system

Abstract

We provide the system. [Solution] A means for analyzing video information received from a video acquisition device and generating disaster progression identification information, A means for analyzing pedestrian flow information acquired from a location data acquisition device and generating information for optimizing evacuation routes, A means for generating safe evacuation route information based on disaster progression identification information and evacuation route optimization information, A means for distributing the aforementioned safe evacuation route information to a communication terminal device, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In recent years, with the frequent occurrence of natural disasters, the speed and safety of evacuation during disasters have been emphasized. However, it has been difficult to grasp the progress of disasters and the movements of evacuees in real time and provide an optimal evacuation route. In addition, conventional evacuation route guidance systems are based on fixed information and cannot respond immediately to changes in the situation, so there is a problem that evacuees may be in danger.

Means for Solving the Problems

[0005] To solve the above problems, the present invention provides a means for analyzing video information received from a video acquisition device to identify the progression of a disaster, and a means for analyzing human flow information obtained from a location data acquisition device to optimize evacuation routes. Furthermore, based on these analysis results, the invention provides a system that generates safe evacuation route information and distributes it to a communication terminal device in real time, thereby enabling the provision of safe and rapid evacuation routes to evacuees at all times.

[0006] A "video acquisition device" is a device that collects video data in real time from a disaster site and transmits it to an external system.

[0007] "Disaster Progress Identification Information" is information that indicates the current state and direction of a disaster by analyzing collected video data.

[0008] A "location data acquisition device" is a device that can collect location information of people within a specific area in real time.

[0009] "Human flow information" refers to information that shows the movement and gathering of people in a specific geographical area.

[0010] "Evacuation route optimization information" is data used to determine the optimal evacuation route based on human flow information and the progress of the disaster.

[0011] "Safe evacuation route information" refers to information about recommended routes for evacuees to evacuate safely in the event of a disaster.

[0012] A "communication terminal device" is a device that receives information transmitted from an external system and presents it to the user. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2]It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined. **MODE FOR CARRYING OUT THE INVENTION**

[0014] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0016] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

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

[0018] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

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

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

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

[0023] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0030] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] This invention provides a system to support safe and rapid evacuation during disasters. The following describes the configuration of the system for implementing this invention and details of its operation.

[0035] The server centrally receives video data from numerous street cameras and drones. This received video data is processed using an AI analysis module to identify the progression of a disaster in real time. For example, in the case of a flood, it can determine the rate at which the water level rises and the extent of the flooding.

[0036] Furthermore, the server also receives pedestrian flow information from location data acquisition devices. This allows for the analysis of people's movements and gatherings via cell phone base stations, GPS devices, and other means. This data is a crucial element in optimizing evacuation routes.

[0037] Based on analyzed disaster progression and human flow information, the server generates the optimal evacuation route. This route is dynamically updated to select the safest and least congested path. For example, if roads are flooded due to heavy rain, the server can suggest an alternative route based on that information.

[0038] The generated evacuation route information is transmitted to a communication terminal device. Based on this received information, the terminal provides the user with visual and audio route guidance. The terminal also obtains the user's current location and provides real-time navigation assistance to guide the user to a safe evacuation.

[0039] Users will use the information presented on the device to carry out a safe evacuation. Especially in situations with multiple evacuation centers, they are required to act according to the instructions provided by the device to avoid congestion. Once the evacuation is complete, the device sends feedback to the server regarding the user's evacuation route and situation. This feedback is used to improve the accuracy of the system.

[0040] Thus, the present invention embodies a system that utilizes video analysis and human flow data to provide the optimal evacuation route in real time and quickly notifies users of this information, in order to support safe evacuation during disasters.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The server receives video data from street cameras and drones. This video data shows the real-time situation at disaster sites.

[0044] Step 2:

[0045] The server analyzes the received video data using an AI analysis module. Through this analysis, it identifies how disasters such as floods and fires are progressing and generates disaster progression identification information.

[0046] Step 3:

[0047] The server collects information on people's movements from location data acquisition devices. This data is analyzed as human flow information to understand areas where evacuees are concentrated and to grasp the flow of evacuation.

[0048] Step 4:

[0049] The server integrates and analyzes disaster progression information and human flow information to calculate the optimal evacuation route. In this process, it designs routes that avoid areas where the disaster is progressing rapidly and congested evacuation routes.

[0050] Step 5:

[0051] The server transmits the generated safe evacuation route information to the communication terminal device. The information includes text, maps, and audio guidance.

[0052] Step 6:

[0053] The terminal analyzes evacuation route information received from the server and provides visual and audio guidance to the user. It also provides real-time navigation based on the user's current location.

[0054] Step 7:

[0055] Users follow the instructions on their devices and move along the designated evacuation routes. If the situation changes based on information obtained along the way, they will be offered a safer alternative route.

[0056] Step 8:

[0057] The terminal sends path information and feedback acquired by the user during evacuation to the server. This information will be used to improve the accuracy of future evacuation route generation.

[0058] (Example 1)

[0059] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0060] To ensure rapid and safe evacuation during disasters, it is necessary to provide appropriate evacuation routes in real time, adapting to changing circumstances. However, conventional evacuation support systems have difficulty accurately grasping the progression of disasters and the movement of people, and dynamically optimizing routes. Furthermore, system improvements based on user feedback have been limited. A new solution to this problem is needed.

[0061] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0062] In this invention, the server includes means for analyzing video information received from a video acquisition device and generating disaster progression identification information, means for analyzing movement pattern information acquired from a location data acquisition device and generating evacuation route optimization information, and means for dynamically generating safe evacuation route information based on the disaster progression identification information and the evacuation route optimization information. This makes it possible to grasp the progress of the disaster and the movement of people in real time and provide safe and efficient evacuation routes.

[0063] A "video acquisition device" is a device that has the function of acquiring real-time video data at disaster sites and transmitting it to a server.

[0064] "Disaster Progress Identification Information" refers to information that shows data regarding the progress and degree of danger of a disaster, analyzed from acquired video information.

[0065] A "location data acquisition device" is a device that has the function of collecting people's location information and movement patterns and providing them to a server.

[0066] "Movement pattern information" refers to data that shows people's movement routes and the movements of groups, and is used to optimize evacuation routes.

[0067] "Evacuation route optimization information" is information that is analyzed based on collected movement pattern data to derive the optimal evacuation route.

[0068] "Safe evacuation route information" refers to information that shows optimized routes to avoid obstacles and dangerous areas and to move away from disasters.

[0069] A "generative AI model" is a machine learning technique that extracts useful features from data to support the optimization of disaster progression and evacuation routes.

[0070] This invention is a system for supporting safe and rapid evacuation during disasters. This system operates through the cooperation of a server, terminals, and users.

[0071] The server first receives real-time video data from video acquisition devices such as street cameras and drones. This video data is analyzed using an AI analysis module to identify the progression of the disaster. Machine learning libraries such as TENSORFLOW® and PyTorch can be used for this AI analysis. The server also collects location data from cell phone base stations and GPS devices and generates pedestrian flow information by analyzing people's movement patterns. This data is crucial for deriving optimal evacuation routes.

[0072] The server dynamically generates the optimal evacuation route based on the generated disaster progression information and human flow information. This route generation process can utilize real-time map data and traffic information. It uses map services such as Google® Maps API to adjust the route to avoid obstacles and hazardous areas.

[0073] The terminal receives evacuation route information transmitted from the server. Using this information, the terminal provides visual and audio route guidance to the user. It utilizes GPS functionality to track the user's current location in real time and displays the route on the screen. Furthermore, it uses an audio guidance function to appropriately guide the user.

[0074] Users evacuate safely based on information provided by their devices. After the evacuation is complete, the devices send user feedback to the server, which is used to improve the system. This feedback includes user opinions on evacuation routes and changes in the environment.

[0075] As a concrete example, during a flood, users can follow the instructions on their device to evacuate to a safe, non-flooded area. An example of a prompt message is, "Design a real-time evacuation route optimization algorithm for floods." In this way, the present invention provides a system that supports rapid and safe evacuation in real time during disasters.

[0076] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0077] Step 1:

[0078] The server first receives video data from street cameras and drones. This input video data is updated in real time to provide a detailed understanding of the disaster site. The video data is stored in a temporary storage device and then passed to an AI analysis module. This module detects disaster-related features in the video and outputs them as disaster progression identification information. For example, in flood areas, it identifies changes in water levels and generates information indicating dangerous areas.

[0079] Step 2:

[0080] The server acquires location data of people from cell phone base stations and GPS devices. This location data is used as input data, and movement pattern information is generated by analyzing pedestrian flow patterns. The server analyzes this information to identify the direction of group movements and evacuation. Based on this information, it predicts the congestion level of evacuation routes and outputs optimized evacuation route information.

[0081] Step 3:

[0082] The server integrates the generated disaster progression identification information and evacuation route optimization information to generate the optimal evacuation route. Based on both input pieces of information, the server dynamically calculates a safe and efficient evacuation route by referring to current map data and real-time traffic information. In this process, a route optimization algorithm is employed to output route information that avoids obstacles and dangerous areas.

[0083] Step 4:

[0084] The server sends the generated evacuation route information to the terminal. The encrypted route information arrives at the terminal via normal communication methods. The terminal analyzes the received information and prepares to guide the user along the evacuation route visually and audibly. Here, the terminal utilizes the user's current location information to provide real-time updated navigation information.

[0085] Step 5:

[0086] The device displays an evacuation route on the screen and guides the user in the right direction via a voice assistant. This process utilizes GPS functionality, ensuring the user's current location on the map is constantly updated. The user follows the displayed route, along with the device's voice instructions, to ensure a safe evacuation.

[0087] Step 6:

[0088] After completing an evacuation, users input feedback into a terminal based on the condition of the evacuation route and their impressions. This feedback is sent from the terminal to the server and stored in a database. The server uses the collected feedback to improve the accuracy of future analyses and refine evacuation plans.

[0089] (Application Example 1)

[0090] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0091] During disasters, safe and efficient evacuation is crucial, but existing systems are insufficient for real-time monitoring of disaster progress and for issuing evacuation orders based on human movement information. Furthermore, information provided to users is limited, and a particular lack of visual navigation is a significant challenge.

[0092] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0093] In this invention, the server includes means for analyzing video information received from a video acquisition device and generating disaster progression identification information, means for analyzing human flow information acquired from a location data acquisition device and generating evacuation route optimization information, and means for generating safe evacuation route information based on the disaster progression identification information and the evacuation route optimization information. This makes it possible to visually present optimal evacuation route information, which is updated in real time, using augmented reality technology, and to provide dynamic navigation support for safe and efficient evacuation.

