the communication status in real time.

[1398] Example: After arriving at a designated location, the terminal deploys an antenna and provides communication services to communication terminals in the affected area.

[1399] User Operation and Monitoring

[1400] Entering damage information and correcting deployment instructions

[1401] Users (disaster response personnel) can manually input disaster information and damage status into the system, allowing for immediate response to fluctuations in emergency communication demand.

[1402] The user can also modify the mobile radio placement instructions as needed.

[1403] Example: The user inputs details of the damage situation at their facility and specifies areas where communication is particularly necessary.

[1404] Condition monitoring and response coordination

[1405] Users can monitor real-time status information through the system's dashboard, checking communication status and mobile radio location information at any time.

[1406] If necessary, instructions can be given to dispatch additional mobile radios.

[1407] Example: A user monitors the communication status of a mobile radio on the dashboard, and if communication traffic increases, sends an instruction to the server to dispatch additional vehicles.

[1408] Hardware and software used

[1409] Frontend: React Native (cross-platform development)

[1410] Backend: Node.js and Express.js (API server)

[1411] Database: MongoDB (NoSQL)

[1412] AI analysis: TensorFlow.js (machine learning model)

[1413] Map display: Google Maps API

[1414] Communication: WebSocket (real-time communication)

[1415] Prompt Sentence Examples

[1416] Examples of disaster information collection

[1417] python

[1418] import requests

[1419] def get_earthquake_data():

[1420] url = 'https: / / api.weather.jp / earthquake'

[1421] response = requests.get(url)

[1422] if response.status_code == 200:

[1423] return response.json()

[1424] else:

[1425] return None

[1426] earthquake_data = get_earthquake_data()

[1427] print(earthquake_data)

[1428] Data analysis and display examples

[1429] javascript

[1430] import as tf from '@tensorflow / tfjs';

[1431] async function analyzeEarthquakeData(data) {

[1432] const model = await tf.loadLayersModel('path / to / model.json');

[1433] const tensor = tf.tensor(data);

[1434] const predictions = model.predict(tensor).dataSync();

[1435] return predictions;

[1436] }

[1437] Example of mobile radio placement instructions

[1438] javascript

[1439] const WebSocket = require('ws');

[1440] const ws = new WebSocket('ws: / / moving_car_address');

[1441] ws.on('open', function open() {

[1442] const config = {

[1443] lat: 35.6895,

[1444] lng: 139.6917,

[1445] route: 'calculated_route_here'

[1446] };

[1447] ws.send(JSON.stringify(config));

[1448] });

[1449] Status monitoring and operation examples

[1450] javascript

[1451] import React, { useState, useEffect} from 'react';

[1452] import MapView, { Marker} from 'react-native-maps';

[1453] export default function Dashboard() {

[1454] const [cars, setCars] = useState([]);

[1455] useEffect(() => {

[1456] const fetchData = async () => {

[1457] const response = await fetch('http: / / server_address / cars');

[1458] const data = await response.json();

[1459] setCars(data);

[1460] };

[1461] fetchData();

[1462] }, []);

[1463] return (

[1464] <mapview style="{{" flex: 1}}>

[1465] {cars.map(car => (

[1466] <marker coordinate="{{" latitude: car.lat, longitude: car.lng}} / >

[1467] ))}

[1468] < / mapview>

[1469] );

[1470] }

[1471] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1472] Step 1:

[1473] Collecting disaster information

[1474] The server collects earthquake data in real time from seismometers and weather information services via API. It also receives damage information from local governments and various sensors, and obtains real-time traffic conditions from a traffic information database. Input data is mainly collected in JSON or XML format. The collected data is stored in MongoDB.

[1475] Specific behavior:

[1476] The server uses the Requests library to send requests to the earthquake data API and receives data in JSON format.

[1477] The server receives damage information in XML format from local governments and sensors via WebSocket or API.

[1478] Input: Earthquake data, damage information, traffic information

[1479] Output: Saved dataset

[1480] Step 2:

[1481] Disaster information analysis

[1482] The server analyzes the collected data using TensorFlow.js to identify the epicenter, seismic intensity, damage extent, etc. This information is displayed on a map using GIS.

[1483] Specific behavior:

[1484] The server loads the TensorFlow.js model and makes predictions using the collected data as input.

[1485] The server converts the analysis results into GeoJSON format and inputs them into a GIS to visualize the affected area.

[1486] Input: Saved dataset

[1487] Output: Map display of the affected area

[1488] Step 3:

[1489] Communications demand forecast

[1490] After identifying affected areas, the server uses machine learning models to predict areas where communication demand will increase, taking into account the locations of important facilities such as evacuation shelters and hospitals.

[1491] Specific behavior:

[1492] The server takes into account the location information of evacuation centers and hospitals and predicts communication demand using a machine learning model.

[1493] An algorithm is implemented to determine the optimum placement location of the mobile radio.

[1494] Input: Damaged area information, location information of evacuation centers and hospitals

[1495] Output: Coordinates of optimal placement point

[1496] Step 4:

[1497] Sending placement instructions

[1498] The server transmits the determined deployment location information (GPS coordinates and route information) to the mobile radio. Upon receiving this information, the mobile radio activates the automatic driving system and departs for the designated deployment location.

[1499] Specific behavior:

[1500] The server converts the GPS coordinates and route information into JSON format and sends it to the mobile radio via WebSocket.

[1501] Input: Coordinates of optimal placement point

[1502] Output: Send placement instructions

[1503] Step 5:

[1504] Autonomous driving and obstacle avoidance

[1505] The terminal (mobile radio) uses an autonomous driving system and image recognition AI to safely move towards the designated deployment point. During the journey, it analyzes obstacles and traffic conditions in real time and recalculates avoidance routes as necessary.

[1506] Specific behavior:

[1507] The mobile radio monitors road conditions using its on-board camera and sensors and performs image analysis in real time.

[1508] If an obstacle is detected, a new route is calculated and the direction of travel is changed immediately.

[1509] Input: GPS coordinates, route information, image data

[1510] Output: Safe travel route

[1511] Step 6:

[1512] Deployment of communications equipment

[1513] When the terminal (mobile radio) arrives at the deployment location, it begins preparations to deploy the wireless communication equipment, deploying antennas and communication devices and beginning to provide communication services in the affected area.

[1514] Specific behavior:

[1515] The mobile radio automatically deploys the antenna and supplies power.

[1516] We will begin providing communication services to surrounding communication terminals.

[1517] Input: Confirmation of arrival at placement point

[1518] Output: Provision of communication services

[1519] Step 7:

[1520] Condition monitoring and response coordination

[1521] Users can monitor real-time status information through the system's dashboard, check communication status and mobile radio location information at any time, and issue instructions to dispatch additional mobile radios as needed.

[1522] Specific behavior:

[1523] Users can access the dashboard through the React Native application to check communication status and mobile radio location information.

