system

Abstract

We provide the system. [Solution] A means for collecting and processing disaster prediction data and geographical information, A means of evaluating disaster risk based on that data, A means for simulating the optimal placement of electric company vehicles based on disaster risk assessment, A means for instructing the movement of an electric company vehicle based on the simulation results, A means of sending electric company vehicles to base stations to supply power in the event of a disaster, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern times, disasters occur frequently, making it difficult to maintain communication infrastructure. Especially during power outages, the power supply to communication base stations is interrupted, resulting in communication failures. An efficient method for quickly responding and ensuring communication under such circumstances is required. Also, means for maximizing the utilization of existing facilities and avoiding additional large-scale infrastructure investments are necessary.

Means for Solving the Problems

[0005] This invention provides a system that collects disaster prediction data and geographic information and evaluates disaster risk based on that data. Based on the disaster risk evaluation, this system simulates the optimal placement of electric company vehicles and instructs the movement of the electric company vehicles based on the simulation results. Furthermore, in the event of a disaster, the system directs the electric company vehicles to base stations to supply power and ensure communication. This minimizes the occurrence of communication disruptions due to disasters and enables a rapid response.

[0006] "Disaster prediction data" refers to historical and current weather and geographical data collected to predict the likelihood of disasters occurring.

[0007] "Geographic information" refers to detailed data about a specific region, such as topography, location information, and infrastructure layout.

[0008] "Disaster risk" is an assessment value that indicates the degree of likelihood of a disaster occurring in a particular place or time.

[0009] An "electric company car" is a vehicle owned by a company that is powered by an electric motor.

[0010] "Optimal allocation" refers to the best way to efficiently allocate resources and personnel to achieve a specific objective.

[0011] A "simulation" is the process of virtually recreating a situation and predicting and evaluating the results.

[0012] A "movement order" refers to giving instructions to move from one point to another based on a specific purpose or reason.

[0013] "Supplying electricity" means providing the necessary power to ensure that equipment and infrastructure function properly.

[0014] A "base station" is a relay facility for wireless communication and is equipment that constitutes part of a communication network.

[0015] "Ensuring communication" refers to the claim of maintaining and restoring the communication infrastructure to prevent communication interruptions.

Brief Description of Drawings

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

Embodiment for Implementing the Invention

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

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

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

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

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

[0022] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0024] [First Embodiment]

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

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

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

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

[0029] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

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

[0031] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

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

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

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

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

[0037] This invention is a system aimed at maintaining communication infrastructure and enabling rapid response during disasters. Specific embodiments of this system are described below.

[0038] System Configuration

[0039] This system consists primarily of the following elements:

[0040] 1. Server: Responsible for data collection, disaster prediction using AI models, and overall system management.

[0041] 2. Terminal (electric company vehicle): Equipped with a power supply function, it moves and supplies power based on instructions from the server.

[0042] 3. User: Operate and monitor the system, and intervene as needed.

[0043] System Operation Overview

[0044] The operation of this system can be broadly classified into the following three stages.

[0045] 1. Disaster prediction using data collection and AI models

[0046] The server collects data from various directories, including weather data, geographic information, and disaster prevention information. This data is preprocessed and input into an AI model to predict the risk of disaster occurrence. In particular, it combines past disaster data with current weather forecast data to predict the scale and location of potential future disasters.

[0047] Specific example: A server retrieves weather data from a weather forecast API, and an AI model uses this data to predict that a typhoon will approach in a few days. The prediction results indicate that the disaster risk is high in a specific area.

[0048] 2. Optimal placement simulation and instructions

[0049] After the disaster risk is assessed, the server uses this information to run a simulation of the placement of electric company vehicles. It selects the electric company vehicles closest to high-risk areas and optimizes their placement. Based on the simulation results, it sends movement instructions to each electric company vehicle.

[0050] Specific example: For areas predicted to be at high disaster risk, the server runs a simulation and sends an instruction to the nearest electric company vehicle to head to that area. For example, if the risk area is City A and the nearest electric company vehicle is Company B, an instruction will be sent to Company B to head to City A.

[0051] 3. Real-time response in the event of a disaster

[0052] In the event of an actual disaster and a power outage at a base station, the server immediately collects information on the damaged base station and instructs the nearest electric vehicle to provide emergency assistance. Upon arrival at the base station, the terminal (electric vehicle) uses its battery to supply power to the base station and assist in restoring communication.

[0053] Specific example: If a disaster causes a power outage at a base station in City C, the server issues an emergency instruction to the nearest electric company vehicle D to proceed. When company vehicle D arrives at the base station, it uses its battery to supply power to the base station, restarting the communication equipment and restoring communication.

[0054] User roles

[0055] The user's role is to monitor the overall situation while the server performs complex data analysis and issues instructions. They are also responsible for manual intervention and system maintenance in the event of unforeseen circumstances.

[0056] Specific example: The user reviews the disaster prediction results generated by the system and makes manual corrections as needed. They also take measures such as preparing spare batteries if the battery level of the electric company vehicle is low.

[0057] This invention enables efficient and rapid maintenance of communication infrastructure during disasters, thereby minimizing communication disruptions. Furthermore, by making maximum use of existing equipment, it avoids the need for additional large-scale investments.

[0058] The following describes the processing flow.

[0059] Program processing steps

[0060] 1. Disaster prediction using data collection and AI models

[0061] Step 1:

[0062] The server collects weather forecast data, historical disaster data, and base station geographic information from multiple data sources. This includes government weather data APIs and data from Earth observation satellites.

[0063] Step 2:

[0064] The server preprocesses the collected data. Specifically, it imputes missing values, removes outliers, and standardizes the data. This ensures data consistency and quality.

[0065] Step 3:

[0066] The server inputs pre-processed data into an AI model to predict disaster risk. For example, it uses machine learning algorithms to assess future disaster risk based on past disaster patterns.

[0067] Step 4:

[0068] Based on the prediction results, the server calculates a disaster risk score for each base station. This is a detailed assessment that includes the scale of the disaster, the date of occurrence, and the scope of impact.

[0069] 2. Optimal placement simulation and instructions

[0070] Step 5:

[0071] The server assesses which base stations are most vulnerable based on their disaster risk scores. Base stations are then categorized according to their risk level.

[0072] Step 6:

[0073] The server simulates the optimal vehicle deployment based on the risk assessment results and the current location information of electric company vehicles. This simulation uses an optimization algorithm to select the electric company vehicle closest to each base station.

[0074] Step 7:

[0075] Based on the simulation results, the server sends movement instructions to each electric company vehicle. Instructions are generated that include a specific travel route and destination.

[0076] Step 8:

[0077] The terminal (electric company vehicle) receives instructions from the server and begins moving towards its destination based on that information. It periodically sends its location and battery level to the server during its journey.

[0078] 3. Real-time response in the event of a disaster

[0079] Step 9:

[0080] If a disaster actually occurs and an anomaly such as a power outage is detected, the server will immediately monitor the status of base stations and identify any base stations that have stopped working.

[0081] Step 10:

[0082] The server sends emergency response instructions to the nearest electric company vehicle. These instructions include procedures for rapid movement and power supply.

[0083] Step 11:

[0084] The terminal (electric company vehicle) receives an emergency instruction and immediately heads to the designated base station. Upon arrival, the EV vehicle prepares to supply power to the base station using its battery.

[0085] Step 12:

[0086] The terminal (electric company vehicle) supplies power to the base station and restarts the communication equipment. During this process, it reports the battery level and supply status to the server.

[0087] Step 13:

[0088] The user monitors the response status during a disaster and makes manual adjustments or instructions as needed. For example, they might take measures such as having additional electric company vehicles on standby.

[0089] Through the steps described above, this system can maintain communication infrastructure and enable a rapid response during disasters.

[0090] (Example 1)

[0091] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0092] In disaster situations where maintaining communication infrastructure and responding quickly are crucial, conventional methods make it difficult to supply power to base stations quickly, leading to prolonged communication disruptions. Therefore, a system is needed to efficiently and rapidly predict disasters, optimally deploy and relocate power supply equipment, and ensure the maintenance of communication infrastructure.

[0093] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0094] In this invention, the server includes means for collecting and preprocessing weather data, geographic information, and disaster prevention information; means for predicting disaster risk using an AI model generated based on the collected data; means for simulating the optimal placement of movable power supply devices based on the disaster risk prediction; means for instructing the movement of the movable power supply devices based on the simulation results; and means for directing the movable power supply devices toward communication devices to supply power in the event of a disaster. This enables the rapid and efficient maintenance of communication infrastructure even in the event of a disaster.

[0095] "Meteorological data" refers to information related to atmospheric conditions, including data such as temperature, humidity, precipitation, wind speed, and wind direction.

[0096] "Geographic information" refers to data that represents the geographical characteristics of a specific region, such as its topography, geology, land use, and population distribution.

[0097] "Disaster prevention information" refers to information about the occurrence and impact of disasters, and includes data such as evacuation sites, evacuation routes, and safety assessments.

[0098] "Preprocessing" refers to the process of organizing and correcting data before data analysis or model input, and includes processes such as imputing missing values, correcting outliers, and normalizing data.

[0099] A "generative AI model" is a model built using machine learning and deep learning techniques, and is a set of algorithms used to perform a specific task (in this case, disaster prediction).

[0100] "Disaster risk" refers to numerical values ​​or indicators used to assess the likelihood of a natural disaster occurring and the extent of the resulting damage.

[0101] A "portable power supply device" is a device that is mobile for supplying electricity, such as a battery pack or generator mounted on a car or drone.

[0102] "Simulation" is a technique for virtually reproducing real-world actions and behaviors on a computer model, and includes using computer simulations to explore optimal placements and actions.

[0103] "Communication equipment" refers to devices used for sending and receiving data, specifically including base stations and routers.

[0104] System Overview

[0105] This invention is a system aimed at maintaining communication infrastructure and enabling rapid response during disasters, and consists of a server, a terminal (a portable power supply device), and a user. The roles of each component are described in detail below.

[0106] Server Role

[0107] 1. Data Collection

[0108] The server periodically collects weather data, geographic information, disaster prevention information, and other data from various APIs and sensors. The main software used is Python, and data collection utilizes the OpenWeatherMap API and the Geospatial Information Authority of Japan's API.

[0109] 2. Data preprocessing

[0110] The server preprocesses the collected data. This preprocessing uses libraries such as Python's Pandas library, specifically performing tasks such as imputing missing values, normalizing the data, and correcting outliers.

[0111] 3. Disaster prediction

[0112] The server inputs pre-processed data into a generating AI model (using TENSORFLOW®) to predict disaster risk. The AI ​​model combines historical disaster data with current weather forecast data to predict the scale and location of potential future disasters.

[0113] Specific example:

[0114] The server retrieves weather data from a weather forecast API (OpenWeatherMap API), and a TensorFlow model uses this data to predict that a typhoon will approach in a few days. The prediction results indicate that the risk of disaster in a specific area is high.

[0115] 4. Placement Simulation

[0116] The server simulates the optimal placement of portable power supply units based on disaster risk. The simulation is performed using the Python SimPy library.

[0117] Specific example:

[0118] For areas predicted to be at high disaster risk, the server uses SimPy to perform simulations and identify the nearest mobile power supply unit. For example, if the risk area is City A and the nearest power supply unit is unit B, an instruction is sent to unit B to move towards City A.

[0119] 5. Movement instructions

[0120] Based on the simulation results, the server sends movement instructions to the movable power supply unit. A 5G network is used for communication.

[0121] Specific example:

[0122] The server sends a 5G communication instruction to the nearest mobile power supply device to move to City A, and the device begins moving according to the received instruction.

[0123] 6. Real-time support

[0124] In the event of a disaster, the server immediately collects information on damaged communication equipment and instructs the nearest mobile power supply unit to take emergency action.

[0125] Specific example:

[0126] If a disaster actually occurs in City X and the communication equipment experiences a power outage, the server will send an emergency instruction to the nearest power supply unit. Once the power supply unit arrives, it will use its battery to power the communication equipment and restore communication.

[0127] Terminal role

[0128] 1. Power supply

[0129] The terminal (a portable power supply device) moves to a specific area and supplies power according to instructions from the server. The device is equipped with a LiDAR sensor and GPS, which allows it to accurately reach the disaster area.

[0130] Specific example:

[0131] The terminal receives instructions from the server, moves to the designated communication device, and uses its battery to receive power.

[0132] User roles

[0133] 1. System monitoring and maintenance

[0134] The user monitors the complex data analysis and instruction issuing performed by the server, and intervenes manually when necessary. They are also responsible for the overall system maintenance.

[0135] Specific example:

[0136] Users review the disaster prediction results generated using the system's GUI and make manual corrections as needed. Additionally, if the battery level of the electric company vehicle (mobile power supply unit) is low, a spare battery is prepared and replaced.

[0137] Example of a prompt

[0138] An example of a prompt to input into a generative AI model is as follows:

[0139] "Use current weather data and historical disaster data to predict potential disasters that may occur in the next week."

[0140] This system provides a key mechanism for quickly and efficiently maintaining communication infrastructure even during disasters, minimizing communication disruptions. Furthermore, by making maximum use of existing equipment, it avoids the need for additional large-scale investments.

[0141] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0142] Step 1: Data Collection

[0143] Processing flow: The server collects weather data, geographic information, and disaster prevention information from various APIs and sensors.

[0144] Specific operation: The server sends requests to the OpenWeatherMap API and the Geospatial Information Authority of Japan API to obtain real-time weather data and geographic information in JSON format, and stores this data in an internal database.

[0145] Input: Weather data and geographic information triggered by requests from the API.

[0146] Output: Meteorological data and geographic information as raw data requiring preprocessing.

[0147] Step 2: Data Preprocessing

[0148] Processing flow: The server prepares the collected data into an applicable format.

[0149] Specific operation: The server uses the Python Pandas library to impute missing data, correct outliers, and normalize the data.

[0150] Input: Collected raw data

[0151] Output: Preprocessed, clean dataset

[0152] Step 3: Disaster Prediction

[0153] Processing flow: The server inputs pre-processed data into an AI model to predict disaster risk.

[0154] Specific operation: The server utilizes TensorFlow to run an AI model using pre-processed data as input, and derives a disaster risk score.

[0155] Input: Preprocessed dataset

[0156] Output: Disaster risk score for each region

[0157] Step 4: Placement Simulation

[0158] Processing flow: The server simulates the optimal placement of movable power supply units based on the disaster risk score.

[0159] Specific operation: The server uses the Python SimPy library to calculate the optimal placement and determine the movement path and placement location.

[0160] Input: Disaster risk score and current power supply location data

[0161] Output: Optimal placement information and movement paths

[0162] Step 5: Movement Instructions

[0163] Processing flow: Based on the simulation results, the server sends instructions to the portable power supply unit.

[0164] Specific operation: The server generates movement instructions and sends them to each device via the 5G network.

[0165] Input: Optimal placement information and travel path

[0166] Output: Movement Instructions

[0167] Step 6: Real-time response

[0168] Processing flow: When a disaster occurs, the server collects information on damaged communication equipment and takes necessary emergency action.

[0169] Specific operation: The server acquires situation reports from the disaster area in real time and issues an emergency relocation instruction to the nearest power supply unit. Upon arrival of the unit, it uses its battery to supply power and restore communication.

[0170] Input: Status data of communication devices during a disaster, current location information

[0171] Output: Emergency evacuation order and power supply order

[0172] Step 7: System Monitoring and Maintenance

[0173] Processing flow: The user monitors the overall status of the system and intervenes and performs maintenance as needed.

[0174] Specific actions: The user monitors the system via a GUI and performs manual corrective operations if an anomaly is detected. They also check the battery level of electric company vehicles and prepare a spare battery if necessary.

[0175] Input: Monitoring data and anomaly alerts from the system.

[0176] Output: Correction operation and maintenance instructions

[0177] (Application Example 1)

[0178] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0179] The need for rapid response and maintenance of communication infrastructure during disasters is increasing, with power supply to communication equipment being particularly important. However, conventional systems have shortcomings in collecting and processing disaster prediction data, making it difficult to optimize the deployment of electric vehicles or receive user instructions in real time. This makes it difficult to respond quickly in the event of a communication failure, and therefore needs to be resolved.

[0180] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0181] In this invention, the server includes means for collecting and processing disaster prediction data and geographic information; means for evaluating disaster risk based on the data; means for simulating the optimal placement of electric vehicles based on the disaster risk evaluation; means for instructing the movement of electric vehicles based on the simulation results; means for directing electric vehicles toward communication equipment and supplying power in the event of a disaster; means for acquiring disaster prediction data in real time using a smart device and notifying the user; and means for the user to send instructions directly to the electric vehicles from a smart device. This enables the maintenance of communication infrastructure and rapid response in real time even during a disaster.

[0182] "Disaster prediction data" refers to data collected to predict the occurrence of disasters, such as weather data, geographical information, and disaster prevention information.

[0183] "Geographic information" refers to geographical data relating to a specific region or location, and includes map information and topographic data.

[0184] "Disaster risk assessment" is the process of analyzing and determining the level of disaster risk a particular region or piece of equipment is exposed to, based on collected disaster prediction data.

[0185] An "electric vehicle" is a vehicle that operates electrically to provide power and transportation during a disaster.

[0186] "Optimal placement simulation" refers to conducting simulations to determine the most effective placement of electric vehicles based on disaster risk assessment results.

[0187] "Movement instruction" refers to the action of instructing an electric vehicle to move to a specific location based on the results of an optimal placement simulation.

[0188] "Communication equipment" refers to the equipment that makes up the communication infrastructure, and includes base stations, relay stations, and so on.

[0189] "Power supply" refers to the act of providing the necessary electricity to communication equipment.

[0190] A "smart device" is a portable information terminal with advanced processing and communication capabilities, such as a smartphone or tablet.

[0191] "Real-time acquisition" means instantly obtaining the latest data and information at the present time.

[0192] "Notification" refers to the act of conveying important information or warnings to a user.

[0193] "Instructions" refer to commanding someone to perform a specific action or movement.

[0194] This invention is a system aimed at maintaining communication infrastructure and enabling rapid response during disasters. Specific embodiments of this system are described below.

[0195] System Configuration

[0196] This system consists primarily of the following elements:

[0197] 1. Server: Responsible for data collection, disaster prediction using AI models, and overall system management.

[0198] 2. Electric vehicles: These vehicles have a power supply function and move and supply power based on instructions from the server.

[0199] 3. User: Operate and monitor the system, and intervene as needed. Also, use smart devices to acquire data in real time, provide notifications, and issue instructions.

[0200] System Operation Overview

[0201] The operation of this system can be broadly classified into the following three stages.

[0202] 1. Disaster prediction using data collection and AI models

[0203] The server collects data from various directories, including weather data, geographic information, and disaster prevention information. This data is preprocessed and input into an AI model to predict the risk of disaster occurrence. In particular, it combines past disaster data with current weather forecast data to predict the scale and location of potential future disasters.

[0204] Specific example: A server retrieves weather data from a weather forecast API, and an AI model uses this data to predict that a typhoon will approach in a few days. The prediction results indicate that the disaster risk in a specific area is high. This information is then communicated to the user via a smart device, prompting them to prepare for the eventuality.

[0205] 2. Optimal placement simulation and instructions

[0206] After the disaster risk is assessed, the server performs a simulation of electric vehicle deployment based on that assessment. It selects the electric vehicles closest to high-risk areas and optimizes their deployment. Based on the simulation results, it sends movement instructions to each electric vehicle.

[0207] Specific example: In areas predicted to be at high disaster risk, the server runs a simulation and instructs the nearest electric vehicle to head towards that area. For example, if the risk area is City A and the nearest electric vehicle is Vehicle B, Vehicle B will be instructed to head towards City A. This instruction is also notified to the user in real time via a smart device.

[0208] 3. Real-time response in the event of a disaster

[0209] In the event of an actual disaster and a power outage to communication equipment, the server will immediately collect information on the damaged equipment and instruct the nearest electric vehicle to respond to the emergency. Upon arrival at the communication equipment, the electric vehicle will use its battery to supply power to the equipment and assist in restoring communication.

[0210] Specific example: If a disaster causes a power outage to the communication equipment in City C, the server issues an emergency instruction to the nearest electric vehicle. When the electric vehicle arrives at the communication equipment, it uses its battery to supply power to the equipment, restarting the communication devices and restoring communication. This entire process is also reported to the user in real time via a smart device.

[0211] Main technologies used

[0212] Server: Performs data collection, disaster prediction using AI models, optimal placement simulations, and instructions. Programming languages ​​such as Python and Java (registered trademark), and AI frameworks such as TensorFlow and PyTorch are used.

[0213] Electric vehicles: These vehicles supply power to communication equipment and provide transportation. They are equipped with GPS and battery management systems.

[0214] Smart devices: Acquire real-time data, provide user notifications, and issue instructions. Dedicated applications will be developed to run on iOS and Android®.

[0215] Examples of prompts for generative AI models

[0216] "Create a prompt message to determine the optimal placement of electric vehicles when the risk of typhoons in Tokyo increases."

[0217] Thus, the present invention provides a system that enables the maintenance of communication infrastructure in real time and rapid response even during disasters.

[0218] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0219] Step 1:

[0220] The server collects data such as weather data, geographic information, and disaster prevention information from various directories and APIs. Input requires various API keys and database connection information, and output is the collected raw data. Data collection is performed periodically and stored in a database to maintain the latest information.

[0221] Step 2:

[0222] The server preprocesses the collected data. This involves imputing missing values, normalizing the data, and removing inconsistent data. The input is the collected raw data, and the output is the clean data after preprocessing. This preprocessing step uses Python's Pandas library or similar tools to clean the data.

[0223] Step 3:

[0224] The server inputs pre-processed data into an AI model to predict disaster risk. The input is clean data, and the output is an assessment of disaster risk. Here, an AI framework such as TensorFlow or PyTorch is used to create a model that combines historical disaster data with current weather data.

[0225] Step 4:

[0226] The server simulates the optimal placement of electric vehicles based on disaster risk assessment results. The inputs are the disaster risk assessment results and the current location information of the electric vehicles, and the output is the optimal placement plan for the electric vehicles. This simulation utilizes pathfinding techniques such as the Dijkstra algorithm and the A algorithm.

[0227] Step 5:

[0228] The server sends movement instructions to the electric vehicles based on the simulation results. The input is the optimal placement plan, and the output is the actual position information of the electric vehicles after the movement instructions are given. These instructions are transmitted in real time via the communication network.

