System

Abstract

A system is provided.SOLUTION: A sensor that measures a water level of a river, a server that receives data from the sensor and determines whether the water level has reached a dangerous water area, means for the server to predict a damage assumed area using weather map data and water level data, and means for the server to generate a flight path of a drone based on the predicted damage assumed area, A system comprising: means for automatically creating a flight plan; means for causing the drone to fly, photographing a damage situation from the sky, and transmitting the data to the server; means for causing the drone to perform evacuation guidance by voice in a damage assumed area; and means for causing the server to transfer the received data to a terminal of a local government staff in real time.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional disaster information transmission methods take time to transmit information, resulting in delays in evacuation and situation assessment. This poses a risk of exacerbating the damage. The purpose of this invention is to solve these problems and enable quick and accurate evacuation guidance and situation assessment. [Means for solving the problem]

[0005] The present invention is a system that includes a sensor that measures the water level of a river, a server that receives data from the sensor and determines whether the water level has reached a dangerous level, means for the server to predict an area expected to be damaged using weather map data and water level data, means for the server to generate a flight path for a drone based on the predicted area expected to be damaged and automatically create a flight plan, means for the drone to fly, photograph the damage situation from the air, and send the data to the server, means for the drone to provide evacuation guidance by voice in the area expected to be damaged, and means for the server to transfer the data received in real time to the terminals of local government employees.

[0006] A "sensor" is a device for measuring the water level of a river and has the function of sending the measurement results to a server.

[0007] A "server" is a computer system that receives data sent from sensors, stores it, analyzes it, and performs the necessary processing.

[0008] A "dangerous water area" is an area where it is judged that there is a high possibility of a disaster occurring if the water level of a river exceeds a certain height.

[0009] "Weather chart data" refers to charts showing weather conditions created based on meteorological observation data, and is data used in forecast models.

[0010] "Expected damage areas" are areas that are likely to be affected by a disaster, as predicted using an AI model.

[0011] A "drone" is an unmanned aerial vehicle that automatically flies a designated flight path and performs tasks such as taking photographs and providing audio guidance.

[0012] A "flight path" is the route a drone will take to reach the expected damage area, and is generated based on predicted data.

[0013] "Real-time" means that the entire process of data generation, transmission, and processing occurs without delay.

[0014] "Local government employee terminals" refer to communication devices such as computers and smartphones that local government employees use to receive disaster information and check the situation.

[0015] "Voice guidance" is a function in which the drone automatically transmits a voice message to residents in areas expected to be affected, urging them to evacuate. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0024] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0037] This invention provides a system that combines sensors that measure river water levels, a server that processes the information, and drones that monitor disaster situations and provide evacuation guidance. This system enables rapid information collection and evacuation guidance for residents in the event of a disaster.

[0038] Program processing flow

[0039] The processing of the system program will be explained in natural language below.

[0040] Water level monitoring with sensors

[0041] 1. The server periodically collects water level data from sensors installed in the river. The sensors measure the river's water level in real time, so the server can receive the latest water level information at any time.

[0042] Determining dangerous waters

[0043] 2. The server determines whether the water level has reached the danger zone based on the received data. If the water level has reached the danger zone, the system proceeds to the next step.

[0044] Prediction of expected damage areas

[0045] 3. The server uses weather map data and past disaster data to predict areas expected to be affected using an AI model (e.g., the Gemini model). This prediction makes it possible to determine which areas will be affected and to what extent.

[0046] Flight planning

[0047] 4. The server generates a flight path for the drone based on the predicted damage area. The generated flight path is sent to the drone and executed automatically.

[0048] Drone flight and evacuation guidance

[0049] 5. The device (drone) begins flying according to the flight path received from the server. During flight, the drone photographs the damage from above and sends the data to the server in real time. The photographed data can be used to grasp the detailed damage situation.

[0050] 6. When the device (drone) reaches the predicted damage area, it begins to provide voice guidance using its built-in speaker. It repeatedly plays messages such as, "Everyone in City A, please evacuate to higher ground immediately."

[0051] Real-time information transfer

[0052] 7. The server transfers the images and video data received from the drone to the local government employee's device in real time, allowing the user (local government employee) to immediately check the situation on site and respond promptly.

[0053] Specific examples

[0054] Case 1: Rising river water levels

[0055] 1. The server receives water level data from a river sensor and detects that the water level has exceeded 3 meters. This data indicates that the water level is beyond the danger zone, and the server switches to disaster response mode.

[0056] 2. The server uses weather map data and the latest water level data to predict the expected damage area, "Urban Area A," using an AI model.

[0057] 3. The server generates a flight path for the drone based on the prediction results and sends it to the drone.

[0058] 4. The device (drone) automatically begins flying and reaches city A. During the flight, it takes video and transmits it to the server in real time.

[0059] 5. The drone will broadcast an audio message in the area of ​​expected damage saying, "Please evacuate to higher ground immediately."

[0060] 6. The server receives data from the drone and transfers it to the local government employee's device, allowing the user (local government employee) to grasp the situation in real time and quickly issue evacuation instructions to residents.

[0061] In this way, the system of the present invention can quickly collect information, grasp the situation, and provide effective evacuation guidance in the event of a disaster.

[0062] The processing flow will be explained below.

[0063] Step 1:

[0064] The server periodically collects water level data from water level sensors installed in the river. The sensors measure the water level in real time and send the data to the server.

[0065] Step 2:

[0066] The server stores the received water level data in a database, which is used for subsequent analysis.

[0067] Step 3:

[0068] The server periodically retrieves the latest water level data from the database and determines whether the water level has reached a dangerous level. If the water level reaches the set dangerous level, an alert is triggered.

[0069] Step 4:

[0070] The server retrieves weather chart data and past disaster data to prepare the data needed for the forecasting model, which is then processed and analyzed within the server.

[0071] Step 5:

[0072] The server uses an AI model (e.g., the Gemini model) to predict the likely damage area based on weather map data and water level data. This prediction identifies which specific areas will be affected.

[0073] Step 6:

[0074] The server automatically generates a drone flight path based on the predicted damage area, and transmits the generated flight plan information to the drone.

[0075] Step 7:

[0076] The terminal (drone) begins flying based on the flight path information received from the server. The drone uses sensors such as GPS to confirm its position and flies the planned path accurately.

[0077] Step 8:

[0078] The terminal (drone) arrives at the predicted damage area and takes pictures of the situation from above. The captured images and video data are sent to the server in real time.

[0079] Step 9:

[0080] The device (drone) plays a pre-recorded evacuation guidance message to residents in the predicted affected area, saying, "Everyone in City A, please evacuate to higher ground immediately."

[0081] Step 10:

[0082] The server receives real-time image and video data sent from the drone and forwards it to the terminals of local government employees.

[0083] Step 11:

[0084] The user (municipal government employee) checks the received real-time data on the terminal, allowing the user to immediately grasp the situation on-site and take the necessary measures promptly.

[0085] Through this series of steps, the system of the present invention can effectively collect information quickly, provide appropriate evacuation instructions, and grasp the situation in real time during a disaster.

[0086] Example 1

[0087] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0088] Conventional disaster monitoring systems have difficulty in real-time monitoring of rising river water levels and issuing prompt evacuation instructions, and effective responses are needed to minimize damage during disasters. In particular, it is challenging to quickly collect information in wide-ranging areas where damage is expected and issue appropriate evacuation instructions to residents.

[0089] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0090] In this invention, the server includes a means for receiving data from the sensor and determining whether the water level has reached a dangerous level, a means for predicting areas expected to be affected by damage using meteorological data and water level data, and a means for generating a flight path for the unmanned aerial vehicle based on the predicted areas expected to be affected and automatically creating a flight plan, which enables rapid information gathering and evacuation instructions to residents in the event of a disaster.

[0091] A "sensor" is a device that measures the water level of a river and transmits the measurement data to a server via a wireless network.

[0092] A "server" is a central processing unit that analyzes data received from sensors and performs various processes based on that data.

[0093] "Weather data" refers to data that indicates current and past weather conditions, such as weather maps, precipitation, and wind speed.

[0094] "Water level data" is quantitative data on the water level of a river measured by a sensor.

[0095] "Expected damage area" refers to an area that is likely to be affected by a predicted disaster.

[0096] An "unmanned aerial vehicle" is an aircraft that can be flown remotely or by automated program, commonly referred to as a drone.

[0097] "Flight route" refers to route information for an unmanned aerial vehicle, including the departure point, intermediate points, and destination.

[0098] A "flight plan" is a plan that includes specific flight routes and operational procedures that an unmanned aerial vehicle will execute based on a predicted damage area.

[0099] "Voice evacuation instructions" are a method of transmitting audio messages urging residents to evacuate via speakers installed on unmanned aerial vehicles.

[0100] "Administrative employee terminal" refers to a computer or mobile device used by an administrative employee to receive and check real-time data from the server.

[0101] The present invention provides a system that combines sensors that measure river water levels, a server that processes information, and an unmanned aerial vehicle that monitors disaster situations and provides evacuation guidance. This system enables rapid information collection and evacuation guidance for residents in the event of a disaster.

[0102] Water level monitoring with sensors

[0103] The sensors are installed in the river and measure the water level periodically. The measurement data is sent to a server via a wireless network. The sensors enable real-time monitoring of the river's water level.

[0104] Determining dangerous waters

[0105] The server analyzes water level data received periodically from the sensors and determines whether the water level has reached a preset danger zone. The database and analysis tools used here enable rapid detection of danger zones.

[0106] Prediction of expected damage areas

[0107] The server uses water level data and meteorological data to generate AI models (e.g., the Gemini model) to predict areas expected to be affected. The server also references data from past disasters to make detailed predictions of the degree of impact and the extent of damage.

[0108] Flight planning

[0109] The server generates a flight path for the drone based on the predicted damage area and transmits this information to the drone, which uses a flight planning tool to create a precise flight path.

[0110] Unmanned aerial vehicle flight and damage monitoring

[0111] The drone begins flying according to the flight path received from the server. During flight, the drone uses its camera to capture images of the damage and transmits the data to the server in real time, allowing for a detailed understanding of the damage situation.

[0112] Evacuation guidance using unmanned aerial vehicles

[0113] When the drone reaches the predicted damage area, it will begin to provide voice guidance using its built-in speaker. For example, it will repeatedly announce messages such as, "Everyone in City A, please evacuate to higher ground immediately."

[0114] Real-time information transfer

[0115] The server transfers the video data received from the unmanned aerial vehicle to the terminals of government officials in real time, allowing them to immediately grasp the situation on the ground and respond promptly.

[0116] Specific examples

[0117] Case 1: Rising river water levels

[0118] The server receives data from the river sensor that the water level has exceeded three meters. This data indicates that the water level is beyond the danger zone, and the server switches to disaster response mode.

[0119] 1. The server uses weather map data and the latest water level data to predict the expected damage area, "Urban Area A," using a generative AI model.

[0120] 2. The server generates a flight path for the unmanned aircraft based on the prediction results and sends it to the unmanned aircraft.

[0121] 3. The unmanned aircraft automatically begins flying and reaches "Urban Area A." During the flight, it takes video and transmits it to the server in real time.

[0122] 4. Unmanned aerial vehicles will broadcast an audio message in areas expected to be affected, saying, "Please evacuate to higher ground immediately."

[0123] 5. The server receives the data sent from the unmanned aerial vehicle and transfers it to the terminals of government officials, allowing them to grasp the situation in real time and issue quick evacuation instructions to residents.

[0124] Prompt Sentence Examples

[0125] Sample prompt 1: "If the water level of a river suddenly rises, how would you predict the areas likely to be affected and guide people to evacuate?"

[0126] Example prompt 2: "Please tell me specifically what the flight route of the unmanned aerial vehicle will be and how to provide evacuation instructions in the event of a flood in City A."

[0127] In this way, the system of the present invention can quickly collect information, grasp the situation, and provide effective evacuation guidance in the event of a disaster.

[0128] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0129] Step 1: Collect water level data from sensors

[0130] The server periodically collects water level data from the sensor. The sensor measures the river's water level every minute and sends the data to the server via a wireless network. The input data is water level information from the sensor, which the server receives and records in a database. Specifically, the server receives data from the sensor, records it in a database, and maintains the latest water level status.

[0131] Input: Water level data from the sensor

[0132] Output: Recorded water level data

[0133] Step 2: Determine the danger zone

[0134] Based on the water level data collected by the server, it determines whether the latest water level has reached the set dangerous water level. The input data is water level information from the sensor, which the server analyzes and compares with the dangerous water level threshold. The output is the result of the determination of whether the dangerous water level has been reached. Specifically, the server analyzes the water level data, compares it with the threshold, and issues a system alert if the dangerous water level has been reached.

[0135] Input: Water level data from the sensor

[0136] Output: Dangerous waters determination result

[0137] Step 3: Prediction of potential damage areas

[0138] The server uses weather map data and past disaster data to utilize an AI model (e.g., the Gemini model) to predict areas of potential damage. The input data is the latest water level data and weather data, which are input into the AI ​​model. The output is the predicted areas of potential damage. Specifically, the server collects weather map data and past disaster data, inputs them into the AI ​​model, obtains the prediction results, and identifies the areas of potential damage.

[0139] Input: Water level data, weather data, past disaster data

[0140] Output: Estimated damage area

[0141] Step 4: Drone flight path generation

[0142] The server generates a flight path for the unmanned aerial vehicle based on the predicted expected damage area. The input data is the location information of the expected damage area, and the flight path is calculated based on this. The output is the generated flight path. Specifically, the server identifies important monitoring points from the prediction results, calculates and generates a flight path, and sends the generated flight path to the unmanned aerial vehicle.

[0143] Input: Location information of the expected damage area

[0144] Output: Flight path information

[0145] Step 5: Fly the drone and monitor the damage

[0146] The terminal (unmanned aerial vehicle) takes off according to the flight route received from the server and flies the specified route. The input data is flight route information, and the unmanned aerial vehicle collects data while flying according to this information. The output is the captured video data. Specifically, the unmanned aerial vehicle flies automatically, takes photos and videos of the location with a camera, and transfers the video data to the server in real time.

[0147] Input: Flight route information

[0148] Output: Recorded video data

[0149] Step 6: Drone evacuation guidance

[0150] When the terminal (unmanned aerial vehicle) reaches the predicted damage area, it uses a built-in speaker to provide voice guidance. The input data is a voice message sent from the server, which the unmanned aerial vehicle relays to residents. The output is a voice guidance message to residents. Specifically, the unmanned aerial vehicle repeatedly plays a designated message, calling on residents to evacuate.

[0151] Input: Voice message

[0152] Output: Voice guidance

[0153] Step 7: Real-time data transfer

[0154] The server transfers real-time images and video data sent from the unmanned aerial vehicle to the terminals of local government employees. The input data is the video data received from the unmanned aerial vehicle, which the server sends to the terminals of local government employees. The output is the data transferred to the terminals of local government employees. Specifically, the server processes the data received from the drone and transfers it to the terminals of local government employees in real time. The administrative staff can then check the data and take on-site action as necessary.

[0155] Input: Video data from an unmanned aerial vehicle

[0156] Output: Data transferred to the administrative staff's terminal

[0157] (Application example 1)

[0158] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0159] When river water levels reach dangerous levels, it is extremely important to quickly and accurately collect disaster information and provide evacuation instructions to residents. Conventional technologies can result in delays in information collection and evacuation instructions, potentially resulting in greater damage. Furthermore, there are limitations to predicting affected areas in real time and generating appropriate evacuation messages. The objective of this invention is to solve these shortcomings and provide an effective disaster response system.

[0160] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0161] In this invention, the server includes a means for predicting estimated damage areas using a generative AI model and generating appropriate evacuation guidance messages for residents, a means for an unmanned aerial vehicle to transfer image data of estimated damage areas to the server in real time and perform continuous predictions and responses using the generative AI model, and a means for a drone to fly and photograph the damage situation from the air and send the data to the server, thereby enabling rapid and accurate information collection and appropriate evacuation guidance.

[0162] A "sensor" is a device that measures the water level of a river in real time and transmits the data to a server.

[0163] The "server" is a central processing unit that receives data from sensors, processes the data, and predicts dangerous water levels and areas of potential damage.

[0164] "Weather map data" is data that shows meteorological information, and is used in particular to grasp meteorological conditions in real time and predict areas likely to be affected.

[0165] An "unmanned aerial vehicle" is an aircraft that is remotely controlled or flies autonomously to monitor disaster situations and collect and transmit data.

[0166] "Flight path" refers to the designated route taken by an unmanned aerial vehicle.

[0167] A "flight plan" refers to a specific plan for an unmanned aerial vehicle to fly automatically based on a flight path.

[0168] "Estimated damage area" refers to an area that the server predicts will be affected by a disaster using weather map data and water level data.

[0169] A "generative AI model" is a model that uses machine learning and artificial intelligence technology to analyze data and predict areas of potential damage.

[0170] "Evacuation instruction messages" refer to audio or text instructions to encourage residents in areas expected to be affected to take appropriate evacuation actions.

[0171] "Image data" refers to photographs and videos of disaster situations taken from the air by unmanned aerial vehicles.

[0172] "Local government employee terminals" refers to communication terminals such as computers and smartphones used by local government employees for disaster response purposes.

[0173] This invention provides a system that combines sensors that measure river water levels, a server that processes the information, and an unmanned aerial vehicle that monitors disaster situations and provides evacuation guidance. This system enables rapid information collection and evacuation guidance for residents in the event of a disaster.

[0174] The entire system is realized by the following hardware and software configuration.

[0175] Hardware Configuration

[0176] 1. Water level sensor: A device installed in a river to measure the water level in real time.

[0177] 2. Server: The central processing unit that receives data from sensors and performs analysis and predictions.

[0178] 3. Unmanned aerial vehicles: Aircraft that monitor disaster situations from the sky, collect data in real time, and provide evacuation instructions to residents.

[0179] 4. Local government employee devices: Communication devices such as computers and smartphones.

[0180] Software Configuration

[0181] 1. Data collection module: Software that collects water level data from sensors and sends it to the server.

[0182] 2. Data analysis module: Software that uses collected data to determine whether water levels have reached dangerous levels and uses a generative AI model to predict potential damage areas.

[0183] 3. Flight plan generation module: Software that generates flight paths for unmanned aerial vehicles based on the expected damage area and automatically creates flight plans.

[0184] 4. Real-time data transfer module: Software that transfers data sent from unmanned aerial vehicles to local government employee terminals in real time.

[0185] 5. Voice guidance module: Software that uses the prediction results to enable unmanned aerial vehicles to provide voice guidance on evacuation in areas expected to be affected.

[0186] Data processing and calculation flow

[0187] The server first collects water level data periodically sent from the sensors. This data is sent to the server in real time and used to determine whether the water level has reached a dangerous level. If the determination is that the water level is dangerous, the server uses weather map data and past disaster data to predict the likely damage area using a generative AI model (e.g., machine learning or artificial intelligence technology).

[0188] Example prompts for generative AI models

[0189] Based on these prompts, the server predicts the expected damage area and generates a flight plan accordingly. The unmanned aerial vehicle then flies along a flight path generated based on the prediction results, photographing the damage situation from the air in real time and sending the data to the server. This data is then received by the devices of local government employees, enabling them to immediately grasp the situation on site and take prompt action.

[0190] Examples of prompt statements

[0191] "Please predict the area of ​​potential damage if the river water level exceeds 3 meters."

[0192] In this way, the entire system will work together to enable rapid and accurate information gathering and appropriate responses in the event of a disaster.

[0193] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0194] Step 1:

[0195] Water level data collection

[0196] The server periodically collects water level data from sensors installed in the river. The input data is the water level measurement data sent from the sensor, and the output data is the water level data stored in the server's internal database. Specifically, the server retrieves data from the sensor using an HTTP request.

[0197] Step 2:

[0198] Determining dangerous waters

[0199] The server determines whether the water level has reached a dangerous level based on the received water level data. The input data is the collected water level data, and the output data is a flag indicating whether the water level has reached a dangerous level. Specifically, the server compares the water level data with the set dangerous water level threshold and sets a flag if the threshold is exceeded.

[0200] Step 3:

[0201] Prediction of expected damage areas

[0202] When a dangerous water area flag is raised, the server uses weather map data and past disaster data to use a generative AI model to predict the area of ​​expected damage. The input data is water level data, weather map data, and past disaster data, and the output data is information on the area of ​​expected damage. In concrete terms, the server gives the generative AI model specific instructions, such as a prompt statement and argument data, such as "area of ​​expected damage if the river water level exceeds 3 meters," and receives the prediction results from the model.

[0203] Step 4:

[0204] Flight plan generation

[0205] The server generates a flight path for the unmanned aerial vehicle based on the predicted damage area and automatically creates a flight plan. The input data is information about the damage area, and the output data is specific flight path information. Specifically, the server calculates the optimal flight path based on GPS data and transmits it to the unmanned aerial vehicle.

[0206] Step 5:

[0207] Unmanned aerial vehicle flight and data collection

[0208] The unmanned aerial vehicle begins flying according to the flight path received from the server. During flight, the unmanned aerial vehicle photographs the damage situation from the sky and transmits the data to the server in real time. The input data is flight path information, and the output data is the photographed image data. Specifically, the unmanned aerial vehicle uses a camera to capture images from the sky and transfers them to the server via wireless communication.

[0209] Step 6:

[0210] Generation and execution of evacuation guidance messages

[0211] Based on the prediction results, the server generates a message calling for evacuation for residents in the predicted damage area and transmits it as audio guidance to the unmanned aerial vehicle. The input data is the predicted damage area and the message information generated by the generation AI model, and the output data is the audio guidance message. Specifically, the server uses the generation AI model to create an evacuation message and plays it through the speaker on the unmanned aerial vehicle.

[0212] Step 7:

[0213] Real-time information transfer

[0214] The server transfers the image and video data received from the unmanned aerial vehicle to the local government employee's device in real time. The input data is image data from the unmanned aerial vehicle, and the output data is real-time video to the local government employee's device. Specifically, the server immediately packets the received data and sends a push notification to each local government employee's device.

[0215] This series of processes enables the system to quickly and accurately collect information and provide appropriate evacuation instructions.

[0216] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0217] This invention is a system that combines sensors that measure river water levels, a server that processes information, drones that monitor disaster situations and provide evacuation guidance, and an emotion engine that recognizes the user's emotions. The system aims to quickly collect information during disasters, provide evacuation guidance to residents, and provide emotional support to local government officials.

[0218] Program processing flow

[0219] The processing of the system program will be explained in natural language below.