[1524] If necessary, instructions to dispatch additional mobile radios are sent to the server.

[1525] Input: Real-time status information

[1526] Output: Send dispatch instructions

[1527] Through these processing steps, rapid and efficient recovery of communication infrastructure in the event of a disaster is achieved.

[1528] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1529] MODE FOR CARRYING OUT THE INVENTION

[1530] This invention relates to a system for efficiently achieving early communication restoration in the event of a disaster. In particular, this system improves the flexibility and effectiveness of disaster response by incorporating an emotion engine that recognizes user emotions. This system consists of three main components: a server, a terminal (mobile wireless vehicle), and a user, which operate in cooperation with each other.

[1531] Server Operation

[1532] Disaster information collection and analysis

[1533] The server collects earthquake occurrence data in real time from seismometers and the Japan Meteorological Agency, receives damage information from local governments and various sensors, and obtains the latest traffic conditions from a traffic information database.

[1534] The server integrates the collected earthquake data with a GIS (geographic information system) to identify the epicenter, seismic intensity, and extent of damage, and then analyzes the damage information and plots the most affected areas on a map.

[1535] Examples:

[1536] The server uses an API to obtain earthquake information from the Japan Meteorological Agency and receives the data in JSON format. It also receives damage information from local governments as XML data and uses it for analysis.

[1537] Forecasting communication demand and determining optimal locations

[1538] After identifying affected areas, the server uses machine learning models to predict areas where communication demand will increase, taking into account the locations of important facilities such as evacuation centers and hospitals.

[1539] The server executes an algorithm to determine the optimal deployment location of the mobile radio vehicles, which optimizes the deployment location based on the extent of damage and communication demand.

[1540] Examples:

[1541] The server predicts that communication demand will increase in areas where evacuation shelters are concentrated, and calculates a parking lot near the center of the area as the placement location.

[1542] Sending placement instructions

[1543] The server sends the GPS coordinates of the determined deployment point and route information to the mobile radio vehicle (terminal). When the terminal receives this information, it activates the autonomous driving system and prepares to depart for the designated deployment point.

[1544] Terminal (mobile radio vehicle) operation

[1545] Autonomous driving and ensuring safety

[1546] The device uses an autonomous driving system and image recognition AI to move towards the designated location, analyzing obstacles and traffic conditions in real time while moving to ensure safe travel.

[1547] If the device detects an obstacle, it immediately recalculates the avoidance route and selects a safe path.

[1548] Examples:

[1549] When the device detects a fallen tree while driving, it automatically calculates a new, safer route based on that information and changes direction.

[1550] Arrival at deployment site and deployment of communications equipment

[1551] When the terminal arrives at the deployment site, it begins preparations for deploying its wireless communication equipment, deploying antennas and communication devices and supplying power.

[1552] The terminal starts providing communication services to surrounding communication terminals and monitors the communication status in real time.

[1553] Examples:

[1554] After arriving at the designated location, the terminal will deploy its antenna and provide communication services to smartphones and radio terminals in the affected area.

[1555] User interaction and emotional engine

[1556] Entering damage information and correcting deployment instructions

[1557] Users (e.g., disaster response personnel) can manually input disaster information and damage status into the system, allowing for immediate response to fluctuations in emergency communication demand.

[1558] If an emotion engine is installed, it will recognize the user's emotional state from voice input and facial expression analysis, and respond optimally based on that information.

[1559] Examples:

[1560] Users input details of the damage to their buildings and specify areas where communication is particularly necessary. If the emotion engine determines that the situation is urgent, it automatically adjusts the priority of deployment locations.

[1561] Condition monitoring and response coordination

[1562] Users can monitor the real-time status information of their mobile wireless vehicles through the system's dashboard, allowing them to check the communication status and vehicle location at any time.

[1563] Real-time emotional data from the emotion engine is also available on the dashboard, and if the emotional situation indicates an emergency, immediate action is required.

[1564] Examples:

[1565] The user monitors the communication status of the mobile wireless vehicle on the dashboard, and when a warning is received from the emotion engine, he or she quickly issues an instruction to dispatch an additional vehicle.

[1566] Emotion Engine Details

[1567] Emotion recognition by emotion engine

[1568] The emotion engine uses the user's voice input, facial expression analysis, and even biometric sensors to collect and analyze emotional data.

[1569] The collected emotional data is used to determine disaster response priorities and is fed back to the entire system.

[1570] Examples:

[1571] The emotion engine analyzes the user's stress level from their tone of voice and vocabulary, and automatically adjusts disaster response priorities based on the results.

[1572] In this way, the system of the present invention utilizes advanced information analysis technology combined with an emotion engine and autonomous driving technology to achieve rapid and effective communication restoration in the event of a disaster. By recognizing the user's emotional state in real time and implementing optimal disaster response measures based on that information, it is possible to facilitate the smooth transmission of information in disaster-stricken areas.

[1573] The processing flow will be explained below.

[1574] Step 1:

[1575] The server collects earthquake occurrence data in real time from seismometers and the Japan Meteorological Agency, receives damage information from local governments and various sensors, and obtains the latest traffic conditions from a traffic information database.

[1576] Step 2:

[1577] The server integrates the collected earthquake data with a GIS (geographic information system) to identify the epicenter, seismic intensity, and extent of damage, and also analyzes the damage information and maps out the most affected areas.

[1578] Examples:

[1579] The server uses an API to obtain earthquake information from the Japan Meteorological Agency and receives the data in JSON format. At the same time, it receives damage information from local governments as XML data and plots the affected areas using GIS software.

[1580] Step 3:

[1581] The server uses machine learning models to predict communication demand within the affected area, taking into account the locations of important facilities such as evacuation centers and hospitals, and identifies areas where communication demand will increase. It also determines the optimal locations for deploying mobile wireless vehicles based on the extent of damage and traffic information.

[1582] Examples:

[1583] The server predicts that communication demand will increase sharply in areas with many evacuation shelters, and calculates the location of the parking lot closest to the center of the area. If necessary, it also sets up avoidance routes based on the extent of damage and traffic conditions.

[1584] Step 4:

[1585] The server sends the GPS coordinates of the determined deployment point and route information to the mobile radio vehicle (terminal), which then begins preparations to activate the autonomous driving system.

[1586] Step 5:

[1587] Based on the deployment location information received from the server, the device activates the autonomous driving system and image recognition AI to depart for the designated deployment location. During the journey, the device analyzes obstacles and traffic conditions to ensure safe travel.

[1588] Step 6:

[1589] The device uses image recognition AI to analyze road conditions and obstacles while moving, and if an obstacle is detected, it recalculates an avoidance route and selects a safe driving path.

[1590] Examples:

[1591] When the device detects a fallen tree or crack in the road while moving, it calculates a new, safer route based on camera and sensor information to avoid the obstacle.

[1592] Step 7:

[1593] When the terminal arrives at the designated deployment location, it begins preparations to deploy its wireless communication equipment, deploying antennas and communication devices and supplying power.