[0229] Step 6:

[0230] The server uses smart devices to notify users of disaster prediction data in real time. The input is the disaster risk assessment result, and the output is a disaster risk notification displayed on the user's smart device. This notification is sent to the user via push notification or SMS.

[0231] Step 7:

[0232] Users can send instructions directly to electric vehicles from their smart devices. Input is user-generated information, and output is the instructions sent to the electric vehicle. This functionality is provided through a dedicated application.

[0233] Step 8:

[0234] In the event of a disaster, the server collects information on damaged communication equipment and instructs the nearest electric vehicle to take emergency action. The input is sensor data from the damaged communication equipment, and the output is emergency action instructions for the electric vehicle. These instructions are also transmitted in real time via the communication network.

[0235] Step 9:

[0236] Upon arrival at the communication equipment, the electric vehicle will use its battery to supply power and assist in restoring communication. The input is the power request of the communication equipment, and the output is the power supply status of the communication equipment. The electric vehicle is equipped with a battery management system to ensure appropriate power supply.

[0237] Thus, the system of the present invention can smoothly integrate the collection and processing of various data, the prediction of disaster risks, the simulation of optimal placement, real-time instructions, and emergency response, enabling a rapid and appropriate disaster response.

[0238] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0239] This invention aims to maintain communication infrastructure and enable rapid response during disasters, and further improves system usability by taking into account the emotional state of the user. Specific embodiments of this system are described below.

[0240] System Configuration

[0241] This system consists primarily of the following elements:

[0242] 1. Server: Responsible for data collection, disaster prediction using AI models, and overall system management.

[0243] 2. Terminal (electric company vehicle): Equipped with a power supply function, it moves and supplies power based on instructions from the server.

[0244] 3. User: Operate and monitor the system, and intervene as needed.

[0245] 4. Emotion Engine: Recognizes the user's emotional state, and system operations and instructions are adapted according to the user's emotions.

[0246] System Operation Overview

[0247] The operation of this system can be broadly classified into the following four stages.

[0248] 1. Disaster prediction using data collection and AI models

[0249] The server collects data from multiple data sources, including weather forecasts, historical disaster data, and base station geographic information. This includes data from government weather data APIs and Earth observation satellites. The collected data is preprocessed and input into an AI model to predict disaster risk.

[0250] Specific example: A server retrieves weather data from a weather forecast API, and an AI model uses this data to predict that a typhoon will approach in a few days. The prediction results indicate that the disaster risk is high in a specific area.

[0251] 2. Optimal placement simulation and instructions

[0252] After the disaster risk is assessed, the server uses this information to run a simulation of the placement of electric company vehicles. It selects the electric company vehicles closest to high-risk areas and optimizes their placement. Based on the simulation results, it sends movement instructions to each electric company vehicle.

[0253] Specific example: For areas predicted to be at high disaster risk, the server runs a simulation and sends an instruction to the nearest electric company vehicle to head to that area. For example, if the risk area is City A and the nearest electric company vehicle is Company B, an instruction will be sent to Company B to head to City A.

[0254] 3. Real-time response in the event of a disaster

[0255] In the event of an actual disaster and a power outage at a base station, the server immediately collects information on the damaged base station and instructs the nearest electric vehicle to provide emergency assistance. Upon arrival at the base station, the terminal (electric vehicle) uses its battery to supply power to the base station and assist in restoring communication.

[0256] Specific example: If a disaster causes a power outage at a base station in City C, the server issues an emergency instruction to the nearest electric company vehicle D to proceed. When company vehicle D arrives at the base station, it uses its battery to supply power to the base station, restarting the communication equipment and restoring communication.

[0257] 4. User support using an emotion engine

[0258] The emotion engine recognizes the user's emotional state in real time and adjusts the system's operation and instructions based on the results. The emotion engine uses speech recognition and facial recognition technology to evaluate the user's emotional state and adjusts the format of notifications and alerts if the user is experiencing stress or anxiety.

[0259] Specific example: If a user is experiencing stress during disaster response, the server uses data from the emotion engine to reduce the frequency of notifications and instructions. It also implements operational adjustments, such as providing detailed situational explanations to help the user feel more secure.

[0260] User roles

[0261] The user plays a role in monitoring the overall situation while the server performs complex data analysis and issues instructions. They are also responsible for manual intervention in the event of unforeseen circumstances and for system maintenance. Furthermore, they act based on system suggestions regarding how to respond to users whose emotions have been recognized by the emotion engine.

[0262] Specific examples: Users review the disaster prediction results generated by the system and make manual corrections as needed. They also take action such as preparing spare batteries if the electric company vehicle's battery level is low. If the emotional engine determines that the user's stress level is high, it flexibly adjusts operations and instructions.

[0263] As described above, the present invention not only enables efficient and rapid maintenance of communication infrastructure during disasters, but also realizes system operation that takes into account the emotional state of users. This makes it possible to minimize communication disruptions and reduce the burden on users.

[0264] The following describes the processing flow.

[0265] Program processing steps

[0266] 1. Disaster prediction using data collection and AI models

[0267] Step 1:

[0268] The server collects weather forecast data, historical disaster data, and base station geographic information from multiple data sources. Specifically, it obtains government weather information and data from Earth observation satellites via APIs.

[0269] Step 2:

[0270] The server preprocesses the collected data. Specifically, it performs data imputation, removal of outliers, and data standardization. This preprocessing improves the accuracy of the analysis.

[0271] Step 3:

[0272] The server inputs pre-processed data into an AI model to predict disaster risk. For example, it uses machine learning algorithms based on historical data to quantify future disaster risk.

[0273] Step 4:

[0274] The server calculates the disaster risk score for each base station from the prediction results. This risk score is calculated based on the scale of the disaster, the occurrence date, the affected area, etc.

[0275] 2. Optimal Placement Simulation and Instructions

[0276] Step 5:

[0277] The server evaluates the risk level of each base station based on the disaster risk score. It classifies high-risk areas and low-risk areas and identifies the base stations that require attention.

[0278] Step 6:

[0279] Based on the risk assessment results, the server uses the current location information of the electric company vehicles to simulate the optimal placement. Using the optimal placement algorithm, it selects the electric company vehicle closest to the high-risk area.

[0280] Step 7:

[0281] Based on the simulation results, the server sends specific movement instructions to the electric company vehicles. These instructions include the movement route and the destination.

[0282] Step 8:

[0283] The terminal (electric company vehicle) receives the movement instructions from the server and starts moving towards the destination. It periodically reports its location information and remaining battery level to the server during the movement.

[0284] 3. Real-time Response during Disaster

[0285] Step 9:

[0286] When a disaster occurs and a base station loses power, the server immediately monitors the power outage information to identify the affected base stations.

[0287] Step 10:

[0288] Based on the power outage information, the server sends emergency response instructions to the nearest electric vehicle. These instructions include promptly heading to a designated base station.

[0289] Step 11:

[0290] The terminal (electric company vehicle) receives the emergency instruction and immediately proceeds to the designated base station. Upon arrival, it prepares to supply power to the base station.

[0291] Step 12:

[0292] The terminal (electric company vehicle) uses its battery to supply power to the base station and restart the communication equipment. It periodically reports the status to the server at the start of supply and during the process.

[0293] 4. User support using an emotion engine

[0294] Step 13:

[0295] The emotion engine uses speech recognition and facial recognition technology to evaluate the user's emotional state in real time. It analyzes the data to detect the user's stress level and emotional state.

[0296] Step 14:

[0297] The server adjusts user actions and instructions based on emotional data obtained from the emotion engine. For example, if a user is experiencing high stress levels, the server may reduce the frequency of notifications.

[0298] Step 15:

[0299] Based on the emotion engine's evaluation results, the user accepts suggestions and instructions from the system. Manual corrections and adjustments are made as needed.

[0300] Step 16:

[0301] The emotion engine continuously monitors the user's emotional state and checks whether the system operations and instructions are appropriately responsive to the user's emotions.

[0302] Through the above steps, this system can maintain the communication infrastructure during disasters and respond quickly, and can also perform operations considering the user's emotional state. Thereby, communication disruptions during disasters can be minimized, and the burden on users can be reduced.

[0303] (Embodiment 2)

[0304] Next, Embodiment 2 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart device 14 is referred to as the "terminal".

[0305] The problem to be solved by the present invention is to quickly and efficiently maintain the communication infrastructure during disasters and improve the operability of the system considering the user's emotional state. Specifically, when the communication facilities lose power supply due to disasters, it aims to respond promptly, restore communication, and provide an optimal operating environment for users even in emergency situations.

[0306] The specific processing by the specific processing unit 290 of the data processing device 12 in Embodiment 2 is realized by the following means.

[0307] In this invention, the server includes: means for collecting meteorological data, past disaster occurrence data, and geographical information of communication facilities from a plurality of data sources; means for preprocessing the collected data and predicting the disaster occurrence risk using a machine learning algorithm; means for simulating the optimal placement of movable power supply devices based on the disaster risk assessment. Thereby, [quick maintenance and recovery of the communication infrastructure during disasters and provision of an operating environment considering the user's emotional state] becomes possible.

[0308] "Data source" refers to the sources of information that a server collects for disaster risk assessment and simulation, such as weather data, past disaster occurrence data, and geographical information of communication facilities.

[0309] "Preprocessing" refers to preparatory work performed before data analysis, such as imputing missing values ​​in collected data, filtering outliers, and normalizing the data.

[0310] A "machine learning algorithm" refers to a mathematical model or statistical method used to predict disaster risk based on collected and pre-processed data.

[0311] "Disaster risk" refers to an indicator that shows the degree to which a disaster is likely to occur in a particular area or at a specific time.

[0312] A "mobile power supply device" refers to electric vehicles or other mobile power supply means that can be moved to supply power to communication equipment during a disaster.

[0313] "Simulation" refers to the process of predicting the optimal placement of movable power supply equipment using a computational model based on disaster risk assessment.

[0314] "Emotional state" refers to an indicator that shows the user's psychological state, such as stress and anxiety.

[0315] The term "emotion engine" refers to a function that uses speech recognition and facial recognition technology to recognize the user's emotional state in real time and adjusts system operations and instructions accordingly.

[0316] This invention aims to maintain communication infrastructure and enable rapid response during disasters, and further improves system usability by taking into account the emotional state of the user. The specific operation and hardware and software used in embodiments of this invention will be described below.

[0317] Hardware and software to be used

[0318] This system primarily uses the following hardware and software.

[0319] 1. Server:

[0320] - Equipped with a high-performance CPU and large-capacity memory.

[0321] - Database management systems (such as MySQL (registered trademark) and PostgreSQL)

[0322] - Machine learning algorithms (such as TensorFlow and PyTorch)

[0323] - API access function

[0324] 2. Terminal (electric company vehicle):

[0325] - GPS module

[0326] - High-capacity battery

[0327] - Wireless communication capabilities (Wi-Fi, 4G / 5G, etc.)

[0328] 3. User:

[0329] - Computer or tablet device for monitoring

[0330] - Camera for voice recognition and facial recognition

[0331] 4. Emotional Engine:

[0332] - Voice analysis software (such as Google® Speech-to-Text)

[0333] - Face recognition software (such as OpenCV or Face++)

[0334] Data collection and processing

[0335] The server collects necessary data from multiple data sources. For example, weather data is obtained from the government's weather data API, and historical disaster occurrence data is collected from Earth observation satellite data. Similarly, geographical information of communication facilities is also obtained. This data is retrieved using API requests and stored on the server in JSON format.

[0336] Data preprocessing and machine learning

[0337] The collected data is preprocessed on the server. This includes imputing missing values, filtering outliers, and normalization. The preprocessed data is then used to predict disaster risk using machine learning algorithms. The algorithms used here are common machine learning frameworks such as TensorFlow and PyTorch.

[0338] Optimal placement simulation

[0339] Once the disaster risk assessment is complete, the server simulates the optimal deployment of electric company vehicles in high-risk areas. This simulation takes into account the current location, battery level, and mobility of the electric company vehicles. Once the optimal deployment is determined, the server sends specific movement instructions to each electric company vehicle.

[0340] Movement instructions and real-time response

[0341] Based on instructions sent from the server, the terminal (electric company vehicle) moves to the designated area. In the event of a disaster and a power outage to communication equipment, the server immediately collects information on the damaged communication equipment and issues emergency response instructions to the nearest electric company vehicle. Once the electric company vehicle arrives at the scene, it uses its high-capacity battery to supply power to the communication equipment and support the restoration of the communication infrastructure.

[0342] Emotion recognition and system adjustment

[0343] The emotion engine uses speech and facial recognition technologies to recognize the user's emotional state in real time. Based on the data obtained from the emotion engine, the server adjusts the frequency of notifications and instructions if the user is experiencing stress or anxiety. It also provides detailed situational explanations to help the user feel more at ease.

[0344] Specific examples and prompt statements

[0345] Specific example:

[0346] The server retrieves weather data from a weather forecast API and inputs it into a machine learning algorithm to predict when a typhoon will approach in a few days. Based on this prediction, it simulates the optimal placement of electric company vehicles and sends instructions to the nearest electric company vehicle.

[0347] Examples of prompts for a generative AI model:

[0348] "Based on weather data from the weather forecast API, predict the typhoon risk for the next two days."

[0349]

[0350] "Identify the location of electric company vehicles closest to areas with a high risk of disaster, and conduct deployment simulations and issue instructions to move them to those areas."

[0351]

[0352] "Identify the electric company vehicles closest to the communication equipment affected by the disaster and power outage, and instruct them to begin supplying power as an emergency response."

[0353]

[0354] "Analyze the user's voice and facial expressions to determine if they are experiencing stress. If the user is stressed, reduce the frequency of notifications and alerts, and provide detailed, reassuring context."

[0355] As described above, the present invention enables the maintenance of communication infrastructure and rapid response during disasters, while simultaneously significantly improving the usability of the system by taking into account the emotional state of the user.

[0356] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0357] Program processing flow

[0358] Step 1: Data Collection

[0359] The server collects necessary data from multiple data sources. Inputs include government weather data APIs, Earth observation satellite data, historical disaster databases, and geographic information from communication facilities. The collected data is stored on the server in JSON format.

[0360] Specific operation: The server periodically sends API requests to retrieve weather forecast data and historical disaster data. For example, "Retrieve weather data from the weather forecast API and save the contents in JSON format."

[0361] Step 2: Data Preprocessing

[0362] The server preprocesses the collected data. The input is the raw data collected in step 1, and the output is the data converted into a format suitable for machine learning algorithms. Specifically, this involves imputing missing values, filtering outliers, and normalizing the data.

[0363] Specific operation: The server scans the data and fills in missing weather data with average values. It also filters outliers and normalizes the data.

[0364] Step 3: Disaster Risk Prediction

[0365] The server inputs pre-processed data into a machine learning algorithm to predict disaster risk. The input is pre-processed data, and the output is a prediction of disaster risk for a specific time and region.

[0366] Specific operation: The server inputs data into AI models built using TensorFlow or PyTorch. For example, "Output the probability of a typhoon or flood occurring in a specific region within the next 72 hours."

[0367] Step 4: Optimal Placement Simulation

[0368] The server simulates the optimal placement of mobile power supply units based on disaster risk predictions. The inputs are the disaster risk assessment results and the current location information of electric company vehicles, and the output is the optimal placement plan for each electric company vehicle.

[0369] Specific operation: The server identifies high-risk areas and checks the current location and battery level of the nearest electric company vehicle. It then runs a simulation to determine the optimal deployment. For example, "Check the location of electric company vehicle B, which is closest to area A, and its battery level, and then plan its deployment to area A."

[0370] Step 5: Movement Instructions

[0371] The server sends movement instructions to each electric company vehicle based on an optimal placement simulation. The input is the simulation result of the optimal placement, and the output is the specific movement instruction to each electric company vehicle.

[0372] Specific operation: The server sends a travel instruction to electric company vehicles equipped with GPS modules, such as "Proceed to area A." For example, "Instruct electric company vehicle B to move to area A."

[0373] Step 6: Real-time response

[0374] The server issues emergency response instructions to the nearest electric company vehicle in the event of a disaster and a power outage to communication equipment. Inputs include information about the power outage and the location of the electric company vehicle, while output is the emergency response instruction.

[0375] Specific operation: The server detects a power outage in the communication equipment and quickly issues an emergency instruction to the nearest electric company vehicle. For example, "If the communication equipment in area C experiences a power outage, the server will instruct the nearest electric company vehicle D to take emergency action and begin supplying power."

[0376] Step 7: Recognizing and responding to emotions

[0377] The emotion engine recognizes the user's emotional state in real time. Input is the user's voice and facial expression data, and output is notifications and instructions tailored to the emotional state.

[0378] Specific operation: The emotion engine uses speech recognition and facial recognition software to analyze the user's emotions. For example, "If the user is feeling stressed, it will reduce the frequency of notifications and provide detailed situational descriptions to provide reassurance."

[0379] As a result, the entire system enables the rapid maintenance and recovery of communication infrastructure during disasters and provides an operating environment that takes into account the emotional state of the user.

[0380] (Application Example 2)

[0381] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0382] Maintaining communication infrastructure during disasters requires speed and effectiveness. However, current systems often fail to adequately consider user stress and anxiety, resulting in increased user burden. Furthermore, real-time information transmission and power supply during disasters are not adequately achieved. A new system is needed to address these problems.

[0383] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting and processing disaster prediction data and geographic information, means for evaluating disaster risk based on the data, means for simulating the optimal placement of electric vehicles based on the disaster risk evaluation, means for instructing the movement of electric vehicles based on the simulation results, means for directing electric vehicles toward a base station to supply power when a disaster occurs, means for monitoring the user's emotional state in real time and adjusting the notification format based on the results, and means for providing user support using an emotion engine. This makes it possible to maintain communication infrastructure during a disaster while providing flexible responses according to the user's emotional state.

[0384] "Disaster prediction data" refers to information used to predict the risk of disasters, including past disaster data and weather forecast data.

[0385] "Geographic information" refers to data about the topography, population density, infrastructure layout, and other characteristics of a specific region.

[0386] "Disaster risk assessment" is the process of evaluating the likelihood of a disaster occurring based on collected disaster prediction data and geographical information.

[0387] An "electric vehicle" is a vehicle that runs on batteries, and in times of disaster, it plays a role in supplying power to communication equipment.

[0388] "Simulating the optimal placement" refers to the process of calculating the most effective way to deploy electric vehicles based on disaster risk assessments.

[0389] "Instructing movement" means issuing a command to the electric vehicle to move to a specific location based on the simulation results.

[0390] "Supplying power" means that an electric vehicle uses its own battery to provide power to external devices such as communication equipment.

[0391] "User emotional state" refers to the mental state a user is experiencing, such as stress, anxiety, or a sense of security.

[0392] "Real-time monitoring" means constantly monitoring the user's emotional state and detecting any changes immediately.

[0393] "Adjusting notification format" means appropriately changing the content and frequency of notifications according to the user's emotional state.

[0394] An "emotion engine" is software that recognizes a user's emotions and adjusts system operations and notifications based on those emotions.

[0395] This invention specifically aims to realize a system that takes into account the maintenance of communication infrastructure and the emotional state of users during disasters, and consists of the following elements. The system mainly consists of a server, a terminal (electric vehicle), a user, and an emotion engine.

[0396] System Configuration

[0397] server

[0398] The server has the following functions:

[0399] 1. Data Collection: The server collects disaster prediction data and geographical information from weather forecast APIs and historical disaster data APIs. This prepares the server for predicting the risk of disasters.

[0400] 2. Disaster Risk Assessment: Based on the collected data, a generative AI model is used to assess the risk of disaster occurrence. This assessment takes into account past disaster data and current weather forecasts.

[0401] 3. Optimal Deployment Simulation: Based on the disaster risk assessment results, the optimal deployment of electric vehicles will be simulated. The simulation will perform calculations to deploy electric vehicles in areas with a high disaster risk so that they can respond quickly.

[0402] 4. Movement Instructions: Based on simulation results, electric vehicles are instructed to move to specific areas. In the event of a disaster, electric vehicles are also instructed to head towards communication base stations to supply power.

[0403] 5. Emotion Monitoring: An emotion engine is used to monitor the user's emotional state in real time. This allows for the adjustment of notification formats to reduce user stress and anxiety.

[0404] Specific example

[0405] For example, a server retrieves weather data from a weather forecast API, and based on that data, a generated AI model assesses whether there is a high risk of a typhoon approaching in the next few days. Based on this result, the server simulates the optimal placement of electric vehicles and instructs the vehicle closest to the high-risk area to head towards that area.

[0406] Terminal (electric vehicle)

[0407] The terminal (electric vehicle) receives movement instructions from the server, moves to the designated area, and supplies power to the base station.

[0408] As a concrete example, if a base station experiences a power outage due to a disaster, the nearest electric vehicle can travel to the base station to supply power, restarting the communication equipment and restoring communication.

[0409] User

[0410] Users receive notifications from the server and take actions or instructions as needed. Additionally, an emotion engine monitors the user's emotional state, and if the user is experiencing stress or anxiety, the notification frequency is reduced and more detailed explanations of the situation are provided.

[0411] Hardware and software to be used

[0412] Hardware:

[0413] smartphone

[0414] Head-mounted display (HMD)

[0415] electric car

[0416] software:

[0417] Emotion Engine

[0418] Disaster Prediction Engine (DisasterPredictor)

[0419] Web API (weather forecast data, historical disaster data)

[0420] Example of a prompt

[0421] "You are an AI designed to design a system aimed at maintaining communication infrastructure and enabling rapid response during disasters. Define the system outline according to the following requirements."

[0422] Design an AI engine that collects weather forecast data and historical disaster data to predict disaster risk.

[0423] Design an algorithm to simulate the optimal placement of electric vehicles.

[0424] The system incorporates an emotion engine that evaluates the user's emotional state in real time and adjusts the notification format accordingly.

[0425] Please also describe in detail the specific steps, the technologies, hardware, software, and format of the notification.

[0426] The above describes the embodiments for carrying out the present invention. This system not only enables the efficient and rapid maintenance of communication infrastructure during disasters, but also allows for flexible responses that take into account the emotional state of users.

[0427] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0428] Step 1:

[0429] The server collects disaster prediction data and geographical information from a weather forecast API and a historical disaster data API. The input consists of weather forecast data and historical disaster data obtained from the APIs, which are then preprocessed. The output of this process consists of preprocessed disaster prediction data and geographical information.