[0094] A "video acquisition device" is a device that acquires video data from cameras, drones, and other equipment installed in disaster areas.

[0095] "Disaster Progress Identification Information" refers to information that identifies the progress of a disaster using AI analysis based on acquired video data.

[0096] A "location data acquisition device" is a device that acquires people's location information from mobile phone base stations and GPS devices.

[0097] "Population flow information" refers to information about the movement and gatherings of people obtained through location data acquisition devices.

[0098] "Evacuation route optimization information" is information used to calculate safe and efficient evacuation routes based on human flow information and disaster progression identification information.

[0099] "Safe evacuation route information" refers to optimal evacuation route information generated based on disaster conditions and human movement data.

[0100] A "communication terminal device" refers to a device used by a user to receive and display information, such as a smartphone or smart glasses.

[0101] Augmented reality technology is a technique that overlays digital information onto the real world, and is used to present evacuation information in a visually easy-to-understand manner.

[0102] "Dynamic navigation assistance" is a function that provides optimal route guidance in real time according to the user's current location and disaster situation.

[0103] This invention is a system for supporting safe and efficient evacuation during disasters. The system mainly consists of a server, a video acquisition device, a location data acquisition device, and a communication terminal device.

[0104] The server receives video information from video acquisition devices such as cameras and drones installed in disaster areas. Then, using an AI analysis module, it generates disaster progression identification information to determine the progression of the disaster from the acquired video. Machine learning algorithms are used in this analysis to improve prediction accuracy.

[0105] Furthermore, the server uses location data acquired via cell phone base stations and GPS devices to analyze human flow information regarding people's movements and gatherings. Based on this analysis, it generates information to optimize evacuation routes. This makes it possible to integrate disaster progression identification information and human flow information to dynamically generate optimal evacuation route information that is safe and less congested.

[0106] The terminal device provides users with easily viewable evacuation route information. Specifically, it visually displays evacuation routes using augmented reality technology via smartphones or smart glasses, and provides dynamic navigation through voice guidance. By acquiring the user's current location in real time and constantly providing the most appropriate evacuation measures according to the situation, it supports safe evacuation.

[0107] As a concrete example, if a user in an area experiencing flooding due to heavy rain uses this system, wearing smart glasses will allow the system to accumulate new routes that avoid dangerous areas such as flooded roads, and this information will be visually presented using augmented reality (AR). An example of the prompt text in this case is as follows:

[0108] "Heavy rain is falling. Please generate an AR-based evacuation route from my current location (latitude: xx, longitude: xx) to the safest shelter, and provide audio guidance. Please also include information about surrounding hazards."

[0109] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0110] Step 1:

[0111] The server receives video data in real time from video acquisition devices installed in the disaster area. This includes street cameras and drones. The received video data is used as input, and an AI analysis module begins processing it, outputting information to identify the progression of the disaster. The AI ​​uses image analysis technology to identify things like rising water levels and the locations of fire trucks.

[0112] Step 2:

[0113] The server acquires pedestrian flow information via cell phone base stations and GPS devices. This provides real-time location data and movement patterns of users as input. By analyzing this information, the server identifies congestion levels and areas of stagnation, and performs pedestrian flow analysis to generate information for optimizing evacuation routes.

[0114] Step 3:

[0115] The server integrates disaster progression identification information from Step 1 and evacuation route optimization information from Step 2 to generate safe evacuation route information. This uses an algorithm that dynamically determines the optimal evacuation route in real time, taking into account road flooding and congestion information. The output evacuation route information is constantly updated according to the disaster situation.

[0116] Step 4:

[0117] The server distributes generated safe evacuation route information to the terminal device. The terminal device receives this information and provides visual and audio guidance to the user. This guides the user from their current location to the safest evacuation shelter. The entered evacuation route information is displayed overlaid on the user's actual field of view using augmented reality (AR) technology.

[0118] Step 5:

[0119] The user begins evacuating by following the route provided by the device. During the evacuation, the device continuously tracks the user's location and provides real-time notifications of new hazards that appear in Step 3 and the status of evacuation shelters. This allows the user to continue taking optimal evacuation actions.

[0120] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0121] The present invention aims to provide more personalized evacuation support by combining a system that assists with evacuation during disasters with an emotion engine that recognizes the user's emotions. The following describes the configuration of the system for implementing the present invention and the details of its operation.

[0122] The server acquires video data from the disaster site and surrounding areas, and uses an AI analysis module to identify the progression of the disaster. This analysis generates real-time disaster progression information, such as the direction of flooding and fires.

[0123] Furthermore, the server analyzes human flow information by collecting people's location data and designs the optimal evacuation route based on the results. This evacuation route optimization information is integrated with the generated disaster progression information to create safe evacuation route information.

[0124] Evacuation route information is transmitted to a communication terminal device, and the user's emotions are recognized by the emotion engine on the terminal. The emotion engine uses the user's voice input and facial recognition data to determine whether the user is feeling stressed or anxious.

[0125] The device adjusts the displayed evacuation route information and notification methods according to the user's emotions. For example, if the device determines that the user is experiencing high levels of stress, it will emphasize visual instructions in addition to voice guidance to provide simpler and clearer directions.

[0126] Users move along the designated evacuation route and perform evacuation actions according to the instructions on the device. After the evacuation is complete, the device sends feedback on the user's evacuation method and route to the server. This will contribute to improving the accuracy of support during future disasters.

[0127] Thus, the present invention provides a system that reduces the stress of evacuation and supports safer and smoother evacuations by personalizing evacuation during disasters and enabling the provision of information according to the user's emotional state.

[0128] The following describes the processing flow.

[0129] Step 1:

[0130] The server receives video data from street cameras and drones. This data reflects the real-time situation at disaster sites.

[0131] Step 2:

[0132] The server processes the received video data using an AI analysis module to generate disaster progression identification information. This allows for the identification of the disaster's progress and affected area.

[0133] Step 3:

[0134] The server receives and analyzes human flow information from location data acquisition devices. This allows for understanding the movements and density of evacuees.

[0135] Step 4:

[0136] Based on disaster progression identification information and human flow information, the server calculates the safest and most efficient evacuation route and generates evacuation route optimization information.

[0137] Step 5:

[0138] The server transmits the generated safe evacuation route information to the communication terminal device. This information includes real-time evacuation route guidance.

[0139] Step 6:

[0140] The device receives information sent from the server and uses its built-in emotion engine to recognize the user's emotions. It uses the user's voice input and camera to determine their current emotional state.

[0141] Step 7:

[0142] The device adjusts evacuation route information appropriately according to the user's emotional state, as determined by the emotion engine. For example, if the user is feeling anxious, the instructions are simplified and visually emphasized.

[0143] Step 8:

[0144] Users follow the instructions on their devices and move along the provided evacuation routes. They evacuate safely while receiving instructions and emotional feedback from the devices as needed.

[0145] Step 9:

[0146] The terminal sends user feedback information to the server. This allows the system to use the feedback to improve evacuation routes and enhance the accuracy of emotion recognition.

[0147] (Example 2)

[0148] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0149] Conventional disaster evacuation support systems provide information on the progression of the disaster and evacuation routes without considering the user's emotional state, which can lead to panic and anxiety. Furthermore, because evacuation information is not updated in real time, responses to rapidly changing disaster situations may be delayed. It is necessary to solve these problems and provide safe, efficient, and personalized evacuation information.

[0150] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0151] In this invention, the server includes means for analyzing visual information received from video collection means to generate disaster progression information, means for analyzing human flow data acquired from location information collection means to generate evacuation route design information, and means for generating safe evacuation route information based on the disaster progression information and evacuation route design information. This makes it possible to safely and accurately provide evacuation information that is updated in real time, taking into account the emotional state of the user.

[0152] "Image acquisition means" refers to equipment or technology for obtaining visual information from disaster sites and surrounding areas, and includes cameras and other visual sensors.

[0153] "Visual information" refers to image data acquired by cameras and other video acquisition devices, and is used to identify the progression of a disaster.

[0154] "Disaster progress information" refers to data generated to identify the degree of the crisis and assess the situation, including the type of disaster, its direction of progression, and the scope of its impact.

[0155] "Location information collection means" refers to devices or technologies for collecting data on the location of people, and includes GPS and other location tracking technologies.

[0156] "Human flow data" refers to data showing the movement and number of people staying in a specific area, and is used to optimize evacuation routes.

[0157] "Evacuation route design information" refers to data that includes proposals for safe and efficient evacuation routes, designed based on disaster conditions and human flow data.

[0158] "Communication equipment" refers to devices used for sending and receiving information, and includes mobile terminals and smart devices.

[0159] "Emotional state" refers to the psychological state a user experiences in a particular situation, such as stress, anxiety, or relief, and it influences the user's reactions and judgments.

[0160] "Information display method" refers to the method of presenting information to users, and includes visual, auditory, or a combination thereof.

[0161] "Artificial intelligence algorithms" refer to computational methods and models used to analyze video information and location data, and include deep learning and machine learning techniques.

[0162] This invention aims to enhance disaster evacuation support and realize a system that provides personalized information to users. This system identifies the progression of a disaster in real time and provides optimal evacuation support according to the emotional state of each individual user.

[0163] The server uses visual devices such as surveillance cameras and drones to acquire video from the disaster site and its surroundings. The acquired visual information is then analyzed by an AI analysis module. This module typically uses machine learning frameworks such as TensorFlow or PyTorch to perform data processing to identify the direction of the disaster's progression and the extent of its impact.

[0164] The server also analyzes people's movements using location data obtained from smartphones and GPS devices. In this process, location information service APIs are used to design optimal evacuation routes based on people flow data. Algorithms such as Dijkstra's algorithm are used for route planning.

[0165] The generated safe evacuation route information is distributed to the terminal via a communication device. Based on the information received from the server, the terminal's emotion engine determines the user's emotional state. The emotion engine utilizes speech recognition and facial recognition technologies to evaluate the user's stress and anxiety levels. Libraries such as OpenCV may be used for this evaluation.

[0166] The device customizes how information is provided based on the emotional data it receives. For example, it presents information in a way that is easy for the user to understand by combining visual and audio guidance. A specific example is inputting a prompt sentence such as "Tell me the best route to evacuate safely as quickly as possible from the flood" into a generating AI model, which then provides information that is immediately relevant to the user.

[0167] Users can evacuate safely by following these instructions and provide feedback via their device after completing the evacuation. This feedback will be used to improve the accuracy of future evacuation assistance.