[1594] Step 8:

[1595] The terminals begin providing communication services at their deployment locations, providing Wi-Fi and mobile communication services to surrounding communication terminals (smartphones and radio terminals) and monitoring communication conditions in real time.

[1596] Step 9:

[1597] Users (disaster response personnel) can manually input disaster information and damage status into the system as needed, allowing for immediate response to changes in emergency communication demand.

[1598] Step 10:

[1599] Users can monitor the real-time status information of their mobile wireless vehicles through the system's dashboard, allowing them to check the communication status and vehicle location at any time.

[1600] Step 11:

[1601] The user uses an emotion engine to analyze the user's voice input and facial expressions, and adjusts the placement locations and response priorities of the mobile radio vehicles based on the emotion data.

[1602] Examples:

[1603] When a user enters detailed damage information into the system, the emotion engine analyzes the urgency of the situation from the user's tone of voice and automatically raises the priority of the deployment location if necessary.

[1604] Step 12:

[1605] The user monitors the communication status of the mobile wireless vehicle on the dashboard and receives real-time warnings from the emotion engine. If the emotion engine indicates an emergency, it will quickly dispatch additional vehicles.

[1606] Examples:

[1607] The user monitors the current communication traffic and emotional state on the dashboard, and if the communication traffic increases and the emotion engine determines that an "emergency" has occurred, it immediately sends instructions to the server to send additional vehicles.

[1608] Example 2

[1609] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1610] When a disaster occurs, rapid and effective restoration of communications in affected areas is required. However, in conventional systems, the collection of disaster information, identification of affected areas, forecasting of communication demand, optimal placement of mobile communication devices, and provision of communication services are all performed in separate processes, making efficient coordination difficult. Furthermore, prioritization of disaster response efforts does not take into account user emotions or the level of urgency, making flexible responses difficult. A system that can solve these problems is needed.

[1611] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting disaster information, means for analyzing the disaster information to identify a damaged area, means for predicting communication demand within the damaged area and determining an optimal deployment point, means for transmitting information about the determined deployment point to a mobile communication device, means for deploying a mobile communication device with an autonomous driving function to the deployment point, means for providing communication services after the mobile communication device reaches the deployment point, and means including an emotion engine that recognizes user emotions and adjusts disaster response priorities. This enables quick and efficient communication restoration in the event of a disaster and realizes flexible disaster response that takes the user's emotional state into consideration.

[1612] "Disaster information" refers to data related to disasters such as earthquakes, tsunamis, fires, and floods.

[1613] "Affected Area" refers to the area affected by a disaster.

[1614] "Communication demand" is an indicator that shows the need for communication services in a specific area.

[1615] "Deployment point" means the optimal location for placing a mobile communication device.

[1616] A "mobile communications device" is a vehicle or device with automated driving capabilities for providing communications services.

[1617] An "emotion engine" is a system or software that recognizes users' emotions, analyzes that data, and adjusts disaster response priorities.

[1618] "Autonomous driving function" refers to a technology or system that allows a vehicle or device to move automatically without human operation.

[1619] "Image recognition artificial intelligence" is a technology or system that acquires image data from cameras or sensors, analyzes it, and recognizes objects and situations.

[1620] MODE FOR CARRYING OUT THE INVENTION

[1621] The present invention is a system that utilizes advanced information analysis technology and autonomous driving technology combined with an emotion engine to achieve rapid and effective communication restoration in the event of a disaster. This system consists of three main components: a server, a terminal (mobile communication device), and a user. A specific embodiment of the system is described below.

[1622] Server Operation

[1623] Collecting disaster information

[1624] The server collects disaster information in real time from seismometers, the Japan Meteorological Agency, local governments, and various sensors. Specifically, it obtains earthquake occurrence data through the Japan Meteorological Agency's API, receives damage information in XML format from local governments, and obtains traffic conditions from a traffic information database.

[1625] Analysis of earthquake data and damage information

[1626] The server integrates the collected earthquake data with a GIS (geographic information system) to identify the epicenter, seismic intensity, and extent of damage. It also analyzes the damage information and plots the most affected areas on a map. This process uses GIS software (e.g., ArcGIS).

[1627] Communications demand forecast

[1628] The server uses machine learning models (e.g., TensorFlow) to predict areas where communication demand will increase, taking into account the locations of important facilities such as evacuation centers and hospitals.

[1629] Determining the optimal location

[1630] The server runs an algorithm to determine the location of the evacuation shelter based on the collected data, evaluating parking lots, plazas, and other locations near the shelter as candidates and selecting the optimal location.

[1631] Sending placement instructions

[1632] The server sends the GPS coordinates of the determined placement point and route information to the mobile communication device, using a communication protocol (e.g., MQTT) to transfer the data.

[1633] Terminal (mobile communication device) operation

[1634] Autonomous driving and ensuring safety

[1635] The mobile communication device moves to the designated location using an autonomous driving system and image recognition AI (e.g., Autoware). During movement, it uses cameras and Lidar sensors to analyze actual road conditions and proceed safely. If an obstacle is detected, it automatically recalculates an avoidance route.

[1636] Deployment of communications equipment

[1637] When the mobile communication device arrives at the deployment site, it begins deploying its communication equipment. It deploys the antenna and communication equipment, installs the equipment using a hydraulic system, and starts up a generator to supply power to the communication equipment. Once deployment is complete, it provides communication services to surrounding communication terminals and monitors the communication status in real time.

[1638] User interaction and emotional engine

[1639] Manual input of damage information and correction of placement instructions

[1640] Users (e.g., disaster response personnel) can manually input disaster information and damage status using a dedicated application. This allows for immediate response to changes in emergency communication demand. In addition, the emotion engine analyzes the user's voice input and facial expressions, and if it determines that the user is in a high-urgency situation, it automatically adjusts the priority of deployment locations.

[1641] Real-time monitoring and emotion engine

[1642] Users can monitor the real-time status of their mobile communication devices using a web-based dashboard. Real-time emotional data from the emotion engine is also available on the dashboard, and if the emotional situation indicates an emergency, immediate action is required.

[1643] Emotion recognition by emotion engine

[1644] The emotion engine uses deep learning models (e.g., OpenVINO) to recognize emotions by analyzing the user's tone of voice and facial expressions. This data is used to prioritize disaster response and is fed back to the entire system.

[1645] Specific examples

[1646] For example, if the server predicts that communication demand will increase in an area where evacuation shelters are concentrated and calculates a parking lot near the center of that area as the location, it will send GPS coordinates and route information to the corresponding mobile communication device. The mobile communication device will activate its autonomous driving system and reach the designated location while avoiding obstacles. After arriving, it will deploy communication equipment and provide communication services to smartphones and radio terminals in the affected area.