[0220] Water level monitoring with sensors

[0221] 1. The server periodically collects water level data from water level sensors installed in the river. The sensors measure the river's water level in real time and send the data to the server.

[0222] Determining dangerous waters

[0223] 2. The server determines whether the water level has reached the danger zone based on the received data. If the water level has reached the danger zone, the system proceeds to the next step.

[0224] Prediction of expected damage areas

[0225] 3. The server uses weather map data and past disaster data to predict areas expected to be affected using an AI model (e.g., the Gemini model). This prediction makes it possible to determine which areas will be affected and to what extent.

[0226] Flight planning

[0227] 4. The server generates a flight path for the drone based on the predicted damage area. The generated flight path is sent to the drone and executed automatically.

[0228] Drone flight and evacuation guidance

[0229] 5. The device (drone) begins flying according to the flight path received from the server. During flight, the drone photographs the damage from above and sends the data to the server in real time. The photographed data can be used to grasp the detailed damage situation.

[0230] 6. When the device (drone) reaches the predicted damage area, it begins to provide voice guidance using its built-in speaker. It repeatedly plays messages such as, "Everyone in City A, please evacuate to higher ground immediately."

[0231] Real-time information transfer

[0232] 7. The server transfers the images and video data received from the drone to the local government employee's device in real time, allowing the user (local government employee) to immediately check the situation on site and respond promptly.

[0233] Use of emotion engine

[0234] 8. The server uses an emotion engine to monitor the stress levels and emotional state of local government employees. If stress levels are found to be elevated, relaxation and support messages are automatically sent.

[0235] 9. The device (drone) will recognize the emotions of residents in the predicted affected area and play appropriate voice guidance depending on their emotional state. For example, if anxiety is rising, it will play a message such as "Please remain calm and follow evacuation instructions."

[0236] Specific examples

[0237] Case 1: Rising river water levels

[0238] 1. The server receives water level data from a river sensor and detects that the water level has exceeded 3 meters. This data indicates that the water level is beyond the danger zone, and the server switches to disaster response mode.

[0239] 2. The server uses weather map data and the latest water level data to predict the expected damage area, "Urban Area A," using an AI model.

[0240] 3. The server generates a flight path for the drone based on the prediction results and sends it to the drone.

[0241] 4. The device (drone) automatically begins flying and reaches city A. During the flight, it takes video and transmits it to the server in real time.

[0242] 5. The drone will broadcast an audio message in the affected area saying, "Please evacuate to higher ground immediately." If residents feel anxious, the emotion recognition system will detect this and switch to a more reassuring message.

[0243] 6. The server receives data from the drone and transfers it to the local government employee's device, allowing the user (local government employee) to grasp the situation in real time and quickly issue evacuation instructions to residents.

[0244] Case 2: Stress management for local government employees

[0245] 1. An emotion engine installed on the server monitors the stress levels of local government employees.

[0246] 2. If the stress level of staff increases during disaster response, the server automatically sends a relaxation message to the staff's device.

[0247] 3. Users (municipal government officials) can reduce stress and continue to respond calmly.

[0248] In this way, the system of the present invention can respond to disasters more effectively by quickly gathering information and providing evacuation instructions during disasters, as well as providing emotional support to local government officials.

[0249] The processing flow will be explained below.

[0250] Step 1:

[0251] The server periodically collects water level data from water level sensors installed in the river. The sensors measure the water level in real time and send the data to the server.

[0252] Step 2:

[0253] The server stores the received water level data in a database, which is used for subsequent analysis.

[0254] Step 3:

[0255] The server periodically retrieves the latest water level data from the database and determines whether the water level has reached a dangerous level. If the water level reaches the set dangerous level, an alert is triggered.

[0256] Step 4:

[0257] The server receives weather chart data and past disaster data, which are then processed and used to predict potential damage areas in the event of a dangerous water zone.

[0258] Step 5:

[0259] The server uses AI models to analyze weather map data and water level data to predict potential damage areas, which can then identify which areas will be affected.

[0260] Step 6:

[0261] The server generates a flight path for the drone based on the predicted damage area, and transmits the generated flight plan information to the drone.

[0262] Step 7:

[0263] The terminal (drone) begins flying based on the flight path information received from the server. The drone uses sensors such as GPS to confirm its position and flies the planned path accurately.

[0264] Step 8:

[0265] The terminal (drone) arrives at the predicted damage area and takes pictures of the situation from above. The captured images and video data are sent to the server in real time.

[0266] Step 9:

[0267] The device (drone) plays a pre-recorded evacuation guidance message to residents in the predicted affected area, saying, "Everyone in City A, please evacuate to higher ground immediately."

[0268] Step 10:

[0269] The server receives real-time image and video data sent from the drone and transfers it to the terminals of local government employees in real time.

[0270] Step 11:

[0271] The server uses an emotion engine to monitor the stress levels and emotional state of local government employees, and if stress is judged to be increasing, it automatically sends relaxation and support messages.

[0272] Step 12:

[0273] The device (drone) recognizes the emotions of residents in the predicted affected area and plays appropriate voice guidance according to their emotional state. For example, if anxiety is rising, it will play a message such as "Please remain calm and follow evacuation instructions."

[0274] Step 13:

[0275] The user (municipal government employee) checks the received real-time data on the device. The user can immediately grasp the situation on the ground and take the necessary measures. In addition, the user can maintain a calm mind by receiving relaxation messages from the emotion engine.

[0276] Through this series of steps, the system of the present invention can effectively gather information quickly, provide appropriate evacuation instructions, and provide emotional support to local government officials in the event of a disaster.

[0277] Example 2

[0278] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0279] During natural disasters, the challenges are to quickly and accurately gather information, provide evacuation instructions to residents, and comprehensively manage the stress of local government employees. In particular, there is a need for a system that can simultaneously grasp on-site information in real time during a disaster and manage the emotions of residents and local government employees.

[0280] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0281] In this invention, the server includes means for receiving data from a sensor measuring the river water level and determining whether the water level has reached a dangerous level, means for predicting potential damage areas using weather map data and water level data, and means for generating a flight path for the flying machine based on the predicted potential damage areas and automatically creating a flight plan, which enables the rapid collection of disaster information, accurate evacuation guidance, and stress management for local government officials.

[0282] A "sensor for measuring river water levels" is a device that measures river water levels in real time and sends the data to a server.

[0283] A "server" is a central processing unit that receives data from sensors, analyzes it, and executes various processes.

[0284] "Weather map data" is a data set containing meteorological information and is used to predict weather fluctuations.

[0285] "Water level data" is a data set that shows the current water level and its fluctuations in a river.

[0286] A "potential damage area" is a specific geographical area that is expected to be affected in the event of a disaster.

[0287] A "flying machine" is a device that can fly autonomously and gather information from the air, generally referring to drones or unmanned aerial vehicles (UAVs).

[0288] "Flight path" means the planned route to be followed by a flying vehicle.

[0289] "Voice evacuation guidance" is a method in which flying machines use voice messages to encourage residents to evacuate.

[0290] An "administrator's terminal" is a computer or mobile device used by an administrator, such as a local government employee.

[0291] The "Emotion Engine" is a system that analyzes an individual's emotional state and monitors stress levels and emotional responses.

[0292] "Stress level" is a measure of the degree of psychological pressure or burden felt by an individual.

[0293] "Emotional state" refers to an individual's current emotional or mood state.

[0294] This invention is a system that uses river water level measurement sensors, a server that processes the data, a flying machine that monitors disaster situations and guides evacuation, and an emotion engine that recognizes the emotions of administrators. The system aims to quickly collect information in the event of a disaster, provide evacuation instructions to residents, and provide emotional support to local government officials.

[0295] First, the main components of the system will be described.

[0296] A river water level measurement sensor is a device that is installed in a specific area of ​​a river and measures water level data in real time. For example, a general water level measurement device is used.

[0297] The server is a device that periodically collects data from the sensors and analyzes it. It is equipped with an analytical algorithm that determines whether the water level has reached a preset danger level. The server also uses weather chart data and past disaster data to predict potential damage areas using an AI model (such as the Gemini model).

[0298] The flying machine (drone) is a device for monitoring the situation in the predicted damage area from the sky, and automatically generates a flight path and flies based on instructions from the server. During the flight, it takes images from the sky and sends the data to the server in real time. It also provides evacuation guidance through audio guidance.

[0299] The administrator's terminal is a device that receives data from the server and checks the situation on site in real time, and has emergency response apps and dedicated software installed.

[0300] The emotion engine is a system that monitors the stress level and emotional state of the administrator and sends relaxation messages as needed.

[0301] Specific examples are shown below.

[0302] Case 1: Rising river water levels

[0303] 1. The server receives water level data from a river sensor and detects that the water level has exceeded 3 meters. This data indicates that the water level has exceeded the danger level, and the server switches to disaster response mode.

[0304] 2. The server uses weather map data and the latest water level data to predict the expected damage area, "Urban Area A," using an AI model.

[0305] 3. The server generates a flight path for the flying machine based on the prediction results and sends it to the flying machine.

[0306] 4. The terminal (flying machine) automatically begins flying and reaches city A. During the flight, it takes video and transmits it to the server in real time.

[0307] 5. Flying machines will broadcast an audio message in the affected area saying, "Please evacuate to higher ground immediately." If residents feel anxious, an emotion recognition system will detect this and switch to a more reassuring message.

[0308] 6. The server receives data from the flying machine and transfers it to the administrator's terminal, allowing the user (administrator) to grasp the situation in real time and quickly issue evacuation instructions to residents.

[0309] Case 2: Stress management for local government employees

[0310] 1. An emotion engine installed on the server monitors the stress levels of local government employees.

[0311] 2. If the stress level of staff increases during disaster response, the server automatically sends a relaxation message to the staff's device.

[0312] 3. Users (staff) can reduce stress and continue to respond calmly.

[0313] To achieve this, the system uses prompt statements such as:

[0314] "Generate an appropriate evacuation guidance message when the river water level reaches 3 meters."

[0315] "Please provide an example of a relaxation message for local government employees when their stress levels increase."

[0316] "Please tell us how you specifically use AI models to predict potential damage areas."

[0317] As described above, the present invention enables the rapid collection of disaster information, accurate evacuation guidance, and emotional support for local government officials, thereby improving disaster response capabilities.

[0318] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0319] Step 1:

[0320] The server collects data from river water level sensors. The input is water level data from the sensors, and the output is water level data stored in a database on the server.

[0321] The server sends an HTTP request to the sensor via the network to retrieve the data. The retrieved data includes a timestamp and geolocation information. For example, "Sensor ID: 001, Water level: 3.2 meters, Timestamp: 2023-10-04T14:00:00Z".

[0322] Step 2:

[0323] The server analyzes the water level data and determines whether the water level has reached the set danger level. The input is the collected water level data, and the output is the setting of the danger state flag.

[0324] The server uses a condition determination algorithm to set a danger flag if the water level exceeds a threshold (e.g., 3 meters). For example, "Current water level: 3.2 meters, Set threshold: 3.0 meters, Danger state: Active."

[0325] Step 3:

[0326] The server inputs weather map data, past disaster data, and the latest water level data into the AI ​​model to predict the likely damage area. The inputs are weather map data, past disaster data, and water level data, and the output is the likely damage area and its impact.

[0327] The server uses Google Cloud Platform's AI services and its own Gemini model to output the prediction results as potentially affected areas and the level of damage (e.g., "Urban Area A: High, Rural Area B: Medium").

[0328] Step 4:

[0329] The server generates a flight path for the flying machine based on the predicted damage area. The input is the predicted damage area and its impact, and the output is flight path data in JSON format.

[0330] The server calculates the optimal flight route and sends the data to the flying machine. For example, "Flight route: Start point (latitude: 35.6895, longitude: 139.6917) → City A (latitude: 35.6895, longitude: 139.7000) → End point (latitude: 35.7000, longitude: 139.7100)".

[0331] Step 5:

[0332] The terminal (flying machine) starts automatic flight according to the flight path received from the server. The input is the flight path data sent from the server, and the output is the captured video data.

[0333] The flying machine flies autonomously along a designated route using GPS, capturing video of the situation from above. The captured video data is then sent to a server in real time. For example, the video may be "video of the flooding situation in City A."

[0334] Step 6:

[0335] When the terminal (flying machine) reaches the predicted damage area, it starts to give voice guidance through the built-in speaker. The input is the evacuation guidance message sent from the server, and the output is the broadcast voice message.

[0336] The flying machine constantly broadcasts messages calling for evacuation. For example, it might say, "Everyone in City A, please evacuate to higher ground immediately." If residents feel anxious, it uses an emotion recognition system to change the message to, "Please remain calm and follow evacuation instructions."

[0337] Step 7:

[0338] The server transfers the image and video data received from the flying machine to the administrator's terminal in real time. The input is the video data from the flying machine, and the output is the real-time video displayed on the administrator's terminal.

[0339] The server transfers data through a dedicated app or web interface, such as "Video showing widespread flooding in City A."

[0340] Step 8:

[0341] The server monitors the stress level and emotional state of the administrator using an emotion engine, where the input is biometric data from the administrator and the output is an assessment of the administrator's emotional state and stress level.

[0342] The emotion engine analyzes biosensor and input data and automatically sends relaxation messages when stress levels rise. For example, "Employee 1's stress level: High, Relaxation Message: 'Take a deep breath and relax.'"

[0343] Step 9:

[0344] The terminal (flying machine) recognizes the emotions of residents in the predicted damage area and provides appropriate voice guidance according to their emotional state. The input is the residents' emotional data collected during flight, and the output is a voice message according to their emotional state.

[0345] The flying machine uses AI to analyze voices and play reassuring messages if anxiety levels are high. For example, "Residents' emotional state: anxiety, guidance message: 'Please remain calm and follow evacuation instructions.'"

[0346] (Application example 2)

[0347] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0348] Conventional river monitoring systems have had issues with rapid response and evacuation guidance in the event of a disaster. Logistics centers also need to streamline inventory management and transportation operations, as well as manage employee stress. The purpose of this invention is to provide a system that can solve these issues and respond efficiently and quickly.

[0349] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0350] In this invention, the server includes: means for receiving data from a sensor measuring the river water level and determining whether the water level has reached a dangerous level; means for predicting an estimated damage area using weather map data and water level data; means for generating a flight path for an unmanned aerial vehicle based on the predicted estimated damage area and automatically creating a flight plan; means for the unmanned aerial vehicle to fly, photograph the damage situation from the air, and transmit the photographed data; means for the unmanned aerial vehicle to provide evacuation guidance via voice in the estimated damage area; means for periodically collecting data from an inventory sensor and determining whether inventory has fallen below a threshold; means for predicting product delivery timing using past data and a generative AI model; means for generating a movement route for an automated transport robot based on the predicted delivery timing and automatically creating a plan; means for the automated transport robot to transport products along the movement route and transmit the data; means for transferring the received data to an employee terminal at a logistics center in real time; and means for monitoring the stress levels of logistics center employees using an emotion engine and sending relaxation messages as necessary. This enables rapid information collection and evacuation guidance during a disaster, efficient inventory management and product delivery, and employee stress management.

[0351] A "sensor for measuring river water levels" is a device that measures river water levels in real time and sends the data to a server.

[0352] A "server" is a central control device that receives data from sensors and processes and analyzes it.

[0353] "Weather map data" refers to data that includes meteorological information and is used for disaster prediction.

[0354] "Expected damage area" refers to an area that is predicted to be affected if a disaster occurs.

[0355] An "unmanned aerial vehicle" is an aircraft that flies under remote control or automatic control.

[0356] A "flight path" is the route that an unmanned aerial vehicle follows as it flies.

[0357] "Periodic" means repeated at regular intervals.

[0358] An "inventory sensor" is a device that measures product inventory in a warehouse.

[0359] A "generative AI model" is a mathematical model used to analyze and predict data generated by artificial intelligence.

[0360] An "automatic transport robot" is a robot that automatically transports goods within a logistics center.

[0361] A "distribution center staff terminal" is a terminal used by staff at a distribution center to display and operate data.

[0362] The "emotion engine" is a system that analyzes the user's emotional state and responds based on the results.

[0363] A "relaxation message" is a message intended to relieve the user's stress.

[0364] This invention is a system that combines sensors that measure river water levels, a server that processes information, an unmanned aerial vehicle that monitors the damage situation and provides evacuation guidance, sensors that monitor inventory, an automatic transport robot, staff terminals at a logistics center, and an emotion engine that recognizes user emotions.

[0365] First, sensors are installed to measure river water levels, collecting real-time data and sending it to a server. The server then analyzes the received data and determines whether the water level has reached a dangerous level. Using weather map data and water level data, a generative AI model is used to predict potential damage areas.

[0366] Once the estimated damage area is predicted, the server generates a flight path for the unmanned aircraft and automatically creates a flight plan. The unmanned aircraft flies to the predicted area and takes photographs of the damage from above. The data is sent to the server and then transferred in real time to the devices of local government employees. The unmanned aircraft also provides audio evacuation guidance in the estimated damage area, urging residents to evacuate quickly.

[0367] Meanwhile, sensors are also installed to measure inventory at the logistics center, and these periodically send inventory data to a server. The server analyzes the received inventory data, and if inventory falls below a threshold, it uses past data and a generative AI model to predict when to bring in the goods. Based on this prediction, it generates an operating route for the automated transport robot and issues instructions to the robot. The automated transport robot transports the goods along the operating route and sends the data to the server. The transport data is also transferred in real time to staff terminals at the logistics center.

[0368] In addition, the emotion engine installed on the server monitors the stress levels of logistics center staff and sends relaxation messages to staff devices as needed.

[0369] As a concrete example, consider the following case:

[0370] Case 1: Rising river water levels

[0371] 1. The server receives water level data from a river sensor and detects that the water level has exceeded 3 meters. This data indicates that the water level is beyond the danger zone, and the server switches to disaster response mode.

[0372] 2. The server uses weather map data and the latest water level data to predict the expected damage area, "Urban Area A," using a generative AI model.

[0373] 3. The server generates a flight path for the unmanned aircraft based on the prediction results and sends it to the unmanned aircraft.

[0374] 4. The unmanned aerial vehicle automatically begins flying and reaches urban area A. During the flight, it takes video and transmits it to the server in real time.

[0375] 5. Unmanned aerial vehicles will broadcast an audio message in areas expected to be affected, saying, "Please evacuate to higher ground immediately." If residents feel anxious, an emotion recognition system will detect this and switch to a more reassuring message.

[0376] 6. The server receives data from the unmanned aerial vehicle and transfers it to the devices of local government officials, allowing them to grasp the situation in real time and quickly issue evacuation instructions to residents.

[0377] Case 2: Inventory management at a logistics center

[0378] 1. The server detects from the inventory sensor that the inventory of "Product A" has fallen below a threshold.

[0379] 2. The server uses past data and the generative AI model to predict the appropriate delivery timing for product A.

[0380] 3. The server generates the movement route of the automated transport robot based on the prediction results and gives instructions.

[0381] 4. The automated transport robot transports the product along the specified route and sends the data acquired during the process to the server.

[0382] 5. The server transfers the transport data from the robot to the staff terminal at the logistics center in real time.

[0383] Prompt Sentence Examples

[0384] text

[0385] Inventory data: Product A has fallen below the threshold of 50.

[0386] Emotional Data: Employee A's stress level is 0.8.

[0387] Instructions: Please reorder immediately and instruct Employee A to take a break.

[0388] In this way, the system of the present invention realizes rapid information gathering and evacuation guidance in the event of a disaster, efficient inventory management and transportation operations at logistics centers, and stress management for employees.

[0389] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0390] Step 1:

[0391] The server receives real-time data from sensors measuring river water levels. This data includes current water level information. Based on this, the server analyzes water level trends and determines in real time whether the water level is reaching a dangerous level.

[0392] Input: River water level data

[0393] Output: Dangerous water level determination result

[0394] Specific behavior:

[0395] The server analyzes the water level data obtained from the sensor.

[0396] The result is compared with a preset threshold value for dangerous waters and a judgment result is generated.

[0397] Step 2:

[0398] If the server determines that the water level has reached a dangerous level, it uses weather map data and the aforementioned water level data to predict areas where damage is likely to occur. Utilizing a generative AI model, it estimates damage for each area based on past data.

[0399] Input: Dangerous water level determination results, weather chart data, water level data

[0400] Output: Estimated damage area forecast

[0401] Specific behavior:

[0402] Weather map data and water level data are imported into the server and input into the generative AI model.

[0403] An AI model analyzes the data and identifies areas likely to be affected.

[0404] Step 3:

[0405] The server generates a flight path for the drone based on the predicted damage area, including the shortest route and a preferred route to the most severely damaged area.

[0406] Input: Estimated damage area forecast

[0407] Output: Flight path of the unmanned aerial vehicle

[0408] Specific behavior:

[0409] The server analyzes the results of the generated AI model and generates an efficient flight path.

[0410] Transmitting flight path data to the unmanned aerial vehicle.

[0411] Step 4:

[0412] The unmanned aerial vehicle will then begin flying according to the received flight path, taking photos of the damage from above and sending the data to a server in real time.

[0413] Input: Unmanned Aerial Vehicle Flight Path

[0414] Output: Photographic data of the damage situation

[0415] Specific behavior:

[0416] The unmanned aerial vehicle follows a designated flight path.

[0417] Images and video data taken from the sky are sent to a server.

[0418] Step 5:

[0419] The server analyzes the image data received from the unmanned aerial vehicle and transfers it in real time to the devices of local government employees, who use the data to quickly grasp the extent of damage at the scene.

[0420] Input: Photographic data of the damage situation

[0421] Output: Real-time data to local government employee terminals

[0422] Specific behavior:

[0423] The server analyzes the data from the unmanned aerial vehicle and extracts the necessary information.

[0424] Data is transferred to local government employee terminals in real time.

[0425] Step 6:

[0426] The server instructs unmanned aerial vehicles in areas expected to be affected to provide voice evacuation guidance, enabling residents to evacuate quickly and smoothly.

[0427] Input: Estimated damage area forecast

[0428] Output: Evacuation guidance voice message

[0429] Specific behavior:

[0430] The server transmits the contents of the voice message to the unmanned aerial vehicle.

[0431] Unmanned aerial vehicles will provide voice evacuation instructions in designated areas.

[0432] Step 7:

[0433] The server periodically receives data from inventory sensors installed in the distribution center and monitors inventory levels. If the inventory level falls below a threshold, it predicts when to bring in products and generates a route for the automated transport robot.