[0430] Step 2:

[0431] The server uses a generated AI model based on the collected data to assess disaster risk. The input for this step is the pre-processed data obtained in step 1, and the AI ​​model performs calculations to calculate the disaster occurrence risk. The output is the disaster occurrence risk assessment result for a specific area.

[0432] Step 3:

[0433] The server simulates the optimal placement of electric vehicles based on the disaster risk assessment results. The input for this step is the disaster risk assessment results obtained in step 2, and the calculations are performed by the placement simulation software. This outputs the optimal placement plan for electric vehicles.

[0434] Step 4:

[0435] The server sends movement instructions to the electric vehicle based on the simulation results. The input for this step is the placement plan obtained in step 3, a movement instruction is generated, and it is sent to the electric vehicle. The output is the movement instruction received by the electric vehicle.

[0436] Step 5:

[0437] In the event of a disaster, a terminal (electric vehicle) will proceed to a communication base station according to instructions from the server and supply power. The input for this step is an emergency instruction from the server, and the specific action involves the electric vehicle moving, connecting the power supply device upon arrival at the base station, and supplying power to the communication equipment. The output is the restoration of communication at the base station.

[0438] Step 6:

[0439] The server uses an emotion engine to monitor the user's emotional state in real time. The input for this step is the user's voice data and facial expression data, which the emotion engine analyzes to evaluate the user's emotional state. The output is the user's emotional state (e.g., stress level).

[0440] Step 7:

[0441] The server adjusts the notification format based on the user's emotional state, as assessed by the emotion engine. The input for this step is the emotional state data obtained in step 6, and the notification format is adjusted accordingly. Specifically, this involves reducing the frequency of notifications or displaying more detailed situational descriptions to alleviate user stress. The output is the adjusted notification format.

[0442] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0443] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0444] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0445] [Second Embodiment]

[0446] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0447] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0448] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0449] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0450] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0451] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0452] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0453] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0454] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0455] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0456] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0457] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0458] This invention is a system aimed at maintaining communication infrastructure and enabling rapid response during disasters. Specific embodiments of this system are described below.

[0459] System Configuration

[0460] This system consists primarily of the following elements:

[0461] 1. Server: Responsible for data collection, disaster prediction using AI models, and overall system management.

[0462] 2. Terminal (electric company vehicle): Equipped with a power supply function, it moves and supplies power based on instructions from the server.

[0463] 3. User: Operate and monitor the system, and intervene as needed.

[0464] System Operation Overview

[0465] The operation of this system can be broadly classified into the following three stages.

[0466] 1. Disaster prediction using data collection and AI models

[0467] The server collects data from various directories, including weather data, geographic information, and disaster prevention information. This data is preprocessed and input into an AI model to predict the risk of disaster occurrence. In particular, it combines past disaster data with current weather forecast data to predict the scale and location of potential future disasters.

[0468] Specific example: A server retrieves weather data from a weather forecast API, and an AI model uses this data to predict that a typhoon will approach in a few days. The prediction results indicate that the disaster risk is high in a specific area.

[0469] 2. Optimal placement simulation and instructions

[0470] After the disaster risk is assessed, the server uses this information to run a simulation of the placement of electric company vehicles. It selects the electric company vehicles closest to high-risk areas and optimizes their placement. Based on the simulation results, it sends movement instructions to each electric company vehicle.

[0471] Specific example: For areas predicted to be at high disaster risk, the server runs a simulation and sends an instruction to the nearest electric company vehicle to head to that area. For example, if the risk area is City A and the nearest electric company vehicle is Company B, an instruction will be sent to Company B to head to City A.

[0472] 3. Real-time response in the event of a disaster

[0473] In the event of an actual disaster and a power outage at a base station, the server immediately collects information on the damaged base station and instructs the nearest electric vehicle to provide emergency assistance. Upon arrival at the base station, the terminal (electric vehicle) uses its battery to supply power to the base station and assist in restoring communication.

[0474] Specific example: If a disaster causes a power outage at a base station in City C, the server issues an emergency instruction to the nearest electric company vehicle D to proceed. When company vehicle D arrives at the base station, it uses its battery to supply power to the base station, restarting the communication equipment and restoring communication.

[0475] User roles

[0476] The user's role is to monitor the overall situation while the server performs complex data analysis and issues instructions. They are also responsible for manual intervention and system maintenance in the event of unforeseen circumstances.

[0477] Specific example: The user reviews the disaster prediction results generated by the system and makes manual corrections as needed. They also take measures such as preparing spare batteries if the battery level of the electric company vehicle is low.

[0478] This invention enables efficient and rapid maintenance of communication infrastructure during disasters, thereby minimizing communication disruptions. Furthermore, by making maximum use of existing equipment, it avoids the need for additional large-scale investments.

[0479] The following describes the processing flow.

[0480] Program processing steps

[0481] 1. Disaster prediction using data collection and AI models

[0482] Step 1:

[0483] The server collects weather forecast data, historical disaster data, and base station geographic information from multiple data sources. This includes government weather data APIs and data from Earth observation satellites.

[0484] Step 2:

[0485] The server preprocesses the collected data. Specifically, it imputes missing values, removes outliers, and standardizes the data. This ensures data consistency and quality.

[0486] Step 3:

[0487] The server inputs pre-processed data into an AI model to predict disaster risk. For example, it uses machine learning algorithms to assess future disaster risk based on past disaster patterns.

[0488] Step 4:

[0489] Based on the prediction results, the server calculates a disaster risk score for each base station. This is a detailed assessment that includes the scale of the disaster, the date of occurrence, and the scope of impact.

[0490] 2. Optimal placement simulation and instructions

[0491] Step 5:

[0492] The server assesses which base stations are most vulnerable based on their disaster risk scores. Base stations are then categorized according to their risk level.

[0493] Step 6:

[0494] The server simulates the optimal vehicle deployment based on the risk assessment results and the current location information of electric company vehicles. This simulation uses an optimization algorithm to select the electric company vehicle closest to each base station.

[0495] Step 7:

[0496] Based on the simulation results, the server sends movement instructions to each electric company vehicle. Instructions are generated that include a specific travel route and destination.

[0497] Step 8:

[0498] The terminal (electric company vehicle) receives instructions from the server and begins moving towards its destination based on that information. It periodically sends its location and battery level to the server during its journey.

[0499] 3. Real-time response in the event of a disaster

[0500] Step 9:

[0501] If a disaster actually occurs and an anomaly such as a power outage is detected, the server will immediately monitor the status of base stations and identify any base stations that have stopped working.

[0502] Step 10:

[0503] The server sends emergency response instructions to the nearest electric company vehicle. These instructions include procedures for rapid movement and power supply.

[0504] Step 11:

[0505] The terminal (electric company vehicle) receives an emergency instruction and immediately heads to the designated base station. Upon arrival, the EV vehicle prepares to supply power to the base station using its battery.

[0506] Step 12:

[0507] The terminal (electric company vehicle) supplies power to the base station and restarts the communication equipment. During this process, it reports the battery level and supply status to the server.

[0508] Step 13:

[0509] The user monitors the response status during a disaster and makes manual adjustments or instructions as needed. For example, they might take measures such as having additional electric company vehicles on standby.

[0510] Through the steps described above, this system can maintain communication infrastructure and enable a rapid response during disasters.

[0511] (Example 1)

[0512] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0513] In disaster situations where maintaining communication infrastructure and responding quickly are crucial, conventional methods make it difficult to supply power to base stations quickly, leading to prolonged communication disruptions. Therefore, a system is needed to efficiently and rapidly predict disasters, optimally deploy and relocate power supply equipment, and ensure the maintenance of communication infrastructure.

[0514] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0515] In this invention, the server includes means for collecting and preprocessing weather data, geographic information, and disaster prevention information; means for predicting disaster risk using an AI model generated based on the collected data; means for simulating the optimal placement of movable power supply devices based on the disaster risk prediction; means for instructing the movement of the movable power supply devices based on the simulation results; and means for directing the movable power supply devices toward communication devices to supply power in the event of a disaster. This enables the rapid and efficient maintenance of communication infrastructure even in the event of a disaster.

[0516] "Meteorological data" refers to information related to atmospheric conditions, including data such as temperature, humidity, precipitation, wind speed, and wind direction.

[0517] "Geographic information" refers to data that represents the geographical characteristics of a specific region, such as its topography, geology, land use, and population distribution.

[0518] "Disaster prevention information" refers to information about the occurrence and impact of disasters, and includes data such as evacuation sites, evacuation routes, and safety assessments.

[0519] "Preprocessing" refers to the process of organizing and correcting data before data analysis or model input, and includes processes such as imputing missing values, correcting outliers, and normalizing data.

[0520] A "generative AI model" is a model built using machine learning and deep learning techniques, and is a set of algorithms used to perform a specific task (in this case, disaster prediction).

[0521] "Disaster risk" refers to numerical values ​​or indicators used to assess the likelihood of a natural disaster occurring and the extent of the resulting damage.

[0522] A "portable power supply device" is a device that is mobile for supplying electricity, such as a battery pack or generator mounted on a car or drone.

[0523] "Simulation" is a technique for virtually reproducing real-world actions and behaviors on a computer model, and includes using computer simulations to explore optimal placements and actions.

[0524] "Communication equipment" refers to devices used for sending and receiving data, specifically including base stations and routers.

[0525] System Overview

[0526] This invention is a system aimed at maintaining communication infrastructure and enabling rapid response during disasters, and consists of a server, a terminal (a portable power supply device), and a user. The roles of each component are described in detail below.

[0527] Server Role

[0528] 1. Data Collection

[0529] The server periodically collects weather data, geographic information, disaster prevention information, and other data from various APIs and sensors. The main software used is Python, and data collection utilizes the OpenWeatherMap API and the Geospatial Information Authority of Japan's API.

[0530] 2. Data preprocessing

[0531] The server preprocesses the collected data. This preprocessing uses libraries such as Python's Pandas library, specifically performing tasks such as imputing missing values, normalizing the data, and correcting outliers.

[0532] 3. Disaster prediction

[0533] The server inputs pre-processed data into a generating AI model (using TensorFlow) to predict disaster risk. The AI ​​model combines historical disaster data with current weather forecast data to predict the scale and location of potential future disasters.

[0534] Specific example:

[0535] The server retrieves weather data from a weather forecast API (OpenWeatherMap API), and a TensorFlow model uses this data to predict that a typhoon will approach in a few days. The prediction results indicate that the risk of disaster in a specific area is high.

[0536] 4. Placement Simulation

[0537] The server simulates the optimal placement of portable power supply units based on disaster risk. The simulation is performed using the Python SimPy library.

[0538] Specific example:

[0539] For areas predicted to be at high disaster risk, the server uses SimPy to perform simulations and identify the nearest mobile power supply unit. For example, if the risk area is City A and the nearest power supply unit is unit B, an instruction is sent to unit B to move towards City A.

[0540] 5. Movement instructions

[0541] Based on the simulation results, the server sends movement instructions to the movable power supply unit. A 5G network is used for communication.

[0542] Specific example:

[0543] The server sends a 5G communication instruction to the nearest mobile power supply device to move to City A, and the device begins moving according to the received instruction.

[0544] 6. Real-time support

[0545] In the event of a disaster, the server immediately collects information on damaged communication equipment and instructs the nearest mobile power supply unit to take emergency action.

[0546] Specific example:

[0547] If a disaster actually occurs in City X and the communication equipment experiences a power outage, the server will send an emergency instruction to the nearest power supply unit. Once the power supply unit arrives, it will use its battery to power the communication equipment and restore communication.

[0548] Terminal role

[0549] 1. Power supply

[0550] The terminal (a portable power supply device) moves to a specific area and supplies power according to instructions from the server. The device is equipped with a LiDAR sensor and GPS, which allows it to accurately reach the disaster area.

[0551] Specific example:

[0552] The terminal receives instructions from the server, moves to the designated communication device, and uses its battery to receive power.

[0553] User roles

[0554] 1. System monitoring and maintenance

[0555] The user monitors the complex data analysis and instruction issuing performed by the server, and intervenes manually when necessary. They are also responsible for the overall system maintenance.

[0556] Specific example:

[0557] Users review the disaster prediction results generated using the system's GUI and make manual corrections as needed. Additionally, if the battery level of the electric company vehicle (mobile power supply unit) is low, a spare battery is prepared and replaced.

[0558] Example of a prompt

[0559] An example of a prompt to input into a generative AI model is as follows:

[0560] "Use current weather data and historical disaster data to predict potential disasters that may occur in the next week."

[0561] This system provides a key mechanism for quickly and efficiently maintaining communication infrastructure even during disasters, minimizing communication disruptions. Furthermore, by making maximum use of existing equipment, it avoids the need for additional large-scale investments.

[0562] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0563] Step 1: Data Collection

[0564] Processing flow: The server collects weather data, geographic information, and disaster prevention information from various APIs and sensors.

[0565] Specific operation: The server sends requests to the OpenWeatherMap API and the Geospatial Information Authority of Japan API to obtain real-time weather data and geographic information in JSON format, and stores this data in an internal database.

[0566] Input: Weather data and geographic information triggered by requests from the API.

[0567] Output: Meteorological data and geographic information as raw data requiring preprocessing.

[0568] Step 2: Data Preprocessing

[0569] Processing flow: The server prepares the collected data into an applicable format.

[0570] Specific operation: The server uses the Python Pandas library to impute missing data, correct outliers, and normalize the data.

[0571] Input: Collected raw data

[0572] Output: Preprocessed, clean dataset

[0573] Step 3: Disaster Prediction

[0574] Processing flow: The server inputs pre-processed data into an AI model to predict disaster risk.

[0575] Specific operation: The server utilizes TensorFlow to run an AI model using pre-processed data as input, and derives a disaster risk score.

[0576] Input: Preprocessed dataset

[0577] Output: Disaster risk score for each region

[0578] Step 4: Placement Simulation

[0579] Processing flow: The server simulates the optimal placement of movable power supply units based on the disaster risk score.

[0580] Specific operation: The server uses the Python SimPy library to calculate the optimal placement and determine the movement path and placement location.

[0581] Input: Disaster risk score and current power supply location data

[0582] Output: Optimal placement information and movement paths

[0583] Step 5: Movement Instructions

[0584] Processing flow: Based on the simulation results, the server sends instructions to the portable power supply unit.

[0585] Specific operation: The server generates movement instructions and sends them to each device via the 5G network.

[0586] Input: Optimal placement information and travel path

[0587] Output: Movement Instructions

[0588] Step 6: Real-time response

[0589] Processing flow: When a disaster occurs, the server collects information on damaged communication equipment and takes necessary emergency action.

[0590] Specific operation: The server acquires situation reports from the disaster area in real time and issues an emergency relocation instruction to the nearest power supply unit. Upon arrival of the unit, it uses its battery to supply power and restore communication.

[0591] Input: Status data of communication devices during a disaster, current location information

[0592] Output: Emergency evacuation order and power supply order

[0593] Step 7: System Monitoring and Maintenance

[0594] Processing flow: The user monitors the overall status of the system and intervenes and performs maintenance as needed.

[0595] Specific actions: The user monitors the system via a GUI and performs manual corrective operations if an anomaly is detected. They also check the battery level of electric company vehicles and prepare a spare battery if necessary.

[0596] Input: Monitoring data and anomaly alerts from the system.

[0597] Output: Correction operation and maintenance instructions

[0598] (Application Example 1)

[0599] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0600] The need for rapid response and maintenance of communication infrastructure during disasters is increasing, with power supply to communication equipment being particularly important. However, conventional systems have shortcomings in collecting and processing disaster prediction data, making it difficult to optimize the deployment of electric vehicles or receive user instructions in real time. This makes it difficult to respond quickly in the event of a communication failure, and therefore needs to be resolved.

[0601] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0602] In this invention, the server includes means for collecting and processing disaster prediction data and geographic information; means for evaluating disaster risk based on the data; means for simulating the optimal placement of electric vehicles based on the disaster risk evaluation; means for instructing the movement of electric vehicles based on the simulation results; means for directing electric vehicles toward communication equipment and supplying power in the event of a disaster; means for acquiring disaster prediction data in real time using a smart device and notifying the user; and means for the user to send instructions directly to the electric vehicles from a smart device. This enables the maintenance of communication infrastructure and rapid response in real time even during a disaster.

[0603] "Disaster prediction data" refers to data collected to predict the occurrence of disasters, such as weather data, geographical information, and disaster prevention information.

[0604] "Geographic information" refers to geographical data relating to a specific region or location, and includes map information and topographic data.

[0605] "Disaster risk assessment" is the process of analyzing and determining the level of disaster risk a particular region or piece of equipment is exposed to, based on collected disaster prediction data.

[0606] An "electric vehicle" is a vehicle that operates electrically to provide power and transportation during a disaster.

[0607] "Optimal placement simulation" refers to conducting simulations to determine the most effective placement of electric vehicles based on disaster risk assessment results.

[0608] "Movement instruction" refers to the action of instructing an electric vehicle to move to a specific location based on the results of an optimal placement simulation.

[0609] "Communication equipment" refers to the equipment that makes up the communication infrastructure, and includes base stations, relay stations, and so on.

[0610] "Power supply" refers to the act of providing the necessary electricity to communication equipment.

[0611] A "smart device" is a portable information terminal with advanced processing and communication capabilities, such as a smartphone or tablet.

[0612] "Real-time acquisition" means instantly obtaining the latest data and information at the present time.

[0613] "Notification" refers to the act of conveying important information or warnings to a user.

[0614] "Instructions" refer to commanding someone to perform a specific action or movement.

[0615] This invention is a system aimed at maintaining communication infrastructure and enabling rapid response during disasters. Specific embodiments of this system are described below.

[0616] System Configuration

[0617] This system consists primarily of the following elements:

[0618] 1. Server: Responsible for data collection, disaster prediction using AI models, and overall system management.

[0619] 2. Electric vehicles: These vehicles have a power supply function and move and supply power based on instructions from the server.

[0620] 3. User: Operate and monitor the system, and intervene as needed. Also, use smart devices to acquire data in real time, provide notifications, and issue instructions.

[0621] System Operation Overview

[0622] The operation of this system can be broadly classified into the following three stages.

[0623] 1. Disaster prediction using data collection and AI models

[0624] The server collects data from various directories, including weather data, geographic information, and disaster prevention information. This data is preprocessed and input into an AI model to predict the risk of disaster occurrence. In particular, it combines past disaster data with current weather forecast data to predict the scale and location of potential future disasters.

[0625] Specific example: A server retrieves weather data from a weather forecast API, and an AI model uses this data to predict that a typhoon will approach in a few days. The prediction results indicate that the disaster risk in a specific area is high. This information is then communicated to the user via a smart device, prompting them to prepare for the eventuality.

[0626] 2. Optimal placement simulation and instructions

[0627] After the disaster risk is assessed, the server performs a simulation of electric vehicle deployment based on that assessment. It selects the electric vehicles closest to high-risk areas and optimizes their deployment. Based on the simulation results, it sends movement instructions to each electric vehicle.

[0628] Specific example: In areas predicted to be at high disaster risk, the server runs a simulation and instructs the nearest electric vehicle to head towards that area. For example, if the risk area is City A and the nearest electric vehicle is Vehicle B, Vehicle B will be instructed to head towards City A. This instruction is also notified to the user in real time via a smart device.

[0629] 3. Real-time response in the event of a disaster

[0630] In the event of an actual disaster and a power outage to communication equipment, the server will immediately collect information on the damaged equipment and instruct the nearest electric vehicle to respond to the emergency. Upon arrival at the communication equipment, the electric vehicle will use its battery to supply power to the equipment and assist in restoring communication.

[0631] Specific example: If a disaster causes a power outage to the communication equipment in City C, the server issues an emergency instruction to the nearest electric vehicle. When the electric vehicle arrives at the communication equipment, it uses its battery to supply power to the equipment, restarting the communication devices and restoring communication. This entire process is also reported to the user in real time via a smart device.

[0632] Main technologies used

[0633] Server: Performs data collection, disaster prediction using AI models, optimal placement simulations, and instructions. Programming languages ​​such as Python and Java, and AI frameworks such as TensorFlow and PyTorch are used.

[0634] Electric vehicles: These vehicles supply power to communication equipment and provide transportation. They are equipped with GPS and battery management systems.

[0635] Smart devices: Acquire real-time data, provide user notifications, and give instructions. Dedicated applications are developed to run on iOS and Android.

[0636] Examples of prompts for generative AI models

[0637] "Create a prompt message to determine the optimal placement of electric vehicles when the risk of typhoons in Tokyo increases."

[0638] Thus, the present invention provides a system that enables the maintenance of communication infrastructure in real time and rapid response even during disasters.

[0639] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0640] Step 1:

[0641] The server collects data such as weather data, geographic information, and disaster prevention information from various directories and APIs. Input requires various API keys and database connection information, and output is the collected raw data. Data collection is performed periodically and stored in a database to maintain the latest information.

[0642] Step 2:

[0643] The server preprocesses the collected data. This involves imputing missing values, normalizing the data, and removing inconsistent data. The input is the collected raw data, and the output is the clean data after preprocessing. This preprocessing step uses Python's Pandas library or similar tools to clean the data.

[0644] Step 3:

[0645] The server inputs pre-processed data into an AI model to predict disaster risk. The input is clean data, and the output is an assessment of disaster risk. Here, an AI framework such as TensorFlow or PyTorch is used to create a model that combines historical disaster data with current weather data.

[0646] Step 4:

[0647] The server simulates the optimal placement of electric vehicles based on disaster risk assessment results. The inputs are the disaster risk assessment results and the current location information of the electric vehicles, and the output is the optimal placement plan for the electric vehicles. This simulation utilizes pathfinding techniques such as the Dijkstra algorithm and the A algorithm.

[0648] Step 5:

[0649] The server sends movement instructions to the electric vehicles based on the simulation results. The input is the optimal placement plan, and the output is the actual position information of the electric vehicles after the movement instructions are given. These instructions are transmitted in real time via the communication network.

[0650] Step 6:

[0651] The server uses smart devices to notify users of disaster prediction data in real time. The input is the disaster risk assessment result, and the output is a disaster risk notification displayed on the user's smart device. This notification is sent to the user via push notification or SMS.

[0652] Step 7:

[0653] Users can send instructions directly to electric vehicles from their smart devices. Input is user-generated information, and output is the instructions sent to the electric vehicle. This functionality is provided through a dedicated application.

[0654] Step 8:

[0655] In the event of a disaster, the server collects information on damaged communication equipment and instructs the nearest electric vehicle to take emergency action. The input is sensor data from the damaged communication equipment, and the output is emergency action instructions for the electric vehicle. These instructions are also transmitted in real time via the communication network.