[1647] Prompt Sentence Examples

[1648] "Collect disaster information and plan the optimal placement of communication equipment based on that information. Also, analyze user sentiment and take appropriate action accordingly."

[1649] In this way, this system utilizes advanced information analysis technology combined with an emotion engine and autonomous driving technology to achieve rapid and effective communication restoration during disasters. By recognizing the user's emotional state in real time and implementing optimal disaster response measures based on that, it is possible to facilitate the transmission of information in disaster-stricken areas.

[1650] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1651] Step 1: Collect disaster information

[1652] Server operation: The server collects data in real time from seismometers, the Japan Meteorological Agency, local governments, traffic information databases, and various sensors. Specifically, the server obtains earthquake occurrence data using the Japan Meteorological Agency's API and receives the data in JSON format. It also receives damage information from local governments in XML format and obtains the latest traffic conditions from the traffic information database.

[1653] Input: Seismometer, Japan Meteorological Agency API, damage information from local governments, traffic information database

[1654] Output: Collected disaster information data

[1655] Specific operation: The server periodically sends API requests to receive earthquake occurrence information in JSON format, and similarly receives damage information in XML format and stores it for analysis.

[1656] Step 2: Analysis of earthquake data and damage information

[1657] Server operation: The collected earthquake data is integrated with a GIS (geographic information system) to identify the epicenter, seismic intensity, and extent of damage. The damage information is then analyzed and the affected areas are plotted on a map. This process uses GIS software (e.g., ArcGIS).

[1658] Input: Collected disaster information data

[1659] Output: Identification of epicenter, seismic intensity, and damage extent

[1660] Specific operation: The data collected by the server is imported into a GIS and visualized geographically to identify the affected area.

[1661] Step 3: Forecast communication demand

[1662] Server operation: Using machine learning models (e.g., TensorFlow), the server predicts areas where communication demand will increase, taking into account the location information of important facilities such as evacuation centers and hospitals.

[1663] Input: Epicenter, seismic intensity, damage extent identification results, and location information of important facilities

[1664] Output: Communication demand forecast results

[1665] Specific operation: The server uses a machine learning model based on past disaster data to predict areas where communication demand will increase.

[1666] Step 4: Determine the optimal location

[1667] Server operation: The algorithm determines the location of the evacuation shelter based on the analysis results. Parking lots and plazas near the shelter are evaluated as candidates, and the optimal location is selected.

[1668] Input: Communication demand forecast results

[1669] Output: Result of placement location determination

[1670] How it works: The server uses an algorithm to evaluate candidate locations and select the optimal placement point.

[1671] Step 5: Send placement instructions

[1672] Server operation: Sends the GPS coordinates and route information of the determined placement point to the mobile communication device. Transfers the data using a communication protocol (e.g., MQTT).

[1673] Input: Result of determining placement location

[1674] Output: Instruction data to the mobile communication device

[1675] Specific operations: The server sends the GPS coordinates and route information to the mobile communication device.

[1676] Step 6: Autonomous driving of mobile radio vehicles

[1677] Device operation: The mobile communication device moves to the designated location using an autonomous driving system and image recognition AI (e.g., Autoware). During the movement, it uses cameras and Lidar sensors to analyze the actual road conditions and proceed safely.

[1678] Input: GPS coordinates and route information from the server

[1679] Output: Mobile device location update information

[1680] How it works: The mobile device uses cameras and Lidar sensors to detect obstacles and calculates avoidance routes if necessary.

[1681] Step 7: Deploying communications equipment

[1682] Terminal operation: When the mobile communication device arrives at the deployment site, it begins deploying its communication equipment. It deploys the antenna and communication equipment, installs the equipment using the hydraulic system, and starts the generator to power the communication equipment.

[1683] Input: Location information of mobile communication device

[1684] Output: Deployed communications equipment

[1685] Specific operation: The mobile communication device deploys the antenna and supplies power to the communication equipment.

[1686] Step 8: Manually enter damage information and modify deployment instructions

[1687] User behavior: The user (e.g., disaster response personnel) manually inputs disaster information and damage status using a dedicated application. The emotion engine analyzes the user's voice input and facial expressions, and if it determines that the situation is urgent, it automatically adjusts the priority of deployment locations.

[1688] Input: Disaster information, damage situation, user voice input, user facial expression data

[1689] Output: Priority adjustment result by the system

[1690] Specific operation: The user inputs information into the application, and the emotion engine performs analysis.

[1691] Step 9: Real-time monitoring and emotion engine usage

[1692] User behavior: Users can monitor the real-time status of their mobile communication devices using a web-based dashboard. They can also check real-time emotional data generated by the emotion engine and take emergency action.

[1693] Input: Status information of mobile communication device, emotion engine data

[1694] Output: Monitoring results and response instructions

[1695] Specific operation: Users monitor real-time information through the dashboard and take appropriate measures as needed.

[1696] Step 10: Emotion Recognition with the Emotion Engine

[1697] Server operation: The emotion engine uses deep learning models (e.g., OpenVINO) to recognize emotions by analyzing the user's tone of voice and facial expressions. This data is used to prioritize disaster response and is fed back to the entire system.

[1698] Input: User's voice tone, facial expression data

[1699] Output: Emotion recognition result

[1700] How it works: The emotion engine analyzes voice tone and facial expression data to assess the user's emotional state, and adjusts disaster response priorities accordingly.

[1701] Through the specific processing and operation of each step, the system of the present invention supports rapid and effective restoration of communications in the event of a disaster, and enables flexible responses that take into account the emotional state of the user.

[1702] (Application example 2)

[1703] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1704] In order to quickly and effectively restore communications during a disaster, it is essential to accurately grasp the damage situation and predict communications demand. However, conventional disaster response systems rely on fixed communications devices, making it difficult to respond flexibly. Furthermore, because they do not take into account the confusion and emotional state of users during a disaster, they are unable to prioritize responses in cases of high urgency. Therefore, the present invention aims to solve these problems by combining mobile wireless devices with emotion recognition technology, thereby realizing quick and effective communications restoration during a disaster.

[1705] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1706] In this invention, the server includes a means for collecting disaster information, a means for analyzing the disaster information to identify the affected area, and a means for predicting communication demand within the affected area and determining the optimal deployment location. This allows for accurate understanding of the damage situation and communication demand, enabling flexible and effective communication restoration. The mobile wireless device also includes a deployment means with an automatic driving function, a means for providing communication services after arriving at the deployment location, an emotion recognition means for recognizing emotions from user voice input and facial expression analysis, and a means for adjusting disaster response priorities based on the emotion data. This enables flexible response taking into account the user's urgency, achieving rapid and effective communication restoration.

[1707] "Disaster information" refers to data and reports on the occurrence of natural disasters, including information on earthquakes, floods, typhoons, etc.

[1708] "Means" refers to the methods or techniques used to achieve a certain goal.

[1709] "Damaged area" refers to the area where material and human damage has occurred due to a disaster.