[0168] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0169] Step 1:

[0170] The server acquires video data from the disaster site and its surroundings. This video data is collected using visual devices such as surveillance cameras and drones. The video data is passed as input to an AI analysis module, which performs analysis to identify the progression of the disaster. Disaster progression information is generated as output. In this step, machine learning techniques are used to perform specific actions to detect changes and anomalies in the video.

[0171] Step 2:

[0172] The server analyzes location information obtained from smartphones and GPS devices to generate pedestrian flow data. By analyzing the location information received as input, it identifies the movement and concentration points of people within a specific area. As output, pedestrian flow analysis data is generated. Specifically, a process is performed to aggregate and visualize a large amount of location data using a location information service API.

[0173] Step 3:

[0174] The server integrates disaster progress information and human flow analysis data to design the optimal evacuation route. The inputs used are real-time updated disaster information and human flow data. Based on this, algorithms such as Dijkstra's algorithm are used to calculate the shortest and safest evacuation route and generate evacuation route information. In this step, multiple routes are compared, and specific routes are generated considering safety and time efficiency.

[0175] Step 4:

[0176] The server transmits the generated safe evacuation route information to the terminal via a communication device. The terminal receives the evacuation route information as output and presents it to the user. In this step, a network communication protocol is used to enable real-time information transmission.

[0177] Step 5:

[0178] The device uses an emotion engine to determine the user's emotional state based on the received evacuation route information. Inputs include data obtained from the user's voice and facial expressions. Outputs include the user's stress level and emotional state. Specific operations include voice analysis and facial recognition using TensorFlow and OpenCV.

[0179] Step 6:

[0180] The device adjusts its display method according to the user's emotional state. For example, if the user is in a high-stress state, visual guidance will be increased and audio guidance will be emphasized. Based on emotional data as input, adjusted information is presented to the user as output. In this step, specific methods for presenting information clearly to the user are applied using UI / UX design tools.

[0181] Step 7:

[0182] Users evacuate based on instructions from their devices and provide feedback after completing the evacuation. Data regarding the user's movement route and speed are considered unnecessary input, while feedback data is sent to the server as output. This feedback includes specific opinions on the appropriateness of the evacuation route and the effectiveness of the instructions.

[0183] (Application Example 2)

[0184] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0185] In times of disaster, supporting swift and accurate evacuation is extremely important, but conventional evacuation support systems do not adequately consider real-time disaster progress information or people's emotional states, making it difficult to evacuate safely while reducing stress.

[0186] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0187] In this invention, the server includes means for analyzing video data acquired from a video analysis device and generating disaster progression information, means for analyzing human flow analysis data obtained from a position sensor device and generating evacuation route suggestion information, and means for evaluating the emotional state using the user's voice information and image recognition data, and adjusting the information presentation method based on that evaluation. This makes it possible to provide appropriate evacuation support according to the individual emotional state during a disaster.

[0188] A "video analysis device" is a device used to acquire video data and analyze its contents.

[0189] "Disaster progress information" refers to information generated to identify and understand the progress of a disaster.

[0190] A "position sensor device" is a device used to determine the position of a moving object.

[0191] "Human flow analysis data" refers to data used to analyze the movement patterns of groups and individuals.

[0192] "Evacuation route suggestion information" refers to information used to suggest routes optimized for evacuation.

[0193] A "mobile communication terminal" is a device equipped with communication functions used in a mobile environment.

[0194] "Voice information" refers to data related to voice obtained from the user.

[0195] "Image recognition data" refers to information recognized based on the analysis of an image.

[0196] "Emotional state" refers to the user's emotions and psychological condition.

[0197] "Information presentation method" refers to the method of how information is presented to the user.

[0198] In this invention, three main elements—a server, a mobile communication terminal, and a user—interact with each other to achieve optimal evacuation support.

[0199] server:

[0200] The server uses video analysis equipment to receive video data from disaster sites and generates disaster progression information using an AI analysis module. Furthermore, it generates evacuation route suggestion information based on human flow analysis data from location sensor devices. This information is processed in real time, and data on disaster progression and evacuation routes is updated immediately. Machine learning frameworks such as TensorFlow and OpenCV are used for processing.

[0201] Mobile communication terminals:

[0202] The mobile communication terminal receives secure evacuation route data transmitted from the server and analyzes the user's emotional state using voice information and image recognition data. Based on the evaluation obtained by the emotion engine, it selects an appropriate method of presenting information. This makes it possible to reduce user anxiety while facilitating a smooth evacuation. The application can operate in Android® and iOS environments.

[0203] User:

[0204] Users take evacuation actions according to instructions from their mobile communication terminals. Emotional states are collected and analyzed in real time using voice input and cameras. For example, in the event of a disaster, a glasses-type device scans the user's facial expressions, and if it determines that the user is in an anxious state, the device provides vivid visual instructions.

[0205] For example, in a flood-stricken city, this system displays the user an evacuation route to the safest high ground, and if the emotion engine detects high stress levels, a visually clear interface is highlighted. Queries such as "How should the evacuation route presentation be adjusted if the user is confused?" can be used as prompts for the generative AI model.

[0206] This configuration enables safe and efficient evacuation during disasters.

[0207] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0208] Step 1:

[0209] The server receives video data from the video analysis device at the disaster site and processes it with an AI analysis module. Based on this input data, it generates disaster progression information to identify the progression of the disaster (e.g., the expansion of the flood area). In this process, an image analysis algorithm is applied to the video data to extract the characteristics of the disaster.

[0210] Step 2:

[0211] The server receives pedestrian flow analysis data from location sensor devices, processes it, and generates evacuation route suggestion information. By analyzing the input location data and determining the current location and movement speed of the crowd, it calculates the optimal evacuation route for the user. In this process, machine learning algorithms are used to model the fluctuation patterns of pedestrian flow data.

[0212] Step 3:

[0213] The server integrates disaster progression information and evacuation route suggestion information to generate safe evacuation route data. This data generation includes a risk assessment of available evacuation routes, and the safest route is selected. The integration process is updated in real time.

[0214] Step 4:

[0215] The device receives safe evacuation route data provided by the server. Next, it collects voice information from the user and images from the camera as input, which is then analyzed by an emotion engine. The user's emotional state (e.g., stress level) is evaluated, and based on this result, the method of presenting evacuation information is adjusted. For example, if stress levels are high, visual feedback is highlighted.

[0216] Step 5:

[0217] The user initiates actual evacuation based on the evacuation route information presented on the device. The device continuously provides real-time navigation in accordance with the user's movement. Navigation updates are constantly adapted to the latest disaster situation and the user's emotional state.

[0218] Step 6:

[0219] After evacuation is complete, the terminal sends feedback to the server regarding the evacuation route and method. This feedback, based on the user's experience, helps improve the system. The collected data is anonymized and used to train AI models for future disaster relief.

[0220] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0221] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0222] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0223] [Second Embodiment]

[0224] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0225] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0226] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0227] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0228] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0229] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0230] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0231] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0232] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0233] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0234] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0235] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0236] This invention provides a system to support safe and rapid evacuation during disasters. The following describes the configuration of the system for implementing this invention and details of its operation.

[0237] The server centrally receives video data from numerous street cameras and drones. This received video data is processed using an AI analysis module to identify the progression of a disaster in real time. For example, in the case of a flood, it can determine the rate at which the water level rises and the extent of the flooding.

[0238] Furthermore, the server also receives pedestrian flow information from location data acquisition devices. This allows for the analysis of people's movements and gatherings via cell phone base stations, GPS devices, and other means. This data is a crucial element in optimizing evacuation routes.

[0239] Based on analyzed disaster progression and human flow information, the server generates the optimal evacuation route. This route is dynamically updated to select the safest and least congested path. For example, if roads are flooded due to heavy rain, the server can suggest an alternative route based on that information.

[0240] The generated evacuation route information is transmitted to a communication terminal device. Based on this received information, the terminal provides the user with visual and audio route guidance. The terminal also obtains the user's current location and provides real-time navigation assistance to guide the user to a safe evacuation.

[0241] Users will use the information presented on the device to carry out a safe evacuation. Especially in situations with multiple evacuation centers, they are required to act according to the instructions provided by the device to avoid congestion. Once the evacuation is complete, the device sends feedback to the server regarding the user's evacuation route and situation. This feedback is used to improve the accuracy of the system.

[0242] Thus, the present invention embodies a system that utilizes video analysis and human flow data to provide the optimal evacuation route in real time and quickly notifies users of this information, in order to support safe evacuation during disasters.

[0243] The following describes the processing flow.

[0244] Step 1:

[0245] The server receives video data from street cameras and drones. This video data shows the real-time situation at disaster sites.

[0246] Step 2:

[0247] The server analyzes the received video data using an AI analysis module. Through this analysis, it identifies how disasters such as floods and fires are progressing and generates disaster progression identification information.

[0248] Step 3:

[0249] The server collects information on people's movements from location data acquisition devices. This data is analyzed as human flow information to understand areas where evacuees are concentrated and to grasp the flow of evacuation.

[0250] Step 4:

[0251] The server integrates and analyzes disaster progression information and human flow information to calculate the optimal evacuation route. In this process, it designs routes that avoid areas where the disaster is progressing rapidly and congested evacuation routes.

[0252] Step 5:

[0253] The server transmits the generated safe evacuation route information to the communication terminal device. The information includes text, maps, and audio guidance.

[0254] Step 6:

[0255] The terminal analyzes evacuation route information received from the server and provides visual and audio guidance to the user. It also provides real-time navigation based on the user's current location.

[0256] Step 7:

[0257] Users follow the instructions on their devices and move along the designated evacuation route. If the situation changes based on information obtained along the way, they will be offered an even safer alternative route.

[0258] Step 8:

[0259] The terminal sends path information and feedback acquired by the user during evacuation to the server. This information will be used to improve the accuracy of future evacuation route generation.

[0260] (Example 1)

[0261] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0262] To ensure rapid and safe evacuation during disasters, it is necessary to provide appropriate evacuation routes in real time, adapting to changing circumstances. However, conventional evacuation support systems have difficulty accurately grasping the progression of disasters and the movement of people, and dynamically optimizing routes. Furthermore, system improvements based on user feedback have been limited. A new solution to this problem is needed.

[0263] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0264] In this invention, the server includes means for analyzing video information received from a video acquisition device and generating disaster progression identification information, means for analyzing movement pattern information acquired from a location data acquisition device and generating evacuation route optimization information, and means for dynamically generating safe evacuation route information based on the disaster progression identification information and the evacuation route optimization information. This makes it possible to grasp the progress of the disaster and the movement of people in real time and provide safe and efficient evacuation routes.

[0265] A "video acquisition device" is a device that has the function of acquiring real-time video data at disaster sites and transmitting it to a server.