[0434] Input: Inventory data

[0435] Output: Delivery timing prediction, transportation route

[0436] Specific behavior:

[0437] The server analyzes inventory data obtained from sensors and inputs it into a generative AI model.

[0438] Predict the timing of product delivery and generate appropriate delivery routes.

[0439] Step 8:

[0440] The automated transport robot delivers products to the designated location according to the route received from the server, and data on the delivery process is also sent to the server in real time.

[0441] Input: Delivery Route

[0442] Output: Transport data

[0443] Specific behavior:

[0444] The automated transport robot transports the goods along the instructed route.

[0445] Data acquired during transportation is sent to the server.

[0446] Step 9:

[0447] The server uses an emotion engine to monitor the stress levels of logistics center staff and sends relaxation messages if it detects high levels of stress.

[0448] Input: Employee emotion data

[0449] Output: Relaxation message

[0450] Specific behavior:

[0451] The server analyzes the stress levels of employees using an emotion engine.

[0452] If necessary, send relaxation messages to staff terminals.

[0453] In this way, each step works in tandem to seamlessly realize disaster response, inventory management, transportation efficiency, and staff stress management.

[0454] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0455] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0456] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0457] [Second embodiment]

[0458] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0459] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0460] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0461] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0462] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0463] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0464] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0465] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0466] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0467] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0468] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0469] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0470] This invention provides a system that combines sensors that measure river water levels, a server that processes the information, and drones that monitor disaster situations and provide evacuation guidance. This system enables rapid information collection and evacuation guidance for residents in the event of a disaster.

[0471] Program processing flow

[0472] The processing of the system program will be explained in natural language below.

[0473] Water level monitoring with sensors

[0474] 1. The server periodically collects water level data from sensors installed in the river. The sensors measure the river's water level in real time, so the server can receive the latest water level information at any time.

[0475] Determining dangerous waters

[0476] 2. The server determines whether the water level has reached the danger zone based on the received data. If the water level has reached the danger zone, the system proceeds to the next step.

[0477] Prediction of expected damage areas

[0478] 3. The server uses weather map data and past disaster data to predict areas expected to be affected using an AI model (e.g., the Gemini model). This prediction makes it possible to determine which areas will be affected and to what extent.

[0479] Flight planning

[0480] 4. The server generates a flight path for the drone based on the predicted damage area. The generated flight path is sent to the drone and executed automatically.

[0481] Drone flight and evacuation guidance

[0482] 5. The device (drone) begins flying according to the flight path received from the server. During flight, the drone photographs the damage from above and sends the data to the server in real time. The photographed data can be used to grasp the detailed damage situation.

[0483] 6. When the device (drone) reaches the predicted damage area, it begins to provide voice guidance using its built-in speaker. It repeatedly plays messages such as, "Everyone in City A, please evacuate to higher ground immediately."

[0484] Real-time information transfer

[0485] 7. The server transfers the images and video data received from the drone to the local government employee's device in real time, allowing the user (local government employee) to immediately check the situation on site and respond promptly.

[0486] Specific examples

[0487] Case 1: Rising river water levels

[0488] 1. The server receives water level data from a river sensor and detects that the water level has exceeded 3 meters. This data indicates that the water level is beyond the danger zone, and the server switches to disaster response mode.

[0489] 2. The server uses weather map data and the latest water level data to predict the expected damage area, "Urban Area A," using an AI model.

[0490] 3. The server generates a flight path for the drone based on the prediction results and sends it to the drone.

[0491] 4. The device (drone) automatically begins flying and reaches city A. During the flight, it takes video and transmits it to the server in real time.

[0492] 5. The drone will broadcast an audio message in the area of ​​expected damage saying, "Please evacuate to higher ground immediately."

[0493] 6. The server receives data from the drone and transfers it to the local government employee's device, allowing the user (local government employee) to grasp the situation in real time and quickly issue evacuation instructions to residents.

[0494] In this way, the system of the present invention can quickly collect information, grasp the situation, and provide effective evacuation guidance in the event of a disaster.

[0495] The processing flow will be explained below.

[0496] Step 1:

[0497] The server periodically collects water level data from water level sensors installed in the river. The sensors measure the water level in real time and send the data to the server.

[0498] Step 2:

[0499] The server stores the received water level data in a database, which is used for subsequent analysis.

[0500] Step 3:

[0501] The server periodically retrieves the latest water level data from the database and determines whether the water level has reached a dangerous level. If the water level reaches the set dangerous level, an alert is triggered.

[0502] Step 4:

[0503] The server retrieves weather chart data and past disaster data to prepare the data needed for the forecasting model, which is then processed and analyzed within the server.

[0504] Step 5:

[0505] The server uses an AI model (e.g., the Gemini model) to predict the likely damage area based on weather map data and water level data. This prediction identifies which specific areas will be affected.

[0506] Step 6:

[0507] The server automatically generates a drone flight path based on the predicted damage area, and transmits the generated flight plan information to the drone.

[0508] Step 7:

[0509] The terminal (drone) begins flying based on the flight path information received from the server. The drone uses sensors such as GPS to confirm its position and flies the planned path accurately.

[0510] Step 8:

[0511] The terminal (drone) arrives at the predicted damage area and takes pictures of the situation from above. The captured images and video data are sent to the server in real time.

[0512] Step 9:

[0513] The device (drone) plays a pre-recorded evacuation guidance message to residents in the predicted affected area, saying, "Everyone in City A, please evacuate to higher ground immediately."

[0514] Step 10:

[0515] The server receives real-time image and video data sent from the drone and forwards it to the terminals of local government employees.

[0516] Step 11:

[0517] The user (municipal government employee) checks the received real-time data on the terminal, allowing the user to immediately grasp the situation on-site and take the necessary measures promptly.

[0518] Through this series of steps, the system of the present invention can effectively collect information quickly, provide appropriate evacuation instructions, and grasp the situation in real time during a disaster.

[0519] Example 1

[0520] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0521] Conventional disaster monitoring systems have difficulty in real-time monitoring of rising river water levels and issuing prompt evacuation instructions, and effective responses are needed to minimize damage during disasters. In particular, it is challenging to quickly collect information in wide-ranging areas where damage is expected and issue appropriate evacuation instructions to residents.

[0522] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0523] In this invention, the server includes a means for receiving data from the sensor and determining whether the water level has reached a dangerous level, a means for predicting areas expected to be affected by damage using meteorological data and water level data, and a means for generating a flight path for the unmanned aerial vehicle based on the predicted areas expected to be affected and automatically creating a flight plan, which enables rapid information gathering and evacuation instructions to residents in the event of a disaster.

[0524] A "sensor" is a device that measures the water level of a river and transmits the measurement data to a server via a wireless network.

[0525] A "server" is a central processing unit that analyzes data received from sensors and performs various processes based on that data.

[0526] "Weather data" refers to data that indicates current and past weather conditions, such as weather maps, precipitation, and wind speed.

[0527] "Water level data" is quantitative data on the water level of a river measured by a sensor.

[0528] "Expected damage area" refers to an area that is likely to be affected by a predicted disaster.

[0529] An "unmanned aerial vehicle" is an aircraft that can be flown remotely or by automated program, commonly referred to as a drone.

[0530] "Flight route" refers to route information for an unmanned aerial vehicle, including the departure point, intermediate points, and destination.

[0531] A "flight plan" is a plan that includes specific flight routes and operational procedures that an unmanned aerial vehicle will execute based on a predicted damage area.

[0532] "Voice evacuation instructions" are a method of transmitting audio messages urging residents to evacuate via speakers installed on unmanned aerial vehicles.

[0533] "Administrative employee terminal" refers to a computer or mobile device used by an administrative employee to receive and check real-time data from the server.

[0534] The present invention provides a system that combines sensors that measure river water levels, a server that processes information, and an unmanned aerial vehicle that monitors disaster situations and provides evacuation guidance. This system enables rapid information collection and evacuation guidance for residents in the event of a disaster.

[0535] Water level monitoring with sensors

[0536] The sensors are installed in the river and measure the water level periodically. The measurement data is sent to a server via a wireless network. The sensors enable real-time monitoring of the river's water level.

[0537] Determining dangerous waters

[0538] The server analyzes water level data received periodically from the sensors and determines whether the water level has reached a preset danger zone. The database and analysis tools used here enable rapid detection of danger zones.

[0539] Prediction of expected damage areas

[0540] The server uses water level data and meteorological data to generate AI models (e.g., the Gemini model) to predict areas expected to be affected. The server also references data from past disasters to make detailed predictions of the degree of impact and the extent of damage.

[0541] Flight planning

[0542] The server generates a flight path for the drone based on the predicted damage area and transmits this information to the drone, which uses a flight planning tool to create a precise flight path.

[0543] Unmanned aerial vehicle flight and damage monitoring

[0544] The drone begins flying according to the flight path received from the server. During flight, the drone uses its camera to capture images of the damage and transmits the data to the server in real time, allowing for a detailed understanding of the damage situation.

[0545] Evacuation guidance using unmanned aerial vehicles

[0546] When the drone reaches the predicted damage area, it will begin to provide voice guidance using its built-in speaker. For example, it will repeatedly announce messages such as, "Everyone in City A, please evacuate to higher ground immediately."

[0547] Real-time information transfer

[0548] The server transfers the video data received from the unmanned aerial vehicle to the terminals of government officials in real time, allowing them to immediately grasp the situation on the ground and respond promptly.

[0549] Specific examples

[0550] Case 1: Rising river water levels

[0551] The server receives data from the river sensor that the water level has exceeded three meters. This data indicates that the water level is beyond the danger zone, and the server switches to disaster response mode.

[0552] 1. The server uses weather map data and the latest water level data to predict the expected damage area, "Urban Area A," using a generative AI model.

[0553] 2. The server generates a flight path for the unmanned aircraft based on the prediction results and sends it to the unmanned aircraft.

[0554] 3. The unmanned aircraft automatically begins flying and reaches "Urban Area A." During the flight, it takes video and transmits it to the server in real time.

[0555] 4. Unmanned aerial vehicles will broadcast an audio message in areas expected to be affected, saying, "Please evacuate to higher ground immediately."

[0556] 5. The server receives the data sent from the unmanned aerial vehicle and transfers it to the terminals of government officials, allowing them to grasp the situation in real time and issue quick evacuation instructions to residents.

[0557] Prompt Sentence Examples

[0558] Sample prompt 1: "If the water level of a river suddenly rises, how would you predict the areas likely to be affected and guide people to evacuate?"

[0559] Example prompt 2: "Please tell me specifically what the flight route of the unmanned aerial vehicle will be and how to provide evacuation instructions in the event of a flood in City A."

[0560] In this way, the system of the present invention can quickly collect information, grasp the situation, and provide effective evacuation guidance in the event of a disaster.

[0561] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0562] Step 1: Collect water level data from sensors

[0563] The server periodically collects water level data from the sensor. The sensor measures the river's water level every minute and sends the data to the server via a wireless network. The input data is water level information from the sensor, which the server receives and records in a database. Specifically, the server receives data from the sensor, records it in a database, and maintains the latest water level status.

[0564] Input: Water level data from the sensor

[0565] Output: Recorded water level data

[0566] Step 2: Determine the danger zone

[0567] Based on the water level data collected by the server, it determines whether the latest water level has reached the set dangerous water level. The input data is water level information from the sensor, which the server analyzes and compares with the dangerous water level threshold. The output is the result of the determination of whether the dangerous water level has been reached. Specifically, the server analyzes the water level data, compares it with the threshold, and issues a system alert if the dangerous water level has been reached.

[0568] Input: Water level data from the sensor

[0569] Output: Dangerous waters determination result

[0570] Step 3: Prediction of potential damage areas

[0571] The server uses weather map data and past disaster data to utilize an AI model (e.g., the Gemini model) to predict areas of potential damage. The input data is the latest water level data and weather data, which are input into the AI ​​model. The output is the predicted areas of potential damage. Specifically, the server collects weather map data and past disaster data, inputs them into the AI ​​model, obtains the prediction results, and identifies the areas of potential damage.

[0572] Input: Water level data, weather data, past disaster data

[0573] Output: Estimated damage area

[0574] Step 4: Drone flight path generation

[0575] The server generates a flight path for the unmanned aerial vehicle based on the predicted expected damage area. The input data is the location information of the expected damage area, and the flight path is calculated based on this. The output is the generated flight path. Specifically, the server identifies important monitoring points from the prediction results, calculates and generates a flight path, and sends the generated flight path to the unmanned aerial vehicle.

[0576] Input: Location information of the expected damage area

[0577] Output: Flight path information

[0578] Step 5: Fly the drone and monitor the damage

[0579] The terminal (unmanned aerial vehicle) takes off according to the flight route received from the server and flies the specified route. The input data is flight route information, and the unmanned aerial vehicle collects data while flying according to this information. The output is the captured video data. Specifically, the unmanned aerial vehicle flies automatically, takes photos and videos of the location with a camera, and transfers the video data to the server in real time.

[0580] Input: Flight route information

[0581] Output: Recorded video data

[0582] Step 6: Drone evacuation guidance

[0583] When the terminal (unmanned aerial vehicle) reaches the predicted damage area, it uses a built-in speaker to provide voice guidance. The input data is a voice message sent from the server, which the unmanned aerial vehicle relays to residents. The output is a voice guidance message to residents. Specifically, the unmanned aerial vehicle repeatedly plays a designated message, calling on residents to evacuate.

[0584] Input: Voice message

[0585] Output: Voice guidance

[0586] Step 7: Real-time data transfer

[0587] The server transfers real-time images and video data sent from the unmanned aerial vehicle to the terminals of local government employees. The input data is the video data received from the unmanned aerial vehicle, which the server sends to the terminals of local government employees. The output is the data transferred to the terminals of local government employees. Specifically, the server processes the data received from the drone and transfers it to the terminals of local government employees in real time. The administrative staff can then check the data and take on-site action as necessary.

[0588] Input: Video data from an unmanned aerial vehicle

[0589] Output: Data transferred to the administrative staff's terminal

[0590] (Application example 1)

[0591] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0592] When river water levels reach dangerous levels, it is extremely important to quickly and accurately collect disaster information and provide evacuation instructions to residents. Conventional technologies can result in delays in information collection and evacuation instructions, potentially resulting in greater damage. Furthermore, there are limitations to predicting affected areas in real time and generating appropriate evacuation messages. The objective of this invention is to solve these shortcomings and provide an effective disaster response system.

[0593] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0594] In this invention, the server includes a means for predicting estimated damage areas using a generative AI model and generating appropriate evacuation guidance messages for residents, a means for an unmanned aerial vehicle to transfer image data of estimated damage areas to the server in real time and perform continuous predictions and responses using the generative AI model, and a means for a drone to fly and photograph the damage situation from the air and send the data to the server, thereby enabling rapid and accurate information collection and appropriate evacuation guidance.

[0595] A "sensor" is a device that measures the water level of a river in real time and transmits the data to a server.

[0596] The "server" is a central processing unit that receives data from sensors, processes the data, and predicts dangerous water levels and areas of potential damage.

[0597] "Weather map data" is data that shows meteorological information, and is used in particular to grasp meteorological conditions in real time and predict areas likely to be affected.

[0598] An "unmanned aerial vehicle" is an aircraft that is remotely controlled or flies autonomously to monitor disaster situations and collect and transmit data.

[0599] "Flight path" refers to the designated route taken by an unmanned aerial vehicle.

[0600] A "flight plan" refers to a specific plan for an unmanned aerial vehicle to fly automatically based on a flight path.

[0601] "Estimated damage area" refers to an area that the server predicts will be affected by a disaster using weather map data and water level data.

[0602] A "generative AI model" is a model that uses machine learning and artificial intelligence technology to analyze data and predict areas of potential damage.

[0603] "Evacuation instruction messages" refer to audio or text instructions to encourage residents in areas expected to be affected to take appropriate evacuation actions.

[0604] "Image data" refers to photographs and videos of disaster situations taken from the air by unmanned aerial vehicles.

[0605] "Local government employee terminals" refers to communication terminals such as computers and smartphones used by local government employees for disaster response purposes.

[0606] This invention provides a system that combines sensors that measure river water levels, a server that processes the information, and an unmanned aerial vehicle that monitors disaster situations and provides evacuation guidance. This system enables rapid information collection and evacuation guidance for residents in the event of a disaster.

[0607] The entire system is realized by the following hardware and software configuration.

[0608] Hardware Configuration

[0609] 1. Water level sensor: A device installed in a river to measure the water level in real time.

[0610] 2. Server: The central processing unit that receives data from sensors and performs analysis and predictions.

[0611] 3. Unmanned aerial vehicles: Aircraft that monitor disaster situations from the sky, collect data in real time, and provide evacuation instructions to residents.

[0612] 4. Local government employee devices: Communication devices such as computers and smartphones.

[0613] Software Configuration

[0614] 1. Data collection module: Software that collects water level data from sensors and sends it to the server.

[0615] 2. Data analysis module: Software that uses collected data to determine whether water levels have reached dangerous levels and uses a generative AI model to predict potential damage areas.

[0616] 3. Flight plan generation module: Software that generates flight paths for unmanned aerial vehicles based on the expected damage area and automatically creates flight plans.

[0617] 4. Real-time data transfer module: Software that transfers data sent from unmanned aerial vehicles to local government employee terminals in real time.

[0618] 5. Voice guidance module: Software that uses the prediction results to enable unmanned aerial vehicles to provide voice guidance on evacuation in areas expected to be affected.

[0619] Data processing and calculation flow

[0620] The server first collects water level data periodically sent from the sensors. This data is sent to the server in real time and used to determine whether the water level has reached a dangerous level. If the determination is that the water level is dangerous, the server uses weather map data and past disaster data to predict the likely damage area using a generative AI model (e.g., machine learning or artificial intelligence technology).

[0621] Example prompts for generative AI models

[0622] Based on these prompts, the server predicts the expected damage area and generates a flight plan accordingly. The unmanned aerial vehicle then flies along a flight path generated based on the prediction results, photographing the damage situation from the air in real time and sending the data to the server. This data is then received by the devices of local government employees, enabling them to immediately grasp the situation on site and take prompt action.

[0623] Examples of prompt statements

[0624] "Please predict the area of ​​potential damage if the river water level exceeds 3 meters."

[0625] In this way, the entire system will work together to enable rapid and accurate information gathering and appropriate responses in the event of a disaster.

[0626] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0627] Step 1:

[0628] Water level data collection

[0629] The server periodically collects water level data from sensors installed in the river. The input data is the water level measurement data sent from the sensor, and the output data is the water level data stored in the server's internal database. Specifically, the server retrieves data from the sensor using an HTTP request.

[0630] Step 2:

[0631] Determining dangerous waters

[0632] The server determines whether the water level has reached a dangerous level based on the received water level data. The input data is the collected water level data, and the output data is a flag indicating whether the water level has reached a dangerous level. Specifically, the server compares the water level data with the set dangerous water level threshold and sets a flag if the threshold is exceeded.

[0633] Step 3:

[0634] Prediction of expected damage areas

[0635] When a dangerous water area flag is raised, the server uses weather map data and past disaster data to use a generative AI model to predict the area of ​​expected damage. The input data is water level data, weather map data, and past disaster data, and the output data is information on the area of ​​expected damage. In concrete terms, the server gives the generative AI model specific instructions, such as a prompt statement and argument data, such as "area of ​​expected damage if the river water level exceeds 3 meters," and receives the prediction results from the model.

[0636] Step 4:

[0637] Flight plan generation

[0638] The server generates a flight path for the unmanned aerial vehicle based on the predicted damage area and automatically creates a flight plan. The input data is information about the damage area, and the output data is specific flight path information. Specifically, the server calculates the optimal flight path based on GPS data and transmits it to the unmanned aerial vehicle.

[0639] Step 5:

[0640] Unmanned aerial vehicle flight and data collection

[0641] The unmanned aerial vehicle begins flying according to the flight path received from the server. During flight, the unmanned aerial vehicle photographs the damage situation from the sky and transmits the data to the server in real time. The input data is flight path information, and the output data is the photographed image data. Specifically, the unmanned aerial vehicle uses a camera to capture images from the sky and transfers them to the server via wireless communication.

[0642] Step 6:

[0643] Generation and execution of evacuation guidance messages

[0644] Based on the prediction results, the server generates a message calling for evacuation for residents in the predicted damage area and transmits it as audio guidance to the unmanned aerial vehicle. The input data is the predicted damage area and the message information generated by the generation AI model, and the output data is the audio guidance message. Specifically, the server uses the generation AI model to create an evacuation message and plays it through the speaker on the unmanned aerial vehicle.

[0645] Step 7:

[0646] Real-time information transfer

[0647] The server transfers the image and video data received from the unmanned aerial vehicle to the local government employee's device in real time. The input data is image data from the unmanned aerial vehicle, and the output data is real-time video to the local government employee's device. Specifically, the server immediately packets the received data and sends a push notification to each local government employee's device.

[0648] This series of processes enables the system to quickly and accurately collect information and provide appropriate evacuation instructions.

[0649] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0650] This invention is a system that combines sensors that measure river water levels, a server that processes information, drones that monitor disaster situations and provide evacuation guidance, and an emotion engine that recognizes the user's emotions. The system aims to quickly collect information during disasters, provide evacuation guidance to residents, and provide emotional support to local government officials.

[0651] Program processing flow

[0652] The processing of the system program will be explained in natural language below.

[0653] Water level monitoring with sensors

[0654] 1. The server periodically collects water level data from water level sensors installed in the river. The sensors measure the river's water level in real time and send the data to the server.

[0655] Determining dangerous waters

[0656] 2. The server determines whether the water level has reached the danger zone based on the received data. If the water level has reached the danger zone, the system proceeds to the next step.

[0657] Prediction of expected damage areas

[0658] 3. The server uses weather map data and past disaster data to predict areas expected to be affected using an AI model (e.g., the Gemini model). This prediction makes it possible to determine which areas will be affected and to what extent.

[0659] Flight planning

[0660] 4. The server generates a flight path for the drone based on the predicted damage area. The generated flight path is sent to the drone and executed automatically.

[0661] Drone flight and evacuation guidance

[0662] 5. The device (drone) begins flying according to the flight path received from the server. During flight, the drone photographs the damage from above and sends the data to the server in real time. The photographed data can be used to grasp the detailed damage situation.

[0663] 6. When the device (drone) reaches the predicted damage area, it begins to provide voice guidance using its built-in speaker. It repeatedly plays messages such as, "Everyone in City A, please evacuate to higher ground immediately."