[1710] "Telecommunications demand" refers to the amount of telecommunications capacity or services required in a particular region or under particular circumstances.

[1711] "Optimal deployment location" refers to the location that is most suitable for communications equipment and facilities to achieve maximum effectiveness.

[1712] "Autonomous driving" refers to a vehicle's ability to travel autonomously without a human driver.

[1713] "Mobile wireless device" refers to a wireless communication device that can be moved from place to place as needed.

[1714] "Location" means a specific location where equipment or facilities are installed.

[1715] "Communication services" refers to services that support the exchange of information in the form of voice calls, data communications, etc.

[1716] "Emotion recognition means" refers to technology that analyzes and recognizes the user's emotional state through voice input and facial expression analysis.

[1717] "Emotion data" refers to information that represents the user's emotional state.

[1718] "Disaster response" refers to actions and measures taken to minimize damage when a disaster occurs.

[1719] "Priority" refers to the degree of importance of performing a task or action before others.

[1720] "User" refers to the people and organizations that use this system to carry out disaster prevention and communication restoration.

[1721] The present invention is a system for quickly and effectively restoring communications in the event of a disaster. This system consists of three main components: a server, a mobile wireless device (terminal), and a user, which operate in conjunction with each other. Specific embodiments of each component are described below.

[1722] Server Operation

[1723] Disaster information collection and analysis

[1724] The server uses APIs to collect earthquake occurrence data, damage information, and traffic information in real time from the Japan Meteorological Agency and other government agencies. This data is received in JSON or XML format and analyzed by the server. The analyzed data is integrated with a GIS (geographic information system) to identify the epicenter, seismic intensity, and extent of damage. Areas that are particularly affected are plotted on a map, and information is provided to users and devices as needed.

[1725] Forecasting communication demand and determining optimal locations

[1726] After identifying the affected areas, the server uses machine learning models to predict areas where communication demand will be high. Taking into account the locations of important facilities such as evacuation centers and hospitals, the server then runs an algorithm to determine the optimal locations for mobile wireless device placement. This placement decision is optimized based on the extent of damage and communication demand.

[1727] Sending placement instructions

[1728] The server then sends the GPS coordinates and route information of the determined deployment point to the mobile wireless device. Upon receiving this information, the device activates the autonomous driving system and prepares to depart for the designated deployment point.

[1729] Terminal (mobile radio device) operation

[1730] Autonomous driving and ensuring safety

[1731] The device uses an autonomous driving system and image recognition algorithms to navigate to the designated deployment location. During the journey, it analyzes obstacles and traffic conditions in real time to ensure safe travel. If an obstacle is detected, it immediately recalculates an avoidance route and selects a safe path.

[1732] Arrival at deployment site and deployment of communications equipment

[1733] When the terminal arrives at the deployment location, it begins preparations for deploying wireless communication equipment. It deploys antennas and communication devices and supplies power. It begins providing communication services to surrounding communication terminals and monitors communication conditions in real time.

[1734] User interaction and emotional engine

[1735] Entering damage information and correcting deployment instructions

[1736] Users can manually input disaster information and damage status into the system, allowing for immediate response to fluctuations in emergency communication demand. If an emotion engine is installed, it will recognize the user's emotional state from voice input and facial expression analysis, and will respond optimally based on that information.

[1737] Condition monitoring and response coordination

[1738] Users can monitor the real-time status information of their mobile wireless devices through the system's dashboard, allowing them to check communication status and vehicle location at any time. Real-time emotion data generated by the emotion engine can also be viewed on the dashboard, allowing for immediate action in the event of an emergency.

[1739] Emotion recognition by emotion engine

[1740] The emotion engine collects and analyzes emotional data using the user's voice input, facial expression analysis, and biometric sensors. The collected emotional data is used to determine disaster response priorities and is fed back to the entire system. For example, it analyzes the user's stress level from their tone of voice and vocabulary, and adjusts emergency response priorities based on the results.

[1741] Examples of specific examples and prompts

[1742] Let's take a specific scenario: a driverless autonomous vehicle arrives at a designated evacuation shelter and deploys its antenna to provide communication services. If the user yells, "Help me! The building is collapsing and I can't escape!", the emotion engine will determine that an emergency response is required and set disaster response as the highest priority.

[1743] Example prompt sentence:

[1744] User audio: "Help! My house is collapsing and I have nowhere to run!"

[1745] Expected sentiment analysis result: 'Urgent'

[1746] As described above, the system of the present invention realizes rapid and flexible communication restoration in the event of a disaster, and enables disaster response that takes into account the emotional state of the user.

[1747] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1748] Step 1: Collecting and analyzing disaster information

[1749] The server collects earthquake occurrence data, damage information, and traffic information in real time from the Japan Meteorological Agency and other government agencies via API. It sends API requests as input and receives data in JSON or XML format as output. This data is analyzed and integrated with GIS to identify the affected area, epicenter, seismic intensity, etc. Specifically, it stores the acquired data in an internal database and uses it for subsequent analysis.

[1750] Step 2: Forecasting communication demand and determining optimal deployment locations

[1751] The server uses a machine learning model based on the collected information on affected areas to predict areas where demand for communications will increase. It uses data on affected areas and location information on important facilities such as evacuation centers and hospitals as input, and calculates the optimal location for placing mobile wireless devices as output. The server then executes an algorithm to determine this location and determines the GPS coordinates of the optimal location. Specifically, it performs calculations using a model that uses this data as input, and identifies areas where demand will be concentrated.

[1752] Step 3: Send placement instructions

[1753] The server sends the GPS coordinates of the determined deployment point and route information to the mobile wireless device. The terminal receives this information and activates the autonomous driving system. The terminal receives the GPS coordinates of the deployment point and route information as input and sets this as output in the autonomous driving system. In concrete terms, the terminal activates the navigation system based on the received route information and prepares to depart for the specified location.

[1754] Step 4: Autonomous driving and safety

[1755] The device uses an autonomous driving system and image recognition algorithms to navigate to a designated deployment point. It uses real-time video and sensor data as input and calculates a safe driving route as output. It analyzes obstacles and traffic conditions in real time and recalculates an avoidance route if an obstacle is detected. Specifically, the device uses sensors and cameras to monitor its surroundings and changes direction as necessary.

[1756] Step 5: Arrival at deployment site and deployment of communications equipment

[1757] When the terminal arrives at the deployment site, it begins preparations for deploying wireless communication equipment. It uses the current location's GPS information and the deployment site settings as input, and deploys the antenna and communication equipment as output. Specifically, it deploys the equipment necessary to supply power and begin providing communication services.

[1758] Step 6: Enter damage information and modify deployment instructions

[1759] Users can manually input disaster information and damage status into the system. The system receives the disaster information and damage status entered by the user as input and updates the data within the system as output. This allows for immediate response to changes in urgent communication demand. Specifically, the system sends the information entered through the user interface to the server and recalculates the areas requiring response.