[0266] "Disaster Progress Identification Information" refers to information that shows data regarding the progress and degree of danger of a disaster, analyzed from acquired video information.

[0267] A "location data acquisition device" is a device that has the function of collecting people's location information and movement patterns and providing them to a server.

[0268] "Movement pattern information" refers to data that shows people's movement routes and the movements of groups, and is used to optimize evacuation routes.

[0269] "Evacuation route optimization information" is information that is analyzed based on collected movement pattern data to derive the optimal evacuation route.

[0270] "Safe evacuation route information" refers to information that shows optimized routes to avoid obstacles and dangerous areas and to move away from disasters.

[0271] A "generative AI model" is a machine learning technique that extracts useful features from data to support the optimization of disaster progression and evacuation routes.

[0272] This invention is a system for supporting safe and rapid evacuation during disasters. This system operates through the cooperation of a server, terminals, and users.

[0273] The server first receives real-time video data from video acquisition devices such as street cameras and drones. This video data is analyzed using an AI analysis module to identify the progression of the disaster. Machine learning libraries such as TensorFlow and PyTorch can be used for this AI analysis. The server also collects location data from cell phone base stations and GPS devices and generates pedestrian flow information by analyzing people's movement patterns. This data is crucial for deriving optimal evacuation routes.

[0274] The server dynamically generates the optimal evacuation route based on the generated disaster progression information and human flow information. This route generation process can utilize real-time map data and traffic information. Map services such as the Google Maps API are used to adjust the route to avoid obstacles and hazardous areas.

[0275] The terminal receives evacuation route information transmitted from the server. Using this information, the terminal provides visual and audio route guidance to the user. It utilizes GPS functionality to track the user's current location in real time and displays the route on the screen. Furthermore, it uses an audio guidance function to appropriately guide the user.

[0276] Users evacuate safely based on information provided by their devices. After the evacuation is complete, the devices send user feedback to the server, which is used to improve the system. This feedback includes user opinions on evacuation routes and changes in the environment.

[0277] As a concrete example, during a flood, users can follow the instructions on their device to evacuate to a safe, non-flooded area. An example of a prompt message is, "Design a real-time evacuation route optimization algorithm for floods." In this way, the present invention provides a system that supports rapid and safe evacuation in real time during disasters.

[0278] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0279] Step 1:

[0280] The server first receives video data from street cameras and drones. This input video data is updated in real time to provide a detailed understanding of the disaster site. The video data is stored in a temporary storage device and then passed to an AI analysis module. This module detects disaster-related features in the video and outputs them as disaster progression identification information. For example, in flood areas, it identifies changes in water levels and generates information indicating dangerous areas.

[0281] Step 2:

[0282] The server obtains people's location data from mobile phone base stations and GPS devices. This location data is used as input data to generate movement pattern information by analyzing the flow pattern of people. The server analyzes this information to identify the collective movement and evacuation direction of people. Based on this information, the server predicts the congestion situation of the evacuation route and outputs optimized evacuation route optimization information.

[0283] Step 3:

[0284] The server integrates the generated disaster progress identification information and evacuation route optimization information to generate an optimal evacuation route. Based on both pieces of input information, the server refers to the current map data and real-time traffic information to dynamically calculate a safe and efficient evacuation route. In this process, a route optimization algorithm works, and route information that avoids obstacles and dangerous areas is output.

[0285] Step 4:

[0286] The server transmits the generated evacuation route information to the terminal. Through normal communication means, the encrypted route information reaches the terminal. The terminal analyzes the received information and prepares to visually and audibly guide the user along the evacuation route. Here, the terminal utilizes the user's current location information to provide navigation information updated in real-time.

[0287] Step 5: <9000910> The terminal displays the evacuation route on the screen for the user and guides the direction to proceed by a voice assistant. In this process, the GPS function is utilized, and the user's current location on the map is constantly updated. The user follows the route displayed along with the voice instructions of the terminal to execute a safe evacuation.

[0289] Step 6:

[0290] After completing an evacuation, users input feedback into a terminal based on the condition of the evacuation route and their impressions. This feedback is sent from the terminal to the server and stored in a database. The server uses the collected feedback to improve the accuracy of future analyses and refine evacuation plans.

[0291] (Application Example 1)

[0292] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0293] During disasters, safe and efficient evacuation is crucial, but existing systems are insufficient for real-time monitoring of disaster progress and for issuing evacuation orders based on human movement information. Furthermore, information provided to users is limited, and a particular lack of visual navigation is a significant challenge.

[0294] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0295] In this invention, the server includes means for analyzing video information received from a video acquisition device and generating disaster progression identification information, means for analyzing human flow information acquired from a location data acquisition device and generating evacuation route optimization information, and means for generating safe evacuation route information based on the disaster progression identification information and the evacuation route optimization information. This makes it possible to visually present optimal evacuation route information, which is updated in real time, using augmented reality technology, and to provide dynamic navigation support for safe and efficient evacuation.

[0296] A "video acquisition device" is a device that acquires video data from cameras, drones, and other equipment installed in disaster areas.

[0297] "Disaster Progress Identification Information" refers to information that identifies the progress of a disaster using AI analysis based on acquired video data.

[0298] A "location data acquisition device" is a device that acquires people's location information from mobile phone base stations and GPS devices.

[0299] "Population flow information" refers to information about the movement and gatherings of people obtained through location data acquisition devices.

[0300] "Evacuation route optimization information" is information used to calculate safe and efficient evacuation routes based on human flow information and disaster progression identification information.

[0301] "Safe evacuation route information" refers to optimal evacuation route information generated based on disaster conditions and human movement data.

[0302] A "communication terminal device" refers to a device used by a user to receive and display information, such as a smartphone or smart glasses.

[0303] Augmented reality technology is a technique that overlays digital information onto the real world, and is used to present evacuation information in a visually easy-to-understand manner.

[0304] "Dynamic navigation assistance" is a function that provides optimal route guidance in real time according to the user's current location and disaster situation.

[0305] This invention is a system for supporting safe and efficient evacuation during disasters. The system mainly consists of a server, a video acquisition device, a location data acquisition device, and a communication terminal device.

[0306] The server receives video information from video acquisition devices such as cameras and drones installed in disaster areas. Then, using an AI analysis module, it generates disaster progression identification information to determine the progression of the disaster from the acquired video. Machine learning algorithms are used in this analysis to improve prediction accuracy.

[0307] Furthermore, the server uses the location data obtained via mobile phone base stations and GPS devices to analyze the flow information regarding people's movements and gatherings. Based on the analysis results, evacuation route optimization information is generated. By integrating the disaster progression specific information and the flow information, it becomes possible to dynamically generate optimal evacuation route information that is safe and less crowded.

[0308] The terminal device provides the optimal evacuation route information to the user in an easy-to-view manner. Specifically, through smartphones, smart glasses, etc., the evacuation route is visually displayed using augmented reality technology, and furthermore, dynamic navigation is implemented through voice guidance. By acquiring the user's current position in real time and constantly providing the optimal evacuation measures according to the situation, it supports safe evacuation.

[0309] As a specific example, when a user in an area affected by flood due to heavy rain uses this system, when wearing smart glasses, new routes avoiding dangerous locations such as flooded roads are accumulated, and that information is visually provided by AR. Examples of the prompt text at this time are as follows:

[0310] "It is raining heavily. Generate an evacuation route by AR display from the current position (latitude: xx, longitude: xx) to the safest evacuation shelter and also provide voice guidance. Include the surrounding danger information as well."

[0311] The flow of the specific processing in Application Example 1 will be described using FIG. 12.

[0312] Step 1:

[0313] The server receives video data in real time from the video acquisition devices installed in the disaster area. This includes street cameras and drones. Using the received video data as input, the AI analysis module starts processing and outputs disaster progression specific information. The AI uses image analysis technology to identify the rise in water level, the position of fire trucks, etc.

[0314] Step 2:

[0315] The server acquires pedestrian flow information via cell phone base stations and GPS devices. This provides real-time location data and movement patterns of users as input. By analyzing this information, the server identifies congestion levels and areas of stagnation, and performs pedestrian flow analysis to generate information for optimizing evacuation routes.

[0316] Step 3:

[0317] The server integrates disaster progression identification information from Step 1 and evacuation route optimization information from Step 2 to generate safe evacuation route information. This uses an algorithm that dynamically determines the optimal evacuation route in real time, taking into account road flooding and congestion information. The output evacuation route information is constantly updated according to the disaster situation.

[0318] Step 4:

[0319] The server distributes generated safe evacuation route information to the terminal device. The terminal device receives this information and provides visual and audio guidance to the user. This guides the user from their current location to the safest evacuation shelter. The entered evacuation route information is displayed overlaid on the user's actual field of view using augmented reality (AR) technology.

[0320] Step 5:

[0321] The user begins evacuating by following the route provided by the device. During the evacuation, the device continuously tracks the user's location and provides real-time notifications of new hazards that appear in Step 3 and the status of evacuation shelters. This allows the user to continue taking optimal evacuation actions.

[0322] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0323] The present invention aims to provide more personalized evacuation support by combining a system that assists with evacuation during disasters with an emotion engine that recognizes the user's emotions. The following describes the configuration of the system for implementing the present invention and the details of its operation.

[0324] The server acquires video data from the disaster site and surrounding areas, and uses an AI analysis module to identify the progression of the disaster. This analysis generates real-time disaster progression information, such as the direction of flooding and fires.

[0325] Furthermore, the server analyzes human flow information by collecting people's location data and designs the optimal evacuation route based on the results. This evacuation route optimization information is integrated with the generated disaster progression information to create safe evacuation route information.

[0326] Evacuation route information is transmitted to a communication terminal device, and the user's emotions are recognized by the emotion engine on the terminal. The emotion engine uses the user's voice input and facial recognition data to determine whether the user is feeling stressed or anxious.

[0327] The device adjusts the displayed evacuation route information and notification methods according to the user's emotions. For example, if the device determines that the user is experiencing high levels of stress, it will emphasize visual instructions in addition to voice guidance to provide simpler and clearer directions.

[0328] Users move along the designated evacuation route and perform evacuation actions according to the instructions on the device. After the evacuation is complete, the device sends feedback on the user's evacuation method and route to the server. This will contribute to improving the accuracy of support during future disasters.

[0329] Thus, the present invention provides a system that reduces the stress of evacuation and supports safer and smoother evacuations by personalizing evacuation during disasters and enabling the provision of information according to the user's emotional state.

[0330] The following describes the processing flow.

[0331] Step 1:

[0332] The server receives video data from street cameras and drones. This data reflects the real-time situation at disaster sites.