[0664] Real-time information transfer

[0665] 7. The server transfers the images and video data received from the drone to the local government employee's device in real time, allowing the user (local government employee) to immediately check the situation on site and respond promptly.

[0666] Use of emotion engine

[0667] 8. The server uses an emotion engine to monitor the stress levels and emotional state of local government employees. If stress levels are found to be elevated, relaxation and support messages are automatically sent.

[0668] 9. The device (drone) will recognize the emotions of residents in the predicted affected area and play appropriate voice guidance depending on their emotional state. For example, if anxiety is rising, it will play a message such as "Please remain calm and follow evacuation instructions."

[0669] Specific examples

[0670] Case 1: Rising river water levels

[0671] 1. The server receives water level data from a river sensor and detects that the water level has exceeded 3 meters. This data indicates that the water level is beyond the danger zone, and the server switches to disaster response mode.

[0672] 2. The server uses weather map data and the latest water level data to predict the expected damage area, "Urban Area A," using an AI model.

[0673] 3. The server generates a flight path for the drone based on the prediction results and sends it to the drone.

[0674] 4. The device (drone) automatically begins flying and reaches city A. During the flight, it takes video and transmits it to the server in real time.

[0675] 5. The drone will broadcast an audio message in the affected area saying, "Please evacuate to higher ground immediately." If residents feel anxious, the emotion recognition system will detect this and switch to a more reassuring message.

[0676] 6. The server receives data from the drone and transfers it to the local government employee's device, allowing the user (local government employee) to grasp the situation in real time and quickly issue evacuation instructions to residents.

[0677] Case 2: Stress management for local government employees

[0678] 1. An emotion engine installed on the server monitors the stress levels of local government employees.

[0679] 2. If the stress level of staff increases during disaster response, the server automatically sends a relaxation message to the staff's device.

[0680] 3. Users (municipal government officials) can reduce stress and continue to respond calmly.

[0681] In this way, the system of the present invention can respond to disasters more effectively by quickly gathering information and providing evacuation instructions during disasters, as well as providing emotional support to local government officials.

[0682] The processing flow will be explained below.

[0683] Step 1:

[0684] The server periodically collects water level data from water level sensors installed in the river. The sensors measure the water level in real time and send the data to the server.

[0685] Step 2:

[0686] The server stores the received water level data in a database, which is used for subsequent analysis.

[0687] Step 3:

[0688] The server periodically retrieves the latest water level data from the database and determines whether the water level has reached a dangerous level. If the water level reaches the set dangerous level, an alert is triggered.

[0689] Step 4:

[0690] The server receives weather chart data and past disaster data, which are then processed and used to predict potential damage areas in the event of a dangerous water zone.

[0691] Step 5:

[0692] The server uses AI models to analyze weather map data and water level data to predict potential damage areas, which can then identify which areas will be affected.

[0693] Step 6:

[0694] The server generates a flight path for the drone based on the predicted damage area, and transmits the generated flight plan information to the drone.

[0695] Step 7:

[0696] The terminal (drone) begins flying based on the flight path information received from the server. The drone uses sensors such as GPS to confirm its position and flies the planned path accurately.

[0697] Step 8:

[0698] The terminal (drone) arrives at the predicted damage area and takes pictures of the situation from above. The captured images and video data are sent to the server in real time.

[0699] Step 9:

[0700] The device (drone) plays a pre-recorded evacuation guidance message to residents in the predicted affected area, saying, "Everyone in City A, please evacuate to higher ground immediately."

[0701] Step 10:

[0702] The server receives real-time image and video data sent from the drone and transfers it to the terminals of local government employees in real time.

[0703] Step 11:

[0704] The server uses an emotion engine to monitor the stress levels and emotional state of local government employees, and if stress is judged to be increasing, it automatically sends relaxation and support messages.

[0705] Step 12:

[0706] The device (drone) recognizes the emotions of residents in the predicted affected area and plays appropriate voice guidance according to their emotional state. For example, if anxiety is rising, it will play a message such as "Please remain calm and follow evacuation instructions."

[0707] Step 13:

[0708] The user (municipal government employee) checks the received real-time data on the device. The user can immediately grasp the situation on the ground and take the necessary measures. In addition, the user can maintain a calm mind by receiving relaxation messages from the emotion engine.

[0709] Through this series of steps, the system of the present invention can effectively gather information quickly, provide appropriate evacuation instructions, and provide emotional support to local government officials in the event of a disaster.

[0710] Example 2

[0711] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0712] During natural disasters, the challenges are to quickly and accurately gather information, provide evacuation instructions to residents, and comprehensively manage the stress of local government employees. In particular, there is a need for a system that can simultaneously grasp on-site information in real time during a disaster and manage the emotions of residents and local government employees.

[0713] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0714] In this invention, the server includes means for receiving data from a sensor measuring the river water level and determining whether the water level has reached a dangerous level, means for predicting potential damage areas using weather map data and water level data, and means for generating a flight path for the flying machine based on the predicted potential damage areas and automatically creating a flight plan, which enables the rapid collection of disaster information, accurate evacuation guidance, and stress management for local government officials.

[0715] A "sensor for measuring river water levels" is a device that measures river water levels in real time and sends the data to a server.

[0716] A "server" is a central processing unit that receives data from sensors, analyzes it, and executes various processes.

[0717] "Weather map data" is a data set containing meteorological information and is used to predict weather fluctuations.

[0718] "Water level data" is a data set that shows the current water level and its fluctuations in a river.

[0719] A "potential damage area" is a specific geographical area that is expected to be affected in the event of a disaster.

[0720] A "flying machine" is a device that can fly autonomously and gather information from the air, generally referring to drones or unmanned aerial vehicles (UAVs).

[0721] "Flight path" means the planned route to be followed by a flying vehicle.

[0722] "Voice evacuation guidance" is a method in which flying machines use voice messages to encourage residents to evacuate.

[0723] An "administrator's terminal" is a computer or mobile device used by an administrator, such as a local government employee.

[0724] The "Emotion Engine" is a system that analyzes an individual's emotional state and monitors stress levels and emotional responses.

[0725] "Stress level" is a measure of the degree of psychological pressure or burden felt by an individual.

[0726] "Emotional state" refers to an individual's current emotional or mood state.

[0727] This invention is a system that uses river water level measurement sensors, a server that processes the data, a flying machine that monitors disaster situations and guides evacuation, and an emotion engine that recognizes the emotions of administrators. The system aims to quickly collect information in the event of a disaster, provide evacuation instructions to residents, and provide emotional support to local government officials.

[0728] First, the main components of the system will be described.

[0729] A river water level measurement sensor is a device that is installed in a specific area of ​​a river and measures water level data in real time. For example, a general water level measurement device is used.

[0730] The server is a device that periodically collects data from the sensors and analyzes it. It is equipped with an analytical algorithm that determines whether the water level has reached a preset danger level. The server also uses weather chart data and past disaster data to predict potential damage areas using an AI model (such as the Gemini model).

[0731] The flying machine (drone) is a device for monitoring the situation in the predicted damage area from the sky, and automatically generates a flight path and flies based on instructions from the server. During the flight, it takes images from the sky and sends the data to the server in real time. It also provides evacuation guidance through audio guidance.

[0732] The administrator's terminal is a device that receives data from the server and checks the situation on site in real time, and has emergency response apps and dedicated software installed.

[0733] The emotion engine is a system that monitors the stress level and emotional state of the administrator and sends relaxation messages as needed.

[0734] Specific examples are shown below.

[0735] Case 1: Rising river water levels

[0736] 1. The server receives water level data from a river sensor and detects that the water level has exceeded 3 meters. This data indicates that the water level has exceeded the danger level, and the server switches to disaster response mode.

[0737] 2. The server uses weather map data and the latest water level data to predict the expected damage area, "Urban Area A," using an AI model.

[0738] 3. The server generates a flight path for the flying machine based on the prediction results and sends it to the flying machine.

[0739] 4. The terminal (flying machine) automatically begins flying and reaches city A. During the flight, it takes video and transmits it to the server in real time.

[0740] 5. Flying machines will broadcast an audio message in the affected area saying, "Please evacuate to higher ground immediately." If residents feel anxious, an emotion recognition system will detect this and switch to a more reassuring message.

[0741] 6. The server receives data from the flying machine and transfers it to the administrator's terminal, allowing the user (administrator) to grasp the situation in real time and quickly issue evacuation instructions to residents.

[0742] Case 2: Stress management for local government employees

[0743] 1. An emotion engine installed on the server monitors the stress levels of local government employees.

[0744] 2. If the stress level of staff increases during disaster response, the server automatically sends a relaxation message to the staff's device.

[0745] 3. Users (staff) can reduce stress and continue to respond calmly.

[0746] To achieve this, the system uses prompt statements such as:

[0747] "Generate an appropriate evacuation guidance message when the river water level reaches 3 meters."

[0748] "Please provide an example of a relaxation message for local government employees when their stress levels increase."

[0749] "Please tell us how you specifically use AI models to predict potential damage areas."

[0750] As described above, the present invention enables the rapid collection of disaster information, accurate evacuation guidance, and emotional support for local government officials, thereby improving disaster response capabilities.

[0751] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0752] Step 1:

[0753] The server collects data from river water level sensors. The input is water level data from the sensors, and the output is water level data stored in a database on the server.

[0754] The server sends an HTTP request to the sensor via the network to retrieve the data. The retrieved data includes a timestamp and geolocation information. For example, "Sensor ID: 001, Water level: 3.2 meters, Timestamp: 2023-10-04T14:00:00Z".

[0755] Step 2:

[0756] The server analyzes the water level data and determines whether the water level has reached the set danger level. The input is the collected water level data, and the output is the setting of the danger state flag.

[0757] The server uses a condition determination algorithm to set a danger flag if the water level exceeds a threshold (e.g., 3 meters). For example, "Current water level: 3.2 meters, Set threshold: 3.0 meters, Danger state: Active."

[0758] Step 3:

[0759] The server inputs weather map data, past disaster data, and the latest water level data into the AI ​​model to predict the likely damage area. The inputs are weather map data, past disaster data, and water level data, and the output is the likely damage area and its impact.

[0760] The server uses Google Cloud Platform's AI services and its own Gemini model to output the prediction results as potentially affected areas and the level of damage (e.g., "Urban Area A: High, Rural Area B: Medium").

[0761] Step 4:

[0762] The server generates a flight path for the flying machine based on the predicted damage area. The input is the predicted damage area and its impact, and the output is flight path data in JSON format.

[0763] The server calculates the optimal flight route and sends the data to the flying machine. For example, "Flight route: Start point (latitude: 35.6895, longitude: 139.6917) → City A (latitude: 35.6895, longitude: 139.7000) → End point (latitude: 35.7000, longitude: 139.7100)".

[0764] Step 5:

[0765] The terminal (flying machine) starts automatic flight according to the flight path received from the server. The input is the flight path data sent from the server, and the output is the captured video data.

[0766] The flying machine flies autonomously along a designated route using GPS, capturing video of the situation from above. The captured video data is then sent to a server in real time. For example, the video may be "video of the flooding situation in City A."

[0767] Step 6:

[0768] When the terminal (flying machine) reaches the predicted damage area, it starts to give voice guidance through the built-in speaker. The input is the evacuation guidance message sent from the server, and the output is the broadcast voice message.

[0769] The flying machine constantly broadcasts messages calling for evacuation. For example, it might say, "Everyone in City A, please evacuate to higher ground immediately." If residents feel anxious, it uses an emotion recognition system to change the message to, "Please remain calm and follow evacuation instructions."

[0770] Step 7:

[0771] The server transfers the image and video data received from the flying machine to the administrator's terminal in real time. The input is the video data from the flying machine, and the output is the real-time video displayed on the administrator's terminal.

[0772] The server transfers data through a dedicated app or web interface, such as "Video showing widespread flooding in City A."

[0773] Step 8:

[0774] The server monitors the stress level and emotional state of the administrator using an emotion engine, where the input is biometric data from the administrator and the output is an assessment of the administrator's emotional state and stress level.

[0775] The emotion engine analyzes biosensor and input data and automatically sends relaxation messages when stress levels rise. For example, "Employee 1's stress level: High, Relaxation Message: 'Take a deep breath and relax.'"

[0776] Step 9:

[0777] The terminal (flying machine) recognizes the emotions of residents in the predicted damage area and provides appropriate voice guidance according to their emotional state. The input is the residents' emotional data collected during flight, and the output is a voice message according to their emotional state.

[0778] The flying machine uses AI to analyze voices and play reassuring messages if anxiety levels are high. For example, "Residents' emotional state: anxiety, guidance message: 'Please remain calm and follow evacuation instructions.'"

[0779] (Application example 2)

[0780] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0781] Conventional river monitoring systems have had issues with rapid response and evacuation guidance in the event of a disaster. Logistics centers also need to streamline inventory management and transportation operations, as well as manage employee stress. The purpose of this invention is to provide a system that can solve these issues and respond efficiently and quickly.

[0782] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0783] In this invention, the server includes: means for receiving data from a sensor measuring the river water level and determining whether the water level has reached a dangerous level; means for predicting an estimated damage area using weather map data and water level data; means for generating a flight path for an unmanned aerial vehicle based on the predicted estimated damage area and automatically creating a flight plan; means for the unmanned aerial vehicle to fly, photograph the damage situation from the air, and transmit the photographed data; means for the unmanned aerial vehicle to provide evacuation guidance via voice in the estimated damage area; means for periodically collecting data from an inventory sensor and determining whether inventory has fallen below a threshold; means for predicting product delivery timing using past data and a generative AI model; means for generating a movement route for an automated transport robot based on the predicted delivery timing and automatically creating a plan; means for the automated transport robot to transport products along the movement route and transmit the data; means for transferring the received data to an employee terminal at a logistics center in real time; and means for monitoring the stress levels of logistics center employees using an emotion engine and sending relaxation messages as necessary. This enables rapid information collection and evacuation guidance during a disaster, efficient inventory management and product delivery, and employee stress management.

[0784] A "sensor for measuring river water levels" is a device that measures river water levels in real time and sends the data to a server.

[0785] A "server" is a central control device that receives data from sensors and processes and analyzes it.

[0786] "Weather map data" refers to data that includes meteorological information and is used for disaster prediction.

[0787] "Expected damage area" refers to an area that is predicted to be affected if a disaster occurs.

[0788] An "unmanned aerial vehicle" is an aircraft that flies under remote control or automatic control.

[0789] A "flight path" is the route that an unmanned aerial vehicle follows as it flies.

[0790] "Periodic" means repeated at regular intervals.

[0791] An "inventory sensor" is a device that measures product inventory in a warehouse.

[0792] A "generative AI model" is a mathematical model used to analyze and predict data generated by artificial intelligence.

[0793] An "automatic transport robot" is a robot that automatically transports goods within a logistics center.

[0794] A "distribution center staff terminal" is a terminal used by staff at a distribution center to display and operate data.

[0795] The "emotion engine" is a system that analyzes the user's emotional state and responds based on the results.

[0796] A "relaxation message" is a message intended to relieve the user's stress.

[0797] This invention is a system that combines sensors that measure river water levels, a server that processes information, an unmanned aerial vehicle that monitors the damage situation and provides evacuation guidance, sensors that monitor inventory, an automatic transport robot, staff terminals at a logistics center, and an emotion engine that recognizes user emotions.

[0798] First, sensors are installed to measure river water levels, collecting real-time data and sending it to a server. The server then analyzes the received data and determines whether the water level has reached a dangerous level. Using weather map data and water level data, a generative AI model is used to predict potential damage areas.

[0799] Once the estimated damage area is predicted, the server generates a flight path for the unmanned aircraft and automatically creates a flight plan. The unmanned aircraft flies to the predicted area and takes photographs of the damage from above. The data is sent to the server and then transferred in real time to the devices of local government employees. The unmanned aircraft also provides audio evacuation guidance in the estimated damage area, urging residents to evacuate quickly.

[0800] Meanwhile, sensors are also installed to measure inventory at the logistics center, and these periodically send inventory data to a server. The server analyzes the received inventory data, and if inventory falls below a threshold, it uses past data and a generative AI model to predict when to bring in the goods. Based on this prediction, it generates an operating route for the automated transport robot and issues instructions to the robot. The automated transport robot transports the goods along the operating route and sends the data to the server. The transport data is also transferred in real time to staff terminals at the logistics center.

[0801] In addition, the emotion engine installed on the server monitors the stress levels of logistics center staff and sends relaxation messages to staff devices as needed.

[0802] As a concrete example, consider the following case:

[0803] Case 1: Rising river water levels

[0804] 1. The server receives water level data from a river sensor and detects that the water level has exceeded 3 meters. This data indicates that the water level is beyond the danger zone, and the server switches to disaster response mode.

[0805] 2. The server uses weather map data and the latest water level data to predict the expected damage area, "Urban Area A," using a generative AI model.

[0806] 3. The server generates a flight path for the unmanned aircraft based on the prediction results and sends it to the unmanned aircraft.

[0807] 4. The unmanned aerial vehicle automatically begins flying and reaches urban area A. During the flight, it takes video and transmits it to the server in real time.

[0808] 5. Unmanned aerial vehicles will broadcast an audio message in areas expected to be affected, saying, "Please evacuate to higher ground immediately." If residents feel anxious, an emotion recognition system will detect this and switch to a more reassuring message.

[0809] 6. The server receives data from the unmanned aerial vehicle and transfers it to the devices of local government officials, allowing them to grasp the situation in real time and quickly issue evacuation instructions to residents.

[0810] Case 2: Inventory management at a logistics center

[0811] 1. The server detects from the inventory sensor that the inventory of "Product A" has fallen below a threshold.

[0812] 2. The server uses past data and the generative AI model to predict the appropriate delivery timing for product A.

[0813] 3. The server generates the movement route of the automated transport robot based on the prediction results and gives instructions.

[0814] 4. The automated transport robot transports the product along the specified route and sends the data acquired during the process to the server.

[0815] 5. The server transfers the transport data from the robot to the staff terminal at the logistics center in real time.

[0816] Prompt Sentence Examples

[0817] text

[0818] Inventory data: Product A has fallen below the threshold of 50.

[0819] Emotional Data: Employee A's stress level is 0.8.

[0820] Instructions: Please reorder immediately and instruct Employee A to take a break.

[0821] In this way, the system of the present invention realizes rapid information gathering and evacuation guidance in the event of a disaster, efficient inventory management and transportation operations at logistics centers, and stress management for employees.

[0822] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0823] Step 1:

[0824] The server receives real-time data from sensors measuring river water levels. This data includes current water level information. Based on this, the server analyzes water level trends and determines in real time whether the water level is reaching a dangerous level.

[0825] Input: River water level data

[0826] Output: Dangerous water level determination result

[0827] Specific behavior:

[0828] The server analyzes the water level data obtained from the sensor.

[0829] The result is compared with a preset threshold value for dangerous waters and a judgment result is generated.

[0830] Step 2:

[0831] If the server determines that the water level has reached a dangerous level, it uses weather map data and the aforementioned water level data to predict areas where damage is likely to occur. Utilizing a generative AI model, it estimates damage for each area based on past data.

[0832] Input: Dangerous water level determination results, weather chart data, water level data

[0833] Output: Estimated damage area forecast

[0834] Specific behavior:

[0835] Weather map data and water level data are imported into the server and input into the generative AI model.

[0836] An AI model analyzes the data and identifies areas likely to be affected.

[0837] Step 3:

[0838] The server generates a flight path for the drone based on the predicted damage area, including the shortest route and a preferred route to the most severely damaged area.

[0839] Input: Estimated damage area forecast

[0840] Output: Flight path of the unmanned aerial vehicle

[0841] Specific behavior:

[0842] The server analyzes the results of the generated AI model and generates an efficient flight path.

[0843] Transmitting flight path data to the unmanned aerial vehicle.

[0844] Step 4:

[0845] The unmanned aerial vehicle will then begin flying according to the received flight path, taking photos of the damage from above and sending the data to a server in real time.

[0846] Input: Unmanned Aerial Vehicle Flight Path

[0847] Output: Photographic data of the damage situation

[0848] Specific behavior:

[0849] The unmanned aerial vehicle follows a designated flight path.

[0850] Images and video data taken from the sky are sent to a server.

[0851] Step 5:

[0852] The server analyzes the image data received from the unmanned aerial vehicle and transfers it in real time to the devices of local government employees, who use the data to quickly grasp the extent of damage at the scene.

[0853] Input: Photographic data of the damage situation

[0854] Output: Real-time data to local government employee terminals

[0855] Specific behavior:

[0856] The server analyzes the data from the unmanned aerial vehicle and extracts the necessary information.

[0857] Data is transferred to local government employee terminals in real time.

[0858] Step 6:

[0859] The server instructs unmanned aerial vehicles in areas expected to be affected to provide voice evacuation guidance, enabling residents to evacuate quickly and smoothly.

[0860] Input: Estimated damage area forecast

[0861] Output: Evacuation guidance voice message

[0862] Specific behavior:

[0863] The server transmits the contents of the voice message to the unmanned aerial vehicle.

[0864] Unmanned aerial vehicles will provide voice evacuation instructions in designated areas.

[0865] Step 7:

[0866] The server periodically receives data from inventory sensors installed in the distribution center and monitors inventory levels. If the inventory level falls below a threshold, it predicts when to bring in products and generates a route for the automated transport robot.

[0867] Input: Inventory data

[0868] Output: Delivery timing prediction, transportation route

[0869] Specific behavior:

[0870] The server analyzes inventory data obtained from sensors and inputs it into a generative AI model.

[0871] Predict the timing of product delivery and generate appropriate delivery routes.

[0872] Step 8:

[0873] The automated transport robot delivers products to the designated location according to the route received from the server, and data on the delivery process is also sent to the server in real time.

[0874] Input: Delivery Route

[0875] Output: Transport data

[0876] Specific behavior:

[0877] The automated transport robot transports the goods along the instructed route.

[0878] Data acquired during transportation is sent to the server.

[0879] Step 9:

[0880] The server uses an emotion engine to monitor the stress levels of logistics center staff and sends relaxation messages if it detects high levels of stress.

[0881] Input: Employee emotion data

[0882] Output: Relaxation message

[0883] Specific behavior:

[0884] The server analyzes the stress levels of employees using an emotion engine.

[0885] If necessary, send relaxation messages to staff terminals.

[0886] In this way, each step works in tandem to seamlessly realize disaster response, inventory management, transportation efficiency, and staff stress management.