[1760] Step 7: Leverage your emotional engine

[1761] An emotion recognition means operates to recognize emotions from the user's voice input and facial expression analysis. It receives audio and video data as input and obtains emotional data as output. Disaster response priorities are adjusted based on the emotional data. Specifically, the emotion recognition algorithm performs voice analysis to detect situations with a high level of urgency. If the user's urgency is high, the priority is automatically raised within the system.

[1762] Step 8: Condition monitoring and response adjustment

[1763] The user monitors real-time status information of the mobile wireless device through the system's dashboard. Status data and communication status during autonomous driving are received as input, and this is displayed on the dashboard as output. Real-time emotion data generated by the emotion engine can also be checked, and immediate action can be taken if an emergency response is required. Specific operations include visualizing the location and communication status of the mobile wireless device on the dashboard, and issuing additional instructions as necessary.

[1764] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1765] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1766] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1767] [Fourth embodiment]

[1768] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1769] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1770] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1771] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1772] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1773] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1774] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1775] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1776] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1777] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1778] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1779] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1780] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1781] MODE FOR CARRYING OUT THE INVENTION

[1782] This invention relates to a system for efficiently achieving early communication restoration in the event of a disaster. This system consists of three main components: a server, a terminal (a mobile radio vehicle), and a user. The cooperation of these components enables rapid communication restoration immediately after a disaster occurs.

[1783] Server Operation

[1784] Disaster information collection and analysis

[1785] The server collects earthquake data in real time from seismometers and the Japan Meteorological Agency, receives damage information sent from local governments and various sensors, and obtains real-time traffic conditions from a traffic information database.

[1786] The server analyzes the collected data using an AI model to identify the epicenter, seismic intensity, extent of damage, etc. Using a GIS (geographic information system), this data is plotted on a map to quickly identify the affected area.

[1787] Examples:

[1788] The server uses an API to obtain earthquake information from the Japan Meteorological Agency and receives the data in JSON format. It also receives damage information from local governments as XML data and uses it for analysis.

[1789] Forecasting communication demand and determining optimal locations

[1790] After identifying affected areas, the server uses machine learning models to predict areas where communication demand will increase, taking into account the locations of important facilities such as evacuation shelters and hospitals.

[1791] The server runs an algorithm to determine the optimal locations for deploying mobile radio vehicles, thereby optimizing communication traffic during disasters.

[1792] Examples:

[1793] The server predicts that communication demand will increase in areas where evacuation shelters are concentrated, and calculates a parking lot near the center of the area as the placement location.

[1794] Sending placement instructions

[1795] The server transmits information about the determined deployment point (GPS coordinates and route information) to the mobile radio vehicle. When the mobile radio vehicle receives this information, it activates its automatic driving system and prepares to depart for the designated deployment point.

[1796] Terminal (mobile radio vehicle) operation

[1797] Autonomous driving and ensuring safety

[1798] The device uses an autonomous driving system and image recognition AI to move towards the designated location, analyzing obstacles and traffic conditions in real time while moving to ensure safe travel.

[1799] If the device detects an obstacle, it immediately recalculates the avoidance route and selects a safe path.

[1800] Examples:

[1801] When the device detects a fallen tree while driving, it automatically calculates a new, safer route based on that information and changes direction.

[1802] Arrival at deployment site and deployment of communications equipment

[1803] When the terminal arrives at the deployment site, it begins preparations for deploying its wireless communication equipment, deploying antennas and communication devices and supplying power.

[1804] The terminal starts providing communication services to surrounding communication terminals and monitors the communication status in real time.

[1805] Examples:

[1806] After arriving at the designated location, the terminal will deploy its antenna and provide communication services to smartphones and radio terminals in the affected area.

[1807] User Operation and Monitoring

[1808] Entering damage information and correcting deployment instructions

[1809] Users (e.g., disaster response personnel) can manually input disaster information and damage status into the system, allowing for immediate response to fluctuations in emergency communication demand.

[1810] The user can also modify the vehicle location instructions as needed.

[1811] Examples:

[1812] Users enter details of the damage to their building and specify areas where communication is particularly necessary.

[1813] Condition monitoring and response coordination

[1814] Users can monitor real-time status information through the system's dashboard, including communication status and the location of mobile wireless vehicles.

[1815] If necessary, orders can be given to dispatch additional mobile radio vehicles.

[1816] Examples:

[1817] The user monitors the communication status of the mobile wireless vehicle on the dashboard, and if communication traffic increases, sends an instruction to the server to dispatch an additional vehicle.

[1818] With these functions and operations, the system of the present invention can achieve rapid and effective restoration of communications in the event of a disaster, facilitating smooth information transmission in disaster-stricken areas.

[1819] The processing flow will be explained below.

[1820] Step 1:

[1821] The server collects earthquake occurrence data in real time from seismometers and the Japan Meteorological Agency, as well as damage information from local governments and various sensors, and obtains the latest traffic conditions from a traffic information database.

[1822] Step 2:

[1823] The server integrates the collected earthquake data with a GIS (geographic information system) to identify the epicenter, seismic intensity, and extent of damage, and then analyzes the damage information and plots the most affected areas on a map.

[1824] Step 3:

[1825] The server uses machine learning models to predict communication demand within the affected area, taking into account the locations of important facilities such as evacuation centers and hospitals, and identifies areas where communication demand is likely to increase.

[1826] Step 4:

[1827] The server executes an algorithm to determine the optimal deployment location of the mobile radio vehicles, which optimizes the deployment location based on the extent of damage and communication demand.

[1828] Step 5:

[1829] The server sends the GPS coordinates of the determined deployment point and route information to the mobile radio vehicle (terminal). When the terminal receives this information, it prepares to start the autonomous driving system.

[1830] Step 6:

[1831] The device activates its autonomous driving system and image recognition AI to depart for the designated location, analyzing the route to the destination in real time and proceeding safely.

[1832] Step 7:

[1833] The device uses image recognition AI to analyze road conditions and obstacles while moving, and if an obstacle is detected, it recalculates an avoidance route and selects a safe driving path.

[1834] Step 8:

[1835] When the terminal arrives at the designated deployment location, it begins preparations to deploy its wireless communication equipment, including deploying antennas and communication devices and supplying power.

[1836] Step 9:

[1837] The terminals begin providing communication services at their deployment locations, providing Wi-Fi and mobile communication services to nearby communication terminals and monitoring communication traffic in real time.

[1838] Step 10:

[1839] Users (disaster response personnel) can manually input disaster information and damage status into the system as needed, allowing for immediate response to emergency communication demands.

[1840] Step 11:

[1841] Users can monitor the real-time status information of their mobile wireless vehicles through the system's dashboard, allowing them to check the communication status and vehicle location at any time.

[1842] Step 12:

[1843] The user can issue instructions to dispatch additional mobile radio vehicles as needed, especially when communication traffic increases, by sending new instructions to the server.