[0333] Step 2:

[0334] The server processes the received video data using an AI analysis module to generate disaster progression identification information. This allows for the identification of the disaster's progress and affected area.

[0335] Step 3:

[0336] The server receives and analyzes human flow information from location data acquisition devices. This allows for understanding the movements and density of evacuees.

[0337] Step 4:

[0338] Based on disaster progression identification information and human flow information, the server calculates the safest and most efficient evacuation route and generates evacuation route optimization information.

[0339] Step 5:

[0340] The server transmits the generated safe evacuation route information to the communication terminal device. This information includes real-time evacuation route guidance.

[0341] Step 6:

[0342] The device receives information sent from the server and uses its built-in emotion engine to recognize the user's emotions. It uses the user's voice input and camera to determine their current emotional state.

[0343] Step 7:

[0344] The device adjusts evacuation route information appropriately according to the user's emotional state, as determined by the emotion engine. For example, if the user is feeling anxious, the instructions are simplified and visually emphasized.

[0345] Step 8:

[0346] Users follow the instructions on their devices and move along the provided evacuation routes. They evacuate safely while receiving instructions and emotional feedback from the devices as needed.

[0347] Step 9:

[0348] The terminal sends user feedback information to the server. This allows the system to use the feedback to improve evacuation routes and enhance the accuracy of emotion recognition.

[0349] (Example 2)

[0350] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0351] Conventional disaster evacuation support systems provide information on the progression of the disaster and evacuation routes without considering the user's emotional state, which can lead to users panicking or feeling anxious. Furthermore, because evacuation information is not updated in real time, responses to rapidly changing disaster situations may be delayed. It is necessary to solve these problems and provide safe, efficient, and personalized evacuation information.

[0352] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0353] In this invention, the server includes means for analyzing visual information received from video collection means and generating disaster progression information, means for analyzing human flow data acquired from location information collection means and generating evacuation route design information, and means for generating safe evacuation route information based on the disaster progression information and evacuation route design information. This makes it possible to safely and accurately provide evacuation information that is updated in real time, taking into account the emotional state of the user.

[0354] "Image acquisition means" refers to equipment or technology for obtaining visual information from disaster sites and surrounding areas, and includes cameras and other visual sensors.

[0355] "Visual information" refers to image data acquired by cameras and other video acquisition devices, and is used to identify the progression of a disaster.

[0356] "Disaster progress information" refers to data generated to identify the degree of the crisis and assess the situation, including the type of disaster, its direction of progression, and the scope of its impact.

[0357] "Location information collection means" refers to devices or technologies for collecting data on the location of people, and includes GPS and other location tracking technologies.

[0358] "Human flow data" refers to data showing the movement and number of people staying in a specific area, and is used to optimize evacuation routes.

[0359] "Evacuation route design information" refers to data that includes proposals for safe and efficient evacuation routes, designed based on disaster conditions and human flow data.

[0360] "Communication equipment" refers to devices used for sending and receiving information, and includes mobile terminals and smart devices.

[0361] "Emotional state" refers to the psychological state a user experiences in a particular situation, such as stress, anxiety, or relief, and it influences the user's reactions and judgments.

[0362] "Information display method" refers to the method of presenting information to users, and includes visual, auditory, or a combination thereof.

[0363] "Artificial intelligence algorithms" refer to computational methods and models used to analyze video information and location data, and include deep learning and machine learning techniques.

[0364] This invention aims to enhance disaster evacuation support and realize a system that provides personalized information to users. This system identifies the progression of a disaster in real time and provides optimal evacuation support according to the emotional state of each individual user.

[0365] The server uses visual devices such as surveillance cameras and drones to acquire video from the disaster site and its surroundings. The acquired visual information is then analyzed by an AI analysis module. This module typically uses machine learning frameworks such as TensorFlow or PyTorch to process the data in order to identify the direction of the disaster's progression and the extent of its impact.

[0366] The server also analyzes people's movements using location data obtained from smartphones and GPS devices. In this process, location information service APIs are used to design optimal evacuation routes based on people flow data. Algorithms such as Dijkstra's algorithm are used for route planning.

[0367] The generated safe evacuation route information is distributed to the terminal via a communication device. Based on the information received from the server, the terminal's emotion engine determines the user's emotional state. The emotion engine utilizes speech recognition and facial recognition technologies to evaluate the user's stress and anxiety levels. Libraries such as OpenCV may be used for this evaluation.

[0368] The device customizes how information is provided based on the emotional data it receives. For example, it presents information in a way that is easy for the user to understand by combining visual and audio guidance. A specific example is inputting a prompt sentence such as "Tell me the best route to evacuate safely as quickly as possible from the flood" into a generating AI model, which then provides information that is immediately relevant to the user.

[0369] Users can evacuate safely by following these instructions and provide feedback via their device after completing the evacuation. This feedback will be used to improve the accuracy of future evacuation assistance.

[0370] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0371] Step 1:

[0372] The server acquires video data from the disaster site and its surroundings. This video data is collected using visual devices such as surveillance cameras and drones. The video data is passed as input to an AI analysis module, which performs analysis to identify the progression of the disaster. Disaster progression information is generated as output. In this step, machine learning techniques are used to perform specific actions to detect changes and anomalies in the video.

[0373] Step 2:

[0374] The server analyzes location information obtained from smartphones and GPS devices to generate pedestrian flow data. By analyzing the location information received as input, it identifies the movement and concentration points of people within a specific area. As output, pedestrian flow analysis data is generated. Specifically, a location information service API is used to aggregate and visualize a large amount of location data.

[0375] Step 3:

[0376] The server integrates disaster progress information and human flow analysis data to design the optimal evacuation route. The inputs used are real-time updated disaster information and human flow data. Based on this, algorithms such as Dijkstra's algorithm are used to calculate the shortest and safest evacuation route and generate evacuation route information. In this step, multiple routes are compared, and specific routes are generated considering safety and time efficiency.

[0377] Step 4:

[0378] The server transmits the generated safe evacuation route information to the terminal via a communication device. The terminal receives the evacuation route information as output and presents it to the user. In this step, a network communication protocol is used to enable real-time information transmission.

[0379] Step 5:

[0380] The device uses an emotion engine to determine the user's emotional state based on the received evacuation route information. Inputs include data obtained from the user's voice and facial expressions. Outputs include the user's stress level and emotional state. Specific operations include voice analysis and facial recognition using TensorFlow and OpenCV.

[0381] Step 6:

[0382] The device adjusts its display method according to the user's emotional state. For example, if the user is in a high-stress state, visual guidance is increased and audio guidance is emphasized. Based on emotional data as input, adjusted information is presented to the user as output. In this step, specific methods for presenting information clearly to the user are applied using UI / UX design tools.

[0383] Step 7:

[0384] Users evacuate based on instructions from their devices and provide feedback after completing the evacuation. Data regarding the user's movement route and speed are considered unnecessary input, while feedback data is sent to the server as output. This feedback includes specific opinions on the appropriateness of the evacuation route and the effectiveness of the instructions.

[0385] (Application Example 2)

[0386] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0387] In times of disaster, supporting swift and accurate evacuation is extremely important, but conventional evacuation support systems do not adequately consider real-time disaster progress information or people's emotional states, making it difficult to evacuate safely while reducing stress.

[0388] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0389] In this invention, the server includes means for analyzing video data acquired from a video analysis device and generating disaster progression information, means for analyzing human flow analysis data obtained from a position sensor device and generating evacuation route suggestion information, and means for evaluating the emotional state using the user's voice information and image recognition data and adjusting the information presentation method based on that evaluation. This makes it possible to provide appropriate evacuation support according to the individual emotional state during a disaster.

[0390] A "video analysis device" is a device used to acquire video data and analyze its contents.

[0391] "Disaster progress information" refers to information generated to identify and understand the progress of a disaster.

[0392] A "position sensor device" is a device used to determine the position of a moving object.

[0393] "Human flow analysis data" refers to data used to analyze the movement patterns of groups and individuals.

[0394] "Evacuation route suggestion information" refers to information used to suggest routes optimized for evacuation.

[0395] A "mobile communication terminal" is a device equipped with communication functions used in a mobile environment.

[0396] "Voice information" refers to data related to voice obtained from the user.

[0397] "Image recognition data" refers to information recognized based on the analysis of an image.

[0398] "Emotional state" refers to the user's emotions and psychological condition.

[0399] "Information presentation method" refers to the method of how information is presented to the user.

[0400] In this invention, three main elements—a server, a mobile communication terminal, and a user—interact with each other to achieve optimal evacuation support.

[0401] server:

[0402] The server uses video analysis equipment to receive video data from disaster sites and generates disaster progression information using an AI analysis module. Furthermore, it generates evacuation route suggestion information based on human flow analysis data from location sensor devices. This information is processed in real time, and data on disaster progression and evacuation routes is updated immediately. Machine learning frameworks such as TensorFlow and OpenCV are used for processing.

[0403] Mobile communication terminals:

[0404] The mobile communication terminal receives secure evacuation route data transmitted from the server and analyzes the user's emotional state using voice information and image recognition data. Based on the evaluation obtained by the emotion engine, it selects an appropriate method of presenting information. This makes it possible to reduce user anxiety while facilitating a smooth evacuation. The application can run on Android and iOS environments.

[0405] User:

[0406] Users take evacuation actions according to instructions from their mobile communication terminals. Emotional states are collected and analyzed in real time using voice input and cameras. For example, in the event of a disaster, a glasses-type device scans the user's facial expressions, and if it determines that the user is in an anxious state, the device provides vivid visual instructions.

[0407] For example, in a flood-stricken city, the system displays the user an evacuation route to the safest high ground, and if the emotion engine detects high stress levels, a visually clear interface is highlighted. Queries such as "How should the evacuation route presentation be adjusted if the user is confused?" can be used as prompts for the generative AI model.

[0408] This configuration enables safe and efficient evacuation during disasters.

[0409] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0410] Step 1:

[0411] The server receives video data from the disaster site from the video analysis device and processes it with an AI analysis module. Based on this input data, it generates disaster progression information to identify the progression of the disaster (e.g., the expansion of the flood area). In this process, an image analysis algorithm is applied to the video data to extract the characteristics of the disaster.

[0412] Step 2:

[0413] The server receives pedestrian flow analysis data from location sensor devices, processes it, and generates evacuation route suggestion information. By analyzing the input location data and determining the current location and movement speed of the crowd, it calculates the optimal evacuation route for the user. In this process, machine learning algorithms are used to model the fluctuation patterns of pedestrian flow data.