[0656] Step 9:

[0657] Upon arrival at the communication equipment, the electric vehicle will use its battery to supply power and assist in restoring communication. The input is the power request of the communication equipment, and the output is the power supply status of the communication equipment. The electric vehicle is equipped with a battery management system to ensure appropriate power supply.

[0658] Thus, the system of the present invention can smoothly integrate the collection and processing of various data, the prediction of disaster risks, the simulation of optimal placement, real-time instructions, and emergency response, enabling a rapid and appropriate disaster response.

[0659] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0660] This invention aims to maintain communication infrastructure and enable rapid response during disasters, and further improves system usability by taking into account the emotional state of the user. Specific embodiments of this system are described below.

[0661] System Configuration

[0662] This system consists primarily of the following elements:

[0663] 1. Server: Responsible for data collection, disaster prediction using AI models, and overall system management.

[0664] 2. Terminal (electric company vehicle): Equipped with a power supply function, it moves and supplies power based on instructions from the server.

[0665] 3. User: Operate and monitor the system, and intervene as needed.

[0666] 4. Emotion Engine: Recognizes the user's emotional state, and system operations and instructions are adapted according to the user's emotions.

[0667] System Operation Overview

[0668] The operation of this system can be broadly classified into the following four stages.

[0669] 1. Disaster prediction using data collection and AI models

[0670] The server collects data from multiple data sources, including weather forecasts, historical disaster data, and base station geographic information. This includes data from government weather data APIs and Earth observation satellites. The collected data is preprocessed and input into an AI model to predict disaster risk.

[0671] Specific example: A server retrieves weather data from a weather forecast API, and an AI model uses this data to predict that a typhoon will approach in a few days. The prediction results indicate that the disaster risk is high in a specific area.

[0672] 2. Optimal placement simulation and instructions

[0673] After the disaster risk is assessed, the server uses this information to run a simulation of the placement of electric company vehicles. It selects the electric company vehicles closest to high-risk areas and optimizes their placement. Based on the simulation results, it sends movement instructions to each electric company vehicle.

[0674] Specific example: For areas predicted to be at high disaster risk, the server runs a simulation and sends an instruction to the nearest electric company vehicle to head to that area. For example, if the risk area is City A and the nearest electric company vehicle is Company B, an instruction will be sent to Company B to head to City A.

[0675] 3. Real-time response in the event of a disaster

[0676] In the event of an actual disaster and a power outage at a base station, the server immediately collects information on the damaged base station and instructs the nearest electric vehicle to provide emergency assistance. Upon arrival at the base station, the terminal (electric vehicle) uses its battery to supply power to the base station and assist in restoring communication.

[0677] Specific example: If a disaster causes a power outage at a base station in City C, the server issues an emergency instruction to the nearest electric company vehicle D to proceed. When company vehicle D arrives at the base station, it uses its battery to supply power to the base station, restarting the communication equipment and restoring communication.

[0678] 4. User support using an emotion engine

[0679] The emotion engine recognizes the user's emotional state in real time and adjusts the system's operation and instructions based on the results. The emotion engine uses speech recognition and facial recognition technology to evaluate the user's emotional state and adjusts the format of notifications and alerts if the user is experiencing stress or anxiety.

[0680] Specific example: If a user is experiencing stress during disaster response, the server uses data from the emotion engine to reduce the frequency of notifications and instructions. It also implements operational adjustments, such as providing detailed situational explanations to help the user feel more secure.

[0681] User roles

[0682] The user plays a role in monitoring the overall situation while the server performs complex data analysis and issues instructions. They are also responsible for manual intervention in the event of unforeseen circumstances and for system maintenance. Furthermore, they act based on system suggestions regarding how to respond to users whose emotions have been recognized by the emotion engine.

[0683] Specific examples: Users review the disaster prediction results generated by the system and make manual corrections as needed. They also take action such as preparing spare batteries if the electric company vehicle's battery level is low. If the emotional engine determines that the user's stress level is high, it flexibly adjusts operations and instructions.

[0684] As described above, the present invention not only enables efficient and rapid maintenance of communication infrastructure during disasters, but also realizes system operation that takes into account the emotional state of users. This makes it possible to minimize communication disruptions and reduce the burden on users.

[0685] The following describes the processing flow.

[0686] Program processing steps

[0687] 1. Disaster prediction using data collection and AI models

[0688] Step 1:

[0689] The server collects weather forecast data, historical disaster data, and base station geographic information from multiple data sources. Specifically, it obtains government weather information and data from Earth observation satellites via APIs.

[0690] Step 2:

[0691] The server preprocesses the collected data. Specifically, it performs data imputation, removal of outliers, and data standardization. This preprocessing improves the accuracy of the analysis.

[0692] Step 3:

[0693] The server inputs pre-processed data into an AI model to predict disaster risk. For example, it uses machine learning algorithms based on historical data to quantify future disaster risk.

[0694] Step 4:

[0695] The server calculates a disaster risk score for each base station based on the prediction results. This risk score is calculated based on factors such as the scale of the disaster, the date of occurrence, and the scope of impact.

[0696] 2. Optimal placement simulation and instructions

[0697] Step 5:

[0698] The server assesses the risk level of each base station based on the disaster risk score. It classifies areas into high-risk and low-risk zones and identifies base stations that require attention.

[0699] Step 6:

[0700] Based on the risk assessment results, the server simulates the optimal placement using the current location information of electric company vehicles. Using an optimal placement algorithm, it selects the electric company vehicle closest to the high-risk area.

[0701] Step 7:

[0702] Based on the simulation results, the server sends specific movement instructions to the electric company vehicle. These instructions include the travel route and destination.

[0703] Step 8:

[0704] The terminal (electric company vehicle) receives movement instructions from the server and begins moving towards its destination. It periodically reports its location and battery level to the server during its journey.

[0705] 3. Real-time response in the event of a disaster

[0706] Step 9:

[0707] If a disaster occurs and a base station experiences a power outage, the server immediately monitors for power outage information and identifies the affected base stations.

[0708] Step 10:

[0709] Based on the power outage information, the server sends emergency response instructions to the nearest electric vehicle. These instructions include promptly heading to a designated base station.

[0710] Step 11:

[0711] The terminal (electric company vehicle) receives the emergency instruction and immediately proceeds to the designated base station. Upon arrival, it prepares to supply power to the base station.

[0712] Step 12:

[0713] The terminal (electric company vehicle) uses its battery to supply power to the base station and restart the communication equipment. It periodically reports the status to the server at the start of supply and during the process.

[0714] 4. User support using an emotion engine

[0715] Step 13:

[0716] The emotion engine uses speech recognition and facial recognition technology to evaluate the user's emotional state in real time. It analyzes the data to detect the user's stress level and emotional state.

[0717] Step 14:

[0718] The server adjusts user actions and instructions based on emotional data obtained from the emotion engine. For example, if a user is experiencing high stress levels, the server may reduce the frequency of notifications.

[0719] Step 15:

[0720] Based on the emotion engine's evaluation results, the user accepts suggestions and instructions from the system. Manual corrections and adjustments are made as needed.

[0721] Step 16:

[0722] The emotion engine continuously monitors the user's emotional state and verifies that the system's actions and instructions are appropriately responding to the user's emotions.

[0723] Through the steps outlined above, this system enables the maintenance of communication infrastructure and rapid response during disasters, while also allowing for operation that takes into account the user's emotional state. This minimizes communication disruptions during disasters and reduces the burden on users.

[0724] (Example 2)

[0725] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0726] The problems that this invention aims to solve are the rapid and efficient maintenance of communication infrastructure during disasters, and the improvement of system operability that takes into account the emotional state of users. Specifically, the objective is to respond quickly to the loss of power supply to communication equipment due to a disaster, restore communication, and provide users with an optimal operating environment even in emergency situations.

[0727] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0728] In this invention, the server includes means for collecting weather data, past disaster occurrence data, and geographic information of communication facilities from multiple data sources; means for preprocessing the collected data and predicting disaster risk using a machine learning algorithm; and means for simulating the optimal placement of movable power supply devices based on the disaster risk assessment. This enables the rapid maintenance and recovery of communication infrastructure during a disaster, and the provision of an operating environment that takes into account the emotional state of the user.

[0729] "Data source" refers to the sources of information that a server collects for disaster risk assessment and simulation, such as weather data, past disaster occurrence data, and geographical information of communication facilities.

[0730] "Preprocessing" refers to preparatory work performed before data analysis, such as imputing missing values ​​in collected data, filtering outliers, and normalizing the data.

[0731] A "machine learning algorithm" refers to a mathematical model or statistical method used to predict disaster risk based on collected and pre-processed data.

[0732] "Disaster risk" refers to an indicator that shows the degree to which a disaster is likely to occur in a particular area or at a specific time.

[0733] A "mobile power supply device" refers to electric vehicles or other mobile power supply means that can be moved to supply power to communication equipment during a disaster.

[0734] "Simulation" refers to the process of predicting the optimal placement of movable power supply equipment using a computational model based on disaster risk assessment.

[0735] "Emotional state" refers to an indicator that shows the user's psychological state, such as stress and anxiety.

[0736] The term "emotion engine" refers to a function that uses speech recognition and facial recognition technology to recognize the user's emotional state in real time and adjusts system operations and instructions accordingly.

[0737] This invention aims to maintain communication infrastructure and enable rapid response during disasters, and further improves system usability by taking into account the emotional state of the user. The specific operation and hardware and software used in embodiments of this invention will be described below.

[0738] Hardware and software to be used

[0739] This system primarily uses the following hardware and software.

[0740] 1. Server:

[0741] - Equipped with a high-performance CPU and large-capacity memory.

[0742] - Database management systems (such as MySQL and PostgreSQL)

[0743] - Machine learning algorithms (such as TensorFlow and PyTorch)

[0744] - API access function

[0745] 2. Terminal (electric company vehicle):

[0746] - GPS module

[0747] - High-capacity battery

[0748] - Wireless communication capabilities (Wi-Fi, 4G / 5G, etc.)

[0749] 3. User:

[0750] - Computer or tablet device for monitoring

[0751] - Camera for voice recognition and facial recognition

[0752] 4. Emotional Engine:

[0753] - Voice analysis software (such as Google Speech-to-Text)

[0754] - Face recognition software (such as OpenCV or Face++)

[0755] Data collection and processing

[0756] The server collects necessary data from multiple data sources. For example, weather data is obtained from the government's weather data API, and historical disaster occurrence data is collected from Earth observation satellite data. Similarly, geographical information of communication facilities is also obtained. This data is retrieved using API requests and stored on the server in JSON format.

[0757] Data preprocessing and machine learning

[0758] The collected data is preprocessed on the server. This includes imputing missing values, filtering outliers, and normalization. The preprocessed data is then used to predict disaster risk using machine learning algorithms. The algorithms used here are common machine learning frameworks such as TensorFlow and PyTorch.

[0759] Optimal placement simulation

[0760] Once the disaster risk assessment is complete, the server simulates the optimal deployment of electric company vehicles in high-risk areas. This simulation takes into account the current location, battery level, and mobility of the electric company vehicles. Once the optimal deployment is determined, the server sends specific movement instructions to each electric company vehicle.

[0761] Movement instructions and real-time response

[0762] Based on instructions sent from the server, the terminal (electric company vehicle) moves to the designated area. In the event of a disaster and a power outage to communication equipment, the server immediately collects information on the damaged communication equipment and issues emergency response instructions to the nearest electric company vehicle. Once the electric company vehicle arrives at the scene, it uses its high-capacity battery to supply power to the communication equipment and support the restoration of the communication infrastructure.

[0763] Emotion recognition and system adjustment

[0764] The emotion engine uses speech and facial recognition technologies to recognize the user's emotional state in real time. Based on the data obtained from the emotion engine, the server adjusts the frequency of notifications and instructions if the user is experiencing stress or anxiety. It also provides detailed situational explanations to help the user feel more at ease.

[0765] Specific examples and prompt statements

[0766] Specific example:

[0767] The server retrieves weather data from a weather forecast API and inputs it into a machine learning algorithm to predict when a typhoon will approach in a few days. Based on this prediction, it simulates the optimal placement of electric company vehicles and sends instructions to the nearest electric company vehicle.

[0768] Examples of prompts for a generative AI model:

[0769] "Based on weather data from the weather forecast API, predict the typhoon risk for the next two days."

[0770]

[0771] "Identify the location of electric company vehicles closest to areas with a high risk of disaster, and conduct deployment simulations and issue instructions to move them to those areas."

[0772]

[0773] "Identify the electric company vehicles closest to the communication equipment affected by the disaster and power outage, and instruct them to begin supplying power as an emergency response."

[0774]

[0775] "Analyze the user's voice and facial expressions to determine if they are experiencing stress. If the user is stressed, reduce the frequency of notifications and alerts, and provide detailed, reassuring context."

[0776] As described above, the present invention enables the maintenance of communication infrastructure and rapid response during disasters, while simultaneously significantly improving the usability of the system by taking into account the emotional state of the user.

[0777] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0778] Program processing flow

[0779] Step 1: Data Collection

[0780] The server collects necessary data from multiple data sources. Inputs include government weather data APIs, Earth observation satellite data, historical disaster databases, and geographic information from communication facilities. The collected data is stored on the server in JSON format.

[0781] Specific operation: The server periodically sends API requests to retrieve weather forecast data and historical disaster data. For example, "Retrieve weather data from the weather forecast API and save the contents in JSON format."

[0782] Step 2: Data Preprocessing

[0783] The server preprocesses the collected data. The input is the raw data collected in step 1, and the output is the data converted into a format suitable for machine learning algorithms. Specifically, this involves imputing missing values, filtering outliers, and normalizing the data.

[0784] Specific operation: The server scans the data and fills in missing weather data with average values. It also filters outliers and normalizes the data.

[0785] Step 3: Disaster Risk Prediction

[0786] The server inputs pre-processed data into a machine learning algorithm to predict disaster risk. The input is pre-processed data, and the output is a prediction of disaster risk for a specific time and region.

[0787] Specific operation: The server inputs data into AI models built using TensorFlow or PyTorch. For example, "Output the probability of a typhoon or flood occurring in a specific region within the next 72 hours."

[0788] Step 4: Optimal Placement Simulation

[0789] The server simulates the optimal placement of mobile power supply units based on disaster risk predictions. The inputs are the disaster risk assessment results and the current location information of electric company vehicles, and the output is the optimal placement plan for each electric company vehicle.

[0790] Specific operation: The server identifies high-risk areas and checks the current location and battery level of the nearest electric company vehicle. It then runs a simulation to determine the optimal deployment. For example, "Check the location of electric company vehicle B, which is closest to area A, and its battery level, and then plan its deployment to area A."

[0791] Step 5: Movement Instructions

[0792] The server sends movement instructions to each electric company vehicle based on an optimal placement simulation. The input is the simulation result of the optimal placement, and the output is the specific movement instruction to each electric company vehicle.

[0793] Specific operation: The server sends a travel instruction to electric company vehicles equipped with GPS modules, such as "Proceed to area A." For example, "Instruct electric company vehicle B to move to area A."

[0794] Step 6: Real-time response

[0795] The server issues emergency response instructions to the nearest electric company vehicle in the event of a disaster and a power outage to communication equipment. Inputs include information about the power outage and the location of the electric company vehicle, while output is the emergency response instruction.

[0796] Specific operation: The server detects a power outage in the communication equipment and quickly issues an emergency instruction to the nearest electric company vehicle. For example, "If the communication equipment in area C experiences a power outage, the server will instruct the nearest electric company vehicle D to take emergency action and begin supplying power."

[0797] Step 7: Recognizing and responding to emotions

[0798] The emotion engine recognizes the user's emotional state in real time. Input is the user's voice and facial expression data, and output is notifications and instructions tailored to the emotional state.

[0799] Specific operation: The emotion engine uses speech recognition and facial recognition software to analyze the user's emotions. For example, "If the user is feeling stressed, it will reduce the frequency of notifications and provide detailed situational descriptions to provide reassurance."

[0800] As a result, the entire system enables the rapid maintenance and recovery of communication infrastructure during disasters and provides an operating environment that takes into account the emotional state of the user.

[0801] (Application Example 2)

[0802] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0803] Maintaining communication infrastructure during disasters requires speed and effectiveness. However, current systems often fail to adequately consider user stress and anxiety, resulting in increased user burden. Furthermore, real-time information transmission and power supply during disasters are not adequately achieved. A new system is needed to address these problems.

[0804] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting and processing disaster prediction data and geographic information, means for evaluating disaster risk based on the data, means for simulating the optimal placement of electric vehicles based on the disaster risk evaluation, means for instructing the movement of electric vehicles based on the simulation results, means for directing electric vehicles toward a base station to supply power when a disaster occurs, means for monitoring the user's emotional state in real time and adjusting the notification format based on the results, and means for providing user support using an emotion engine. This makes it possible to maintain communication infrastructure during a disaster while providing flexible responses according to the user's emotional state.

[0805] "Disaster prediction data" refers to information used to predict the risk of disasters, including past disaster data and weather forecast data.

[0806] "Geographic information" refers to data about the topography, population density, infrastructure layout, and other characteristics of a specific region.

[0807] "Disaster risk assessment" is the process of evaluating the likelihood of a disaster occurring based on collected disaster prediction data and geographical information.

[0808] An "electric vehicle" is a vehicle that runs on batteries, and in times of disaster, it plays a role in supplying power to communication equipment.

[0809] "Simulating the optimal placement" refers to the process of calculating the most effective way to deploy electric vehicles based on disaster risk assessments.

[0810] "Instructing movement" means issuing a command to the electric vehicle to move to a specific location based on the simulation results.

[0811] "Supplying power" means that an electric vehicle uses its own battery to provide power to external devices such as communication equipment.

[0812] "User emotional state" refers to the mental state a user is experiencing, such as stress, anxiety, or a sense of security.

[0813] "Real-time monitoring" means constantly monitoring the user's emotional state and detecting any changes immediately.

[0814] "Adjusting notification format" means appropriately changing the content and frequency of notifications according to the user's emotional state.

[0815] An "emotion engine" is software that recognizes a user's emotions and adjusts system operations and notifications based on those emotions.

[0816] This invention specifically aims to realize a system that takes into account the maintenance of communication infrastructure and the emotional state of users during disasters, and consists of the following elements. The system mainly consists of a server, a terminal (electric vehicle), a user, and an emotion engine.

[0817] System Configuration

[0818] server

[0819] The server has the following functions:

[0820] 1. Data Collection: The server collects disaster prediction data and geographical information from weather forecast APIs and historical disaster data APIs. This prepares the server for predicting the risk of disasters.

[0821] 2. Disaster Risk Assessment: Based on the collected data, a generative AI model is used to assess the risk of disaster occurrence. This assessment takes into account past disaster data and current weather forecasts.

[0822] 3. Optimal Deployment Simulation: Based on the disaster risk assessment results, the optimal deployment of electric vehicles will be simulated. The simulation will perform calculations to deploy electric vehicles in areas with a high disaster risk so that they can respond quickly.

[0823] 4. Movement Instructions: Based on simulation results, electric vehicles are instructed to move to specific areas. In the event of a disaster, electric vehicles are also instructed to head towards communication base stations to supply power.

[0824] 5. Emotion Monitoring: An emotion engine is used to monitor the user's emotional state in real time. This allows for the adjustment of notification formats to reduce user stress and anxiety.

[0825] Specific example

[0826] For example, a server retrieves weather data from a weather forecast API, and based on that data, a generated AI model assesses whether there is a high risk of a typhoon approaching in the next few days. Based on this result, the server simulates the optimal placement of electric vehicles and instructs the vehicle closest to the high-risk area to head towards that area.

[0827] Terminal (electric vehicle)

[0828] The terminal (electric vehicle) receives movement instructions from the server, moves to the designated area, and supplies power to the base station.

[0829] As a concrete example, if a base station experiences a power outage due to a disaster, the nearest electric vehicle can travel to the base station to supply power, restarting the communication equipment and restoring communication.

[0830] User

[0831] Users receive notifications from the server and take actions or instructions as needed. Additionally, an emotion engine monitors the user's emotional state, and if the user is experiencing stress or anxiety, the notification frequency is reduced and more detailed explanations of the situation are provided.

[0832] Hardware and software to be used

[0833] Hardware:

[0834] smartphone

[0835] Head-mounted display (HMD)

[0836] electric car

[0837] software:

[0838] Emotion Engine

[0839] Disaster Prediction Engine (DisasterPredictor)

[0840] Web API (weather forecast data, historical disaster data)

[0841] Example of a prompt

[0842] "You are an AI designed to design a system aimed at maintaining communication infrastructure and enabling rapid response during disasters. Define the system outline according to the following requirements."

[0843] Design an AI engine that collects weather forecast data and historical disaster data to predict disaster risk.

[0844] Design an algorithm to simulate the optimal placement of electric vehicles.

[0845] The system incorporates an emotion engine that evaluates the user's emotional state in real time and adjusts the notification format accordingly.

[0846] Please also describe in detail the specific steps, the technologies, hardware, software, and format of the notification.

[0847] The above describes the embodiments for carrying out the present invention. This system not only enables the efficient and rapid maintenance of communication infrastructure during disasters, but also allows for flexible responses that take into account the emotional state of users.

[0848] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0849] Step 1:

[0850] The server collects disaster prediction data and geographical information from a weather forecast API and a historical disaster data API. The input consists of weather forecast data and historical disaster data obtained from the APIs, which are then preprocessed. The output of this process consists of preprocessed disaster prediction data and geographical information.

[0851] Step 2:

[0852] The server uses a generated AI model based on the collected data to assess disaster risk. The input for this step is the pre-processed data obtained in step 1, and the AI ​​model performs calculations to calculate the disaster occurrence risk. The output is the disaster occurrence risk assessment result for a specific area.

[0853] Step 3:

[0854] The server simulates the optimal placement of electric vehicles based on the disaster risk assessment results. The input for this step is the disaster risk assessment results obtained in step 2, and the calculations are performed by the placement simulation software. This outputs the optimal placement plan for electric vehicles.

[0855] Step 4:

[0856] The server sends movement instructions to the electric vehicle based on the simulation results. The input for this step is the placement plan obtained in step 3, a movement instruction is generated, and it is sent to the electric vehicle. The output is the movement instruction received by the electric vehicle.