[1844] Example 1

[1845] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1846] Rapid restoration of communications in the event of a disaster is extremely important for saving lives and sharing information. However, with conventional systems, identifying the extent of damage, forecasting communication demand, and optimally deploying mobile wireless vehicles were all done manually, making it difficult to respond quickly. Furthermore, the accuracy of autonomous driving and obstacle avoidance was insufficient, and ensuring the safety of mobile wireless vehicles also posed challenges. Furthermore, deploying communications equipment and providing services required human labor, making it difficult to quickly restore communications.

[1847] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1848] In this invention, the server includes means for collecting disaster information, means for analyzing the disaster information and identifying the affected area, means for predicting communication demand within the affected area using a generative AI model and determining the optimal deployment location, means for deploying mobile wireless vehicles including an automatic driving system to the deployment location, means for automatically deploying communication equipment to provide communication services after the mobile wireless vehicles reach the deployment location, and means for the user to manually input disaster information and correct the deployment instructions for the mobile wireless vehicles, thereby enabling quick and efficient communication restoration.

[1849] "Disaster information" refers to data and information related to natural disasters such as earthquakes, tsunamis, typhoons, and floods.

[1850] "Damaged area" refers to the region or area affected by a disaster.

[1851] "Communication demand" refers to the amount and necessity of communication services required in a particular region or area.

[1852] A "generative AI model" is a machine learning or artificial intelligence model used to analyze data and predict patterns.

[1853] The "optimal deployment location" refers to a location or position where a mobile radio vehicle can be deployed efficiently and achieve maximum effectiveness.

[1854] An "autonomous driving system" refers to technology and devices that enable vehicles to drive themselves and travel to designated routes and destinations.

[1855] A "mobile wireless vehicle" is a vehicle equipped with wireless communication equipment that can provide communication services while moving.

[1856] "Communications equipment" means equipment such as antennas, transmitters, and receivers used to provide communications services.

[1857] "Users" refer to the people who operate this system and those involved in disaster response.

[1858] "Deployment instructions" are instructions or orders to deploy a mobile radio vehicle at a specific location.

[1859] MODE FOR CARRYING OUT THE INVENTION

[1860] The present invention relates to a system for efficiently achieving early communication restoration in the event of a disaster. This system consists of three main components: a server, a terminal (a mobile wireless vehicle), and a user. Specific embodiments are described below.

[1861] Server Operation

[1862] Disaster information collection and analysis

[1863] The server first collects earthquake data through seismometers and the Japan Meteorological Agency's API. The collected data is sent to the server in JSON format. It then receives damage information in XML format from local governments and various sensors, and obtains real-time traffic conditions from a traffic information database. To do this, the server uses high-performance data analysis software and AI models. Specifically, it uses a GIS (geographic information system) to plot the collected data on a map and identify the affected areas.

[1864] Examples:

[1865] The server uses an API to obtain earthquake information from the Japan Meteorological Agency and receives the data in JSON format. It also receives damage information from local governments as XML data and uses GIS to quickly identify affected areas.

[1866] Forecasting communication demand and determining optimal locations

[1867] After identifying the affected areas, the server uses a generative AI model to predict areas where communication demand will increase. The predictive model takes into account past disaster data, population data, and the locations of important facilities such as evacuation centers and hospitals. The server then runs an algorithm to determine the optimal placement locations for mobile radio vehicles, thereby optimizing communication traffic.

[1868] Examples:

[1869] The server predicts that communication demand will increase in areas where evacuation shelters are concentrated, and calculates a parking lot near the center of the area as the location for deployment.

[1870] Sending placement instructions

[1871] The server transmits information about the determined deployment point (GPS coordinates and route information) to the mobile radio vehicle. When the mobile radio vehicle receives this information, it activates its automatic driving system and prepares to depart for the designated deployment point.

[1872] Terminal (mobile radio vehicle) operation

[1873] Autonomous driving and ensuring safety

[1874] The device uses an autonomous driving system and image recognition AI to move toward the designated location. During movement, it analyzes obstacles and traffic conditions in real time to ensure safe movement. If an obstacle is detected, it immediately recalculates an avoidance route and selects a safe path.

[1875] Examples:

[1876] When the device detects a fallen tree while driving, it automatically calculates a new, safer route based on that information and changes its direction of travel.

[1877] Arrival at deployment site and deployment of communications equipment

[1878] When the terminal arrives at the deployment location, it begins preparations for deploying wireless communication equipment. It deploys antennas and communication devices and supplies power. It begins providing communication services to surrounding communication terminals and monitors communication conditions in real time.

[1879] Examples:

[1880] After arriving at the designated location, the terminal will deploy its antenna and provide communication services to smartphones and radio terminals in the affected area.

[1881] User Operation and Monitoring

[1882] Manual input of damage information and correction of placement instructions

[1883] Users can manually input disaster information and damage status into the system, supplementing the information needed to respond quickly to fluctuations in emergency communication demand. It is also possible to revise mobile radio vehicle deployment instructions as needed.

[1884] Examples:

[1885] Users enter details of the damage to their building and specify areas where communication is particularly necessary.

[1886] Condition monitoring and dispatch of additional vehicles

[1887] Users can use the system dashboard to monitor the system status in real time, check communication status and vehicle location, and issue instructions to dispatch additional vehicles if necessary.

[1888] Examples:

[1889] The user monitors the communication status of the mobile wireless vehicle on the dashboard, and if communication traffic increases, sends an instruction to the server to dispatch additional vehicles.

[1890] Examples of specific prompts to input to the generative AI model

[1891] Prompt statement:

[1892] "Please explain in detail the operating procedures of the server of the communications recovery system in the event of a disaster, from real-time data collection and data analysis, to forecasting communications demand, determining the placement locations of mobile radio vehicles, and sending placement instructions."

[1893] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1894] Step 1:

[1895] The server collects earthquake data in real time from seismometers and the Japan Meteorological Agency's API. The earthquake information obtained as input is in JSON format. The server uses this data to extract information such as the time of the earthquake, epicenter, and seismic intensity. The processed earthquake information is obtained as output.

[1896] Specific behavior:

[1897] The server makes an API request, receives earthquake data in JSON format from the Japan Meteorological Agency, and analyzes it.

[1898] Step 2:

[1899] The server receives damage information in XML format from local governments and various sensors. The damage information received as input is also in XML format. The server analyzes this and extracts information on the state of building collapse and human casualties. The output is a database containing the damage information.

[1900] Specific behavior:

[1901] The server receives and analyzes the XML data and stores the damage status in a database.

[1902] Step 3:

[1903] The server obtains real-time traffic conditions from a traffic information database. The traffic information collected as input is obtained via API. The server analyzes this information and extracts road passability and congestion information. The output is the analyzed traffic information.

[1904] Specific behavior:

[1905] The server calls the traffic information API to obtain and analyze real-time traffic conditions.