[0887] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0888] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0889] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0890] [Third embodiment]

[0891] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0892] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0893] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0894] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0895] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0896] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0897] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0898] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0899] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0900] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0901] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0902] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0903] This invention provides a system that combines sensors that measure river water levels, a server that processes the information, and drones that monitor disaster situations and provide evacuation guidance. This system enables rapid information collection and evacuation guidance for residents in the event of a disaster.

[0904] Program processing flow

[0905] The processing of the system program will be explained in natural language below.

[0906] Water level monitoring with sensors

[0907] 1. The server periodically collects water level data from sensors installed in the river. The sensors measure the river's water level in real time, so the server can receive the latest water level information at any time.

[0908] Determining dangerous waters

[0909] 2. The server determines whether the water level has reached the danger zone based on the received data. If the water level has reached the danger zone, the system proceeds to the next step.

[0910] Prediction of expected damage areas

[0911] 3. The server uses weather map data and past disaster data to predict areas expected to be affected using an AI model (e.g., the Gemini model). This prediction makes it possible to determine which areas will be affected and to what extent.

[0912] Flight planning

[0913] 4. The server generates a flight path for the drone based on the predicted damage area. The generated flight path is sent to the drone and executed automatically.

[0914] Drone flight and evacuation guidance

[0915] 5. The device (drone) begins flying according to the flight path received from the server. During flight, the drone photographs the damage from above and sends the data to the server in real time. The photographed data can be used to grasp the detailed damage situation.

[0916] 6. When the device (drone) reaches the predicted damage area, it begins to provide voice guidance using its built-in speaker. It repeatedly plays messages such as, "Everyone in City A, please evacuate to higher ground immediately."

[0917] Real-time information transfer

[0918] 7. The server transfers the images and video data received from the drone to the local government employee's device in real time, allowing the user (local government employee) to immediately check the situation on site and respond promptly.

[0919] Specific examples

[0920] Case 1: Rising river water levels

[0921] 1. The server receives water level data from a river sensor and detects that the water level has exceeded 3 meters. This data indicates that the water level is beyond the danger zone, and the server switches to disaster response mode.

[0922] 2. The server uses weather map data and the latest water level data to predict the expected damage area, "Urban Area A," using an AI model.

[0923] 3. The server generates a flight path for the drone based on the prediction results and sends it to the drone.

[0924] 4. The device (drone) automatically begins flying and reaches city A. During the flight, it takes video and transmits it to the server in real time.

[0925] 5. The drone will broadcast an audio message in the area of ​​expected damage saying, "Please evacuate to higher ground immediately."

[0926] 6. The server receives data from the drone and transfers it to the local government employee's device, allowing the user (local government employee) to grasp the situation in real time and quickly issue evacuation instructions to residents.

[0927] In this way, the system of the present invention can quickly collect information, grasp the situation, and provide effective evacuation guidance in the event of a disaster.

[0928] The processing flow will be explained below.

[0929] Step 1:

[0930] The server periodically collects water level data from water level sensors installed in the river. The sensors measure the water level in real time and send the data to the server.

[0931] Step 2:

[0932] The server stores the received water level data in a database, which is used for subsequent analysis.

[0933] Step 3:

[0934] The server periodically retrieves the latest water level data from the database and determines whether the water level has reached a dangerous level. If the water level reaches the set dangerous level, an alert is triggered.

[0935] Step 4:

[0936] The server retrieves weather chart data and past disaster data to prepare the data needed for the forecasting model, which is then processed and analyzed within the server.

[0937] Step 5:

[0938] The server uses an AI model (e.g., the Gemini model) to predict the likely damage area based on weather map data and water level data. This prediction identifies which specific areas will be affected.

[0939] Step 6:

[0940] The server automatically generates a drone flight path based on the predicted damage area, and transmits the generated flight plan information to the drone.

[0941] Step 7:

[0942] The terminal (drone) begins flying based on the flight path information received from the server. The drone uses sensors such as GPS to confirm its position and flies the planned path accurately.

[0943] Step 8:

[0944] The terminal (drone) arrives at the predicted damage area and takes pictures of the situation from above. The captured images and video data are sent to the server in real time.

[0945] Step 9:

[0946] The device (drone) plays a pre-recorded evacuation guidance message to residents in the predicted affected area, saying, "Everyone in City A, please evacuate to higher ground immediately."

[0947] Step 10:

[0948] The server receives real-time image and video data sent from the drone and forwards it to the terminals of local government employees.

[0949] Step 11:

[0950] The user (municipal government employee) checks the received real-time data on the terminal, allowing the user to immediately grasp the situation on-site and take the necessary measures promptly.

[0951] Through this series of steps, the system of the present invention can effectively collect information quickly, provide appropriate evacuation instructions, and grasp the situation in real time during a disaster.

[0952] Example 1

[0953] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0954] Conventional disaster monitoring systems have difficulty in real-time monitoring of rising river water levels and issuing prompt evacuation instructions, and effective responses are needed to minimize damage during disasters. In particular, it is challenging to quickly collect information in wide-ranging areas where damage is expected and issue appropriate evacuation instructions to residents.

[0955] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0956] In this invention, the server includes a means for receiving data from the sensor and determining whether the water level has reached a dangerous level, a means for predicting areas expected to be affected by damage using meteorological data and water level data, and a means for generating a flight path for the unmanned aerial vehicle based on the predicted areas expected to be affected and automatically creating a flight plan, which enables rapid information gathering and evacuation instructions to residents in the event of a disaster.

[0957] A "sensor" is a device that measures the water level of a river and transmits the measurement data to a server via a wireless network.

[0958] A "server" is a central processing unit that analyzes data received from sensors and performs various processes based on that data.

[0959] "Weather data" refers to data that indicates current and past weather conditions, such as weather maps, precipitation, and wind speed.

[0960] "Water level data" is quantitative data on the water level of a river measured by a sensor.

[0961] "Expected damage area" refers to an area that is likely to be affected by a predicted disaster.

[0962] An "unmanned aerial vehicle" is an aircraft that can be flown remotely or by automated program, commonly referred to as a drone.

[0963] "Flight route" refers to route information for an unmanned aerial vehicle, including the departure point, intermediate points, and destination.

[0964] A "flight plan" is a plan that includes specific flight routes and operational procedures that an unmanned aerial vehicle will execute based on a predicted damage area.

[0965] "Voice evacuation instructions" are a method of transmitting audio messages urging residents to evacuate via speakers installed on unmanned aerial vehicles.

[0966] "Administrative employee terminal" refers to a computer or mobile device used by an administrative employee to receive and check real-time data from the server.

[0967] The present invention provides a system that combines sensors that measure river water levels, a server that processes information, and an unmanned aerial vehicle that monitors disaster situations and provides evacuation guidance. This system enables rapid information collection and evacuation guidance for residents in the event of a disaster.

[0968] Water level monitoring with sensors

[0969] The sensors are installed in the river and measure the water level periodically. The measurement data is sent to a server via a wireless network. The sensors enable real-time monitoring of the river's water level.

[0970] Determining dangerous waters

[0971] The server analyzes water level data received periodically from the sensors and determines whether the water level has reached a preset danger zone. The database and analysis tools used here enable rapid detection of danger zones.

[0972] Prediction of expected damage areas

[0973] The server uses water level data and meteorological data to generate AI models (e.g., the Gemini model) to predict areas expected to be affected. The server also references data from past disasters to make detailed predictions of the degree of impact and the extent of damage.

[0974] Flight planning

[0975] The server generates a flight path for the drone based on the predicted damage area and transmits this information to the drone, which uses a flight planning tool to create a precise flight path.

[0976] Unmanned aerial vehicle flight and damage monitoring

[0977] The drone begins flying according to the flight path received from the server. During flight, the drone uses its camera to capture images of the damage and transmits the data to the server in real time, allowing for a detailed understanding of the damage situation.

[0978] Evacuation guidance using unmanned aerial vehicles

[0979] When the drone reaches the predicted damage area, it will begin to provide voice guidance using its built-in speaker. For example, it will repeatedly announce messages such as, "Everyone in City A, please evacuate to higher ground immediately."

[0980] Real-time information transfer

[0981] The server transfers the video data received from the unmanned aerial vehicle to the terminals of government officials in real time, allowing them to immediately grasp the situation on the ground and respond promptly.

[0982] Specific examples

[0983] Case 1: Rising river water levels

[0984] The server receives data from the river sensor that the water level has exceeded three meters. This data indicates that the water level is beyond the danger zone, and the server switches to disaster response mode.

[0985] 1. The server uses weather map data and the latest water level data to predict the expected damage area, "Urban Area A," using a generative AI model.

[0986] 2. The server generates a flight path for the unmanned aircraft based on the prediction results and sends it to the unmanned aircraft.

[0987] 3. The unmanned aircraft automatically begins flying and reaches "Urban Area A." During the flight, it takes video and transmits it to the server in real time.

[0988] 4. Unmanned aerial vehicles will broadcast an audio message in areas expected to be affected, saying, "Please evacuate to higher ground immediately."

[0989] 5. The server receives the data sent from the unmanned aerial vehicle and transfers it to the terminals of government officials, allowing them to grasp the situation in real time and issue quick evacuation instructions to residents.

[0990] Prompt Sentence Examples

[0991] Sample prompt 1: "If the water level of a river suddenly rises, how would you predict the areas likely to be affected and guide people to evacuate?"

[0992] Example prompt 2: "Please tell me specifically what the flight route of the unmanned aerial vehicle will be and how to provide evacuation instructions in the event of a flood in City A."

[0993] In this way, the system of the present invention can quickly collect information, grasp the situation, and provide effective evacuation guidance in the event of a disaster.

[0994] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0995] Step 1: Collect water level data from sensors

[0996] The server periodically collects water level data from the sensor. The sensor measures the river's water level every minute and sends the data to the server via a wireless network. The input data is water level information from the sensor, which the server receives and records in a database. Specifically, the server receives data from the sensor, records it in a database, and maintains the latest water level status.

[0997] Input: Water level data from the sensor

[0998] Output: Recorded water level data

[0999] Step 2: Determine the danger zone

[1000] Based on the water level data collected by the server, it determines whether the latest water level has reached the set dangerous water level. The input data is water level information from the sensor, which the server analyzes and compares with the dangerous water level threshold. The output is the result of the determination of whether the dangerous water level has been reached. Specifically, the server analyzes the water level data, compares it with the threshold, and issues a system alert if the dangerous water level has been reached.

[1001] Input: Water level data from the sensor

[1002] Output: Dangerous waters determination result

[1003] Step 3: Prediction of potential damage areas

[1004] The server uses weather map data and past disaster data to utilize an AI model (e.g., the Gemini model) to predict areas of potential damage. The input data is the latest water level data and weather data, which are input into the AI ​​model. The output is the predicted areas of potential damage. Specifically, the server collects weather map data and past disaster data, inputs them into the AI ​​model, obtains the prediction results, and identifies the areas of potential damage.

[1005] Input: Water level data, weather data, past disaster data

[1006] Output: Estimated damage area

[1007] Step 4: Drone flight path generation

[1008] The server generates a flight path for the unmanned aerial vehicle based on the predicted expected damage area. The input data is the location information of the expected damage area, and the flight path is calculated based on this. The output is the generated flight path. Specifically, the server identifies important monitoring points from the prediction results, calculates and generates a flight path, and sends the generated flight path to the unmanned aerial vehicle.

[1009] Input: Location information of the expected damage area

[1010] Output: Flight path information

[1011] Step 5: Fly the drone and monitor the damage

[1012] The terminal (unmanned aerial vehicle) takes off according to the flight route received from the server and flies the specified route. The input data is flight route information, and the unmanned aerial vehicle collects data while flying according to this information. The output is the captured video data. Specifically, the unmanned aerial vehicle flies automatically, takes photos and videos of the location with a camera, and transfers the video data to the server in real time.

[1013] Input: Flight route information

[1014] Output: Recorded video data

[1015] Step 6: Drone evacuation guidance

[1016] When the terminal (unmanned aerial vehicle) reaches the predicted damage area, it uses a built-in speaker to provide voice guidance. The input data is a voice message sent from the server, which the unmanned aerial vehicle relays to residents. The output is a voice guidance message to residents. Specifically, the unmanned aerial vehicle repeatedly plays a designated message, calling on residents to evacuate.

[1017] Input: Voice message

[1018] Output: Voice guidance

[1019] Step 7: Real-time data transfer

[1020] The server transfers real-time images and video data sent from the unmanned aerial vehicle to the terminals of local government employees. The input data is the video data received from the unmanned aerial vehicle, which the server sends to the terminals of local government employees. The output is the data transferred to the terminals of local government employees. Specifically, the server processes the data received from the drone and transfers it to the terminals of local government employees in real time. The administrative staff can then check the data and take on-site action as necessary.

[1021] Input: Video data from an unmanned aerial vehicle

[1022] Output: Data transferred to the administrative staff's terminal

[1023] (Application example 1)

[1024] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1025] When river water levels reach dangerous levels, it is extremely important to quickly and accurately collect disaster information and provide evacuation instructions to residents. Conventional technologies can result in delays in information collection and evacuation instructions, potentially resulting in greater damage. Furthermore, there are limitations to predicting affected areas in real time and generating appropriate evacuation messages. The objective of this invention is to solve these shortcomings and provide an effective disaster response system.

[1026] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1027] In this invention, the server includes a means for predicting estimated damage areas using a generative AI model and generating appropriate evacuation guidance messages for residents, a means for an unmanned aerial vehicle to transfer image data of estimated damage areas to the server in real time and perform continuous predictions and responses using the generative AI model, and a means for a drone to fly and photograph the damage situation from the air and send the data to the server, thereby enabling rapid and accurate information collection and appropriate evacuation guidance.

[1028] A "sensor" is a device that measures the water level of a river in real time and transmits the data to a server.

[1029] The "server" is a central processing unit that receives data from sensors, processes the data, and predicts dangerous water levels and areas of potential damage.

[1030] "Weather map data" is data that shows meteorological information, and is used in particular to grasp meteorological conditions in real time and predict areas likely to be affected.

[1031] An "unmanned aerial vehicle" is an aircraft that is remotely controlled or flies autonomously to monitor disaster situations and collect and transmit data.

[1032] "Flight path" refers to the designated route taken by an unmanned aerial vehicle.

[1033] A "flight plan" refers to a specific plan for an unmanned aerial vehicle to fly automatically based on a flight path.

[1034] "Estimated damage area" refers to an area that the server predicts will be affected by a disaster using weather map data and water level data.

[1035] A "generative AI model" is a model that uses machine learning and artificial intelligence technology to analyze data and predict areas of potential damage.

[1036] "Evacuation instruction messages" refer to audio or text instructions to encourage residents in areas expected to be affected to take appropriate evacuation actions.

[1037] "Image data" refers to photographs and videos of disaster situations taken from the air by unmanned aerial vehicles.

[1038] "Local government employee terminals" refers to communication terminals such as computers and smartphones used by local government employees for disaster response purposes.

[1039] This invention provides a system that combines sensors that measure river water levels, a server that processes the information, and an unmanned aerial vehicle that monitors disaster situations and provides evacuation guidance. This system enables rapid information collection and evacuation guidance for residents in the event of a disaster.

[1040] The entire system is realized by the following hardware and software configuration.

[1041] Hardware Configuration

[1042] 1. Water level sensor: A device installed in a river to measure the water level in real time.

[1043] 2. Server: The central processing unit that receives data from sensors and performs analysis and predictions.

[1044] 3. Unmanned aerial vehicles: Aircraft that monitor disaster situations from the sky, collect data in real time, and provide evacuation instructions to residents.

[1045] 4. Local government employee devices: Communication devices such as computers and smartphones.

[1046] Software Configuration

[1047] 1. Data collection module: Software that collects water level data from sensors and sends it to the server.

[1048] 2. Data analysis module: Software that uses collected data to determine whether water levels have reached dangerous levels and uses a generative AI model to predict potential damage areas.

[1049] 3. Flight plan generation module: Software that generates flight paths for unmanned aerial vehicles based on the expected damage area and automatically creates flight plans.

[1050] 4. Real-time data transfer module: Software that transfers data sent from unmanned aerial vehicles to local government employee terminals in real time.

[1051] 5. Voice guidance module: Software that uses the prediction results to enable unmanned aerial vehicles to provide voice guidance on evacuation in areas expected to be affected.

[1052] Data processing and calculation flow

[1053] The server first collects water level data periodically sent from the sensors. This data is sent to the server in real time and used to determine whether the water level has reached a dangerous level. If the determination is that the water level is dangerous, the server uses weather map data and past disaster data to predict the likely damage area using a generative AI model (e.g., machine learning or artificial intelligence technology).

[1054] Example prompts for generative AI models

[1055] Based on these prompts, the server predicts the expected damage area and generates a flight plan accordingly. The unmanned aerial vehicle then flies along a flight path generated based on the prediction results, photographing the damage situation from the air in real time and sending the data to the server. This data is then received by the devices of local government employees, enabling them to immediately grasp the situation on site and take prompt action.

[1056] Examples of prompt statements

[1057] "Please predict the area of ​​potential damage if the river water level exceeds 3 meters."

[1058] In this way, the entire system will work together to enable rapid and accurate information gathering and appropriate responses in the event of a disaster.

[1059] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1060] Step 1:

[1061] Water level data collection

[1062] The server periodically collects water level data from sensors installed in the river. The input data is the water level measurement data sent from the sensor, and the output data is the water level data stored in the server's internal database. Specifically, the server retrieves data from the sensor using an HTTP request.

[1063] Step 2:

[1064] Determining dangerous waters

[1065] The server determines whether the water level has reached a dangerous level based on the received water level data. The input data is the collected water level data, and the output data is a flag indicating whether the water level has reached a dangerous level. Specifically, the server compares the water level data with the set dangerous water level threshold and sets a flag if the threshold is exceeded.

[1066] Step 3:

[1067] Prediction of expected damage areas

[1068] When a dangerous water area flag is raised, the server uses weather map data and past disaster data to use a generative AI model to predict the area of ​​expected damage. The input data is water level data, weather map data, and past disaster data, and the output data is information on the area of ​​expected damage. In concrete terms, the server gives the generative AI model specific instructions, such as a prompt statement and argument data, such as "area of ​​expected damage if the river water level exceeds 3 meters," and receives the prediction results from the model.

[1069] Step 4:

[1070] Flight plan generation

[1071] The server generates a flight path for the unmanned aerial vehicle based on the predicted damage area and automatically creates a flight plan. The input data is information about the damage area, and the output data is specific flight path information. Specifically, the server calculates the optimal flight path based on GPS data and transmits it to the unmanned aerial vehicle.

[1072] Step 5:

[1073] Unmanned aerial vehicle flight and data collection

[1074] The unmanned aerial vehicle begins flying according to the flight path received from the server. During flight, the unmanned aerial vehicle photographs the damage situation from the sky and transmits the data to the server in real time. The input data is flight path information, and the output data is the photographed image data. Specifically, the unmanned aerial vehicle uses a camera to capture images from the sky and transfers them to the server via wireless communication.

[1075] Step 6:

[1076] Generation and execution of evacuation guidance messages

[1077] Based on the prediction results, the server generates a message calling for evacuation for residents in the predicted damage area and transmits it as audio guidance to the unmanned aerial vehicle. The input data is the predicted damage area and the message information generated by the generation AI model, and the output data is the audio guidance message. Specifically, the server uses the generation AI model to create an evacuation message and plays it through the speaker on the unmanned aerial vehicle.

[1078] Step 7:

[1079] Real-time information transfer

[1080] The server transfers the image and video data received from the unmanned aerial vehicle to the local government employee's device in real time. The input data is image data from the unmanned aerial vehicle, and the output data is real-time video to the local government employee's device. Specifically, the server immediately packets the received data and sends a push notification to each local government employee's device.

[1081] This series of processes enables the system to quickly and accurately collect information and provide appropriate evacuation instructions.

[1082] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1083] This invention is a system that combines sensors that measure river water levels, a server that processes information, drones that monitor disaster situations and provide evacuation guidance, and an emotion engine that recognizes the user's emotions. The system aims to quickly collect information during disasters, provide evacuation guidance to residents, and provide emotional support to local government officials.

[1084] Program processing flow

[1085] The processing of the system program will be explained in natural language below.

[1086] Water level monitoring with sensors

[1087] 1. The server periodically collects water level data from water level sensors installed in the river. The sensors measure the river's water level in real time and send the data to the server.

[1088] Determining dangerous waters

[1089] 2. The server determines whether the water level has reached the danger zone based on the received data. If the water level has reached the danger zone, the system proceeds to the next step.

[1090] Prediction of expected damage areas

[1091] 3. The server uses weather map data and past disaster data to predict areas expected to be affected using an AI model (e.g., the Gemini model). This prediction makes it possible to determine which areas will be affected and to what extent.

[1092] Flight planning

[1093] 4. The server generates a flight path for the drone based on the predicted damage area. The generated flight path is sent to the drone and executed automatically.

[1094] Drone flight and evacuation guidance

[1095] 5. The device (drone) begins flying according to the flight path received from the server. During flight, the drone photographs the damage from above and sends the data to the server in real time. The photographed data can be used to grasp the detailed damage situation.

[1096] 6. When the device (drone) reaches the predicted damage area, it begins to provide voice guidance using its built-in speaker. It repeatedly plays messages such as, "Everyone in City A, please evacuate to higher ground immediately."

[1097] Real-time information transfer

[1098] 7. The server transfers the images and video data received from the drone to the local government employee's device in real time, allowing the user (local government employee) to immediately check the situation on site and respond promptly.

[1099] Use of emotion engine

[1100] 8. The server uses an emotion engine to monitor the stress levels and emotional state of local government employees. If stress levels are found to be elevated, relaxation and support messages are automatically sent.

[1101] 9. The device (drone) will recognize the emotions of residents in the predicted affected area and play appropriate voice guidance depending on their emotional state. For example, if anxiety is rising, it will play a message such as "Please remain calm and follow evacuation instructions."

[1102] Specific examples

[1103] Case 1: Rising river water levels

[1104] 1. The server receives water level data from a river sensor and detects that the water level has exceeded 3 meters. This data indicates that the water level is beyond the danger zone, and the server switches to disaster response mode.

[1105] 2. The server uses weather map data and the latest water level data to predict the expected damage area, "Urban Area A," using an AI model.

[1106] 3. The server generates a flight path for the drone based on the prediction results and sends it to the drone.

[1107] 4. The device (drone) automatically begins flying and reaches city A. During the flight, it takes video and transmits it to the server in real time.