[0414] Step 3:

[0415] The server integrates disaster progression information and evacuation route suggestion information to generate safe evacuation route data. This data generation includes a risk assessment of available evacuation routes, and the safest route is selected. The integration process is updated in real time.

[0416] Step 4:

[0417] The device receives safe evacuation route data provided by the server. Next, it collects voice information from the user and images from the camera as input, which is then analyzed by an emotion engine. The user's emotional state (e.g., stress level) is evaluated, and based on this result, the method of presenting evacuation information is adjusted. For example, if stress levels are high, visual feedback is highlighted.

[0418] Step 5:

[0419] The user initiates actual evacuation based on the evacuation route information presented on the device. The device continuously provides real-time navigation in accordance with the user's movement. Navigation updates are constantly adapted to the latest disaster situation and the user's emotional state.

[0420] Step 6:

[0421] After evacuation is complete, the terminal sends feedback to the server regarding the evacuation route and method. This feedback, based on the user's experience, helps improve the system. The collected data is anonymized and used to train AI models for future disaster relief.

[0422] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0423] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0424] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0425] [Third Embodiment]

[0426] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0427] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0428] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0429] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0430] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0431] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0432] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0433] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0434] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0435] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0436] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0437] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0438] This invention provides a system to support safe and rapid evacuation during disasters. The following describes the configuration of the system for implementing this invention and details of its operation.

[0439] The server centrally receives video data from numerous street cameras and drones. This received video data is processed using an AI analysis module to identify the progression of a disaster in real time. For example, in the case of a flood, it can determine the rate at which the water level rises and the extent of the flooding.

[0440] Furthermore, the server also receives pedestrian flow information from location data acquisition devices. This allows for the analysis of people's movements and gatherings via cell phone base stations, GPS devices, and other means. This data is a crucial element in optimizing evacuation routes.

[0441] Based on analyzed disaster progression and human flow information, the server generates the optimal evacuation route. This route is dynamically updated to select the safest and least congested path. For example, if roads are flooded due to heavy rain, the server can suggest an alternative route based on that information.

[0442] The generated evacuation route information is transmitted to a communication terminal device. Based on this received information, the terminal provides the user with visual and audio route guidance. The terminal also obtains the user's current location and provides real-time navigation assistance to guide the user to a safe evacuation.

[0443] Users will use the information presented on the device to carry out a safe evacuation. Especially in situations with multiple evacuation centers, they are required to act according to the instructions provided by the device to avoid congestion. Once the evacuation is complete, the device sends feedback to the server regarding the user's evacuation route and situation. This feedback is used to improve the accuracy of the system.

[0444] Thus, the present invention embodies a system that utilizes video analysis and human flow data to provide the optimal evacuation route in real time and quickly notifies users of this information, in order to support safe evacuation during disasters.

[0445] The following describes the processing flow.

[0446] Step 1:

[0447] The server receives video data from street cameras and drones. This video data shows the real-time situation at disaster sites.

[0448] Step 2:

[0449] The server analyzes the received video data using an AI analysis module. Through this analysis, it identifies how disasters such as floods and fires are progressing and generates disaster progression identification information.

[0450] Step 3:

[0451] The server collects information on people's movements from location data acquisition devices. This data is analyzed as human flow information to understand areas where evacuees are concentrated and to grasp the flow of evacuation.

[0452] Step 4:

[0453] The server integrates and analyzes disaster progression information and human flow information to calculate the optimal evacuation route. In this process, it designs routes that avoid areas where the disaster is progressing rapidly and congested evacuation routes.

[0454] Step 5:

[0455] The server transmits the generated safe evacuation route information to the communication terminal device. The information includes text, maps, and audio guidance.

[0456] Step 6:

[0457] The terminal analyzes evacuation route information received from the server and provides visual and audio guidance to the user. It also provides real-time navigation based on the user's current location.

[0458] Step 7:

[0459] Users follow the instructions on their devices and move along the designated evacuation route. If the situation changes based on information obtained along the way, they will be offered an even safer alternative route.

[0460] Step 8:

[0461] The terminal sends path information and feedback acquired by the user during evacuation to the server. This information will be used to improve the accuracy of future evacuation route generation.

[0462] (Example 1)

[0463] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0464] To ensure rapid and safe evacuation during disasters, it is necessary to provide appropriate evacuation routes in real time, adapting to changing circumstances. However, conventional evacuation support systems have difficulty accurately grasping the progression of disasters and the movement of people, and dynamically optimizing routes. Furthermore, system improvements based on user feedback have been limited. A new solution to this problem is needed.

[0465] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0466] In this invention, the server includes means for analyzing video information received from a video acquisition device and generating disaster progression identification information, means for analyzing movement pattern information acquired from a location data acquisition device and generating evacuation route optimization information, and means for dynamically generating safe evacuation route information based on the disaster progression identification information and the evacuation route optimization information. This makes it possible to grasp the progress of the disaster and the movement of people in real time and provide safe and efficient evacuation routes.

[0467] A "video acquisition device" is a device that has the function of acquiring real-time video data at disaster sites and transmitting it to a server.

[0468] "Disaster Progress Identification Information" refers to information that shows data regarding the progress and degree of danger of a disaster, analyzed from acquired video information.

[0469] A "location data acquisition device" is a device that has the function of collecting people's location information and movement patterns and providing them to a server.

[0470] "Movement pattern information" refers to data that shows people's movement routes and the movements of groups, and is used to optimize evacuation routes.

[0471] "Evacuation route optimization information" is information that is analyzed based on collected movement pattern data to derive the optimal evacuation route.

[0472] "Safe evacuation route information" refers to information that shows optimized routes to avoid obstacles and dangerous areas and to move away from disasters.

[0473] A "generative AI model" is a machine learning technique that extracts useful features from data to support the optimization of disaster progression and evacuation routes.

[0474] This invention is a system for supporting safe and rapid evacuation during disasters. This system operates through the cooperation of a server, terminals, and users.

[0475] The server first receives real-time video data from video acquisition devices such as street cameras and drones. This video data is analyzed using an AI analysis module to identify the progression of the disaster. Machine learning libraries such as TensorFlow and PyTorch can be used for this AI analysis. The server also collects location data from cell phone base stations and GPS devices and generates pedestrian flow information by analyzing people's movement patterns. This data is crucial for deriving optimal evacuation routes.

[0476] The server dynamically generates the optimal evacuation route based on the generated disaster progression information and human flow information. This route generation process can utilize real-time map data and traffic information. Map services such as the Google Maps API are used to adjust the route to avoid obstacles and hazardous areas.

[0477] The terminal receives evacuation route information transmitted from the server. Using this information, the terminal provides visual and audio route guidance to the user. It utilizes GPS functionality to track the user's current location in real time and displays the route on the screen. Furthermore, it uses an audio guidance function to appropriately guide the user.

[0478] Users evacuate safely based on information provided by their devices. After the evacuation is complete, the devices send user feedback to the server, which is used to improve the system. This feedback includes user opinions on evacuation routes and changes in the environment.

[0479] As a concrete example, during a flood, users can follow the instructions on their device to evacuate to a safe, non-flooded area. An example of a prompt message is, "Design a real-time evacuation route optimization algorithm for floods." In this way, the present invention provides a system that supports rapid and safe evacuation in real time during disasters.

[0480] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0481] Step 1:

[0482] The server first receives video data from street cameras and drones. This input video data is updated in real time to provide a detailed understanding of the disaster site. The video data is stored in a temporary storage device and then passed to an AI analysis module. This module detects disaster-related features in the video and outputs them as disaster progression identification information. For example, in flood areas, it identifies changes in water levels and generates information indicating dangerous areas.

[0483] Step 2:

[0484] The server acquires location data of people from cell phone base stations and GPS devices. This location data is used as input data, and movement pattern information is generated by analyzing pedestrian flow patterns. The server analyzes this information to identify the direction of group movements and evacuation. Based on this information, it predicts the congestion level of evacuation routes and outputs optimized evacuation route information.

[0485] Step 3:

[0486] The server integrates the generated disaster progression identification information and evacuation route optimization information to create the optimal evacuation route. Based on both input pieces of information, the server dynamically calculates a safe and efficient evacuation route by referring to current map data and real-time traffic information. In this process, a route optimization algorithm is employed to output route information that avoids obstacles and dangerous areas.

[0487] Step 4:

[0488] The server sends the generated evacuation route information to the terminal. The encrypted route information arrives at the terminal via normal communication methods. The terminal analyzes the received information and prepares to guide the user along the evacuation route visually and audibly. Here, the terminal utilizes the user's current location information to provide real-time updated navigation information.

[0489] Step 5:

[0490] The device displays an evacuation route on the screen and guides the user in the right direction via a voice assistant. This process utilizes GPS functionality, ensuring the user's current location on the map is constantly updated. The user follows the displayed route, along with the device's voice instructions, to ensure a safe evacuation.

[0491] Step 6:

[0492] After completing an evacuation, users input feedback into a terminal based on the condition of the evacuation route and their impressions. This feedback is sent from the terminal to the server and stored in a database. The server uses the collected feedback to improve the accuracy of future analyses and refine evacuation plans.

[0493] (Application Example 1)

[0494] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0495] During disasters, safe and efficient evacuation is crucial, but existing systems are insufficient for real-time monitoring of disaster progress and for issuing evacuation orders based on human movement information. Furthermore, information provided to users is limited, and a particular lack of visual navigation is a significant challenge.

[0496] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0497] In this invention, the server includes means for analyzing video information received from a video acquisition device and generating disaster progression identification information, means for analyzing human flow information acquired from a location data acquisition device and generating evacuation route optimization information, and means for generating safe evacuation route information based on the disaster progression identification information and the evacuation route optimization information. This makes it possible to visually present optimal evacuation route information, which is updated in real time, using augmented reality technology, and to provide dynamic navigation support for safe and efficient evacuation.

[0498] A "video acquisition device" is a device that acquires video data from cameras, drones, and other equipment installed in disaster areas.

[0499] "Disaster Progress Identification Information" refers to information that identifies the progress of a disaster using AI analysis based on acquired video data.

[0500] A "location data acquisition device" is a device that acquires people's location information from mobile phone base stations and GPS devices.

[0501] "Population flow information" refers to information about the movement and gatherings of people obtained through location data acquisition devices.

[0502] "Evacuation route optimization information" is information used to calculate safe and efficient evacuation routes based on human flow information and disaster progression identification information.

[0503] "Safe evacuation route information" refers to optimal evacuation route information generated based on disaster conditions and human movement data.

[0504] A "communication terminal device" refers to a device used by a user to receive and display information, such as a smartphone or smart glasses.

[0505] Augmented reality technology is a technique that overlays digital information onto the real world, and is used to present evacuation information in a visually easy-to-understand manner.