[1906] Step 4:

[1907] The server uses a generative AI model to predict affected areas and communication demand based on collected earthquake data, damage information, and traffic information. The inputs are the earthquake data, damage information, and traffic information previously collected and analyzed. Using the generative AI model, information on predicted communication demand areas and damaged areas is obtained. The output is map data of the predicted damaged areas and communication demand areas.

[1908] Specific behavior:

[1909] The server inputs data into the generative AI model and plots the affected area and communication demand forecast results.

[1910] Step 5:

[1911] The server determines the optimal location for deploying mobile wireless vehicles based on the predicted communication demand area. The input is the predicted communication demand area information, and the output is the GPS coordinates of the optimal deployment location.

[1912] Specific behavior:

[1913] The server uses machine learning algorithms to calculate the optimal placement locations for points within the affected area where communication demand is high.

[1914] Step 6:

[1915] The server sends the GPS coordinates of the determined deployment point and route information to the mobile radio vehicle. The input is the GPS coordinates of the optimal deployment point and route information. The output is deployment instructions to the mobile radio vehicle.

[1916] Specific behavior:

[1917] The server generates JSON data containing GPS coordinates and route information and sends it to the mobile radio vehicle.

[1918] Step 7:

[1919] The terminal (mobile wireless vehicle) activates the autonomous driving system based on the deployment instructions received from the server. The inputs are the GPS coordinates and route information received from the server. The terminal activates the autonomous driving system and automatically moves toward the designated deployment point. The output is arrival at the deployment point.

[1920] Specific behavior:

[1921] The device will begin autonomous driving based on route information and proceed while recognizing traffic signals and road signs.

[1922] Step 8:

[1923] As the device moves, it uses image recognition AI and sensors to detect obstacles and navigate safely. The input is real-time image data and sensor data. The device analyzes this and recalculates an avoidance route if necessary. The output is an updated safe route.

[1924] Specific behavior:

[1925] If the device detects a fallen tree or obstacle, it will automatically calculate a new route and change direction.

[1926] Step 9:

[1927] After the terminal arrives at the designated deployment point, it begins preparations to deploy wireless communication equipment. The input is arrival information for the deployment point. The terminal deploys the antenna and communication equipment and supplies power. The output is that communication is ready.

[1928] Specific behavior:

[1929] The device automatically deploys its antenna and powers on its communications equipment.

[1930] Step 10:

[1931] The terminal starts providing communication services to surrounding communication terminals and monitors the communication status in real time. The input is the request data for the communication service. The terminal analyzes this and communicates appropriately. The output is the status information of the provided communication service.

[1932] Specific behavior:

[1933] The device provides communication services to surrounding smartphones and radio devices and monitors communication conditions.

[1934] Step 11:

[1935] Users manually input disaster information and damage status into the system and modify the deployment instructions for mobile radio vehicles as necessary. The inputs are the manually entered disaster information and damage status. Based on this, the system recalculates and generates updated deployment instructions as output.

[1936] Specific behavior:

[1937] The user uses the dashboard to input information and modify the placement instructions as needed.

[1938] Step 12:

[1939] The user monitors real-time status information through the system's dashboard and issues instructions to dispatch additional mobile radio vehicles as needed. The input is real-time status information collected from the dashboard. The output is an instruction to dispatch additional vehicles.

[1940] Specific behavior:

[1941] The user monitors the communication status and location of the mobile wireless vehicles on the dashboard and issues an instruction to dispatch additional vehicles if communication traffic increases.

[1942] (Application example 1)

[1943] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1944] Conventional communication restoration systems for disaster recovery require time-consuming collection and analysis of disaster information, identification of affected areas, prediction of communication demand, and optimal deployment of mobile radios, making it difficult to quickly restore communication infrastructure. Other issues include limited real-time tracking of mobile radios and limited obstacle avoidance functions for safe operation. Furthermore, the lack of appropriate AI analysis and map display functions for emergency communication restoration makes it difficult for disaster response personnel to respond quickly.

[1945] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1946] In this invention, the server includes means for collecting disaster information, means for analyzing the disaster information to identify the affected area, means for predicting communication demand within the affected area and determining the optimal deployment location, means for deploying mobile radios with autonomous driving functions to the deployment location, means for providing communication services after the mobile radios reach the deployment location, means for tracking the progress and location information of the mobile radios in real time, and means for performing AI analysis and displaying maps to support emergency communication restoration. This enables rapid and efficient restoration of communication infrastructure, safe and reliable operation of mobile radios, and appropriate emergency response by disaster response personnel.

[1947] "Disaster information" refers to data on natural disasters such as earthquakes and typhoons, as well as information on the damage caused by these disasters.

[1948] "Affected Area" refers to the area directly or indirectly affected by a natural disaster.

[1949] "Communications demand" refers to the need for communications services at a particular time and place.

[1950] The "optimal placement point" refers to a location determined to most effectively place a mobile radio.

[1951] "Autonomous driving function" refers to the function of a mobile radio that allows it to move autonomously without human operation.

[1952] "Mobile radio" refers to communication equipment that can be moved to provide temporary communication services in the event of a disaster.

[1953] "Progress" refers to information about the location and status of the mobile radio as it progresses.

[1954] "Location information" refers to geographic coordinate data of a specific location.

[1955] "Real-time" refers to events and data processing that occur nearly simultaneously.

[1956] "Tracking" refers to the continuous monitoring of the current location and progress of a mobile radio.

[1957] "AI analytics" refers to the process of using artificial intelligence to analyze large amounts of data and derive specific goals or results.

[1958] "Map display" refers to the visual presentation of data or information on a map using a geographic information system.

[1959] "Communication services" refers to services that provide means of communication such as voice, data, and internet.

[1960] This invention relates to a system for efficiently achieving early communication restoration in the event of a disaster. This system consists of three main components: a server, a terminal (mobile radio), and a user. These components work together to enable rapid communication restoration immediately after a disaster occurs.

[1961] Server Operation

[1962] Disaster information collection and analysis

[1963] The server collects earthquake data in real time from seismometers and weather information services, receives damage information sent from local governments and various sensors, and obtains real-time traffic conditions from a traffic information database.

[1964] The server analyzes the collected data using an AI model to identify the epicenter, seismic intensity, extent of damage, etc. Using a GIS (geographic information ...

Claims

1. A means of collecting disaster information; means for analyzing the disaster information and identifying a damaged area; means for predicting communication demand within the affected area and determining an optimal deployment location; means for deploying a mobile radio vehicle having an automatic driving function at the deployment location; means for providing communication services after the mobile radio vehicle has reached a deployment point; A system including:

2. The system according to claim 1, wherein the mobile wireless vehicle uses image recognition AI to analyze road conditions and obstacles and avoid obstacles during autonomous driving.

3. The system of claim 1 , wherein the disaster information includes earthquake data, damage information, and traffic information.

Images