[1108] 5. The drone will broadcast an audio message in the affected area saying, "Please evacuate to higher ground immediately." If residents feel anxious, the emotion recognition system will detect this and switch to a more reassuring message.

[1109] 6. The server receives data from the drone and transfers it to the local government employee's device, allowing the user (local government employee) to grasp the situation in real time and quickly issue evacuation instructions to residents.

[1110] Case 2: Stress management for local government employees

[1111] 1. An emotion engine installed on the server monitors the stress levels of local government employees.

[1112] 2. If the stress level of staff increases during disaster response, the server automatically sends a relaxation message to the staff's device.

[1113] 3. Users (municipal government officials) can reduce stress and continue to respond calmly.

[1114] In this way, the system of the present invention can respond to disasters more effectively by quickly gathering information and providing evacuation instructions during disasters, as well as providing emotional support to local government officials.

[1115] The processing flow will be explained below.

[1116] Step 1:

[1117] The server periodically collects water level data from water level sensors installed in the river. The sensors measure the water level in real time and send the data to the server.

[1118] Step 2:

[1119] The server stores the received water level data in a database, which is used for subsequent analysis.

[1120] Step 3:

[1121] The server periodically retrieves the latest water level data from the database and determines whether the water level has reached a dangerous level. If the water level reaches the set dangerous level, an alert is triggered.

[1122] Step 4:

[1123] The server receives weather chart data and past disaster data, which are then processed and used to predict potential damage areas in the event of a dangerous water zone.

[1124] Step 5:

[1125] The server uses AI models to analyze weather map data and water level data to predict potential damage areas, which can then identify which areas will be affected.

[1126] Step 6:

[1127] The server generates a flight path for the drone based on the predicted damage area, and transmits the generated flight plan information to the drone.

[1128] Step 7:

[1129] The terminal (drone) begins flying based on the flight path information received from the server. The drone uses sensors such as GPS to confirm its position and flies the planned path accurately.

[1130] Step 8:

[1131] The terminal (drone) arrives at the predicted damage area and takes pictures of the situation from above. The captured images and video data are sent to the server in real time.

[1132] Step 9:

[1133] The device (drone) plays a pre-recorded evacuation guidance message to residents in the predicted affected area, saying, "Everyone in City A, please evacuate to higher ground immediately."

[1134] Step 10:

[1135] The server receives real-time image and video data sent from the drone and transfers it to the terminals of local government employees in real time.

[1136] Step 11:

[1137] The server uses an emotion engine to monitor the stress levels and emotional state of local government employees, and if stress is judged to be increasing, it automatically sends relaxation and support messages.

[1138] Step 12:

[1139] The device (drone) recognizes the emotions of residents in the predicted affected area and plays appropriate voice guidance according to their emotional state. For example, if anxiety is rising, it will play a message such as "Please remain calm and follow evacuation instructions."

[1140] Step 13:

[1141] The user (municipal government employee) checks the received real-time data on the device. The user can immediately grasp the situation on the ground and take the necessary measures. In addition, the user can maintain a calm mind by receiving relaxation messages from the emotion engine.

[1142] Through this series of steps, the system of the present invention can effectively gather information quickly, provide appropriate evacuation instructions, and provide emotional support to local government officials in the event of a disaster.

[1143] Example 2

[1144] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1145] During natural disasters, the challenges are to quickly and accurately gather information, provide evacuation instructions to residents, and comprehensively manage the stress of local government employees. In particular, there is a need for a system that can simultaneously grasp on-site information in real time during a disaster and manage the emotions of residents and local government employees.

[1146] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1147] In this invention, the server includes means for receiving data from a sensor measuring the river water level and determining whether the water level has reached a dangerous level, means for predicting potential damage areas using weather map data and water level data, and means for generating a flight path for the flying machine based on the predicted potential damage areas and automatically creating a flight plan, which enables the rapid collection of disaster information, accurate evacuation guidance, and stress management for local government officials.

[1148] A "sensor for measuring river water levels" is a device that measures river water levels in real time and sends the data to a server.

[1149] A "server" is a central processing unit that receives data from sensors, analyzes it, and executes various processes.

[1150] "Weather map data" is a data set containing meteorological information and is used to predict weather fluctuations.

[1151] "Water level data" is a data set that shows the current water level and its fluctuations in a river.

[1152] A "potential damage area" is a specific geographical area that is expected to be affected in the event of a disaster.

[1153] A "flying machine" is a device that can fly autonomously and gather information from the air, generally referring to drones or unmanned aerial vehicles (UAVs).

[1154] "Flight path" means the planned route to be followed by a flying vehicle.

[1155] "Voice evacuation guidance" is a method in which flying machines use voice messages to encourage residents to evacuate.

[1156] An "administrator's terminal" is a computer or mobile device used by an administrator, such as a local government employee.

[1157] The "Emotion Engine" is a system that analyzes an individual's emotional state and monitors stress levels and emotional responses.

[1158] "Stress level" is a measure of the degree of psychological pressure or burden felt by an individual.

[1159] "Emotional state" refers to an individual's current emotional or mood state.

[1160] This invention is a system that uses river water level measurement sensors, a server that processes the data, a flying machine that monitors disaster situations and guides evacuation, and an emotion engine that recognizes the emotions of administrators. The system aims to quickly collect information in the event of a disaster, provide evacuation instructions to residents, and provide emotional support to local government officials.

[1161] First, the main components of the system will be described.

[1162] A river water level measurement sensor is a device that is installed in a specific area of ​​a river and measures water level data in real time. For example, a general water level measurement device is used.

[1163] The server is a device that periodically collects data from the sensors and analyzes it. It is equipped with an analytical algorithm that determines whether the water level has reached a preset danger level. The server also uses weather chart data and past disaster data to predict potential damage areas using an AI model (such as the Gemini model).

[1164] The flying machine (drone) is a device for monitoring the situation in the predicted damage area from the sky, and automatically generates a flight path and flies based on instructions from the server. During the flight, it takes images from the sky and sends the data to the server in real time. It also provides evacuation guidance through audio guidance.

[1165] The administrator's terminal is a device that receives data from the server and checks the situation on site in real time, and has emergency response apps and dedicated software installed.

[1166] The emotion engine is a system that monitors the stress level and emotional state of the administrator and sends relaxation messages as needed.

[1167] Specific examples are shown below.

[1168] Case 1: Rising river water levels

[1169] 1. The server receives water level data from a river sensor and detects that the water level has exceeded 3 meters. This data indicates that the water level has exceeded the danger level, and the server switches to disaster response mode.

[1170] 2. The server uses weather map data and the latest water level data to predict the expected damage area, "Urban Area A," using an AI model.

[1171] 3. The server generates a flight path for the flying machine based on the prediction results and sends it to the flying machine.

[1172] 4. The terminal (flying machine) automatically begins flying and reaches city A. During the flight, it takes video and transmits it to the server in real time.

[1173] 5. Flying machines will broadcast an audio message in the affected area saying, "Please evacuate to higher ground immediately." If residents feel anxious, an emotion recognition system will detect this and switch to a more reassuring message.

[1174] 6. The server receives data from the flying machine and transfers it to the administrator's terminal, allowing the user (administrator) to grasp the situation in real time and quickly issue evacuation instructions to residents.

[1175] Case 2: Stress management for local government employees

[1176] 1. An emotion engine installed on the server monitors the stress levels of local government employees.

[1177] 2. If the stress level of staff increases during disaster response, the server automatically sends a relaxation message to the staff's device.

[1178] 3. Users (staff) can reduce stress and continue to respond calmly.

[1179] To achieve this, the system uses prompt statements such as:

[1180] "Generate an appropriate evacuation guidance message when the river water level reaches 3 meters."

[1181] "Please provide an example of a relaxation message for local government employees when their stress levels increase."

[1182] "Please tell us how you specifically use AI models to predict potential damage areas."

[1183] As described above, the present invention enables the rapid collection of disaster information, accurate evacuation guidance, and emotional support for local government officials, thereby improving disaster response capabilities.

[1184] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1185] Step 1:

[1186] The server collects data from river water level sensors. The input is water level data from the sensors, and the output is water level data stored in a database on the server.

[1187] The server sends an HTTP request to the sensor via the network to retrieve the data. The retrieved data includes a timestamp and geolocation information. For example, "Sensor ID: 001, Water level: 3.2 meters, Timestamp: 2023-10-04T14:00:00Z".

[1188] Step 2:

[1189] The server analyzes the water level data and determines whether the water level has reached the set danger level. The input is the collected water level data, and the output is the setting of the danger state flag.

[1190] The server uses a condition determination algorithm to set a danger flag if the water level exceeds a threshold (e.g., 3 meters). For example, "Current water level: 3.2 meters, Set threshold: 3.0 meters, Danger state: Active."

[1191] Step 3:

[1192] The server inputs weather map data, past disaster data, and the latest water level data into the AI ​​model to predict the likely damage area. The inputs are weather map data, past disaster data, and water level data, and the output is the likely damage area and its impact.

[1193] The server uses Google Cloud Platform's AI services and its own Gemini model to output the prediction results as potentially affected areas and the level of damage (e.g., "Urban Area A: High, Rural Area B: Medium").

[1194] Step 4:

[1195] The server generates a flight path for the flying machine based on the predicted damage area. The input is the predicted damage area and its impact, and the output is flight path data in JSON format.

[1196] The server calculates the optimal flight route and sends the data to the flying machine. For example, "Flight route: Start point (latitude: 35.6895, longitude: 139.6917) → City A (latitude: 35.6895, longitude: 139.7000) → End point (latitude: 35.7000, longitude: 139.7100)".

[1197] Step 5:

[1198] The terminal (flying machine) starts automatic flight according to the flight path received from the server. The input is the flight path data sent from the server, and the output is the captured video data.

[1199] The flying machine flies autonomously along a designated route using GPS, capturing video of the situation from above. The captured video data is then sent to a server in real time. For example, the video may be "video of the flooding situation in City A."

[1200] Step 6:

[1201] When the terminal (flying machine) reaches the predicted damage area, it starts to give voice guidance through the built-in speaker. The input is the evacuation guidance message sent from the server, and the output is the broadcast voice message.

[1202] The flying machine constantly broadcasts messages calling for evacuation. For example, it might say, "Everyone in City A, please evacuate to higher ground immediately." If residents feel anxious, it uses an emotion recognition system to change the message to, "Please remain calm and follow evacuation instructions."

[1203] Step 7:

[1204] The server transfers the image and video data received from the flying machine to the administrator's terminal in real time. The input is the video data from the flying machine, and the output is the real-time video displayed on the administrator's terminal.

[1205] The server transfers data through a dedicated app or web interface, such as "Video showing widespread flooding in City A."

[1206] Step 8:

[1207] The server monitors the stress level and emotional state of the administrator using an emotion engine, where the input is biometric data from the administrator and the output is an assessment of the administrator's emotional state and stress level.

[1208] The emotion engine analyzes biosensor and input data and automatically sends relaxation messages when stress levels rise. For example, "Employee 1's stress level: High, Relaxation Message: 'Take a deep breath and relax.'"

[1209] Step 9:

[1210] The terminal (flying machine) recognizes the emotions of residents in the predicted damage area and provides appropriate voice guidance according to their emotional state. The input is the residents' emotional data collected during flight, and the output is a voice message according to their emotional state.

[1211] The flying machine uses AI to analyze voices and play reassuring messages if anxiety levels are high. For example, "Residents' emotional state: anxiety, guidance message: 'Please remain calm and follow evacuation instructions.'"

[1212] (Application example 2)

[1213] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1214] Conventional river monitoring systems have had issues with rapid response and evacuation guidance in the event of a disaster. Logistics centers also need to streamline inventory management and transportation operations, as well as manage employee stress. The purpose of this invention is to provide a system that can solve these issues and respond efficiently and quickly.

[1215] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1216] In this invention, the server includes: means for receiving data from a sensor measuring the river water level and determining whether the water level has reached a dangerous level; means for predicting an estimated damage area using weather map data and water level data; means for generating a flight path for an unmanned aerial vehicle based on the predicted estimated damage area and automatically creating a flight plan; means for the unmanned aerial vehicle to fly, photograph the damage situation from the air, and transmit the photographed data; means for the unmanned aerial vehicle to provide evacuation guidance via voice in the estimated damage area; means for periodically collecting data from an inventory sensor and determining whether inventory has fallen below a threshold; means for predicting product delivery timing using past data and a generative AI model; means for generating a movement route for an automated transport robot based on the predicted delivery timing and automatically creating a plan; means for the automated transport robot to transport products along the movement route and transmit the data; means for transferring the received data to an employee terminal at a logistics center in real time; and means for monitoring the stress levels of logistics center employees using an emotion engine and sending relaxation messages as necessary. This enables rapid information collection and evacuation guidance during a disaster, efficient inventory management and product delivery, and employee stress management.

[1217] A "sensor for measuring river water levels" is a device that measures river water levels in real time and sends the data to a server.

[1218] A "server" is a central control device that receives data from sensors and processes and analyzes it.

[1219] "Weather map data" refers to data that includes meteorological information and is used for disaster prediction.

[1220] "Expected damage area" refers to an area that is predicted to be affected if a disaster occurs.

[1221] An "unmanned aerial vehicle" is an aircraft that flies under remote control or automatic control.

[1222] A "flight path" is the route that an unmanned aerial vehicle follows as it flies.

[1223] "Periodic" means repeated at regular intervals.

[1224] An "inventory sensor" is a device that measures product inventory in a warehouse.

[1225] A "generative AI model" is a mathematical model used to analyze and predict data generated by artificial intelligence.

[1226] An "automatic transport robot" is a robot that automatically transports goods within a logistics center.

[1227] A "distribution center staff terminal" is a terminal used by staff at a distribution center to display and operate data.

[1228] The "emotion engine" is a system that analyzes the user's emotional state and responds based on the results.

[1229] A "relaxation message" is a message intended to relieve the user's stress.

[1230] This invention is a system that combines sensors that measure river water levels, a server that processes information, an unmanned aerial vehicle that monitors the damage situation and provides evacuation guidance, sensors that monitor inventory, an automatic transport robot, staff terminals at a logistics center, and an emotion engine that recognizes user emotions.

[1231] First, sensors are installed to measure river water levels, collecting real-time data and sending it to a server. The server then analyzes the received data and determines whether the water level has reached a dangerous level. Using weather map data and water level data, a generative AI model is used to predict potential damage areas.

[1232] Once the estimated damage area is predicted, the server generates a flight path for the unmanned aircraft and automatically creates a flight plan. The unmanned aircraft flies to the predicted area and takes photographs of the damage from above. The data is sent to the server and then transferred in real time to the devices of local government employees. The unmanned aircraft also provides audio evacuation guidance in the estimated damage area, urging residents to evacuate quickly.

[1233] Meanwhile, sensors are also installed to measure inventory at the logistics center, and these periodically send inventory data to a server. The server analyzes the received inventory data, and if inventory falls below a threshold, it uses past data and a generative AI model to predict when to bring in the goods. Based on this prediction, it generates an operating route for the automated transport robot and issues instructions to the robot. The automated transport robot transports the goods along the operating route and sends the data to the server. The transport data is also transferred in real time to staff terminals at the logistics center.

[1234] In addition, the emotion engine installed on the server monitors the stress levels of logistics center staff and sends relaxation messages to staff devices as needed.

[1235] As a concrete example, consider the following case:

[1236] Case 1: Rising river water levels

[1237] 1. The server receives water level data from a river sensor and detects that the water level has exceeded 3 meters. This data indicates that the water level is beyond the danger zone, and the server switches to disaster response mode.

[1238] 2. The server uses weather map data and the latest water level data to predict the expected damage area, "Urban Area A," using a generative AI model.

[1239] 3. The server generates a flight path for the unmanned aircraft based on the prediction results and sends it to the unmanned aircraft.

[1240] 4. The unmanned aerial vehicle automatically begins flying and reaches urban area A. During the flight, it takes video and transmits it to the server in real time.

[1241] 5. Unmanned aerial vehicles will broadcast an audio message in areas expected to be affected, saying, "Please evacuate to higher ground immediately." If residents feel anxious, an emotion recognition system will detect this and switch to a more reassuring message.

[1242] 6. The server receives data from the unmanned aerial vehicle and transfers it to the devices of local government officials, allowing them to grasp the situation in real time and quickly issue evacuation instructions to residents.

[1243] Case 2: Inventory management at a logistics center

[1244] 1. The server detects from the inventory sensor that the inventory of "Product A" has fallen below a threshold.

[1245] 2. The server uses past data and the generative AI model to predict the appropriate delivery timing for product A.

[1246] 3. The server generates the movement route of the automated transport robot based on the prediction results and gives instructions.

[1247] 4. The automated transport robot transports the product along the specified route and sends the data acquired during the process to the server.

[1248] 5. The server transfers the transport data from the robot to the staff terminal at the logistics center in real time.

[1249] Prompt Sentence Examples

[1250] text

[1251] Inventory data: Product A has fallen below the threshold of 50.

[1252] Emotional Data: Employee A's stress level is 0.8.

[1253] Instructions: Please reorder immediately and instruct Employee A to take a break.

[1254] In this way, the system of the present invention realizes rapid information gathering and evacuation guidance in the event of a disaster, efficient inventory management and transportation operations at logistics centers, and stress management for employees.

[1255] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1256] Step 1:

[1257] The server receives real-time data from sensors measuring river water levels. This data includes current water level information. Based on this, the server analyzes water level trends and determines in real time whether the water level is reaching a dangerous level.

[1258] Input: River water level data

[1259] Output: Dangerous water level determination result

[1260] Specific behavior:

[1261] The server analyzes the water level data obtained from the sensor.

[1262] The result is compared with a preset threshold value for dangerous waters and a judgment result is generated.

[1263] Step 2:

[1264] If the server determines that the water level has reached a dangerous level, it uses weather map data and the aforementioned water level data to predict areas where damage is likely to occur. Utilizing a generative AI model, it estimates damage for each area based on past data.

[1265] Input: Dangerous water level determination results, weather chart data, water level data

[1266] Output: Estimated damage area forecast

[1267] Specific behavior:

[1268] Weather map data and water level data are imported into the server and input into the generative AI model.

[1269] An AI model analyzes the data and identifies areas likely to be affected.

[1270] Step 3:

[1271] The server generates a flight path for the drone based on the predicted damage area, including the shortest route and a preferred route to the most severely damaged area.

[1272] Input: Estimated damage area forecast

[1273] Output: Flight path of the unmanned aerial vehicle

[1274] Specific behavior:

[1275] The server analyzes the results of the generated AI model and generates an efficient flight path.

[1276] Transmitting flight path data to the unmanned aerial vehicle.

[1277] Step 4:

[1278] The unmanned aerial vehicle will then begin flying according to the received flight path, taking photos of the damage from above and sending the data to a server in real time.

[1279] Input: Unmanned Aerial Vehicle Flight Path

[1280] Output: Photographic data of the damage situation

[1281] Specific behavior:

[1282] The unmanned aerial vehicle follows a designated flight path.

[1283] Images and video data taken from the sky are sent to a server.

[1284] Step 5:

[1285] The server analyzes the image data received from the unmanned aerial vehicle and transfers it in real time to the devices of local government employees, who use the data to quickly grasp the extent of damage at the scene.

[1286] Input: Photographic data of the damage situation

[1287] Output: Real-time data to local government employee terminals

[1288] Specific behavior:

[1289] The server analyzes the data from the unmanned aerial vehicle and extracts the necessary information.

[1290] Data is transferred to local government employee terminals in real time.

[1291] Step 6:

[1292] The server instructs unmanned aerial vehicles in areas expected to be affected to provide voice evacuation guidance, enabling residents to evacuate quickly and smoothly.

[1293] Input: Estimated damage area forecast

[1294] Output: Evacuation guidance voice message

[1295] Specific behavior:

[1296] The server transmits the contents of the voice message to the unmanned aerial vehicle.

[1297] Unmanned aerial vehicles will provide voice evacuation instructions in designated areas.

[1298] Step 7:

[1299] The server periodically receives data from inventory sensors installed in the distribution center and monitors inventory levels. If the inventory level falls below a threshold, it predicts when to bring in products and generates a route for the automated transport robot.

[1300] Input: Inventory data

[1301] Output: Delivery timing prediction, transportation route

[1302] Specific behavior:

[1303] The server analyzes inventory data obtained from sensors and inputs it into a generative AI model.

[1304] Predict the timing of product delivery and generate appropriate delivery routes.

[1305] Step 8:

[1306] The automated transport robot delivers products to the designated location according to the route received from the server, and data on the delivery process is also sent to the server in real time.

[1307] Input: Delivery Route

[1308] Output: Transport data

[1309] Specific behavior:

[1310] The automated transport robot transports the goods along the instructed route.

[1311] Data acquired during transportation is sent to the server.

[1312] Step 9:

[1313] The server uses an emotion engine to monitor the stress levels of logistics center staff and sends relaxation messages if it detects high levels of stress.

[1314] Input: Employee emotion data

[1315] Output: Relaxation message

[1316] Specific behavior:

[1317] The server analyzes the stress levels of employees using an emotion engine.

[1318] If necessary, send relaxation messages to staff terminals.

[1319] In this way, each step works in tandem to seamlessly realize disaster response, inventory management, transportation efficiency, and staff stress management.

[1320] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1321] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1322] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1323] [Fourth embodiment]

[1324] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1325] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1326] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1327] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1328] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1329] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1330] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1331] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1332] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1333] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1334] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1335] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1336] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1337] This invention provides a system that combines sensors that measure river water levels, a server that processes the information, and drones that monitor disaster situations and provide evacuation guidance. This system enables rapid information collection and evacuation guidance for residents in the event of a disaster.

[1338] Program processing flow

[1339] The processing of the system program will be explained in natural language below.

[1340] Water level monitoring with sensors

[1341] 1. The server periodically collects water level data from sensors installed in the river. The sensors measure the river's water level in real time, so the server can receive the latest water level information at any time.

[1342] Determining dangerous waters

[1343] 2. The server determines whether the water level has reached the danger zone based on the received data. If the water level has reached the danger zone, the system proceeds to the next step.

[1344] Prediction of expected damage areas

[1345] 3. The server uses weather map data and past disaster data to predict areas expected to be affected using an AI model (e.g., the Gemini model). This prediction makes it possible to determine which areas will be affected and to what extent.

[1346] Flight planning

[1347] 4. The server generates a flight path for the drone based on the predicted damage area. The generated flight path is sent to the drone and executed automatically.