[0857] Step 5:

[0858] In the event of a disaster, a terminal (electric vehicle) will proceed to a communication base station according to instructions from the server and supply power. The input for this step is an emergency instruction from the server, and the specific action involves the electric vehicle moving, connecting the power supply device upon arrival at the base station, and supplying power to the communication equipment. The output is the restoration of communication at the base station.

[0859] Step 6:

[0860] The server uses an emotion engine to monitor the user's emotional state in real time. The input for this step is the user's voice data and facial expression data, which the emotion engine analyzes to evaluate the user's emotional state. The output is the user's emotional state (e.g., stress level).

[0861] Step 7:

[0862] The server adjusts the notification format based on the user's emotional state, as assessed by the emotion engine. The input for this step is the emotional state data obtained in step 6, and the notification format is adjusted accordingly. Specifically, this involves reducing the frequency of notifications or displaying more detailed situational descriptions to alleviate user stress. The output is the adjusted notification format.

[0863] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0864] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0865] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0866] [Third Embodiment]

[0867] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0868] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0869] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0870] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0871] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0872] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0873] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0874] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0875] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0876] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0877] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0878] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0879] This invention is a system aimed at maintaining communication infrastructure and enabling rapid response during disasters. Specific embodiments of this system are described below.

[0880] System Configuration

[0881] This system consists primarily of the following elements:

[0882] 1. Server: Responsible for data collection, disaster prediction using AI models, and overall system management.

[0883] 2. Terminal (electric company vehicle): Equipped with a power supply function, it moves and supplies power based on instructions from the server.

[0884] 3. User: Operate and monitor the system, and intervene as needed.

[0885] System Operation Overview

[0886] The operation of this system can be broadly classified into the following three stages.

[0887] 1. Disaster prediction using data collection and AI models

[0888] The server collects data from various directories, including weather data, geographic information, and disaster prevention information. This data is preprocessed and input into an AI model to predict the risk of disaster occurrence. In particular, it combines past disaster data with current weather forecast data to predict the scale and location of potential future disasters.

[0889] Specific example: A server retrieves weather data from a weather forecast API, and an AI model uses this data to predict that a typhoon will approach in a few days. The prediction results indicate that the disaster risk is high in a specific area.

[0890] 2. Optimal placement simulation and instructions

[0891] After the disaster risk is assessed, the server uses this information to run a simulation of the placement of electric company vehicles. It selects the electric company vehicles closest to high-risk areas and optimizes their placement. Based on the simulation results, it sends movement instructions to each electric company vehicle.

[0892] Specific example: For areas predicted to be at high disaster risk, the server runs a simulation and sends an instruction to the nearest electric company vehicle to head to that area. For example, if the risk area is City A and the nearest electric company vehicle is Company B, an instruction will be sent to Company B to head to City A.

[0893] 3. Real-time response in the event of a disaster

[0894] In the event of an actual disaster and a power outage at a base station, the server immediately collects information on the damaged base station and instructs the nearest electric vehicle to provide emergency assistance. Upon arrival at the base station, the terminal (electric vehicle) uses its battery to supply power to the base station and assist in restoring communication.

[0895] Specific example: If a disaster causes a power outage at a base station in City C, the server issues an emergency instruction to the nearest electric company vehicle D to proceed. When company vehicle D arrives at the base station, it uses its battery to supply power to the base station, restarting the communication equipment and restoring communication.

[0896] User roles

[0897] The user's role is to monitor the overall situation while the server performs complex data analysis and issues instructions. They are also responsible for manual intervention and system maintenance in the event of unforeseen circumstances.

[0898] Specific example: The user reviews the disaster prediction results generated by the system and makes manual corrections as needed. They also take measures such as preparing spare batteries if the battery level of the electric company vehicle is low.

[0899] This invention enables efficient and rapid maintenance of communication infrastructure during disasters, thereby minimizing communication disruptions. Furthermore, by making maximum use of existing equipment, it avoids the need for additional large-scale investments.

[0900] The following describes the processing flow.

[0901] Program processing steps

[0902] 1. Disaster prediction using data collection and AI models

[0903] Step 1:

[0904] The server collects weather forecast data, historical disaster data, and base station geographic information from multiple data sources. This includes government weather data APIs and data from Earth observation satellites.

[0905] Step 2:

[0906] The server preprocesses the collected data. Specifically, it imputes missing values, removes outliers, and standardizes the data. This ensures data consistency and quality.

[0907] Step 3:

[0908] The server inputs pre-processed data into an AI model to predict disaster risk. For example, it uses machine learning algorithms to assess future disaster risk based on past disaster patterns.

[0909] Step 4:

[0910] Based on the prediction results, the server calculates a disaster risk score for each base station. This is a detailed assessment that includes the scale of the disaster, the date of occurrence, and the scope of impact.

[0911] 2. Optimal placement simulation and instructions

[0912] Step 5:

[0913] The server assesses which base stations are most vulnerable based on their disaster risk scores. Base stations are then categorized according to their risk level.

[0914] Step 6:

[0915] The server simulates the optimal vehicle deployment based on the risk assessment results and the current location information of electric company vehicles. This simulation uses an optimization algorithm to select the electric company vehicle closest to each base station.

[0916] Step 7:

[0917] Based on the simulation results, the server sends movement instructions to each electric company vehicle. Instructions are generated that include a specific travel route and destination.

[0918] Step 8:

[0919] The terminal (electric company vehicle) receives instructions from the server and begins moving towards its destination based on that information. It periodically sends its location and battery level to the server during its journey.

[0920] 3. Real-time response in the event of a disaster

[0921] Step 9:

[0922] If a disaster actually occurs and an anomaly such as a power outage is detected, the server will immediately monitor the status of base stations and identify any base stations that have stopped working.

[0923] Step 10:

[0924] The server sends emergency response instructions to the nearest electric company vehicle. These instructions include procedures for rapid movement and power supply.

[0925] Step 11:

[0926] The terminal (electric company vehicle) receives an emergency instruction and immediately heads to the designated base station. Upon arrival, the EV vehicle prepares to supply power to the base station using its battery.

[0927] Step 12:

[0928] The terminal (electric company vehicle) supplies power to the base station and restarts the communication equipment. During this process, it reports the battery level and supply status to the server.

[0929] Step 13:

[0930] The user monitors the response status during a disaster and makes manual adjustments or instructions as needed. For example, they might take measures such as having additional electric company vehicles on standby.

[0931] Through the steps described above, this system can maintain communication infrastructure and enable a rapid response during disasters.

[0932] (Example 1)

[0933] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0934] In disaster situations where maintaining communication infrastructure and responding quickly are crucial, conventional methods make it difficult to supply power to base stations quickly, leading to prolonged communication disruptions. Therefore, a system is needed to efficiently and rapidly predict disasters, optimally deploy and relocate power supply equipment, and ensure the maintenance of communication infrastructure.

[0935] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0936] In this invention, the server includes means for collecting and preprocessing weather data, geographic information, and disaster prevention information; means for predicting disaster risk using an AI model generated based on the collected data; means for simulating the optimal placement of movable power supply devices based on the disaster risk prediction; means for instructing the movement of the movable power supply devices based on the simulation results; and means for directing the movable power supply devices toward communication devices to supply power in the event of a disaster. This enables the rapid and efficient maintenance of communication infrastructure even in the event of a disaster.

[0937] "Meteorological data" refers to information related to atmospheric conditions, including data such as temperature, humidity, precipitation, wind speed, and wind direction.

[0938] "Geographic information" refers to data that represents the geographical characteristics of a specific region, such as its topography, geology, land use, and population distribution.

[0939] "Disaster prevention information" refers to information about the occurrence and impact of disasters, and includes data such as evacuation sites, evacuation routes, and safety assessments.

[0940] "Preprocessing" refers to the process of organizing and correcting data before data analysis or model input, and includes processes such as imputing missing values, correcting outliers, and normalizing data.

[0941] A "generative AI model" is a model built using machine learning and deep learning techniques, and is a set of algorithms used to perform a specific task (in this case, disaster prediction).

[0942] "Disaster risk" refers to numerical values ​​or indicators used to assess the likelihood of a natural disaster occurring and the extent of the resulting damage.

[0943] A "portable power supply device" is a device that is mobile for supplying electricity, such as a battery pack or generator mounted on a car or drone.

[0944] "Simulation" is a technique for virtually reproducing real-world actions and behaviors on a computer model, and includes using computer simulations to explore optimal placements and actions.

[0945] "Communication equipment" refers to devices used for sending and receiving data, specifically including base stations and routers.

[0946] System Overview

[0947] This invention is a system aimed at maintaining communication infrastructure and enabling rapid response during disasters, and consists of a server, a terminal (a portable power supply device), and a user. The roles of each component are described in detail below.

[0948] Server Role

[0949] 1. Data Collection

[0950] The server periodically collects weather data, geographic information, disaster prevention information, and other data from various APIs and sensors. The main software used is Python, and data collection utilizes the OpenWeatherMap API and the Geospatial Information Authority of Japan's API.

[0951] 2. Data preprocessing

[0952] The server preprocesses the collected data. This preprocessing uses libraries such as Python's Pandas library, specifically performing tasks such as imputing missing values, normalizing the data, and correcting outliers.

[0953] 3. Disaster prediction

[0954] The server inputs pre-processed data into a generating AI model (using TensorFlow) to predict disaster risk. The AI ​​model combines historical disaster data with current weather forecast data to predict the scale and location of potential future disasters.

[0955] Specific example:

[0956] The server retrieves weather data from a weather forecast API (OpenWeatherMap API), and a TensorFlow model uses this data to predict that a typhoon will approach in a few days. The prediction results indicate that the risk of disaster in a specific area is high.

[0957] 4. Placement Simulation

[0958] The server simulates the optimal placement of portable power supply units based on disaster risk. The simulation is performed using the Python SimPy library.

[0959] Specific example:

[0960] For areas predicted to be at high disaster risk, the server uses SimPy to perform simulations and identify the nearest mobile power supply unit. For example, if the risk area is City A and the nearest power supply unit is unit B, an instruction is sent to unit B to move towards City A.

[0961] 5. Movement instructions

[0962] Based on the simulation results, the server sends movement instructions to the movable power supply unit. A 5G network is used for communication.

[0963] Specific example:

[0964] The server sends a 5G communication instruction to the nearest mobile power supply device to move to City A, and the device begins moving according to the received instruction.

[0965] 6. Real-time support

[0966] In the event of a disaster, the server immediately collects information on damaged communication equipment and instructs the nearest mobile power supply unit to take emergency action.

[0967] Specific example:

[0968] If a disaster actually occurs in City X and the communication equipment experiences a power outage, the server will send an emergency instruction to the nearest power supply unit. Once the power supply unit arrives, it will use its battery to power the communication equipment and restore communication.

[0969] Terminal role

[0970] 1. Power supply

[0971] The terminal (a portable power supply device) moves to a specific area and supplies power according to instructions from the server. The device is equipped with a LiDAR sensor and GPS, which allows it to accurately reach the disaster area.

[0972] Specific example:

[0973] The terminal receives instructions from the server, moves to the designated communication device, and uses its battery to receive power.

[0974] User roles

[0975] 1. System monitoring and maintenance

[0976] The user monitors the complex data analysis and instruction issuing performed by the server, and intervenes manually when necessary. They are also responsible for the overall system maintenance.

[0977] Specific example:

[0978] Users review the disaster prediction results generated using the system's GUI and make manual corrections as needed. Additionally, if the battery level of the electric company vehicle (mobile power supply unit) is low, a spare battery is prepared and replaced.

[0979] Example of a prompt

[0980] An example of a prompt to input into a generative AI model is as follows:

[0981] "Use current weather data and historical disaster data to predict potential disasters that may occur in the next week."

[0982] This system provides a key mechanism for quickly and efficiently maintaining communication infrastructure even during disasters, minimizing communication disruptions. Furthermore, by making maximum use of existing equipment, it avoids the need for additional large-scale investments.

[0983] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0984] Step 1: Data Collection

[0985] Processing flow: The server collects weather data, geographic information, and disaster prevention information from various APIs and sensors.

[0986] Specific operation: The server sends requests to the OpenWeatherMap API and the Geospatial Information Authority of Japan API to obtain real-time weather data and geographic information in JSON format, and stores this data in an internal database.

[0987] Input: Weather data and geographic information triggered by requests from the API.

[0988] Output: Meteorological data and geographic information as raw data requiring preprocessing.

[0989] Step 2: Data Preprocessing

[0990] Processing flow: The server prepares the collected data into an applicable format.

[0991] Specific operation: The server uses the Python Pandas library to impute missing data, correct outliers, and normalize the data.

[0992] Input: Collected raw data

[0993] Output: Preprocessed, clean dataset

[0994] Step 3: Disaster Prediction

[0995] Processing flow: The server inputs pre-processed data into an AI model to predict disaster risk.

[0996] Specific operation: The server utilizes TensorFlow to run an AI model using pre-processed data as input, and derives a disaster risk score.

[0997] Input: Preprocessed dataset

[0998] Output: Disaster risk score for each region

[0999] Step 4: Placement Simulation

[1000] Processing flow: The server simulates the optimal placement of movable power supply units based on the disaster risk score.

[1001] Specific operation: The server uses the Python SimPy library to calculate the optimal placement and determine the movement path and placement location.

[1002] Input: Disaster risk score and current power supply location data

[1003] Output: Optimal placement information and movement paths

[1004] Step 5: Movement Instructions

[1005] Processing flow: Based on the simulation results, the server sends instructions to the portable power supply unit.

[1006] Specific operation: The server generates movement instructions and sends them to each device via the 5G network.

[1007] Input: Optimal placement information and travel path

[1008] Output: Movement Instructions

[1009] Step 6: Real-time response

[1010] Processing flow: When a disaster occurs, the server collects information on damaged communication equipment and takes necessary emergency action.

[1011] Specific operation: The server acquires situation reports from the disaster area in real time and issues an emergency relocation instruction to the nearest power supply unit. Upon arrival of the unit, it uses its battery to supply power and restore communication.

[1012] Input: Status data of communication devices during a disaster, current location information

[1013] Output: Emergency evacuation order and power supply order

[1014] Step 7: System Monitoring and Maintenance

[1015] Processing flow: The user monitors the overall status of the system and intervenes and performs maintenance as needed.

[1016] Specific actions: The user monitors the system via a GUI and performs manual corrective operations if an anomaly is detected. They also check the battery level of electric company vehicles and prepare a spare battery if necessary.

[1017] Input: Monitoring data and anomaly alerts from the system.

[1018] Output: Correction operation and maintenance instructions

[1019] (Application Example 1)

[1020] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1021] The need for rapid response and maintenance of communication infrastructure during disasters is increasing, with power supply to communication equipment being particularly important. However, conventional systems have shortcomings in collecting and processing disaster prediction data, making it difficult to optimize the deployment of electric vehicles or receive user instructions in real time. This makes it difficult to respond quickly in the event of a communication failure, and therefore needs to be resolved.

[1022] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1023] In this invention, the server includes means for collecting and processing disaster prediction data and geographic information; means for evaluating disaster risk based on the data; means for simulating the optimal placement of electric vehicles based on the disaster risk evaluation; means for instructing the movement of electric vehicles based on the simulation results; means for directing electric vehicles toward communication equipment and supplying power in the event of a disaster; means for acquiring disaster prediction data in real time using a smart device and notifying the user; and means for the user to send instructions directly to the electric vehicles from a smart device. This enables the maintenance of communication infrastructure and rapid response in real time even during a disaster.

[1024] "Disaster prediction data" refers to data collected to predict the occurrence of disasters, such as weather data, geographical information, and disaster prevention information.

[1025] "Geographic information" refers to geographical data relating to a specific region or location, and includes map information and topographic data.

[1026] "Disaster risk assessment" is the process of analyzing and determining the level of disaster risk a particular region or piece of equipment is exposed to, based on collected disaster prediction data.

[1027] An "electric vehicle" is a vehicle that operates electrically to provide power and transportation during a disaster.

[1028] "Optimal placement simulation" refers to conducting simulations to determine the most effective placement of electric vehicles based on disaster risk assessment results.

[1029] "Movement instruction" refers to the action of instructing an electric vehicle to move to a specific location based on the results of an optimal placement simulation.

[1030] "Communication equipment" refers to the equipment that makes up the communication infrastructure, and includes base stations, relay stations, and so on.

[1031] "Power supply" refers to the act of providing the necessary electricity to communication equipment.

[1032] A "smart device" is a portable information terminal with advanced processing and communication capabilities, such as a smartphone or tablet.

[1033] "Real-time acquisition" means instantly obtaining the latest data and information at the present time.

[1034] "Notification" refers to the act of conveying important information or warnings to a user.

[1035] "Instructions" refer to commanding someone to perform a specific action or movement.

[1036] This invention is a system aimed at maintaining communication infrastructure and enabling rapid response during disasters. Specific embodiments of this system are described below.

[1037] System Configuration

[1038] This system consists primarily of the following elements:

[1039] 1. Server: Responsible for data collection, disaster prediction using AI models, and overall system management.

[1040] 2. Electric vehicles: These vehicles have a power supply function and move and supply power based on instructions from the server.

[1041] 3. User: Operate and monitor the system, and intervene as needed. Also, use smart devices to acquire data in real time, provide notifications, and issue instructions.

[1042] System Operation Overview

[1043] The operation of this system can be broadly classified into the following three stages.

[1044] 1. Disaster prediction using data collection and AI models

[1045] The server collects data from various directories, including weather data, geographic information, and disaster prevention information. This data is preprocessed and input into an AI model to predict the risk of disaster occurrence. In particular, it combines past disaster data with current weather forecast data to predict the scale and location of potential future disasters.

[1046] Specific example: A server retrieves weather data from a weather forecast API, and an AI model uses this data to predict that a typhoon will approach in a few days. The prediction results indicate that the disaster risk in a specific area is high. This information is then communicated to the user via a smart device, prompting them to prepare for the eventuality.

[1047] 2. Optimal placement simulation and instructions

[1048] After the disaster risk is assessed, the server performs a simulation of electric vehicle deployment based on that assessment. It selects the electric vehicles closest to high-risk areas and optimizes their deployment. Based on the simulation results, it sends movement instructions to each electric vehicle.

[1049] Specific example: In areas predicted to be at high disaster risk, the server runs a simulation and instructs the nearest electric vehicle to head towards that area. For example, if the risk area is City A and the nearest electric vehicle is Vehicle B, Vehicle B will be instructed to head towards City A. This instruction is also notified to the user in real time via a smart device.

[1050] 3. Real-time response in the event of a disaster

[1051] In the event of an actual disaster and a power outage to communication equipment, the server will immediately collect information on the damaged equipment and instruct the nearest electric vehicle to respond to the emergency. Upon arrival at the communication equipment, the electric vehicle will use its battery to supply power to the equipment and assist in restoring communication.

[1052] Specific example: If a disaster causes a power outage to the communication equipment in City C, the server issues an emergency instruction to the nearest electric vehicle. When the electric vehicle arrives at the communication equipment, it uses its battery to supply power to the equipment, restarting the communication devices and restoring communication. This entire process is also reported to the user in real time via a smart device.

[1053] Main technologies used

[1054] Server: Performs data collection, disaster prediction using AI models, optimal placement simulations, and instructions. Programming languages ​​such as Python and Java, and AI frameworks such as TensorFlow and PyTorch are used.

[1055] Electric vehicles: These vehicles supply power to communication equipment and provide transportation. They are equipped with GPS and battery management systems.

[1056] Smart devices: Acquire real-time data, provide user notifications, and give instructions. Dedicated applications are developed to run on iOS and Android.

[1057] Examples of prompts for generative AI models

[1058] "Create a prompt message to determine the optimal placement of electric vehicles when the risk of typhoons in Tokyo increases."

[1059] Thus, the present invention provides a system that enables the maintenance of communication infrastructure in real time and rapid response even during disasters.

[1060] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1061] Step 1:

[1062] The server collects data such as weather data, geographic information, and disaster prevention information from various directories and APIs. Input requires various API keys and database connection information, and output is the collected raw data. Data collection is performed periodically and stored in a database to maintain the latest information.

[1063] Step 2:

[1064] The server preprocesses the collected data. This involves imputing missing values, normalizing the data, and removing inconsistent data. The input is the collected raw data, and the output is the clean data after preprocessing. This preprocessing step uses Python's Pandas library or similar tools to clean the data.

[1065] Step 3:

[1066] The server inputs pre-processed data into an AI model to predict disaster risk. The input is clean data, and the output is an assessment of disaster risk. Here, an AI framework such as TensorFlow or PyTorch is used to create a model that combines historical disaster data with current weather data.

[1067] Step 4:

[1068] The server simulates the optimal placement of electric vehicles based on disaster risk assessment results. The inputs are the disaster risk assessment results and the current location information of the electric vehicles, and the output is the optimal placement plan for the electric vehicles. This simulation utilizes pathfinding techniques such as the Dijkstra algorithm and the A algorithm.

[1069] Step 5:

[1070] The server sends movement instructions to the electric vehicles based on the simulation results. The input is the optimal placement plan, and the output is the actual position information of the electric vehicles after the movement instructions are given. These instructions are transmitted in real time via the communication network.

[1071] Step 6:

[1072] The server uses smart devices to notify users of disaster prediction data in real time. The input is the disaster risk assessment result, and the output is a disaster risk notification displayed on the user's smart device. This notification is sent to the user via push notification or SMS.

[1073] Step 7:

[1074] Users can send instructions directly to electric vehicles from their smart devices. Input is user-generated information, and output is the instructions sent to the electric vehicle. This functionality is provided through a dedicated application.

[1075] Step 8:

[1076] In the event of a disaster, the server collects information on damaged communication equipment and instructs the nearest electric vehicle to take emergency action. The input is sensor data from the damaged communication equipment, and the output is emergency action instructions for the electric vehicle. These instructions are also transmitted in real time via the communication network.

[1077] Step 9:

[1078] Upon arrival at the communication equipment, the electric vehicle will use its battery to supply power and assist in restoring communication. The input is the power request of the communication equipment, and the output is the power supply status of the communication equipment. The electric vehicle is equipped with a battery management system to ensure appropriate power supply.

[1079] Thus, the system of the present invention can smoothly integrate the collection and processing of various data, the prediction of disaster risks, the simulation of optimal placement, real-time instructions, and emergency response, enabling a rapid and appropriate disaster response.

[1080] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1081] This invention aims to maintain communication infrastructure and enable rapid response during disasters, and further improves system usability by taking into account the emotional state of the user. Specific embodiments of this system are described below.

[1082] System Configuration

[1083] This system consists primarily of the following elements:

[1084] 1. Server: Responsible for data collection, disaster prediction using AI models, and overall system management.