[0506] "Dynamic navigation assistance" is a function that provides optimal route guidance in real time according to the user's current location and disaster situation.

[0507] This invention is a system for supporting safe and efficient evacuation during disasters. The system mainly consists of a server, a video acquisition device, a location data acquisition device, and a communication terminal device.

[0508] The server receives video information from video acquisition devices such as cameras and drones installed in disaster areas. Then, using an AI analysis module, it generates disaster progression identification information to determine the progression of the disaster from the acquired video. Machine learning algorithms are used in this analysis to improve prediction accuracy.

[0509] Furthermore, the server uses location data acquired via cell phone base stations and GPS devices to analyze human flow information regarding people's movements and gatherings. Based on this analysis, it generates information to optimize evacuation routes. This makes it possible to integrate disaster progression identification information and human flow information to dynamically generate optimal evacuation route information that is safe and less congested.

[0510] The terminal device provides users with easily viewable evacuation route information. Specifically, it visually displays evacuation routes using augmented reality technology via smartphones or smart glasses, and provides dynamic navigation through voice guidance. By acquiring the user's current location in real time and constantly providing the most appropriate evacuation measures according to the situation, it supports safe evacuation.

[0511] As a concrete example, if a user in an area experiencing flooding due to heavy rain uses this system, wearing smart glasses will allow the system to accumulate new routes that avoid dangerous areas such as flooded roads, and this information will be visually presented using augmented reality (AR). An example of the prompt text in this case is as follows:

[0512] "Heavy rain is falling. Please generate an AR-based evacuation route from my current location (latitude: xx, longitude: xx) to the safest shelter, and provide audio guidance. Please also include information about surrounding hazards."

[0513] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0514] Step 1:

[0515] The server receives video data in real time from video acquisition devices installed in the disaster area. This includes street cameras and drones. The received video data is used as input, and an AI analysis module begins processing it, outputting information to identify the progression of the disaster. The AI ​​uses image analysis technology to identify things like rising water levels and the locations of fire trucks.

[0516] Step 2:

[0517] The server acquires pedestrian flow information via cell phone base stations and GPS devices. This provides real-time location data and movement patterns of users as input. By analyzing this information, the server identifies congestion levels and areas of stagnation, and performs pedestrian flow analysis to generate information for optimizing evacuation routes.

[0518] Step 3:

[0519] The server integrates disaster progression identification information from Step 1 and evacuation route optimization information from Step 2 to generate safe evacuation route information. This uses an algorithm that dynamically determines the optimal evacuation route in real time, taking into account road flooding and congestion information. The output evacuation route information is constantly updated according to the disaster situation.

[0520] Step 4:

[0521] The server distributes generated safe evacuation route information to the terminal device. The terminal device receives this information and provides visual and audio guidance to the user. This guides the user from their current location to the safest evacuation shelter. The entered evacuation route information is displayed overlaid on the user's actual field of view using augmented reality (AR) technology.

[0522] Step 5:

[0523] The user begins evacuating by following the route provided by the device. During the evacuation, the device continuously tracks the user's location and provides real-time notifications of new hazards that appear in Step 3 and the status of evacuation shelters. This allows the user to continue taking optimal evacuation actions.

[0524] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0525] The present invention aims to provide more personalized evacuation support by combining a system that assists with evacuation during disasters with an emotion engine that recognizes the user's emotions. The following describes the configuration of the system for implementing the present invention and the details of its operation.

[0526] The server acquires video data from the disaster site and surrounding areas, and uses an AI analysis module to identify the progression of the disaster. This analysis generates real-time disaster progression information, such as the direction of flooding and fires.

[0527] Furthermore, the server analyzes human flow information by collecting people's location data and designs the optimal evacuation route based on the results. This evacuation route optimization information is integrated with the generated disaster progression information to create safe evacuation route information.

[0528] Evacuation route information is transmitted to a communication terminal device, and the user's emotions are recognized by the emotion engine on the terminal. The emotion engine uses the user's voice input and facial recognition data to determine whether the user is feeling stressed or anxious.

[0529] The device adjusts the displayed evacuation route information and notification methods according to the user's emotions. For example, if the device determines that the user is experiencing high levels of stress, it will emphasize visual instructions in addition to voice guidance to provide simpler and clearer directions.

[0530] Users move along the designated evacuation route and perform evacuation actions according to the instructions on the device. After the evacuation is complete, the device sends feedback on the user's evacuation method and route to the server. This will contribute to improving the accuracy of support during future disasters.

[0531] Thus, the present invention provides a system that reduces the stress of evacuation and supports safer and smoother evacuations by personalizing evacuation during disasters and enabling the provision of information according to the user's emotional state.

[0532] The following describes the processing flow.

[0533] Step 1:

[0534] The server receives video data from street cameras and drones. This data reflects the real-time situation at disaster sites.

[0535] Step 2:

[0536] The server processes the received video data using an AI analysis module to generate disaster progression identification information. This allows for the identification of the disaster's progress and affected area.

[0537] Step 3:

[0538] The server receives and analyzes human flow information from location data acquisition devices. This allows for understanding the movements and density of evacuees.

[0539] Step 4:

[0540] Based on disaster progression identification information and human flow information, the server calculates the safest and most efficient evacuation route and generates evacuation route optimization information.

[0541] Step 5:

[0542] The server transmits the generated safe evacuation route information to the communication terminal device. This information includes real-time evacuation route guidance.

[0543] Step 6:

[0544] The device receives information sent from the server and uses its built-in emotion engine to recognize the user's emotions. It uses the user's voice input and camera to determine their current emotional state.

[0545] Step 7:

[0546] The device adjusts evacuation route information appropriately according to the user's emotional state, as determined by the emotion engine. For example, if the user is feeling anxious, the instructions are simplified and visually emphasized.

[0547] Step 8:

[0548] Users follow the instructions on their devices and move along the provided evacuation routes. They evacuate safely while receiving instructions and emotional feedback from the devices as needed.

[0549] Step 9:

[0550] The terminal sends user feedback information to the server. This allows the system to use the feedback to improve evacuation routes and enhance the accuracy of emotion recognition.

[0551] (Example 2)

[0552] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0553] Conventional disaster evacuation support systems provide information on the progression of the disaster and evacuation routes without considering the user's emotional state, which can lead to users panicking or feeling anxious. Furthermore, because evacuation information is not updated in real time, responses to rapidly changing disaster situations may be delayed. It is necessary to solve these problems and provide safe, efficient, and personalized evacuation information.

[0554] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0555] In this invention, the server includes means for analyzing visual information received from video collection means and generating disaster progression information, means for analyzing human flow data acquired from location information collection means and generating evacuation route design information, and means for generating safe evacuation route information based on the disaster progression information and evacuation route design information. This makes it possible to safely and accurately provide evacuation information that is updated in real time, taking into account the emotional state of the user.

[0556] "Image acquisition means" refers to equipment or technology for obtaining visual information from disaster sites and surrounding areas, and includes cameras and other visual sensors.

[0557] "Visual information" refers to image data acquired by cameras and other video acquisition devices, and is used to identify the progression of a disaster.

[0558] "Disaster progress information" refers to data generated to identify the degree of the crisis and assess the situation, including the type of disaster, its direction of progression, and the scope of its impact.

[0559] "Location information collection means" refers to devices or technologies for collecting data on the location of people, and includes GPS and other location tracking technologies.

[0560] "Human flow data" refers to data showing the movement and number of people staying in a specific area, and is used to optimize evacuation routes.

[0561] "Evacuation route design information" refers to data that includes proposals for safe and efficient evacuation routes, designed based on disaster conditions and human flow data.

[0562] "Communication equipment" refers to devices used for sending and receiving information, and includes mobile terminals and smart devices.

[0563] "Emotional state" refers to the psychological state a user experiences in a particular situation, such as stress, anxiety, or relief, and it influences the user's reactions and judgments.

[0564] "Information display method" refers to the method of presenting information to users, and includes visual, auditory, or a combination thereof.

[0565] "Artificial intelligence algorithms" refer to computational methods and models used to analyze video information and location data, and include deep learning and machine learning techniques.

[0566] This invention aims to enhance disaster evacuation support and realize a system that provides personalized information to users. This system identifies the progression of a disaster in real time and provides optimal evacuation support according to the emotional state of each individual user.

[0567] The server uses visual devices such as surveillance cameras and drones to acquire video from the disaster site and its surroundings. The acquired visual information is then analyzed by an AI analysis module. This module typically uses machine learning frameworks such as TensorFlow or PyTorch to process the data in order to identify the direction of the disaster's progression and the extent of its impact.

[0568] The server also analyzes people's movements using location data obtained from smartphones and GPS devices. In this process, location information service APIs are used to design optimal evacuation routes based on people flow data. Algorithms such as Dijkstra's algorithm are used for route planning.

[0569] The generated safe evacuation route information is distributed to the terminal via a communication device. Based on the information received from the server, the terminal's emotion engine determines the user's emotional state. The emotion engine utilizes speech recognition and facial recognition technologies to evaluate the user's stress and anxiety levels. Libraries such as OpenCV may be used for this evaluation.

[0570] The device customizes how information is provided based on the emotional data it receives. For example, it presents information in a way that is easy for the user to understand by combining visual and audio guidance. A specific example is inputting a prompt sentence such as "Tell me the best route to evacuate safely as quickly as possible from the flood" into a generating AI model, which then provides information that is immediately relevant to the user.

[0571] Users can evacuate safely by following these instructions and provide feedback via their device after completing the evacuation. This feedback will be used to improve the accuracy of future evacuation assistance.

[0572] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0573] Step 1:

[0574] The server acquires video data from the disaster site and its surroundings. This video data is collected using visual devices such as surveillance cameras and drones. The video data is passed as input to an AI analysis module, which performs analysis to identify the progression of the disaster. Disaster progression information is generated as output. In this step, machine learning techniques are used to perform specific actions to detect changes and anomalies in the video.

[0575] Step 2:

[0576] The server analyzes location information obtained from smartphones and GPS devices to generate pedestrian flow data. By analyzing the location information received as input, it identifies the movement and concentration points of people within a specific area. As output, pedestrian flow analysis data is generated. Specifically, a location information service API is used to aggregate and visualize a large amount of location data.

[0577] Step 3:

[0578] The server integrates disaster progress information and human flow analysis data to design the optimal evacuation route. The inputs used are real-time updated disaster information and human flow data. Based on this, algorithms such as Dijkstra's algorithm are used to calculate the shortest and safest evacuation route and generate evacuation route information. In this step, multiple routes are compared, and specific routes are generated considering safety and time efficiency.