[1348] Drone flight and evacuation guidance

[1349] 5. The device (drone) begins flying according to the flight path received from the server. During flight, the drone photographs the damage from above and sends the data to the server in real time. The photographed data can be used to grasp the detailed damage situation.

[1350] 6. When the device (drone) reaches the predicted damage area, it begins to provide voice guidance using its built-in speaker. It repeatedly plays messages such as, "Everyone in City A, please evacuate to higher ground immediately."

[1351] Real-time information transfer

[1352] 7. The server transfers the images and video data received from the drone to the local government employee's device in real time, allowing the user (local government employee) to immediately check the situation on site and respond promptly.

[1353] Specific examples

[1354] Case 1: Rising river water levels

[1355] 1. The server receives water level data from a river sensor and detects that the water level has exceeded 3 meters. This data indicates that the water level is beyond the danger zone, and the server switches to disaster response mode.

[1356] 2. The server uses weather map data and the latest water level data to predict the expected damage area, "Urban Area A," using an AI model.

[1357] 3. The server generates a flight path for the drone based on the prediction results and sends it to the drone.

[1358] 4. The device (drone) automatically begins flying and reaches city A. During the flight, it takes video and transmits it to the server in real time.

[1359] 5. The drone will broadcast an audio message in the area of ​​expected damage saying, "Please evacuate to higher ground immediately."

[1360] 6. The server receives data from the drone and transfers it to the local government employee's device, allowing the user (local government employee) to grasp the situation in real time and quickly issue evacuation instructions to residents.

[1361] In this way, the system of the present invention can quickly collect information, grasp the situation, and provide effective evacuation guidance in the event of a disaster.

[1362] The processing flow will be explained below.

[1363] Step 1:

[1364] The server periodically collects water level data from water level sensors installed in the river. The sensors measure the water level in real time and send the data to the server.

[1365] Step 2:

[1366] The server stores the received water level data in a database, which is used for subsequent analysis.

[1367] Step 3:

[1368] The server periodically retrieves the latest water level data from the database and determines whether the water level has reached a dangerous level. If the water level reaches the set dangerous level, an alert is triggered.

[1369] Step 4:

[1370] The server retrieves weather chart data and past disaster data to prepare the data needed for the forecasting model, which is then processed and analyzed within the server.

[1371] Step 5:

[1372] The server uses an AI model (e.g., the Gemini model) to predict the likely damage area based on weather map data and water level data. This prediction identifies which specific areas will be affected.

[1373] Step 6:

[1374] The server automatically generates a drone flight path based on the predicted damage area, and transmits the generated flight plan information to the drone.

[1375] Step 7:

[1376] The terminal (drone) begins flying based on the flight path information received from the server. The drone uses sensors such as GPS to confirm its position and flies the planned path accurately.

[1377] Step 8:

[1378] The terminal (drone) arrives at the predicted damage area and takes pictures of the situation from above. The captured images and video data are sent to the server in real time.

[1379] Step 9:

[1380] The device (drone) plays a pre-recorded evacuation guidance message to residents in the predicted affected area, saying, "Everyone in City A, please evacuate to higher ground immediately."

[1381] Step 10:

[1382] The server receives real-time image and video data sent from the drone and forwards it to the terminals of local government employees.

[1383] Step 11:

[1384] The user (municipal government employee) checks the received real-time data on the terminal, allowing the user to immediately grasp the situation on-site and take the necessary measures promptly.

[1385] Through this series of steps, the system of the present invention can effectively collect information quickly, provide appropriate evacuation instructions, and grasp the situation in real time during a disaster.

[1386] Example 1

[1387] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1388] Conventional disaster monitoring systems have difficulty in real-time monitoring of rising river water levels and issuing prompt evacuation instructions, and effective responses are needed to minimize damage during disasters. In particular, it is challenging to quickly collect information in wide-ranging areas where damage is expected and issue appropriate evacuation instructions to residents.

[1389] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1390] In this invention, the server includes a means for receiving data from the sensor and determining whether the water level has reached a dangerous level, a means for predicting areas expected to be affected by damage using meteorological data and water level data, and a means for generating a flight path for the unmanned aerial vehicle based on the predicted areas expected to be affected and automatically creating a flight plan, which enables rapid information gathering and evacuation instructions to residents in the event of a disaster.

[1391] A "sensor" is a device that measures the water level of a river and transmits the measurement data to a server via a wireless network.

[1392] A "server" is a central processing unit that analyzes data received from sensors and performs various processes based on that data.

[1393] "Weather data" refers to data that indicates current and past weather conditions, such as weather maps, precipitation, and wind speed.

[1394] "Water level data" is quantitative data on the water level of a river measured by a sensor.

[1395] "Expected damage area" refers to an area that is likely to be affected by a predicted disaster.

[1396] An "unmanned aerial vehicle" is an aircraft that can be flown remotely or by automated program, commonly referred to as a drone.

[1397] "Flight route" refers to route information for an unmanned aerial vehicle, including the departure point, intermediate points, and destination.

[1398] A "flight plan" is a plan that includes specific flight routes and operational procedures that an unmanned aerial vehicle will execute based on a predicted damage area.

[1399] "Voice evacuation instructions" are a method of transmitting audio messages urging residents to evacuate via speakers installed on unmanned aerial vehicles.

[1400] "Administrative employee terminal" refers to a computer or mobile device used by an administrative employee to receive and check real-time data from the server.

[1401] The present invention provides a system that combines sensors that measure river water levels, a server that processes information, and an unmanned aerial vehicle that monitors disaster situations and provides evacuation guidance. This system enables rapid information collection and evacuation guidance for residents in the event of a disaster.

[1402] Water level monitoring with sensors

[1403] The sensors are installed in the river and measure the water level periodically. The measurement data is sent to a server via a wireless network. The sensors enable real-time monitoring of the river's water level.

[1404] Determining dangerous waters

[1405] The server analyzes water level data received periodically from the sensors and determines whether the water level has reached a preset danger zone. The database and analysis tools used here enable rapid detection of danger zones.

[1406] Prediction of expected damage areas

[1407] The server uses water level data and meteorological data to generate AI models (e.g., the Gemini model) to predict areas expected to be affected. The server also references data from past disasters to make detailed predictions of the degree of impact and the extent of damage.

[1408] Flight planning

[1409] The server generates a flight path for the drone based on the predicted damage area and transmits this information to the drone, which uses a flight planning tool to create a precise flight path.

[1410] Unmanned aerial vehicle flight and damage monitoring

[1411] The drone begins flying according to the flight path received from the server. During flight, the drone uses its camera to capture images of the damage and transmits the data to the server in real time, allowing for a detailed understanding of the damage situation.

[1412] Evacuation guidance using unmanned aerial vehicles

[1413] When the drone reaches the predicted damage area, it will begin to provide voice guidance using its built-in speaker. For example, it will repeatedly announce messages such as, "Everyone in City A, please evacuate to higher ground immediately."

[1414] Real-time information transfer

[1415] The server transfers the video data received from the unmanned aerial vehicle to the terminals of government officials in real time, allowing them to immediately grasp the situation on the ground and respond promptly.

[1416] Specific examples

[1417] Case 1: Rising river water levels

[1418] The server receives data from the river sensor that the water level has exceeded three meters. This data indicates that the water level is beyond the danger zone, and the server switches to disaster response mode.

[1419] 1. The server uses weather map data and the latest water level data to predict the expected damage area, "Urban Area A," using a generative AI model.

[1420] 2. The server generates a flight path for the unmanned aircraft based on the prediction results and sends it to the unmanned aircraft.

[1421] 3. The unmanned aircraft automatically begins flying and reaches "Urban Area A." During the flight, it takes video and transmits it to the server in real time.

[1422] 4. Unmanned aerial vehicles will broadcast an audio message in areas expected to be affected, saying, "Please evacuate to higher ground immediately."

[1423] 5. The server receives the data sent from the unmanned aerial vehicle and transfers it to the terminals of government officials, allowing them to grasp the situation in real time and issue quick evacuation instructions to residents.

[1424] Prompt Sentence Examples

[1425] Sample prompt 1: "If the water level of a river suddenly rises, how would you predict the areas likely to be affected and guide people to evacuate?"

[1426] Example prompt 2: "Please tell me specifically what the flight route of the unmanned aerial vehicle will be and how to provide evacuation instructions in the event of a flood in City A."

[1427] In this way, the system of the present invention can quickly collect information, grasp the situation, and provide effective evacuation guidance in the event of a disaster.

[1428] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1429] Step 1: Collect water level data from sensors

[1430] The server periodically collects water level data from the sensor. The sensor measures the river's water level every minute and sends the data to the server via a wireless network. The input data is water level information from the sensor, which the server receives and records in a database. Specifically, the server receives data from the sensor, records it in a database, and maintains the latest water level status.

[1431] Input: Water level data from the sensor

[1432] Output: Recorded water level data

[1433] Step 2: Determine the danger zone

[1434] Based on the water level data collected by the server, it determines whether the latest water level has reached the set dangerous water level. The input data is water level information from the sensor, which the server analyzes and compares with the dangerous water level threshold. The output is the result of the determination of whether the dangerous water level has been reached. Specifically, the server analyzes the water level data, compares it with the threshold, and issues a system alert if the dangerous water level has been reached.

[1435] Input: Water level data from the sensor

[1436] Output: Dangerous waters determination result

[1437] Step 3: Prediction of potential damage areas

[1438] The server uses weather map data and past disaster data to utilize an AI model (e.g., the Gemini model) to predict areas of potential damage. The input data is the latest water level data and weather data, which are input into the AI ​​model. The output is the predicted areas of potential damage. Specifically, the server collects weather map data and past disaster data, inputs them into the AI ​​model, obtains the prediction results, and identifies the areas of potential damage.

[1439] Input: Water level data, weather data, past disaster data

[1440] Output: Estimated damage area

[1441] Step 4: Drone flight path generation

[1442] The server generates a flight path for the unmanned aerial vehicle based on the predicted expected damage area. The input data is the location information of the expected damage area, and the flight path is calculated based on this. The output is the generated flight path. Specifically, the server identifies important monitoring points from the prediction results, calculates and generates a flight path, and sends the generated flight path to the unmanned aerial vehicle.

[1443] Input: Location information of the expected damage area

[1444] Output: Flight path information

[1445] Step 5: Fly the drone and monitor the damage

[1446] The terminal (unmanned aerial vehicle) takes off according to the flight route received from the server and flies the specified route. The input data is flight route information, and the unmanned aerial vehicle collects data while flying according to this information. The output is the captured video data. Specifically, the unmanned aerial vehicle flies automatically, takes photos and videos of the location with a camera, and transfers the video data to the server in real time.

[1447] Input: Flight route information

[1448] Output: Recorded video data

[1449] Step 6: Drone evacuation guidance

[1450] When the terminal (unmanned aerial vehicle) reaches the predicted damage area, it uses a built-in speaker to provide voice guidance. The input data is a voice message sent from the server, which the unmanned aerial vehicle relays to residents. The output is a voice guidance message to residents. Specifically, the unmanned aerial vehicle repeatedly plays a designated message, calling on residents to evacuate.

[1451] Input: Voice message

[1452] Output: Voice guidance

[1453] Step 7: Real-time data transfer

[1454] The server transfers real-time images and video data sent from the unmanned aerial vehicle to the terminals of local government employees. The input data is the video data received from the unmanned aerial vehicle, which the server sends to the terminals of local government employees. The output is the data transferred to the terminals of local government employees. Specifically, the server processes the data received from the drone and transfers it to the terminals of local government employees in real time. The administrative staff can then check the data and take on-site action as necessary.

[1455] Input: Video data from an unmanned aerial vehicle

[1456] Output: Data transferred to the administrative staff's terminal

[1457] (Application example 1)

[1458] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1459] When river water levels reach dangerous levels, it is extremely important to quickly and accurately collect disaster information and provide evacuation instructions to residents. Conventional technologies can result in delays in information collection and evacuation instructions, potentially resulting in greater damage. Furthermore, there are limitations to predicting affected areas in real time and generating appropriate evacuation messages. The objective of this invention is to solve these shortcomings and provide an effective disaster response system.

[1460] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1461] In this invention, the server includes a means for predicting estimated damage areas using a generative AI model and generating appropriate evacuation guidance messages for residents, a means for an unmanned aerial vehicle to transfer image data of estimated damage areas to the server in real time and perform continuous predictions and responses using the generative AI model, and a means for a drone to fly and photograph the damage situation from the air and send the data to the server, thereby enabling rapid and accurate information collection and appropriate evacuation guidance.

[1462] A "sensor" is a device that measures the water level of a river in real time and transmits the data to a server.

[1463] The "server" is a central processing unit that receives data from sensors, processes the data, and predicts dangerous water levels and areas of potential damage.

[1464] "Weather map data" is data that shows meteorological information, and is used in particular to grasp meteorological conditions in real time and predict areas likely to be affected.

[1465] An "unmanned aerial vehicle" is an aircraft that is remotely controlled or flies autonomously to monitor disaster situations and collect and transmit data.

[1466] "Flight path" refers to the designated route taken by an unmanned aerial vehicle.

[1467] A "flight plan" refers to a specific plan for an unmanned aerial vehicle to fly automatically based on a flight path.

[1468] "Estimated damage area" refers to an area that the server predicts will be affected by a disaster using weather map data and water level data.

[1469] A "generative AI model" is a model that uses machine learning and artificial intelligence technology to analyze data and predict areas of potential damage.

[1470] "Evacuation instruction messages" refer to audio or text instructions to encourage residents in areas expected to be affected to take appropriate evacuation actions.

[1471] "Image data" refers to photographs and videos of disaster situations taken from the air by unmanned aerial vehicles.

[1472] "Local government employee terminals" refers to communication terminals such as computers and smartphones used by local government employees for disaster response purposes.

[1473] This invention provides a system that combines sensors that measure river water levels, a server that processes the information, and an unmanned aerial vehicle that monitors disaster situations and provides evacuation guidance. This system enables rapid information collection and evacuation guidance for residents in the event of a disaster.

[1474] The entire system is realized by the following hardware and software configuration.

[1475] Hardware Configuration

[1476] 1. Water level sensor: A device installed in a river to measure the water level in real time.

[1477] 2. Server: The central processing unit that receives data from sensors and performs analysis and predictions.

[1478] 3. Unmanned aerial vehicles: Aircraft that monitor disaster situations from the sky, collect data in real time, and provide evacuation instructions to residents.

[1479] 4. Local government employee devices: Communication devices such as computers and smartphones.

[1480] Software Configuration

[1481] 1. Data collection module: Software that collects water level data from sensors and sends it to the server.

[1482] 2. Data analysis module: Software that uses collected data to determine whether water levels have reached dangerous levels and uses a generative AI model to predict potential damage areas.

[1483] 3. Flight plan generation module: Software that generates flight paths for unmanned aerial vehicles based on the expected damage area and automatically creates flight plans.

[1484] 4. Real-time data transfer module: Software that transfers data sent from unmanned aerial vehicles to local government employee terminals in real time.

[1485] 5. Voice guidance module: Software that uses the prediction results to enable unmanned aerial vehicles to provide voice guidance on evacuation in areas expected to be affected.

[1486] Data processing and calculation flow

[1487] The server first collects water level data periodically sent from the sensors. This data is sent to the server in real time and used to determine whether the water level has reached a dangerous level. If the determination is that the water level is dangerous, the server uses weather map data and past disaster data to predict the likely damage area using a generative AI model (e.g., machine learning or artificial intelligence technology).

[1488] Example prompts for generative AI models

[1489] Based on these prompts, the server predicts the expected damage area and generates a flight plan accordingly. The unmanned aerial vehicle then flies along a flight path generated based on the prediction results, photographing the damage situation from the air in real time and sending the data to the server. This data is then received by the devices of local government employees, enabling them to immediately grasp the situation on site and take prompt action.

[1490] Examples of prompt statements

[1491] "Please predict the area of ​​potential damage if the river water level exceeds 3 meters."

[1492] In this way, the entire system will work together to enable rapid and accurate information gathering and appropriate responses in the event of a disaster.

[1493] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1494] Step 1:

[1495] Water level data collection

[1496] The server periodically collects water level data from sensors installed in the river. The input data is the water level measurement data sent from the sensor, and the output data is the water level data stored in the server's internal database. Specifically, the server retrieves data from the sensor using an HTTP request.

[1497] Step 2:

[1498] Determining dangerous waters

[1499] The server determines whether the water level has reached a dangerous level based on the received water level data. The input data is the collected water level data, and the output data is a flag indicating whether the water level has reached a dangerous level. Specifically, the server compares the water level data with the set dangerous water level threshold and sets a flag if the threshold is exceeded.

[1500] Step 3:

[1501] Prediction of expected damage areas

[1502] When a dangerous water area flag is raised, the server uses weather map data and past disaster data to use a generative AI model to predict the area of ​​expected damage. The input data is water level data, weather map data, and past disaster data, and the output data is information on the area of ​​expected damage. In concrete terms, the server gives the generative AI model specific instructions, such as a prompt statement and argument data, such as "area of ​​expected damage if the river water level exceeds 3 meters," and receives the prediction results from the model.

[1503] Step 4:

[1504] Flight plan generation

[1505] The server generates a flight path for the unmanned aerial vehicle based on the predicted damage area and automatically creates a flight plan. The input data is information about the damage area, and the output data is specific flight path information. Specifically, the server calculates the optimal flight path based on GPS data and transmits it to the unmanned aerial vehicle.

[1506] Step 5:

[1507] Unmanned aerial vehicle flight and data collection

[1508] The unmanned aerial vehicle begins flying according to the flight path received from the server. During flight, the unmanned aerial vehicle photographs the damage situation from the sky and transmits the data to the server in real time. The input data is flight path information, and the output data is the photographed image data. Specifically, the unmanned aerial vehicle uses a camera to capture images from the sky and transfers them to the server via wireless communication.

[1509] Step 6:

[1510] Generation and execution of evacuation guidance messages

[1511] Based on the prediction results, the server generates a message calling for evacuation for residents in the predicted damage area and transmits it as audio guidance to the unmanned aerial vehicle. The input data is the predicted damage area and the message information generated by the generation AI model, and the output data is the audio guidance message. Specifically, the server uses the generation AI model to create an evacuation message and plays it through the speaker on the unmanned aerial vehicle.

[1512] Step 7:

[1513] Real-time information transfer

[1514] The server transfers the image and video data received from the unmanned aerial vehicle to the local government employee's device in real time. The input data is image data from the unmanned aerial vehicle, and the output data is real-time video to the local government employee's device. Specifically, the server immediately packets the received data and sends a push notification to each local government employee's device.

[1515] This series of processes enables the system to quickly and accurately collect information and provide appropriate evacuation instructions.

[1516] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1517] This invention is a system that combines sensors that measure river water levels, a server that processes information, drones that monitor disaster situations and provide evacuation guidance, and an emotion engine that recognizes the user's emotions. The system aims to quickly collect information during disasters, provide evacuation guidance to residents, and provide emotional support to local government officials.

[1518] Program processing flow

[1519] The processing of the system program will be explained in natural language below.

[1520] Water level monitoring with sensors

[1521] 1. The server periodically collects water level data from water level sensors installed in the river. The sensors measure the river's water level in real time and send the data to the server.

[1522] Determining dangerous waters

[1523] 2. The server determines whether the water level has reached the danger zone based on the received data. If the water level has reached the danger zone, the system proceeds to the next step.

[1524] Prediction of expected damage areas

[1525] 3. The server uses weather map data and past disaster data to predict areas expected to be affected using an AI model (e.g., the Gemini model). This prediction makes it possible to determine which areas will be affected and to what extent.

[1526] Flight planning

[1527] 4. The server generates a flight path for the drone based on the predicted damage area. The generated flight path is sent to the drone and executed automatically.

[1528] Drone flight and evacuation guidance

[1529] 5. The device (drone) begins flying according to the flight path received from the server. During flight, the drone photographs the damage from above and sends the data to the server in real time. The photographed data can be used to grasp the detailed damage situation.

[1530] 6. When the device (drone) reaches the predicted damage area, it begins to provide voice guidance using its built-in speaker. It repeatedly plays messages such as, "Everyone in City A, please evacuate to higher ground immediately."

[1531] Real-time information transfer

[1532] 7. The server transfers the images and video data received from the drone to the local government employee's device in real time, allowing the user (local government employee) to immediately check the situation on site and respond promptly.

[1533] Use of emotion engine

[1534] 8. The server uses an emotion engine to monitor the stress levels and emotional state of local government employees. If stress levels are found to be elevated, relaxation and support messages are automatically sent.

[1535] 9. The device (drone) will recognize the emotions of residents in the predicted affected area and play appropriate voice guidance depending on their emotional state. For example, if anxiety is rising, it will play a message such as "Please remain calm and follow evacuation instructions."

[1536] Specific examples

[1537] Case 1: Rising river water levels

[1538] 1. The server receives water level data from a river sensor and detects that the water level has exceeded 3 meters. This data indicates that the water level is beyond the danger zone, and the server switches to disaster response mode.

[1539] 2. The server uses weather map data and the latest water level data to predict the expected damage area, "Urban Area A," using an AI model.

[1540] 3. The server generates a flight path for the drone based on the prediction results and sends it to the drone.

[1541] 4. The device (drone) automatically begins flying and reaches city A. During the flight, it takes video and transmits it to the server in real time.

[1542] 5. The drone will broadcast an audio message in the affected area saying, "Please evacuate to higher ground immediately." If residents feel anxious, the emotion recognition system will detect this and switch to a more reassuring message.

[1543] 6. The server receives data from the drone and transfers it to the local government employee's device, allowing the user (local government employee) to grasp the situation in real time and quickly issue evacuation instructions to residents.

[1544] Case 2: Stress management for local government employees

[1545] 1. An emotion engine installed on the server monitors the stress levels of local government employees.

[1546] 2. If the stress level of staff increases during disaster response, the server automatically sends a relaxation message to the staff's device.

[1547] 3. Users (municipal government officials) can reduce stress and continue to respond calmly.

[1548] In this way, the system of the present invention can respond to disasters more effectively by quickly gathering information and providing evacuation instructions during disasters, as well as providing emotional support to local government officials.

[1549] The processing flow will be explained below.

[1550] Step 1:

[1551] The server periodically collects water level data from water level sensors installed in the river. The sensors measure the water level in real time and send the data to the server.

[1552] Step 2:

[1553] The server stores the received water level data in a database, which is used for subsequent analysis.