[1085] 2. Terminal (electric company vehicle): Equipped with a power supply function, it moves and supplies power based on instructions from the server.

[1086] 3. User: Operate and monitor the system, and intervene as needed.

[1087] 4. Emotion Engine: Recognizes the user's emotional state, and system operations and instructions are adapted according to the user's emotions.

[1088] System Operation Overview

[1089] The operation of this system can be broadly classified into the following four stages.

[1090] 1. Disaster prediction using data collection and AI models

[1091] The server collects data from multiple data sources, including weather forecasts, historical disaster data, and base station geographic information. This includes data from government weather data APIs and Earth observation satellites. The collected data is preprocessed and input into an AI model to predict disaster risk.

[1092] Specific example: A server retrieves weather data from a weather forecast API, and an AI model uses this data to predict that a typhoon will approach in a few days. The prediction results indicate that the disaster risk is high in a specific area.

[1093] 2. Optimal placement simulation and instructions

[1094] After the disaster risk is assessed, the server uses this information to run a simulation of the placement of electric company vehicles. It selects the electric company vehicles closest to high-risk areas and optimizes their placement. Based on the simulation results, it sends movement instructions to each electric company vehicle.

[1095] Specific example: For areas predicted to be at high disaster risk, the server runs a simulation and sends an instruction to the nearest electric company vehicle to head to that area. For example, if the risk area is City A and the nearest electric company vehicle is Company B, an instruction will be sent to Company B to head to City A.

[1096] 3. Real-time response in the event of a disaster

[1097] In the event of an actual disaster and a power outage at a base station, the server immediately collects information on the damaged base station and instructs the nearest electric vehicle to provide emergency assistance. Upon arrival at the base station, the terminal (electric vehicle) uses its battery to supply power to the base station and assist in restoring communication.

[1098] Specific example: If a disaster causes a power outage at a base station in City C, the server issues an emergency instruction to the nearest electric company vehicle D to proceed. When company vehicle D arrives at the base station, it uses its battery to supply power to the base station, restarting the communication equipment and restoring communication.

[1099] 4. User support using an emotion engine

[1100] The emotion engine recognizes the user's emotional state in real time and adjusts the system's operation and instructions based on the results. The emotion engine uses speech recognition and facial recognition technology to evaluate the user's emotional state and adjusts the format of notifications and alerts if the user is experiencing stress or anxiety.

[1101] Specific example: If a user is experiencing stress during disaster response, the server uses data from the emotion engine to reduce the frequency of notifications and instructions. It also implements operational adjustments, such as providing detailed situational explanations to help the user feel more secure.

[1102] User roles

[1103] The user plays a role in monitoring the overall situation while the server performs complex data analysis and issues instructions. They are also responsible for manual intervention in the event of unforeseen circumstances and for system maintenance. Furthermore, they act based on system suggestions regarding how to respond to users whose emotions have been recognized by the emotion engine.

[1104] Specific examples: Users review the disaster prediction results generated by the system and make manual corrections as needed. They also take action such as preparing spare batteries if the electric company vehicle's battery level is low. If the emotional engine determines that the user's stress level is high, it flexibly adjusts operations and instructions.

[1105] As described above, the present invention not only enables efficient and rapid maintenance of communication infrastructure during disasters, but also realizes system operation that takes into account the emotional state of users. This makes it possible to minimize communication disruptions and reduce the burden on users.

[1106] The following describes the processing flow.

[1107] Program processing steps

[1108] 1. Disaster prediction using data collection and AI models

[1109] Step 1:

[1110] The server collects weather forecast data, historical disaster data, and base station geographic information from multiple data sources. Specifically, it obtains government weather information and data from Earth observation satellites via APIs.

[1111] Step 2:

[1112] The server preprocesses the collected data. Specifically, it performs data imputation, removal of outliers, and data standardization. This preprocessing improves the accuracy of the analysis.

[1113] Step 3:

[1114] The server inputs pre-processed data into an AI model to predict disaster risk. For example, it uses machine learning algorithms based on historical data to quantify future disaster risk.

[1115] Step 4:

[1116] The server calculates a disaster risk score for each base station based on the prediction results. This risk score is calculated based on factors such as the scale of the disaster, the date of occurrence, and the scope of impact.

[1117] 2. Optimal placement simulation and instructions

[1118] Step 5:

[1119] The server assesses the risk level of each base station based on the disaster risk score. It classifies areas into high-risk and low-risk zones and identifies base stations that require attention.

[1120] Step 6:

[1121] Based on the risk assessment results, the server simulates the optimal placement using the current location information of electric company vehicles. Using an optimal placement algorithm, it selects the electric company vehicle closest to the high-risk area.

[1122] Step 7:

[1123] Based on the simulation results, the server sends specific movement instructions to the electric company vehicle. These instructions include the travel route and destination.

[1124] Step 8:

[1125] The terminal (electric company vehicle) receives movement instructions from the server and begins moving towards its destination. It periodically reports its location and battery level to the server during its journey.

[1126] 3. Real-time response in the event of a disaster

[1127] Step 9:

[1128] If a disaster occurs and a base station experiences a power outage, the server immediately monitors for power outage information and identifies the affected base stations.

[1129] Step 10:

[1130] Based on the power outage information, the server sends emergency response instructions to the nearest electric vehicle. These instructions include promptly heading to a designated base station.

[1131] Step 11:

[1132] The terminal (electric company vehicle) receives the emergency instruction and immediately proceeds to the designated base station. Upon arrival, it prepares to supply power to the base station.

[1133] Step 12:

[1134] The terminal (electric company vehicle) uses its battery to supply power to the base station and restart the communication equipment. It periodically reports the status to the server at the start of supply and during the process.

[1135] 4. User support using an emotion engine

[1136] Step 13:

[1137] The emotion engine uses speech recognition and facial recognition technology to evaluate the user's emotional state in real time. It analyzes the data to detect the user's stress level and emotional state.

[1138] Step 14:

[1139] The server adjusts user actions and instructions based on emotional data obtained from the emotion engine. For example, if a user is experiencing high stress levels, the server may reduce the frequency of notifications.

[1140] Step 15:

[1141] Based on the emotion engine's evaluation results, the user accepts suggestions and instructions from the system. Manual corrections and adjustments are made as needed.

[1142] Step 16:

[1143] The emotion engine continuously monitors the user's emotional state and verifies that the system's actions and instructions are appropriately responding to the user's emotions.

[1144] Through the steps outlined above, this system enables the maintenance of communication infrastructure and rapid response during disasters, while also allowing for operation that takes into account the user's emotional state. This minimizes communication disruptions during disasters and reduces the burden on users.

[1145] (Example 2)

[1146] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1147] The problems that this invention aims to solve are the rapid and efficient maintenance of communication infrastructure during disasters, and the improvement of system operability that takes into account the emotional state of users. Specifically, the objective is to respond quickly to the loss of power supply to communication equipment due to a disaster, restore communication, and provide users with an optimal operating environment even in emergency situations.

[1148] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1149] In this invention, the server includes means for collecting weather data, past disaster occurrence data, and geographic information of communication facilities from multiple data sources; means for preprocessing the collected data and predicting disaster risk using a machine learning algorithm; and means for simulating the optimal placement of movable power supply devices based on the disaster risk assessment. This enables the rapid maintenance and recovery of communication infrastructure during a disaster, and the provision of an operating environment that takes into account the emotional state of the user.

[1150] "Data source" refers to the sources of information that a server collects for disaster risk assessment and simulation, such as weather data, past disaster occurrence data, and geographical information of communication facilities.

[1151] "Preprocessing" refers to preparatory work performed before data analysis, such as imputing missing values ​​in collected data, filtering outliers, and normalizing the data.

[1152] A "machine learning algorithm" refers to a mathematical model or statistical method used to predict disaster risk based on collected and pre-processed data.

[1153] "Disaster risk" refers to an indicator that shows the degree to which a disaster is likely to occur in a particular area or at a specific time.

[1154] A "mobile power supply device" refers to electric vehicles or other mobile power supply means that can be moved to supply power to communication equipment during a disaster.

[1155] "Simulation" refers to the process of predicting the optimal placement of movable power supply equipment using a computational model based on disaster risk assessment.

[1156] "Emotional state" refers to an indicator that shows the user's psychological state, such as stress and anxiety.

[1157] The term "emotion engine" refers to a function that uses speech recognition and facial recognition technology to recognize the user's emotional state in real time and adjusts system operations and instructions accordingly.

[1158] This invention aims to maintain communication infrastructure and enable rapid response during disasters, and further improves system usability by taking into account the emotional state of the user. The specific operation and hardware and software used in embodiments of this invention will be described below.

[1159] Hardware and software to be used

[1160] This system primarily uses the following hardware and software.

[1161] 1. Server:

[1162] - Equipped with a high-performance CPU and large-capacity memory.

[1163] - Database management systems (such as MySQL and PostgreSQL)

[1164] - Machine learning algorithms (such as TensorFlow and PyTorch)

[1165] - API access function

[1166] 2. Terminal (electric company vehicle):

[1167] - GPS module

[1168] - High-capacity battery

[1169] - Wireless communication capabilities (Wi-Fi, 4G / 5G, etc.)

[1170] 3. User:

[1171] - Computer or tablet device for monitoring

[1172] - Camera for voice recognition and facial recognition

[1173] 4. Emotional Engine:

[1174] - Voice analysis software (such as Google Speech-to-Text)

[1175] - Face recognition software (such as OpenCV or Face++)

[1176] Data collection and processing

[1177] The server collects necessary data from multiple data sources. For example, weather data is obtained from the government's weather data API, and historical disaster occurrence data is collected from Earth observation satellite data. Similarly, geographical information of communication facilities is also obtained. This data is retrieved using API requests and stored on the server in JSON format.

[1178] Data preprocessing and machine learning

[1179] The collected data is preprocessed on the server. This includes imputing missing values, filtering outliers, and normalization. The preprocessed data is then used to predict disaster risk using machine learning algorithms. The algorithms used here are common machine learning frameworks such as TensorFlow and PyTorch.

[1180] Optimal placement simulation

[1181] Once the disaster risk assessment is complete, the server simulates the optimal deployment of electric company vehicles in high-risk areas. This simulation takes into account the current location, battery level, and mobility of the electric company vehicles. Once the optimal deployment is determined, the server sends specific movement instructions to each electric company vehicle.

[1182] Movement instructions and real-time response

[1183] Based on instructions sent from the server, the terminal (electric company vehicle) moves to the designated area. In the event of a disaster and a power outage to communication equipment, the server immediately collects information on the damaged communication equipment and issues emergency response instructions to the nearest electric company vehicle. Once the electric company vehicle arrives at the scene, it uses its high-capacity battery to supply power to the communication equipment and support the restoration of the communication infrastructure.

[1184] Emotion recognition and system adjustment

[1185] The emotion engine uses speech and facial recognition technologies to recognize the user's emotional state in real time. Based on the data obtained from the emotion engine, the server adjusts the frequency of notifications and instructions if the user is experiencing stress or anxiety. It also provides detailed situational explanations to help the user feel more at ease.

[1186] Specific examples and prompt statements

[1187] Specific example:

[1188] The server retrieves weather data from a weather forecast API and inputs it into a machine learning algorithm to predict when a typhoon will approach in a few days. Based on this prediction, it simulates the optimal placement of electric company vehicles and sends instructions to the nearest electric company vehicle.

[1189] Examples of prompts for a generative AI model:

[1190] "Based on weather data from the weather forecast API, predict the typhoon risk for the next two days."

[1191]

[1192] "Identify the location of electric company vehicles closest to areas with a high risk of disaster, and conduct deployment simulations and issue instructions to move them to those areas."

[1193]

[1194] "Identify the electric company vehicles closest to the communication equipment affected by the disaster and power outage, and instruct them to begin supplying power as an emergency response."

[1195]

[1196] "Analyze the user's voice and facial expressions to determine if they are experiencing stress. If the user is stressed, reduce the frequency of notifications and alerts, and provide detailed, reassuring context."

[1197] As described above, the present invention enables the maintenance of communication infrastructure and rapid response during disasters, while simultaneously significantly improving the usability of the system by taking into account the emotional state of the user.

[1198] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1199] Program processing flow

[1200] Step 1: Data Collection

[1201] The server collects necessary data from multiple data sources. Inputs include government weather data APIs, Earth observation satellite data, historical disaster databases, and geographic information from communication facilities. The collected data is stored on the server in JSON format.

[1202] Specific operation: The server periodically sends API requests to retrieve weather forecast data and historical disaster data. For example, "Retrieve weather data from the weather forecast API and save the contents in JSON format."

[1203] Step 2: Data Preprocessing

[1204] The server preprocesses the collected data. The input is the raw data collected in step 1, and the output is the data converted into a format suitable for machine learning algorithms. Specifically, this involves imputing missing values, filtering outliers, and normalizing the data.

[1205] Specific operation: The server scans the data and fills in missing weather data with average values. It also filters outliers and normalizes the data.

[1206] Step 3: Disaster Risk Prediction

[1207] The server inputs pre-processed data into a machine learning algorithm to predict disaster risk. The input is pre-processed data, and the output is a prediction of disaster risk for a specific time and region.

[1208] Specific operation: The server inputs data into AI models built using TensorFlow or PyTorch. For example, "Output the probability of a typhoon or flood occurring in a specific region within the next 72 hours."

[1209] Step 4: Optimal Placement Simulation

[1210] The server simulates the optimal placement of mobile power supply units based on disaster risk predictions. The inputs are the disaster risk assessment results and the current location information of electric company vehicles, and the output is the optimal placement plan for each electric company vehicle.

[1211] Specific operation: The server identifies high-risk areas and checks the current location and battery level of the nearest electric company vehicle. It then runs a simulation to determine the optimal deployment. For example, "Check the location of electric company vehicle B, which is closest to area A, and its battery level, and then plan its deployment to area A."

[1212] Step 5: Movement Instructions

[1213] The server sends movement instructions to each electric company vehicle based on an optimal placement simulation. The input is the simulation result of the optimal placement, and the output is the specific movement instruction to each electric company vehicle.

[1214] Specific operation: The server sends a travel instruction to electric company vehicles equipped with GPS modules, such as "Proceed to area A." For example, "Instruct electric company vehicle B to move to area A."

[1215] Step 6: Real-time response

[1216] The server issues emergency response instructions to the nearest electric company vehicle in the event of a disaster and a power outage to communication equipment. Inputs include information about the power outage and the location of the electric company vehicle, while output is the emergency response instruction.

[1217] Specific operation: The server detects a power outage in the communication equipment and quickly issues an emergency instruction to the nearest electric company vehicle. For example, "If the communication equipment in area C experiences a power outage, the server will instruct the nearest electric company vehicle D to take emergency action and begin supplying power."

[1218] Step 7: Recognizing and responding to emotions

[1219] The emotion engine recognizes the user's emotional state in real time. Input is the user's voice and facial expression data, and output is notifications and instructions tailored to the emotional state.

[1220] Specific operation: The emotion engine uses speech recognition and facial recognition software to analyze the user's emotions. For example, "If the user is feeling stressed, it will reduce the frequency of notifications and provide detailed situational descriptions to provide reassurance."

[1221] As a result, the entire system enables the rapid maintenance and recovery of communication infrastructure during disasters and provides an operating environment that takes into account the emotional state of the user.

[1222] (Application Example 2)

[1223] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1224] Maintaining communication infrastructure during disasters requires speed and effectiveness. However, current systems often fail to adequately consider user stress and anxiety, resulting in increased user burden. Furthermore, real-time information transmission and power supply during disasters are not adequately achieved. A new system is needed to address these problems.

[1225] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting and processing disaster prediction data and geographic information, means for evaluating disaster risk based on the data, means for simulating the optimal placement of electric vehicles based on the disaster risk evaluation, means for instructing the movement of electric vehicles based on the simulation results, means for directing electric vehicles toward a base station to supply power when a disaster occurs, means for monitoring the user's emotional state in real time and adjusting the notification format based on the results, and means for providing user support using an emotion engine. This makes it possible to maintain communication infrastructure during a disaster while providing flexible responses according to the user's emotional state.

[1226] "Disaster prediction data" refers to information used to predict the risk of disasters, including past disaster data and weather forecast data.

[1227] "Geographic information" refers to data about the topography, population density, infrastructure layout, and other characteristics of a specific region.

[1228] "Disaster risk assessment" is the process of evaluating the likelihood of a disaster occurring based on collected disaster prediction data and geographical information.

[1229] An "electric vehicle" is a vehicle that runs on batteries, and in times of disaster, it plays a role in supplying power to communication equipment.

[1230] "Simulating the optimal placement" refers to the process of calculating the most effective way to deploy electric vehicles based on disaster risk assessments.

[1231] "Instructing movement" means issuing a command to the electric vehicle to move to a specific location based on the simulation results.

[1232] "Supplying power" means that an electric vehicle uses its own battery to provide power to external devices such as communication equipment.

[1233] "User emotional state" refers to the mental state a user is experiencing, such as stress, anxiety, or a sense of security.

[1234] "Real-time monitoring" means constantly monitoring the user's emotional state and detecting any changes immediately.

[1235] "Adjusting notification format" means appropriately changing the content and frequency of notifications according to the user's emotional state.

[1236] An "emotion engine" is software that recognizes a user's emotions and adjusts system operations and notifications based on those emotions.

[1237] This invention specifically aims to realize a system that takes into account the maintenance of communication infrastructure and the emotional state of users during disasters, and consists of the following elements. The system mainly consists of a server, a terminal (electric vehicle), a user, and an emotion engine.

[1238] System Configuration

[1239] server

[1240] The server has the following functions:

[1241] 1. Data Collection: The server collects disaster prediction data and geographical information from weather forecast APIs and historical disaster data APIs. This prepares the server for predicting the risk of disasters.

[1242] 2. Disaster Risk Assessment: Based on the collected data, a generative AI model is used to assess the risk of disaster occurrence. This assessment takes into account past disaster data and current weather forecasts.

[1243] 3. Optimal Deployment Simulation: Based on the disaster risk assessment results, the optimal deployment of electric vehicles will be simulated. The simulation will perform calculations to deploy electric vehicles in areas with a high disaster risk so that they can respond quickly.

[1244] 4. Movement Instructions: Based on simulation results, electric vehicles are instructed to move to specific areas. In the event of a disaster, electric vehicles are also instructed to head towards communication base stations to supply power.

[1245] 5. Emotion Monitoring: An emotion engine is used to monitor the user's emotional state in real time. This allows for the adjustment of notification formats to reduce user stress and anxiety.

[1246] Specific example

[1247] For example, a server retrieves weather data from a weather forecast API, and based on that data, a generated AI model assesses whether there is a high risk of a typhoon approaching in the next few days. Based on this result, the server simulates the optimal placement of electric vehicles and instructs the vehicle closest to the high-risk area to head towards that area.

[1248] Terminal (electric vehicle)

[1249] The terminal (electric vehicle) receives movement instructions from the server, moves to the designated area, and supplies power to the base station.

[1250] As a concrete example, if a base station experiences a power outage due to a disaster, the nearest electric vehicle can travel to the base station to supply power, restarting the communication equipment and restoring communication.

[1251] User

[1252] Users receive notifications from the server and take actions or instructions as needed. Additionally, an emotion engine monitors the user's emotional state, and if the user is experiencing stress or anxiety, the notification frequency is reduced and more detailed explanations of the situation are provided.

[1253] Hardware and software to be used

[1254] Hardware:

[1255] smartphone

[1256] Head-mounted display (HMD)

[1257] electric car

[1258] software:

[1259] Emotion Engine

[1260] Disaster Prediction Engine (DisasterPredictor)

[1261] Web API (weather forecast data, historical disaster data)

[1262] Example of a prompt

[1263] "You are an AI designed to design a system aimed at maintaining communication infrastructure and enabling rapid response during disasters. Define the system outline according to the following requirements."

[1264] Design an AI engine that collects weather forecast data and historical disaster data to predict disaster risk.

[1265] Design an algorithm to simulate the optimal placement of electric vehicles.

[1266] The system incorporates an emotion engine that evaluates the user's emotional state in real time and adjusts the notification format accordingly.

[1267] Please also describe in detail the specific steps, the technologies, hardware, software, and format of the notification.

[1268] The above describes the embodiments for carrying out the present invention. This system not only enables the efficient and rapid maintenance of communication infrastructure during disasters, but also allows for flexible responses that take into account the emotional state of users.

[1269] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1270] Step 1:

[1271] The server collects disaster prediction data and geographical information from a weather forecast API and a historical disaster data API. The input consists of weather forecast data and historical disaster data obtained from the APIs, which are then preprocessed. The output of this process consists of preprocessed disaster prediction data and geographical information.

[1272] Step 2:

[1273] The server uses a generated AI model based on the collected data to assess disaster risk. The input for this step is the pre-processed data obtained in step 1, and the AI ​​model performs calculations to calculate the disaster occurrence risk. The output is the disaster occurrence risk assessment result for a specific area.

[1274] Step 3:

[1275] The server simulates the optimal placement of electric vehicles based on the disaster risk assessment results. The input for this step is the disaster risk assessment results obtained in step 2, and the calculations are performed by the placement simulation software. This outputs the optimal placement plan for electric vehicles.

[1276] Step 4:

[1277] The server sends movement instructions to the electric vehicle based on the simulation results. The input for this step is the placement plan obtained in step 3, a movement instruction is generated, and it is sent to the electric vehicle. The output is the movement instruction received by the electric vehicle.

[1278] Step 5:

[1279] In the event of a disaster, a terminal (electric vehicle) will proceed to a communication base station according to instructions from the server and supply power. The input for this step is an emergency instruction from the server, and the specific action involves the electric vehicle moving, connecting the power supply device upon arrival at the base station, and supplying power to the communication equipment. The output is the restoration of communication at the base station.

[1280] Step 6:

[1281] The server uses an emotion engine to monitor the user's emotional state in real time. The input for this step is the user's voice data and facial expression data, which the emotion engine analyzes to evaluate the user's emotional state. The output is the user's emotional state (e.g., stress level).

[1282] Step 7:

[1283] The server adjusts the notification format based on the user's emotional state, as assessed by the emotion engine. The input for this step is the emotional state data obtained in step 6, and the notification format is adjusted accordingly. Specifically, this involves reducing the frequency of notifications or displaying more detailed situational descriptions to alleviate user stress. The output is the adjusted notification format.