[1554] Step 3:

[1555] The server periodically retrieves the latest water level data from the database and determines whether the water level has reached a dangerous level. If the water level reaches the set dangerous level, an alert is triggered.

[1556] Step 4:

[1557] The server receives weather chart data and past disaster data, which are then processed and used to predict potential damage areas in the event of a dangerous water zone.

[1558] Step 5:

[1559] The server uses AI models to analyze weather map data and water level data to predict potential damage areas, which can then identify which areas will be affected.

[1560] Step 6:

[1561] The server generates a flight path for the drone based on the predicted damage area, and transmits the generated flight plan information to the drone.

[1562] Step 7:

[1563] The terminal (drone) begins flying based on the flight path information received from the server. The drone uses sensors such as GPS to confirm its position and flies the planned path accurately.

[1564] Step 8:

[1565] The terminal (drone) arrives at the predicted damage area and takes pictures of the situation from above. The captured images and video data are sent to the server in real time.

[1566] Step 9:

[1567] The device (drone) plays a pre-recorded evacuation guidance message to residents in the predicted affected area, saying, "Everyone in City A, please evacuate to higher ground immediately."

[1568] Step 10:

[1569] The server receives real-time image and video data sent from the drone and transfers it to the terminals of local government employees in real time.

[1570] Step 11:

[1571] The server uses an emotion engine to monitor the stress levels and emotional state of local government employees, and if stress is judged to be increasing, it automatically sends relaxation and support messages.

[1572] Step 12:

[1573] The device (drone) recognizes the emotions of residents in the predicted affected area and plays appropriate voice guidance according to their emotional state. For example, if anxiety is rising, it will play a message such as "Please remain calm and follow evacuation instructions."

[1574] Step 13:

[1575] The user (municipal government employee) checks the received real-time data on the device. The user can immediately grasp the situation on the ground and take the necessary measures. In addition, the user can maintain a calm mind by receiving relaxation messages from the emotion engine.

[1576] Through this series of steps, the system of the present invention can effectively gather information quickly, provide appropriate evacuation instructions, and provide emotional support to local government officials in the event of a disaster.

[1577] Example 2

[1578] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1579] During natural disasters, the challenges are to quickly and accurately gather information, provide evacuation instructions to residents, and comprehensively manage the stress of local government employees. In particular, there is a need for a system that can simultaneously grasp on-site information in real time during a disaster and manage the emotions of residents and local government employees.

[1580] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1581] In this invention, the server includes means for receiving data from a sensor measuring the river water level and determining whether the water level has reached a dangerous level, means for predicting potential damage areas using weather map data and water level data, and means for generating a flight path for the flying machine based on the predicted potential damage areas and automatically creating a flight plan, which enables the rapid collection of disaster information, accurate evacuation guidance, and stress management for local government officials.

[1582] A "sensor for measuring river water levels" is a device that measures river water levels in real time and sends the data to a server.

[1583] A "server" is a central processing unit that receives data from sensors, analyzes it, and executes various processes.

[1584] "Weather map data" is a data set containing meteorological information and is used to predict weather fluctuations.

[1585] "Water level data" is a data set that shows the current water level and its fluctuations in a river.

[1586] A "potential damage area" is a specific geographical area that is expected to be affected in the event of a disaster.

[1587] A "flying machine" is a device that can fly autonomously and gather information from the air, generally referring to drones or unmanned aerial vehicles (UAVs).

[1588] "Flight path" means the planned route to be followed by a flying vehicle.

[1589] "Voice evacuation guidance" is a method in which flying machines use voice messages to encourage residents to evacuate.

[1590] An "administrator's terminal" is a computer or mobile device used by an administrator, such as a local government employee.

[1591] The "Emotion Engine" is a system that analyzes an individual's emotional state and monitors stress levels and emotional responses.

[1592] "Stress level" is a measure of the degree of psychological pressure or burden felt by an individual.

[1593] "Emotional state" refers to an individual's current emotional or mood state.

[1594] This invention is a system that uses river water level measurement sensors, a server that processes the data, a flying machine that monitors disaster situations and guides evacuation, and an emotion engine that recognizes the emotions of administrators. The system aims to quickly collect information in the event of a disaster, provide evacuation instructions to residents, and provide emotional support to local government officials.

[1595] First, the main components of the system will be described.

[1596] A river water level measurement sensor is a device that is installed in a specific area of ​​a river and measures water level data in real time. For example, a general water level measurement device is used.

[1597] The server is a device that periodically collects data from the sensors and analyzes it. It is equipped with an analytical algorithm that determines whether the water level has reached a preset danger level. The server also uses weather chart data and past disaster data to predict potential damage areas using an AI model (such as the Gemini model).

[1598] The flying machine (drone) is a device for monitoring the situation in the predicted damage area from the sky, and automatically generates a flight path and flies based on instructions from the server. During the flight, it takes images from the sky and sends the data to the server in real time. It also provides evacuation guidance through audio guidance.

[1599] The administrator's terminal is a device that receives data from the server and checks the situation on site in real time, and has emergency response apps and dedicated software installed.

[1600] The emotion engine is a system that monitors the stress level and emotional state of the administrator and sends relaxation messages as needed.

[1601] Specific examples are shown below.

[1602] Case 1: Rising river water levels

[1603] 1. The server receives water level data from a river sensor and detects that the water level has exceeded 3 meters. This data indicates that the water level has exceeded the danger level, and the server switches to disaster response mode.

[1604] 2. The server uses weather map data and the latest water level data to predict the expected damage area, "Urban Area A," using an AI model.

[1605] 3. The server generates a flight path for the flying machine based on the prediction results and sends it to the flying machine.

[1606] 4. The terminal (flying machine) automatically begins flying and reaches city A. During the flight, it takes video and transmits it to the server in real time.

[1607] 5. Flying machines will broadcast an audio message in the affected area saying, "Please evacuate to higher ground immediately." If residents feel anxious, an emotion recognition system will detect this and switch to a more reassuring message.

[1608] 6. The server receives data from the flying machine and transfers it to the administrator's terminal, allowing the user (administrator) to grasp the situation in real time and quickly issue evacuation instructions to residents.

[1609] Case 2: Stress management for local government employees

[1610] 1. An emotion engine installed on the server monitors the stress levels of local government employees.

[1611] 2. If the stress level of staff increases during disaster response, the server automatically sends a relaxation message to the staff's device.

[1612] 3. Users (staff) can reduce stress and continue to respond calmly.

[1613] To achieve this, the system uses prompt statements such as:

[1614] "Generate an appropriate evacuation guidance message when the river water level reaches 3 meters."

[1615] "Please provide an example of a relaxation message for local government employees when their stress levels increase."

[1616] "Please tell us how you specifically use AI models to predict potential damage areas."

[1617] As described above, the present invention enables the rapid collection of disaster information, accurate evacuation guidance, and emotional support for local government officials, thereby improving disaster response capabilities.

[1618] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1619] Step 1:

[1620] The server collects data from river water level sensors. The input is water level data from the sensors, and the output is water level data stored in a database on the server.

[1621] The server sends an HTTP request to the sensor via the network to retrieve the data. The retrieved data includes a timestamp and geolocation information. For example, "Sensor ID: 001, Water level: 3.2 meters, Timestamp: 2023-10-04T14:00:00Z".

[1622] Step 2:

[1623] The server analyzes the water level data and determines whether the water level has reached the set danger level. The input is the collected water level data, and the output is the setting of the danger state flag.

[1624] The server uses a condition determination algorithm to set a danger flag if the water level exceeds a threshold (e.g., 3 meters). For example, "Current water level: 3.2 meters, Set threshold: 3.0 meters, Danger state: Active."

[1625] Step 3:

[1626] The server inputs weather map data, past disaster data, and the latest water level data into the AI ​​model to predict the likely damage area. The inputs are weather map data, past disaster data, and water level data, and the output is the likely damage area and its impact.

[1627] The server uses Google Cloud Platform's AI services and its own Gemini model to output the prediction results as potentially affected areas and the level of damage (e.g., "Urban Area A: High, Rural Area B: Medium").

[1628] Step 4:

[1629] The server generates a flight path for the flying machine based on the predicted damage area. The input is the predicted damage area and its impact, and the output is flight path data in JSON format.

[1630] The server calculates the optimal flight route and sends the data to the flying machine. For example, "Flight route: Start point (latitude: 35.6895, longitude: 139.6917) → City A (latitude: 35.6895, longitude: 139.7000) → End point (latitude: 35.7000, longitude: 139.7100)".

[1631] Step 5:

[1632] The terminal (flying machine) starts automatic flight according to the flight path received from the server. The input is the flight path data sent from the server, and the output is the captured video data.

[1633] The flying machine flies autonomously along a designated route using GPS, capturing video of the situation from above. The captured video data is then sent to a server in real time. For example, the video may be "video of the flooding situation in City A."

[1634] Step 6:

[1635] When the terminal (flying machine) reaches the predicted damage area, it starts to give voice guidance through the built-in speaker. The input is the evacuation guidance message sent from the server, and the output is the broadcast voice message.

[1636] The flying machine constantly broadcasts messages calling for evacuation. For example, it might say, "Everyone in City A, please evacuate to higher ground immediately." If residents feel anxious, it uses an emotion recognition system to change the message to, "Please remain calm and follow evacuation instructions."

[1637] Step 7:

[1638] The server transfers the image and video data received from the flying machine to the administrator's terminal in real time. The input is the video data from the flying machine, and the output is the real-time video displayed on the administrator's terminal.

[1639] The server transfers data through a dedicated app or web interface, such as "Video showing widespread flooding in City A."

[1640] Step 8:

[1641] The server monitors the stress level and emotional state of the administrator using an emotion engine, where the input is biometric data from the administrator and the output is an assessment of the administrator's emotional state and stress level.

[1642] The emotion engine analyzes biosensor and input data and automatically sends relaxation messages when stress levels rise. For example, "Employee 1's stress level: High, Relaxation Message: 'Take a deep breath and relax.'"

[1643] Step 9:

[1644] The terminal (flying machine) recognizes the emotions of residents in the predicted damage area and provides appropriate voice guidance according to their emotional state. The input is the residents' emotional data collected during flight, and the output is a voice message according to their emotional state.

[1645] The flying machine uses AI to analyze voices and play reassuring messages if anxiety levels are high. For example, "Residents' emotional state: anxiety, guidance message: 'Please remain calm and follow evacuation instructions.'"

[1646] (Application example 2)

[1647] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1648] Conventional river monitoring systems have had issues with rapid response and evacuation guidance in the event of a disaster. Logistics centers also need to streamline inventory management and transportation operations, as well as manage employee stress. The purpose of this invention is to provide a system that can solve these issues and respond efficiently and quickly.

[1649] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1650] In this invention, the server includes: means for receiving data from a sensor measuring the river water level and determining whether the water level has reached a dangerous level; means for predicting an estimated damage area using weather map data and water level data; means for generating a flight path for an unmanned aerial vehicle based on the predicted estimated damage area and automatically creating a flight plan; means for the unmanned aerial vehicle to fly, photograph the damage situation from the air, and transmit the photographed data; means for the unmanned aerial vehicle to provide evacuation guidance via voice in the estimated damage area; means for periodically collecting data from an inventory sensor and determining whether inventory has fallen below a threshold; means for predicting product delivery timing using past data and a generative AI model; means for generating a movement route for an automated transport robot based on the predicted delivery timing and automatically creating a plan; means for the automated transport robot to transport products along the movement route and transmit the data; means for transferring the received data to an employee terminal at a logistics center in real time; and means for monitoring the stress levels of logistics center employees using an emotion engine and sending relaxation messages as necessary. This enables rapid information collection and evacuation guidance during a disaster, efficient inventory management and product delivery, and employee stress management.

[1651] A "sensor for measuring river water levels" is a device that measures river water levels in real time and sends the data to a server.

[1652] A "server" is a central control device that receives data from sensors and processes and analyzes it.

[1653] "Weather map data" refers to data that includes meteorological information and is used for disaster prediction.

[1654] "Expected damage area" refers to an area that is predicted to be affected if a disaster occurs.

[1655] An "unmanned aerial vehicle" is an aircraft that flies under remote control or automatic control.

[1656] A "flight path" is the route that an unmanned aerial vehicle follows as it flies.

[1657] "Periodic" means repeated at regular intervals.

[1658] An "inventory sensor" is a device that measures product inventory in a warehouse.

[1659] A "generative AI model" is a mathematical model used to analyze and predict data generated by artificial intelligence.

[1660] An "automatic transport robot" is a robot that automatically transports goods within a logistics center.

[1661] A "distribution center staff terminal" is a terminal used by staff at a distribution center to display and operate data.

[1662] The "emotion engine" is a system that analyzes the user's emotional state and responds based on the results.

[1663] A "relaxation message" is a message intended to relieve the user's stress.

[1664] This invention is a system that combines sensors that measure river water levels, a server that processes information, an unmanned aerial vehicle that monitors the damage situation and provides evacuation guidance, sensors that monitor inventory, an automatic transport robot, staff terminals at a logistics center, and an emotion engine that recognizes user emotions.

[1665] First, sensors are installed to measure river water levels, collecting real-time data and sending it to a server. The server then analyzes the received data and determines whether the water level has reached a dangerous level. Using weather map data and water level data, a generative AI model is used to predict potential damage areas.

[1666] Once the estimated damage area is predicted, the server generates a flight path for the unmanned aircraft and automatically creates a flight plan. The unmanned aircraft flies to the predicted area and takes photographs of the damage from above. The data is sent to the server and then transferred in real time to the devices of local government employees. The unmanned aircraft also provides audio evacuation guidance in the estimated damage area, urging residents to evacuate quickly.

[1667] Meanwhile, sensors are also installed to measure inventory at the logistics center, and these periodically send inventory data to a server. The server analyzes the received inventory data, and if inventory falls below a threshold, it uses past data and a generative AI model to predict when to bring in the goods. Based on this prediction, it generates an operating route for the automated transport robot and issues instructions to the robot. The automated transport robot transports the goods along the operating route and sends the data to the server. The transport data is also transferred in real time to staff terminals at the logistics center.

[1668] In addition, the emotion engine installed on the server monitors the stress levels of logistics center staff and sends relaxation messages to staff devices as needed.

[1669] As a concrete example, consider the following case:

[1670] Case 1: Rising river water levels

[1671] 1. The server receives water level data from a river sensor and detects that the water level has exceeded 3 meters. This data indicates that the water level is beyond the danger zone, and the server switches to disaster response mode.

[1672] 2. The server uses weather map data and the latest water level data to predict the expected damage area, "Urban Area A," using a generative AI model.

[1673] 3. The server generates a flight path for the unmanned aircraft based on the prediction results and sends it to the unmanned aircraft.

[1674] 4. The unmanned aerial vehicle automatically begins flying and reaches urban area A. During the flight, it takes video and transmits it to the server in real time.

[1675] 5. Unmanned aerial vehicles will broadcast an audio message in areas expected to be affected, saying, "Please evacuate to higher ground immediately." If residents feel anxious, an emotion recognition system will detect this and switch to a more reassuring message.

[1676] 6. The server receives data from the unmanned aerial vehicle and transfers it to the devices of local government officials, allowing them to grasp the situation in real time and quickly issue evacuation instructions to residents.

[1677] Case 2: Inventory management at a logistics center

[1678] 1. The server detects from the inventory sensor that the inventory of "Product A" has fallen below a threshold.

[1679] 2. The server uses past data and the generative AI model to predict the appropriate delivery timing for product A.

[1680] 3. The server generates the movement route of the automated transport robot based on the prediction results and gives instructions.

[1681] 4. The automated transport robot transports the product along the specified route and sends the data acquired during the process to the server.

[1682] 5. The server transfers the transport data from the robot to the staff terminal at the logistics center in real time.

[1683] Prompt Sentence Examples

[1684] text

[1685] Inventory data: Product A has fallen below the threshold of 50.

[1686] Emotional Data: Employee A's stress level is 0.8.

[1687] Instructions: Please reorder immediately and instruct Employee A to take a break.

[1688] In this way, the system of the present invention realizes rapid information gathering and evacuation guidance in the event of a disaster, efficient inventory management and transportation operations at logistics centers, and stress management for employees.

[1689] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1690] Step 1:

[1691] The server receives real-time data from sensors measuring river water levels. This data includes current water level information. Based on this, the server analyzes water level trends and determines in real time whether the water level is reaching a dangerous level.

[1692] Input: River water level data

[1693] Output: Dangerous water level determination result

[1694] Specific behavior:

[1695] The server analyzes the water level data obtained from the sensor.

[1696] The result is compared with a preset threshold value for dangerous waters and a judgment result is generated.

[1697] Step 2:

[1698] If the server determines that the water level has reached a dangerous level, it uses weather map data and the aforementioned water level data to predict areas where damage is likely to occur. Utilizing a generative AI model, it estimates damage for each area based on past data.

[1699] Input: Dangerous water level determination results, weather chart data, water level data

[1700] Output: Estimated damage area forecast

[1701] Specific behavior:

[1702] Weather map data and water level data are imported into the server and input into the generative AI model.

[1703] An AI model analyzes the data and identifies areas likely to be affected.

[1704] Step 3:

[1705] The server generates a flight path for the drone based on the predicted damage area, including the shortest route and a preferred route to the most severely damaged area.

[1706] Input: Estimated damage area forecast

[1707] Output: Flight path of the unmanned aerial vehicle

[1708] Specific behavior:

[1709] The server analyzes the results of the generated AI model and generates an efficient flight path.

[1710] Transmitting flight path data to the unmanned aerial vehicle.

[1711] Step 4:

[1712] The unmanned aerial vehicle will then begin flying according to the received flight path, taking photos of the damage from above and sending the data to a server in real time.

[1713] Input: Unmanned Aerial Vehicle Flight Path

[1714] Output: Photographic data of the damage situation

[1715] Specific behavior:

[1716] The unmanned aerial vehicle follows a designated flight path.

[1717] Images and video data taken from the sky are sent to a server.

[1718] Step 5:

[1719] The server analyzes the image data received from the unmanned aerial vehicle and transfers it in real time to the devices of local government employees, who use the data to quickly grasp the extent of damage at the scene.

[1720] Input: Photographic data of the damage situation

[1721] Output: Real-time data to local government employee terminals

[1722] Specific behavior:

[1723] The server analyzes the data from the unmanned aerial vehicle and extracts the necessary information.

[1724] Data is transferred to local government employee terminals in real time.

[1725] Step 6:

[1726] The server instructs unmanned aerial vehicles in areas expected to be affected to provide voice evacuation guidance, enabling residents to evacuate quickly and smoothly.

[1727] Input: Estimated damage area forecast

[1728] Output: Evacuation guidance voice message

[1729] Specific behavior:

[1730] The server transmits the contents of the voice message to the unmanned aerial vehicle.

[1731] Unmanned aerial vehicles will provide voice evacuation instructions in designated areas.

[1732] Step 7:

[1733] The server periodically receives data from inventory sensors installed in the distribution center and monitors inventory levels. If the inventory level falls below a threshold, it predicts when to bring in products and generates a route for the automated transport robot.

[1734] Input: Inventory data

[1735] Output: Delivery timing prediction, transportation route

[1736] Specific behavior:

[1737] The server analyzes inventory data obtained from sensors and inputs it into a generative AI model.

[1738] Predict the timing of product delivery and generate appropriate delivery routes.

[1739] Step 8:

[1740] The automated transport robot delivers products to the designated location according to the route received from the server, and data on the delivery process is also sent to the server in real time.

[1741] Input: Delivery Route

[1742] Output: Transport data

[1743] Specific behavior:

[1744] The automated transport robot transports the goods along the instructed route.

[1745] Data acquired during transportation is sent to the server.

[1746] Step 9:

[1747] The server uses an emotion engine to monitor the stress levels of logistics center staff and sends relaxation messages if it detects high levels of stress.

[1748] Input: Employee emotion data

[1749] Output: Relaxation message

[1750] Specific behavior:

[1751] The server analyzes the stress levels of employees using an emotion engine.

[1752] If necessary, send relaxation messages to staff terminals.

[1753] In this way, each step works in tandem to seamlessly realize disaster response, inventory management, transportation efficiency, and staff stress management.

[1754] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1755] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1756] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1757] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1758] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1759] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1760] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1761] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1762] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1763] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1764] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1765] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1766] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1767] 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.

[1768] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1769] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1770] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1771] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1772] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1773] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1774] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1775] The following is further disclosed regarding the above embodiment.

[1776] (Claim 1)

[1777] A sensor that measures the water level of the river,

[1778] a server that receives data from the sensor and determines whether the water level has reached a dangerous level;

[1779] a means for the server to predict an area expected to be damaged by using weather chart data and water level data;

[1780] A means for the server to generate a flight path for the drone based on the predicted estimated damage area and automatically create a flight plan;

[1781] A means for the drone to fly, photograph the damage situation from above, and transmit the data to the server;

[1782] A means for the drone to provide evacuation guidance by voice in an area where damage is expected;

[1783] means for transferring the data received by the server to the terminal of a local government employee in real time;

[1784] A system including:

[1785] (Claim 2)

[1786] The system according to claim 1, wherein the center includes means for monitoring the water level of the river in real time and periodically transmitting the data to the server.

[1787] (Claim 3)

[1788] The system of claim 1, further comprising a means for the server to generate a message based on the prediction results, urging residents in the predicted damage area to evacuate, and to transmit the message as an audio guide to the drone.

[1789] "Example 1"

[1790] (Claim 1)

[1791] A sensor that measures the water level of the river,

[1792] a server that receives data from the sensor and determines whether the water level has reached a dangerous level;

[1793] A means for the server to predict an area expected to be affected by damage using meteorological data and water level data;

[1794] A means for the server to generate a flight path for the unmanned aerial vehicle based on the predicted damage ar...

Claims

1. A sensor that measures the water level of the river, a server that receives data from the sensor and determines whether the water level has reached a dangerous level; a means for the server to predict an area expected to be damaged by using weather chart data and water level data; A means for the server to generate a flight path for the drone based on the predicted estimated damage area and automatically create a flight plan; A means for the drone to fly, photograph the damage situation from above, and transmit the data to the server; A means for the drone to provide evacuation guidance by voice in an area where damage is expected; means for transferring the data received by the server to the terminal of a local government employee in real time; A system including:

2. The system according to claim 1, wherein the center includes means for monitoring the water level of the river in real time and periodically transmitting the data to the server.

3. The system according to claim 1, further comprising a means for generating a message urging residents in the predicted damage area to evacuate based on the prediction results and transmitting the message as an audio guide to the drone.

Images