[1284] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1285] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1286] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1287] [Fourth Embodiment]

[1288] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1289] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1290] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1291] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1292] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1293] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1294] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1295] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1296] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1297] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1298] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1299] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1300] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1301] This invention is a system aimed at maintaining communication infrastructure and enabling rapid response during disasters. Specific embodiments of this system are described below.

[1302] System Configuration

[1303] This system consists primarily of the following elements:

[1304] 1. Server: Responsible for data collection, disaster prediction using AI models, and overall system management.

[1305] 2. Terminal (electric company vehicle): Equipped with a power supply function, it moves and supplies power based on instructions from the server.

[1306] 3. User: Operate and monitor the system, and intervene as needed.

[1307] System Operation Overview

[1308] The operation of this system can be broadly classified into the following three stages.

[1309] 1. Disaster prediction using data collection and AI models

[1310] The server collects data from various directories, including weather data, geographic information, and disaster prevention information. This data is preprocessed and input into an AI model to predict the risk of disaster occurrence. In particular, it combines past disaster data with current weather forecast data to predict the scale and location of potential future disasters.

[1311] Specific example: A server retrieves weather data from a weather forecast API, and an AI model uses this data to predict that a typhoon will approach in a few days. The prediction results indicate that the disaster risk is high in a specific area.

[1312] 2. Optimal placement simulation and instructions

[1313] After the disaster risk is assessed, the server uses this information to run a simulation of the placement of electric company vehicles. It selects the electric company vehicles closest to high-risk areas and optimizes their placement. Based on the simulation results, it sends movement instructions to each electric company vehicle.

[1314] Specific example: For areas predicted to be at high disaster risk, the server runs a simulation and sends an instruction to the nearest electric company vehicle to head to that area. For example, if the risk area is City A and the nearest electric company vehicle is Company B, an instruction will be sent to Company B to head to City A.

[1315] 3. Real-time response in the event of a disaster

[1316] In the event of an actual disaster and a power outage at a base station, the server immediately collects information on the damaged base station and instructs the nearest electric vehicle to provide emergency assistance. Upon arrival at the base station, the terminal (electric vehicle) uses its battery to supply power to the base station and assist in restoring communication.

[1317] Specific example: If a disaster causes a power outage at a base station in City C, the server issues an emergency instruction to the nearest electric company vehicle D to proceed. When company vehicle D arrives at the base station, it uses its battery to supply power to the base station, restarting the communication equipment and restoring communication.

[1318] User roles

[1319] The user's role is to monitor the overall situation while the server performs complex data analysis and issues instructions. They are also responsible for manual intervention and system maintenance in the event of unforeseen circumstances.

[1320] Specific example: The user reviews the disaster prediction results generated by the system and makes manual corrections as needed. They also take measures such as preparing spare batteries if the battery level of the electric company vehicle is low.

[1321] This invention enables efficient and rapid maintenance of communication infrastructure during disasters, thereby minimizing communication disruptions. Furthermore, by making maximum use of existing equipment, it avoids the need for additional large-scale investments.

[1322] The following describes the processing flow.

[1323] Program processing steps

[1324] 1. Disaster prediction using data collection and AI models

[1325] Step 1:

[1326] The server collects weather forecast data, historical disaster data, and base station geographic information from multiple data sources. This includes government weather data APIs and data from Earth observation satellites.

[1327] Step 2:

[1328] The server preprocesses the collected data. Specifically, it imputes missing values, removes outliers, and standardizes the data. This ensures data consistency and quality.

[1329] Step 3:

[1330] The server inputs pre-processed data into an AI model to predict disaster risk. For example, it uses machine learning algorithms to assess future disaster risk based on past disaster patterns.

[1331] Step 4:

[1332] Based on the prediction results, the server calculates a disaster risk score for each base station. This is a detailed assessment that includes the scale of the disaster, the date of occurrence, and the scope of impact.

[1333] 2. Optimal placement simulation and instructions

[1334] Step 5:

[1335] The server assesses which base stations are most vulnerable based on their disaster risk scores. Base stations are then categorized according to their risk level.

[1336] Step 6:

[1337] The server simulates the optimal vehicle deployment based on the risk assessment results and the current location information of electric company vehicles. This simulation uses an optimization algorithm to select the electric company vehicle closest to each base station.

[1338] Step 7:

[1339] Based on the simulation results, the server sends movement instructions to each electric company vehicle. Instructions are generated that include a specific travel route and destination.

[1340] Step 8:

[1341] The terminal (electric company vehicle) receives instructions from the server and begins moving towards its destination based on that information. It periodically sends its location and battery level to the server during its journey.

[1342] 3. Real-time response in the event of a disaster

[1343] Step 9:

[1344] If a disaster actually occurs and an anomaly such as a power outage is detected, the server will immediately monitor the status of base stations and identify any base stations that have stopped working.

[1345] Step 10:

[1346] The server sends emergency response instructions to the nearest electric company vehicle. These instructions include procedures for rapid movement and power supply.

[1347] Step 11:

[1348] The terminal (electric company vehicle) receives an emergency instruction and immediately heads to the designated base station. Upon arrival, the EV vehicle prepares to supply power to the base station using its battery.

[1349] Step 12:

[1350] The terminal (electric company vehicle) supplies power to the base station and restarts the communication equipment. During this process, it reports the battery level and supply status to the server.

[1351] Step 13:

[1352] The user monitors the response status during a disaster and makes manual adjustments or instructions as needed. For example, they might take measures such as having additional electric company vehicles on standby.

[1353] Through the steps described above, this system can maintain communication infrastructure and enable a rapid response during disasters.

[1354] (Example 1)

[1355] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1356] In disaster situations where maintaining communication infrastructure and responding quickly are crucial, conventional methods make it difficult to supply power to base stations quickly, leading to prolonged communication disruptions. Therefore, a system is needed to efficiently and rapidly predict disasters, optimally deploy and relocate power supply equipment, and ensure the maintenance of communication infrastructure.

[1357] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1358] In this invention, the server includes means for collecting and preprocessing weather data, geographic information, and disaster prevention information; means for predicting disaster risk using an AI model generated based on the collected data; means for simulating the optimal placement of movable power supply devices based on the disaster risk prediction; means for instructing the movement of the movable power supply devices based on the simulation results; and means for directing the movable power supply devices toward communication devices to supply power in the event of a disaster. This enables the rapid and efficient maintenance of communication infrastructure even in the event of a disaster.

[1359] "Meteorological data" refers to information related to atmospheric conditions, including data such as temperature, humidity, precipitation, wind speed, and wind direction.

[1360] "Geographic information" refers to data that represents the geographical characteristics of a specific region, such as its topography, geology, land use, and population distribution.

[1361] "Disaster prevention information" refers to information about the occurrence and impact of disasters, and includes data such as evacuation sites, evacuation routes, and safety assessments.

[1362] "Preprocessing" refers to the process of organizing and correcting data before data analysis or model input, and includes processes such as imputing missing values, correcting outliers, and normalizing data.

[1363] A "generative AI model" is a model built using machine learning and deep learning techniques, and is a set of algorithms used to perform a specific task (in this case, disaster prediction).

[1364] "Disaster risk" refers to numerical values ​​or indicators used to assess the likelihood of a natural disaster occurring and the extent of the resulting damage.

[1365] A "portable power supply device" is a device that is mobile for supplying electricity, such as a battery pack or generator mounted on a car or drone.

[1366] "Simulation" is a technique for virtually reproducing real-world actions and behaviors on a computer model, and includes using computer simulations to explore optimal placements and actions.

[1367] "Communication equipment" refers to devices used for sending and receiving data, specifically including base stations and routers.

[1368] System Overview

[1369] This invention is a system aimed at maintaining communication infrastructure and enabling rapid response during disasters, and consists of a server, a terminal (a portable power supply device), and a user. The roles of each component are described in detail below.

[1370] Server Role

[1371] 1. Data Collection

[1372] The server periodically collects weather data, geographic information, disaster prevention information, and other data from various APIs and sensors. The main software used is Python, and data collection utilizes the OpenWeatherMap API and the Geospatial Information Authority of Japan's API.

[1373] 2. Data preprocessing

[1374] The server preprocesses the collected data. This preprocessing uses libraries such as Python's Pandas library, specifically performing tasks such as imputing missing values, normalizing the data, and correcting outliers.

[1375] 3. Disaster prediction

[1376] The server inputs pre-processed data into a generating AI model (using TensorFlow) to predict disaster risk. The AI ​​model combines historical disaster data with current weather forecast data to predict the scale and location of potential future disasters.

[1377] Specific example:

[1378] The server retrieves weather data from a weather forecast API (OpenWeatherMap API), and a TensorFlow model uses this data to predict that a typhoon will approach in a few days. The prediction results indicate that the risk of disaster in a specific area is high.

[1379] 4. Placement Simulation

[1380] The server simulates the optimal placement of portable power supply units based on disaster risk. The simulation is performed using the Python SimPy library.

[1381] Specific example:

[1382] For areas predicted to be at high disaster risk, the server uses SimPy to perform simulations and identify the nearest mobile power supply unit. For example, if the risk area is City A and the nearest power supply unit is unit B, an instruction is sent to unit B to move towards City A.

[1383] 5. Movement instructions

[1384] Based on the simulation results, the server sends movement instructions to the movable power supply unit. A 5G network is used for communication.

[1385] Specific example:

[1386] The server sends a 5G communication instruction to the nearest mobile power supply device to move to City A, and the device begins moving according to the received instruction.

[1387] 6. Real-time support

[1388] In the event of a disaster, the server immediately collects information on damaged communication equipment and instructs the nearest mobile power supply unit to take emergency action.

[1389] Specific example:

[1390] If a disaster actually occurs in City X and the communication equipment experiences a power outage, the server will send an emergency instruction to the nearest power supply unit. Once the power supply unit arrives, it will use its battery to power the communication equipment and restore communication.

[1391] Terminal role

[1392] 1. Power supply

[1393] The terminal (a portable power supply device) moves to a specific area and supplies power according to instructions from the server. The device is equipped with a LiDAR sensor and GPS, which allows it to accurately reach the disaster area.

[1394] Specific example:

[1395] The terminal receives instructions from the server, moves to the designated communication device, and uses its battery to receive power.

[1396] User roles

[1397] 1. System monitoring and maintenance

[1398] The user monitors the complex data analysis and instruction issuing performed by the server, and intervenes manually when necessary. They are also responsible for the overall system maintenance.

[1399] Specific example:

[1400] Users review the disaster prediction results generated using the system's GUI and make manual corrections as needed. Additionally, if the battery level of the electric company vehicle (mobile power supply unit) is low, a spare battery is prepared and replaced.

[1401] Example of a prompt

[1402] An example of a prompt to input into a generative AI model is as follows:

[1403] "Use current weather data and historical disaster data to predict potential disasters that may occur in the next week."

[1404] This system provides a key mechanism for quickly and efficiently maintaining communication infrastructure even during disasters, minimizing communication disruptions. Furthermore, by making maximum use of existing equipment, it avoids the need for additional large-scale investments.

[1405] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1406] Step 1: Data Collection

[1407] Processing flow: The server collects weather data, geographic information, and disaster prevention information from various APIs and sensors.

[1408] Specific operation: The server sends requests to the OpenWeatherMap API and the Geospatial Information Authority of Japan API to obtain real-time weather data and geographic information in JSON format, and stores this data in an internal database.

[1409] Input: Weather data and geographic information triggered by requests from the API.

[1410] Output: Meteorological data and geographic information as raw data requiring preprocessing.

[1411] Step 2: Data Preprocessing

[1412] Processing flow: The server prepares the collected data into an applicable format.

[1413] Specific operation: The server uses the Python Pandas library to impute missing data, correct outliers, and normalize the data.

[1414] Input: Collected raw data

[1415] Output: Preprocessed, clean dataset

[1416] Step 3: Disaster Prediction

[1417] Processing flow: The server inputs pre-processed data into an AI model to predict disaster risk.

[1418] Specific operation: The server utilizes TensorFlow to run an AI model using pre-processed data as input, and derives a disaster risk score.

[1419] Input: Preprocessed dataset

[1420] Output: Disaster risk score for each region

[1421] Step 4: Placement Simulation

[1422] Processing flow: The server simulates the optimal placement of movable power supply units based on the disaster risk score.

[1423] Specific operation: The server uses the Python SimPy library to calculate the optimal placement and determine the movement path and placement location.

[1424] Input: Disaster risk score and current power supply location data

[1425] Output: Optimal placement information and movement paths

[1426] Step 5: Movement Instructions

[1427] Processing flow: Based on the simulation results, the server sends instructions to the portable power supply unit.

[1428] Specific operation: The server generates movement instructions and sends them to each device via the 5G network.

[1429] Input: Optimal placement information and travel path

[1430] Output: Movement Instructions

[1431] Step 6: Real-time response

[1432] Processing flow: When a disaster occurs, the server collects information on damaged communication equipment and takes necessary emergency action.

[1433] Specific operation: The server acquires situation reports from the disaster area in real time and issues an emergency relocation instruction to the nearest power supply unit. Upon arrival of the unit, it uses its battery to supply power and restore communication.

[1434] Input: Status data of communication devices during a disaster, current location information

[1435] Output: Emergency evacuation order and power supply order

[1436] Step 7: System Monitoring and Maintenance

[1437] Processing flow: The user monitors the overall status of the system and intervenes and performs maintenance as needed.

[1438] Specific actions: The user monitors the system via a GUI and performs manual corrective operations if an anomaly is detected. They also check the battery level of electric company vehicles and prepare a spare battery if necessary.

[1439] Input: Monitoring data and anomaly alerts from the system.

[1440] Output: Correction operation and maintenance instructions

[1441] (Application Example 1)

[1442] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1443] The need for rapid response and maintenance of communication infrastructure during disasters is increasing, with power supply to communication equipment being particularly important. However, conventional systems have shortcomings in collecting and processing disaster prediction data, making it difficult to optimize the deployment of electric vehicles or receive user instructions in real time. This makes it difficult to respond quickly in the event of a communication failure, and therefore needs to be resolved.

[1444] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1445] In this invention, the server includes means for collecting and processing disaster prediction data and geographic information; means for evaluating disaster risk based on the data; means for simulating the optimal placement of electric vehicles based on the disaster risk evaluation; means for instructing the movement of electric vehicles based on the simulation results; means for directing electric vehicles toward communication equipment and supplying power in the event of a disaster; means for acquiring disaster prediction data in real time using a smart device and notifying the user; and means for the user to send instructions directly to the electric vehicles from a smart device. This enables the maintenance of communication infrastructure and rapid response in real time even during a disaster.

[1446] "Disaster prediction data" refers to data collected to predict the occurrence of disasters, such as weather data, geographical information, and disaster prevention information.

[1447] "Geographic information" refers to geographical data relating to a specific region or location, and includes map information and topographic data.

[1448] "Disaster risk assessment" is the process of analyzing and determining the level of disaster risk a particular region or piece of equipment is exposed to, based on collected disaster prediction data.

[1449] An "electric vehicle" is a vehicle that operates electrically to provide power and transportation during a disaster.

[1450] "Optimal placement simulation" refers to conducting simulations to determine the most effective placement of electric vehicles based on disaster risk assessment results.

[1451] "Movement instruction" refers to the action of instructing an electric vehicle to move to a specific location based on the results of an optimal placement simulation.

[1452] "Communication equipment" refers to the equipment that makes up the communication infrastructure, and includes base stations, relay stations, and so on.

[1453] "Power supply" refers to the act of providing the necessary electricity to communication equipment.

[1454] A "smart device" is a portable information terminal with advanced processing and communication capabilities, such as a smartphone or tablet.

[1455] "Real-time acquisition" means instantly obtaining the latest data and information at the present time.

[1456] "Notification" refers to the act of conveying important information or warnings to a user.

[1457] "Instructions" refer to commanding someone to perform a specific action or movement.

[1458] This invention is a system aimed at maintaining communication infrastructure and enabling rapid response during disasters. Specific embodiments of this system are described below.

[1459] System Configuration

[1460] This system consists primarily of the following elements:

[1461] 1. Server: Responsible for data collection, disaster prediction using AI models, and overall system management.

[1462] 2. Electric vehicles: These vehicles have a power supply function and move and supply power based on instructions from the server.

[1463] 3. User: Operate and monitor the system, and intervene as needed. Also, use smart devices to acquire data in real time, provide notifications, and issue instructions.

[1464] System Operation Overview

[1465] The operation of this system can be broadly classified into the following three stages.

[1466] 1. Disaster prediction using data collection and AI models

[1467] The server collects data from various directories, including weather data, geographic information, and disaster prevention information. This data is preprocessed and input into an AI model to predict the risk of disaster occurrence. In particular, it combines past disaster data with current weather forecast data to predict the scale and location of potential future disasters.

[1468] Specific example: A server retrieves weather data from a weather forecast API, and an AI model uses this data to predict that a typhoon will approach in a few days. The prediction results indicate that the disaster risk in a specific area is high. This information is then communicated to the user via a smart device, prompting them to prepare for the eventuality.

[1469] 2. Optimal placement simulation and instructions

[1470] After the disaster risk is assessed, the server performs a simulation of electric vehicle deployment based on that assessment. It selects the electric vehicles closest to high-risk areas and optimizes their deployment. Based on the simulation results, it sends movement instructions to each electric vehicle.

[1471] Specific example: In areas predicted to be at high disaster risk, the server runs a simulation and instructs the nearest electric vehicle to head towards that area. For example, if the risk area is City A and the nearest electric vehicle is Vehicle B, Vehicle B will be instructed to head towards City A. This instruction is also notified to the user in real time via a smart device.

[1472] 3. Real-time response in the event of a disaster

[1473] In the event of an actual disaster and a power outage to communication equipment, the server will immediately collect information on the damaged equipment and instruct the nearest electric vehicle to respond to the emergency. Upon arrival at the communication equipment, the electric vehicle will use its battery to supply power to the equipment and assist in restoring communication.

[1474] Specific example: If a disaster causes a power outage to the communication equipment in City C, the server issues an emergency instruction to the nearest electric vehicle. When the electric vehicle arrives at the communication equipment, it uses its battery to supply power to the equipment, restarting the communication devices and restoring communication. This entire process is also reported to the user in real time via a smart device.

[1475] Main technologies used

[1476] Server: Performs data collection, disaster prediction using AI models, optimal placement simulations, and instructions. Programming languages ​​such as Python and Java, and AI frameworks such as TensorFlow and PyTorch are used.

[1477] Electric vehicles: These vehicles supply power to communication equipment and provide transportation. They are equipped with GPS and battery management systems.

[1478] Smart devices: Acquire real-time data, provide user notifications, and give instructions. Dedicated applications are developed to run on iOS and Android.

[1479] Examples of prompts for generative AI models

[1480] "Create a prompt message to determine the optimal placement of electric vehicles when the risk of typhoons in Tokyo increases."

[1481] Thus, the present invention provides a system that enables the maintenance of communication infrastructure in real time and rapid response even during disasters.

[1482] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1483] Step 1:

[1484] The server collects data such as weather data, geographic information, and disaster prevention information from various directories and APIs. Input requires various API keys and database connection information, and output is the collected raw data. Data collection is performed periodically and stored in a database to maintain the latest information.

[1485] Step 2:

[1486] The server preprocesses the collected data. This involves imputing missing values, normalizing the data, and removing inconsistent data. The input is the collected raw data, and the output is the clean data after preprocessing. This preprocessing step uses Python's Pandas library or similar tools to clean the data.

[1487] Step 3:

[1488] The server inputs pre-processed data into an AI model to predict disaster risk. The input is clean data, and the output is an assessment of disaster risk. Here, an AI framework such as TensorFlow or PyTorch is used to create a model that combines historical disaster data with current weather data.

[1489] Step 4:

[1490] The server simulates the optimal placement of electric vehicles based on disaster risk assessment results. The inputs are the disaster risk assessment results and the current location information of the electric vehicles, and the output is the optimal placement plan for the electric vehicles. This simulation utilizes pathfinding techniques such as the Dijkstra algorithm and the A algorithm.

[1491] Step 5:

[1492] The server sends movement instructions to the electric vehicles based on the simulation results. The input is the optimal placement plan, and the output is the actual position information of the electric vehicles after the movement instructions are given. These instructions are transmitted in real time via the communication network.

[1493] Step 6:

[1494] The server uses smart devices to notify users of disaster prediction data in real time. The input is the disaster risk assessment result, and the output is a disaster risk notification displayed on the user's smart device. This notification is sent to the user via push notification or SMS.

[1495] Step 7:

[1496] Users can send instructions directly to electric vehicles from their smart devices. Input is user-generated information, and output is the instructions sent to the electric vehicle. This functionality is provided through a dedicated application.

[1497] Step 8:

[1498] In the event of a disaster, the server collects information on damaged communication equipment and instructs the nearest electric vehicle to take emergency action. The input is sensor data from the damaged communication equipment, and the output is emergency action instructions for the electric vehicle. These instructions are also transmitted in real time via the communication network.

[1499] Step 9:

[1500] Upon arrival at the communication equipment, the electric vehicle will use its battery to supply power and assist in restoring communication. The input is the power request of the communication equipment, and the output is the power supply status of the communication equipment. The electric vehicle is equipped with a battery management system to ensure appropriate power supply.

[1501] Thus, the system of the present invention can smoothly integrate the collection and processing of various data, the prediction of disaster risks, the simulation of optimal placement, real-time instructions, and emergency response, enabling a rapid and appropriate disaster response.

[1502] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1503] This invention aims to maintain communication infrastructure and enable rapid response during disasters, and further improves system usability by taking into account the emotional state of the user. Specific embodiments of this system are described below.

[1504] System Configuration

[1505] This system consists primarily of the following elements:

[1506] 1. Server: Responsible for data collection, disaster prediction using AI models, and overall system management.

[1507] 2. Terminal (electric company vehicle): Equipped with a power supply function, it moves and supplies power based on instructions from the server.

[1508] 3. User: Operate and monitor the system, and intervene as needed.

[1509] 4. Emotion Engine: Recognizes the user's emotional state, and system operations and instructions are adapted according to the user's emotions.

[1510] System Operation Overview

[1511] The operation of this system can be broadly classified into the following four stages.

[1512] 1. Disaster prediction using data collection and AI models

[1513] The server collects data from multiple data sources, including weather forecasts, historical disaster data, and base station geographic information. This includes data from government weather data APIs and Earth observation satellites. The collected data is preprocessed and input into an AI model to predict disaster risk.

[1514] Specific example: A server retrieves weather data from a weather forecast API, and an AI model uses this data to predict that a typhoon will approach in a few days. The prediction results indicate that the disaster risk is high in a specific area.

[1515] 2. Optimal placement simulation and instructions

[1516] After the disaster risk is assessed, the server uses this information to run a simulation of the placement of electric company vehicles. It selects the electric company vehicles closest to high-risk areas and optimizes their placement. Based on the simulation results, it sends movement instructions to each electric company vehicle.

[1517] Specific example: For areas predicted to be at high disaster risk, the server runs a simulation and sends an instruction to the nearest electric company vehicle to head to that area. For example, if the risk area is City A and the nearest electric company vehicle is Company B, an instruction will be sent to Company B to head to City A.

[1518] 3. Real-time response in the event of a disaster

[1519] In the event of an actual disaster and a power outage at a base station, the server immediately collects information on the damaged base station and instructs the nearest electric vehicle to provide emergency assistance. Upon arrival at the base station, the terminal (electric vehicle) uses its battery to supply power to the base station and assist in restoring communication.

[1520] Specific example: If a disaster causes a power outage at a base station in City C, the server issues an emergency instruction to the nearest electric company vehicle D to proceed. When company vehicle D arrives at the base station, it uses its battery to supply power to the base station, restarting the communication equipment and restoring communication.

[1521] 4. User support using an emotion engine

[1522] The emotion engine recognizes the user's emotional state in real time and adjusts the system's operation and instructions based on the results. The emotion engine uses speech recognition and facial recognition technology to evaluate the user's emotional state and adjusts the format of notifications and alerts if the user is experiencing stress or anxiety.

[1523] Specific example: If a user is experiencing stress during disaster response, the server uses data from the emotion engine to reduce the frequency of notifications and instructions. It also implements operational adjustments, such as providing detailed situational explanations to help the user feel more secure.

[1524] User roles

[1525] The user plays a role in monitoring the overall situation while the server performs complex data analysis and issues instructions. They are also responsible for manual intervention in the event of unforeseen circumstances and for system maintenance. Furthermore, they act based on system suggestions regarding how to respond to users whose emotions have been recognized by the emotion engine.

[1526] Specific examples: Users review the disaster prediction results generated by the system and make manual corrections as needed. They also take action such as preparing spare batteries if the electric company vehicle's battery level is low. If the emotional engine determines that the user's stress level is high, it flexibly adjusts operations and instructions.

[1527] As described above, the present invention not only enables efficient and rapid maintenance of communication infrastructure during disasters, but also realizes system operation that takes into account the emotional state of users. This makes it possible to minimize communication disruptions and reduce the burden on users.

[1528] The following describes the processing flow.

[1529] Program processing steps

[1530] 1. Disaster prediction using data collection and AI models

[1531] Step 1:

[1532] The server collects weather forecast data, historical disaster data, and base station geographic information from multiple data sources. Specifically, it obtains government weather information and data from Earth observation satellites via APIs.

[1533] Step 2:

[1534] The server preprocesses the collected data. Specifically, it performs data imputation, removal of outliers, and data standardization. This preprocessing improves the accuracy of the analysis.

[1535] Step 3:

[1536] The server inputs pre-processed data into an AI model to predict disaster risk. For example, it uses machine learning algorithms based on historical data to quantify future disaster risk.

[1537] Step 4:

[1538] The server calculates a disaster risk score for each base station based on the prediction results. This risk score is calculated based on factors such as the scale of the disaster, the date of occurrence, and the scope of impact.

[1539] 2. Optimal placement simulation and instructions

[1540] Step 5:

[1541] The server assesses the risk level of each base station based on the disaster risk score. It classifies areas into high-risk and low-risk zones and identifies base stations that require attention.

[1542] Step 6:

[1543] Based on the risk assessment results, the server simulates the optimal placement using the current location information of electric company vehicles. Using an optimal placement algorithm, it selects the electric company vehicle closest to the high-risk area.

[1544] Step 7:

[1545] Based on the simulation results, the server sends specific movement instructions to the electric company vehicle. These instructions include the travel route and destination.

[1546] Step 8:

[1547] The terminal (electric company vehicle) receives movement instructions from the server and begins moving towards its destination. It periodically reports its location and battery level to the server during its journey.

[1548] 3. Real-time response in the event of a disaster

[1549] Step 9:

[1550] If a disaster occurs and a base station experiences a power outage, the server immediately monitors for power outage information and identifies the affected base stations.

[1551] Step 10:

[1552] Based on the power outage information, the server sends emergency response instructions to the nearest electric vehicle. These instructions include promptly heading to a designated base station.

[1553] Step 11:

[1554] The terminal (electric company vehicle) receives the emergency instruction and immediately proceeds to the designated base station. Upon arrival, it prepares to supply power to the base station.

[1555] Step 12:

[1556] The terminal (electric company vehicle) uses its battery to supply power to the base station and restart the communication equipment. It periodically reports the status to the server at the start of supply and during the process.

[1557] 4. User support using an emotion engine

[1558] Step 13:

[1559] The emotion engine uses speech recognition and facial recognition technology to evaluate the user's emotional state in real time. It analyzes the data to detect the user's stress level and emotional state.

[1560] Step 14:

[1561] The server adjusts user actions and instructions based on emotional data obtained from the emotion engine. For example, if a user is experiencing high stress levels, the server may reduce the frequency of notifications.

[1562] Step 15:

[1563] Based on the emotion engine's evaluation results, the user accepts suggestions and instructions from the system. Manual corrections and adjustments are made as needed.

[1564] Step 16:

[1565] The emotion engine continuously monitors the user's emotional state and verifies that the system's actions and instructions are appropriately responding to the user's emotions.

[1566] Through the steps outlined above, this system enables the maintenance of communication infrastructure and rapid response during disasters, while also allowing for operation that takes into account the user's emotional state. This minimizes communication disruptions during disasters and reduces the burden on users.

[1567] (Example 2)

[1568] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1569] The problems that this invention aims to solve are the rapid and efficient maintenance of communication infrastructure during disasters, and the improvement of system operability that takes into account the emotional state of users. Specifically, the objective is to respond quickly to the loss of power supply to communication equipment due to a disaster, restore communication, and provide users with an optimal operating environment even in emergency situations.

[1570] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1571] In this invention, the server includes means for collecting weather data, past disaster occurrence data, and geographic information of communication facilities from multiple data sources; means for preprocessing the collected data and predicting disaster risk using a machine learning algorithm; and means for simulating the optimal placement of movable power supply devices based on the disaster risk assessment. This enables the rapid maintenance and recovery of communication infrastructure during a disaster, and the provision of an operating environment that takes into account the emotional state of the user.

[1572] "Data source" refers to the sources of information that a server collects for disaster risk assessment and simulation, such as weather data, past disaster occurrence data, and geographical information of communication facilities.

[1573] "Preprocessing" refers to preparatory work performed before data analysis, such as imputing missing values ​​in collected data, filtering outliers, and normalizing the data.

[1574] A "machine learning algorithm" refers to a mathematical model or statistical method used to predict disaster risk based on collected and pre-processed data.

[1575] "Disaster risk" refers to an indicator that shows the degree to which a disaster is likely to occur in a particular area or at a specific time.

[1576] A "mobile power supply device" refers to electric vehicles or other mobile power supply means that can be moved to supply power to communication equipment during a disaster.

[1577] "Simulation" refers to the process of predicting the optimal placement of movable power supply equipment using a computational model based on disaster risk assessment.

[1578] "Emotional state" refers to an indicator that shows the user's psychological state, such as stress and anxiety.

[1579] The term "emotion engine" refers to a function that uses speech recognition and facial recognition technology to recognize the user's emotional state in real time and adjusts system operations and instructions accordingly.

[1580] This invention aims to maintain communication infrastructure and enable rapid response during disasters, and further improves system usability by taking into account the emotional state of the user. The specific operation and hardware and software used in embodiments of this invention will be described below.

[1581] Hardware and software to be used

[1582] This system primarily uses the following hardware and software.

[1583] 1. Server:

[1584] - Equipped with a high-performance CPU and large-capacity memory.

[1585] - Database management systems (such as MySQL and PostgreSQL)

[1586] - Machine learning algorithms (such as TensorFlow and PyTorch)

[1587] - API access function

[1588] 2. Terminal (electric company vehicle):

[1589] - GPS module

[1590] - High-capacity battery

[1591] - Wireless communication capabilities (Wi-Fi, 4G / 5G, etc.)

[1592] 3. User:

[1593] - Computer or tablet device for monitoring

[1594] - Camera for voice recognition and facial recognition

[1595] 4. Emotional Engine:

[1596] - Voice analysis software (such as Google Speech-to-Text)

[1597] - Face recognition software (such as OpenCV or Face++)

[1598] Data collection and processing

[1599] The server collects necessary data from multiple data sources. For example, weather data is obtained from the government's weather data API, and historical disaster occurrence data is collected from Earth observation satellite data. Similarly, geographical information of communication facilities is also obtained. This data is retrieved using API requests and stored on the server in JSON format.

[1600] Data preprocessing and machine learning

[1601] The collected data is preprocessed on the server. This includes imputing missing values, filtering outliers, and normalization. The preprocessed data is then used to predict disaster risk using machine learning algorithms. The algorithms used here are common machine learning frameworks such as TensorFlow and PyTorch.

[1602] Optimal placement simulation

[1603] Once the disaster risk assessment is complete, the server simulates the optimal deployment of electric company vehicles in high-risk areas. This simulation takes into account the current location, battery level, and mobility of the electric company vehicles. Once the optimal deployment is determined, the server sends specific movement instructions to each electric company vehicle.

[1604] Movement instructions and real-time response

[1605] Based on instructions sent from the server, the terminal (electric company vehicle) moves to the designated area. In the event of a disaster and a power outage to communication equipment, the server immediately collects information on the damaged communication equipment and issues emergency response instructions to the nearest electric company vehicle. Once the electric company vehicle arrives at the scene, it uses its high-capacity battery to supply power to the communication equipment and support the restoration of the communication infrastructure.

[1606] Emotion recognition and system adjustment

[1607] The emotion engine uses speech and facial recognition technologies to recognize the user's emotional state in real time. Based on the data obtained from the emotion engine, the server adjusts the frequency of notifications and instructions if the user is experiencing stress or anxiety. It also provides detailed situational explanations to help the user feel more at ease.

[1608] Specific examples and prompt statements

[1609] Specific example:

[1610] The server retrieves weather data from a weather forecast API and inputs it into a machine learning algorithm to predict when a typhoon will approach in a few days. Based on this prediction, it simulates the optimal placement of electric company vehicles and sends instructions to the nearest electric company vehicle.

[1611] Examples of prompts for a generative AI model:

[1612] "Based on weather data from the weather forecast API, predict the typhoon risk for the next two days."

[1613]

[1614] "Identify the location of electric company vehicles closest to areas with a high risk of disaster, and conduct deployment simulations and issue instructions to move them to those areas."

[1615]

[1616] "Identify the electric company vehicles closest to the communication equipment affected by the disaster and power outage, and instruct them to begin supplying power as an emergency response."

[1617]

[1618] "Analyze the user's voice and facial expressions to determine if they are experiencing stress. If the user is stressed, reduce the frequency of notifications and alerts, and provide detailed, reassuring context."

[1619] As described above, the present invention enables the maintenance of communication infrastructure and rapid response during disasters, while simultaneously significantly improving the usability of the system by taking into account the emotional state of the user.

[1620] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1621] Program processing flow

[1622] Step 1: Data Collection

[1623] The server collects necessary data from multiple data sources. Inputs include government weather data APIs, Earth observation satellite data, historical disaster databases, and geographic information from communication facilities. The collected data is stored on the server in JSON format.

[1624] Specific operation: The server periodically sends API requests to retrieve weather forecast data and historical disaster data. For example, "Retrieve weather data from the weather forecast API and save the contents in JSON format."

[1625] Step 2: Data Preprocessing

[1626] The server preprocesses the collected data. The input is the raw data collected in step 1, and the output is the data converted into a format suitable for machine learning algorithms. Specifically, this involves imputing missing values, filtering outliers, and normalizing the data.

[1627] Specific operation: The server scans the data and fills in missing weather data with average values. It also filters outliers and normalizes the data.

[1628] Step 3: Disaster Risk Prediction

[1629] The server inputs pre-processed data into a machine learning algorithm to predict disaster risk. The input is pre-processed data, and the output is a prediction of disaster risk for a specific time and region.

[1630] Specific operation: The server inputs data into AI models built using TensorFlow or PyTorch. For example, "Output the probability of a typhoon or flood occurring in a specific region within the next 72 hours."

[1631] Step 4: Optimal Placement Simulation

[1632] The server simulates the optimal placement of mobile power supply units based on disaster risk predictions. The inputs are the disaster risk assessment results and the current location information of electric company vehicles, and the output is the optimal placement plan for each electric company vehicle.

[1633] Specific operation: The server identifies high-risk areas and checks the current location and battery level of the nearest electric company vehicle. It then runs a simulation to determine the optimal deployment. For example, "Check the location of electric company vehicle B, which is closest to area A, and its battery level, and then plan its deployment to area A."

[1634] Step 5: Movement Instructions

[1635] The server sends movement instructions to each electric company vehicle based on an optimal placement simulation. The input is the simulation result of the optimal placement, and the output is the specific movement instruction to each electric company vehicle.

[1636] Specific operation: The server sends a travel instruction to electric company vehicles equipped with GPS modules, such as "Proceed to area A." For example, "Instruct electric company vehicle B to move to area A."

[1637] Step 6: Real-time response

[1638] The server issues emergency response instructions to the nearest electric company vehicle in the event of a disaster and a power outage to communication equipment. Inputs include information about the power outage and the location of the electric company vehicle, while output is the emergency response instruction.

[1639] Specific operation: The server detects a power outage in the communication equipment and quickly issues an emergency instruction to the nearest electric company vehicle. For example, "If the communication equipment in area C experiences a power outage, the server will instruct the nearest electric company vehicle D to take emergency action and begin supplying power."

[1640] Step 7: Recognizing and responding to emotions

[1641] The emotion engine recognizes the user's emotional state in real time. Input is the user's voice and facial expression data, and output is notifications and instructions tailored to the emotional state.

[1642] Specific operation: The emotion engine uses speech recognition and facial recognition software to analyze the user's emotions. For example, "If the user is feeling stressed, it will reduce the frequency of notifications and provide detailed situational descriptions to provide reassurance."

[1643] As a result, the entire system enables the rapid maintenance and recovery of communication infrastructure during disasters and provides an operating environment that takes into account the emotional state of the user.

[1644] (Application Example 2)

[1645] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1646] Maintaining communication infrastructure during disasters requires speed and effectiveness. However, current systems often fail to adequately consider user stress and anxiety, resulting in increased user burden. Furthermore, real-time information transmission and power supply during disasters are not adequately achieved. A new system is needed to address these problems.

[1647] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting and processing disaster prediction data and geographic information, means for evaluating disaster risk based on the data, means for simulating the optimal placement of electric vehicles based on the disaster risk evaluation, means for instructing the movement of electric vehicles based on the simulation results, means for directing electric vehicles toward a base station to supply power when a disaster occurs, means for monitoring the user's emotional state in real time and adjusting the notification format based on the results, and means for providing user support using an emotion engine. This makes it possible to maintain communication infrastructure during a disaster while providing flexible responses according to the user's emotional state.

[1648] "Disaster prediction data" refers to information used to predict the risk of disasters, including past disaster data and weather forecast data.

[1649] "Geographic information" refers to data about the topography, population density, infrastructure layout, and other characteristics of a specific region.

[1650] "Disaster risk assessment" is the process of evaluating the likelihood of a disaster occurring based on collected disaster prediction data and geographical information.

[1651] An "electric vehicle" is a vehicle that runs on batteries, and in times of disaster, it plays a role in supplying power to communication equipment.

[1652] "Simulating the optimal placement" refers to the process of calculating the most effective way to deploy electric vehicles based on disaster risk assessments.

[1653] "Instructing movement" means issuing a command to the electric vehicle to move to a specific location based on the simulation results.

[1654] "Supplying power" means that an electric vehicle uses its own battery to provide power to external devices such as communication equipment.

[1655] "User emotional state" refers to the mental state a user is experiencing, such as stress, anxiety, or a sense of security.

[1656] "Real-time monitoring" means constantly monitoring the user's emotional state and detecting any changes immediately.

[1657] "Adjusting notification format" means appropriately changing the content and frequency of notifications according to the user's emotional state.

[1658] An "emotion engine" is software that recognizes a user's emotions and adjusts system operations and notifications based on those emotions.

[1659] This invention specifically aims to realize a system that takes into account the maintenance of communication infrastructure and the emotional state of users during disasters, and consists of the following elements. The system mainly consists of a server, a terminal (electric vehicle), a user, and an emotion engine.

[1660] System Configuration

[1661] server

[1662] The server has the following functions:

[1663] 1. Data Collection: The server collects disaster prediction data and geographical information from weather forecast APIs and historical disaster data APIs. This prepares the server for predicting the risk of disasters.

[1664] 2. Disaster Risk Assessment: Based on the collected data, a generative AI model is used to assess the risk of disaster occurrence. This assessment takes into account past disaster data and current weather forecasts.

[1665] 3. Optimal Deployment Simulation: Based on the disaster risk assessment results, the optimal deployment of electric vehicles will be simulated. The simulation will perform calculations to deploy electric vehicles in areas with a high disaster risk so that they can respond quickly.

[1666] 4. Movement Instructions: Based on simulation results, electric vehicles are instructed to move to specific areas. In the event of a disaster, electric vehicles are also instructed to head towards communication base stations to supply power.

[1667] 5. Emotion Monitoring: An emotion engine is used to monitor the user's emotional state in real time. This allows for the adjustment of notification formats to reduce user stress and anxiety.

[1668] Specific example

[1669] For example, a server retrieves weather data from a weather forecast API, and based on that data, a generated AI model assesses whether there is a high risk of a typhoon approaching in the next few days. Based on this result, the server simulates the optimal placement of electric vehicles and instructs the vehicle closest to the high-risk area to head towards that area.

[1670] Terminal (electric vehicle)

[1671] The terminal (electric vehicle) receives movement instructions from the server, moves to the designated area, and supplies power to the base station.

[1672] As a concrete example, if a base station experiences a power outage due to a disaster, the nearest electric vehicle can travel to the base station to supply power, restarting the communication equipment and restoring communication.

[1673] User

[1674] Users receive notifications from the server and take actions or instructions as needed. Additionally, an emotion engine monitors the user's emotional state, and if the user is experiencing stress or anxiety, the notification frequency is reduced and more detailed explanations of the situation are provided.

[1675] Hardware and software to be used

[1676] Hardware:

[1677] smartphone

[1678] Head-mounted display (HMD)

[1679] electric car

[1680] software:

[1681] Emotion Engine

[1682] Disaster Prediction Engine (DisasterPredictor)

[1683] Web API (weather forecast data, historical disaster data)

[1684] Example of a prompt

[1685] "You are an AI designed to design a system aimed at maintaining communication infrastructure and enabling rapid response during disasters. Define the system outline according to the following requirements."

[1686] Design an AI engine that collects weather forecast data and historical disaster data to predict disaster risk.

[1687] Design an algorithm to simulate the optimal placement of electric vehicles.

[1688] The system incorporates an emotion engine that evaluates the user's emotional state in real time and adjusts the notification format accordingly.

[1689] Please also describe in detail the specific steps, the technologies, hardware, software, and format of the notification.

[1690] The above describes the embodiments for carrying out the present invention. This system not only enables the efficient and rapid maintenance of communication infrastructure during disasters, but also allows for flexible responses that take into account the emotional state of users.

[1691] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1692] Step 1:

[1693] The server collects disaster prediction data and geographical information from a weather forecast API and a historical disaster data API. The input consists of weather forecast data and historical disaster data obtained from the APIs, which are then preprocessed. The output of this process consists of preprocessed disaster prediction data and geographical information.

[1694] Step 2:

[1695] The server uses a generated AI model based on the collected data to assess disaster risk. The input for this step is the pre-processed data obtained in step 1, and the AI ​​model performs calculations to calculate the disaster occurrence risk. The output is the disaster occurrence risk assessment result for a specific area.

[1696] Step 3:

[1697] The server simulates the optimal placement of electric vehicles based on the disaster risk assessment results. The input for this step is the disaster risk assessment results obtained in step 2, and the calculations are performed by the placement simulation software. This outputs the optimal placement plan for electric vehicles.

[1698] Step 4:

[1699] The server sends movement instructions to the electric vehicle based on the simulation results. The input for this step is the placement plan obtained in step 3, a movement instruction is generated, and it is sent to the electric vehicle. The output is the movement instruction received by the electric vehicle.

[1700] Step 5:

[1701] In the event of a disaster, a terminal (electric vehicle) will proceed to a communication base station according to instructions from the server and supply power. The input for this step is an emergency instruction from the server, and the specific action involves the electric vehicle moving, connecting the power supply device upon arrival at the base station, and supplying power to the communication equipment. The output is the restoration of communication at the base station.

[1702] Step 6:

[1703] The server uses an emotion engine to monitor the user's emotional state in real time. The input for this step is the user's voice data and facial expression data, which the emotion engine analyzes to evaluate the user's emotional state. The output is the user's emotional state (e.g., stress level).

[1704] Step 7:

[1705] The server adjusts the notification format based on the user's emotional state, as assessed by the emotion engine. The input for this step is the emotional state data obtained in step 6, and the notification format is adjusted accordingly. Specifically, this involves reducing the frequency of notifications or displaying more detailed situational descriptions to alleviate user stress. The output is the adjusted notification format.

[1706] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1707] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1708] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1709] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1710] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1711] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1712] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1713] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1714] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1715] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1716] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1717] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1718] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1719] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1720] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1721] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1722] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1723] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1724] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1725] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1726] All documents, patent applications, and technical standards described herein are incorpora...

Claims

1. A means of collecting and processing disaster prediction data and geographic information, A means of evaluating disaster risk based on that data, A means for simulating the optimal placement of electric company vehicles based on disaster risk assessment, A means for instructing the movement of an electric company vehicle based on the simulation results, A means of sending electric company vehicles to base stations to supply power in the event of a disaster, A system that includes this.

2. The system according to claim 1, which optimally positions electric vehicles for the purpose of securing power supply to base stations based on the results of a disaster risk assessment.

3. The system according to claim 1, which monitors the power supply status of base stations in real time when a disaster occurs and monitors the battery status of electric company vehicles.

Images