[0579] Step 4:

[0580] The server transmits the generated safe evacuation route information to the terminal via a communication device. The terminal receives the evacuation route information as output and presents it to the user. In this step, a network communication protocol is used to enable real-time information transmission.

[0581] Step 5:

[0582] The device uses an emotion engine to determine the user's emotional state based on the received evacuation route information. Inputs include data obtained from the user's voice and facial expressions. Outputs include the user's stress level and emotional state. Specific operations include voice analysis and facial recognition using TensorFlow and OpenCV.

[0583] Step 6:

[0584] The device adjusts its display method according to the user's emotional state. For example, if the user is in a high-stress state, visual guidance is increased and audio guidance is emphasized. Based on emotional data as input, adjusted information is presented to the user as output. In this step, specific methods for presenting information clearly to the user are applied using UI / UX design tools.

[0585] Step 7:

[0586] Users evacuate based on instructions from their devices and provide feedback after completing the evacuation. Data regarding the user's movement route and speed are considered unnecessary input, while feedback data is sent to the server as output. This feedback includes specific opinions on the appropriateness of the evacuation route and the effectiveness of the instructions.

[0587] (Application Example 2)

[0588] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0589] In times of disaster, supporting swift and accurate evacuation is extremely important, but conventional evacuation support systems do not adequately consider real-time disaster progress information or people's emotional states, making it difficult to evacuate safely while reducing stress.

[0590] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0591] In this invention, the server includes means for analyzing video data acquired from a video analysis device and generating disaster progression information, means for analyzing human flow analysis data obtained from a position sensor device and generating evacuation route suggestion information, and means for evaluating the emotional state using the user's voice information and image recognition data and adjusting the information presentation method based on that evaluation. This makes it possible to provide appropriate evacuation support according to the individual emotional state during a disaster.

[0592] A "video analysis device" is a device used to acquire video data and analyze its contents.

[0593] "Disaster progress information" refers to information generated to identify and understand the progress of a disaster.

[0594] A "position sensor device" is a device used to determine the position of a moving object.

[0595] "Human flow analysis data" refers to data used to analyze the movement patterns of groups and individuals.

[0596] "Evacuation route suggestion information" refers to information used to suggest routes optimized for evacuation.

[0597] A "mobile communication terminal" is a device equipped with communication functions used in a mobile environment.

[0598] "Voice information" refers to data related to voice obtained from the user.

[0599] "Image recognition data" refers to information recognized based on the analysis of an image.

[0600] "Emotional state" refers to the user's emotions and psychological condition.

[0601] "Information presentation method" refers to the method of how information is presented to the user.

[0602] In this invention, three main elements—a server, a mobile communication terminal, and a user—interact with each other to achieve optimal evacuation support.

[0603] server:

[0604] The server uses video analysis equipment to receive video data from disaster sites and generates disaster progression information using an AI analysis module. Furthermore, it generates evacuation route suggestion information based on human flow analysis data from location sensor devices. This information is processed in real time, and data on disaster progression and evacuation routes is updated immediately. Machine learning frameworks such as TensorFlow and OpenCV are used for processing.

[0605] Mobile communication terminals:

[0606] The mobile communication terminal receives secure evacuation route data transmitted from the server and analyzes the user's emotional state using voice information and image recognition data. Based on the evaluation obtained by the emotion engine, it selects an appropriate method of presenting information. This makes it possible to reduce user anxiety while facilitating a smooth evacuation. The application can run on Android and iOS environments.

[0607] User:

[0608] Users take evacuation actions according to instructions from their mobile communication terminals. Emotional states are collected and analyzed in real time using voice input and cameras. For example, in the event of a disaster, a glasses-type device scans the user's facial expressions, and if it determines that the user is in an anxious state, the device provides vivid visual instructions.

[0609] For example, in a flood-stricken city, the system displays the user an evacuation route to the safest high ground, and if the emotion engine detects high stress levels, a visually clear interface is highlighted. Queries such as "How should the evacuation route presentation be adjusted if the user is confused?" can be used as prompts for the generative AI model.

[0610] This configuration enables safe and efficient evacuation during disasters.

[0611] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0612] Step 1:

[0613] The server receives video data from the disaster site from the video analysis device and processes it with an AI analysis module. Based on this input data, it generates disaster progression information to identify the progression of the disaster (e.g., the expansion of the flood area). In this process, an image analysis algorithm is applied to the video data to extract the characteristics of the disaster.

[0614] Step 2:

[0615] The server receives pedestrian flow analysis data from location sensor devices, processes it, and generates evacuation route suggestion information. By analyzing the input location data and determining the current location and movement speed of the crowd, it calculates the optimal evacuation route for the user. In this process, machine learning algorithms are used to model the fluctuation patterns of pedestrian flow data.

[0616] Step 3:

[0617] The server integrates disaster progression information and evacuation route suggestion information to generate safe evacuation route data. This data generation includes a risk assessment of available evacuation routes, and the safest route is selected. The integration process is updated in real time.

[0618] Step 4:

[0619] The device receives safe evacuation route data provided by the server. Next, it collects voice information from the user and images from the camera as input, which is then analyzed by an emotion engine. The user's emotional state (e.g., stress level) is evaluated, and based on this result, the method of presenting evacuation information is adjusted. For example, if stress levels are high, visual feedback is highlighted.

[0620] Step 5:

[0621] The user initiates actual evacuation based on the evacuation route information presented on the device. The device continuously provides real-time navigation in accordance with the user's movement. Navigation updates are constantly adapted to the latest disaster situation and the user's emotional state.

[0622] Step 6:

[0623] After evacuation is complete, the terminal sends feedback to the server regarding the evacuation route and method. This feedback, based on the user's experience, helps improve the system. The collected data is anonymized and used to train AI models for future disaster relief.

[0624] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0625] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0626] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0627] [Fourth Embodiment]

[0628] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0629] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0630] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0631] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0632] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0633] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0634] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0635] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0636] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0637] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0638] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0639] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0640] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0641] This invention provides a system to support safe and rapid evacuation during disasters. The following describes the configuration of the system for implementing this invention and details of its operation.

[0642] The server centrally receives video data from numerous street cameras and drones. This received video data is processed using an AI analysis module to identify the progression of a disaster in real time. For example, in the case of a flood, it can determine the rate at which the water level rises and the extent of the flooding.

[0643] Furthermore, the server also receives pedestrian flow information from location data acquisition devices. This allows for the analysis of people's movements and gatherings via cell phone base stations, GPS devices, and other means. This data is a crucial element in optimizing evacuation routes.

[0644] Based on analyzed disaster progression and human flow information, the server generates the optimal evacuation route. This route is dynamically updated to select the safest and least congested path. For example, if roads are flooded due to heavy rain, the server can suggest an alternative route based on that information.

[0645] The generated evacuation route information is transmitted to a communication terminal device. Based on this received information, the terminal provides the user with visual and audio route guidance. The terminal also obtains the user's current location and provides real-time navigation assistance to guide the user to a safe evacuation.

[0646] Users will use the information presented on the device to carry out a safe evacuation. Especially in situations with multiple evacuation centers, they are required to act according to the instructions provided by the device to avoid congestion. Once the evacuation is complete, the device sends feedback to the server regarding the user's evacuation route and situation. This feedback is used to improve the accuracy of the system.

[0647] Thus, the present invention embodies a system that utilizes video analysis and human flow data to provide the optimal evacuation route in real time and quickly notifies users of this information, in order to support safe evacuation during disasters.

[0648] The following describes the processing flow.

[0649] Step 1:

[0650] The server receives video data from street cameras and drones. This video data shows the real-time situation at disaster sites.

[0651] Step 2:

[0652] The server analyzes the received video data using an AI analysis module. Through this analysis, it identifies how disasters such as floods and fires are progressing and generates disaster progression identification information.

[0653] Step 3:

[0654] The server collects information on people's movements from location data acquisition devices. This data is analyzed as human flow information to understand areas where evacuees are concentrated and to grasp the flow of evacuation.

[0655] Step 4:

[0656] The server integrates and analyzes disaster progression information and human flow information to calculate the optimal evacuation route. In this process, it designs routes that avoid areas where the disaster is progressing rapidly and congested evacuation routes.

[0657] Step 5:

[0658] The server transmits the generated safe evacuation route information to the communication terminal device. The information includes text, maps, and audio guidance.

[0659] Step 6:

[0660] The terminal analyzes evacuation route information received from the server and provides visual and audio guidance to the user. It also provides real-time navigation based on the user's current location.

[0661] Step 7:

[0662] Users follow the instructions on their devices and move along the designated evacuation route. If the situation changes based on information obtained along the way, they will be offered an even safer alternative route.

[0663] Step 8:

[0664] The terminal sends path information and feedback acquired by the user during evacuation to the server. This information will be used to improve the accuracy of future evacuation route generation.

[0665] (Example 1)

[0666] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0667] To ensure rapid and safe evacuation during disasters, it is necessary to provide appropriate evacuation routes in real time, adapting to changing circumstances. However, conventional evacuation support systems have difficulty accurately grasping the progression of disasters and the movement of people, and dynamically optimizing routes. Furthermore, system improvements based on user feedback have been limited. A new solution to this problem is needed.

[0668] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0669] In this invention, the server includes means for analyzing video information received from a video acquisition device and generating disaster progression identification information, means for analyzing movement pattern information acquired from a location data acquisition device and generating evacuation route optimization information, and means for dynamically generating safe evacuation route information based on the disaster progression identification information and the evacuation route optimization information. This makes it possible to grasp the progress of the disaster and the movement of people in real time and provide safe and efficient evacuation routes.

[0670] A "video acquisition device" is a device that has the function of acquiring real-time video data at disaster sites and transmitting it to a server.

[0671] "Disaster Progress Identification Information" refers to information that shows data regarding the progress and degree of danger of a disaster, analyzed from acquired video information.

[0672] A "location data acquisition device" is a device that has the function of collecting people's location information and movement patterns and providing them to a server.

[0673] "Movement pattern information" refers to data that shows people's movement routes and the movements of groups, and is used to optimize evacuation routes.

[0674] "Evacuation route optimization information" is information that is analyzed based on collected movement pattern data to derive the optimal evacuation route.

[0675] "Safe evacuation route information" refers to information that shows optimized routes to avoid obstacles and dangerous areas and to move away from disasters.

[0676] A "generative AI model" is a machine learning technique that extracts useful features from data to support the optimization of disaster progression and evacuation routes.

[0677] This invention is a system for supporting safe and rapid evacuation during disasters. This system operates through the cooperation of a server, terminals, and users.

[0678] The server first receives real-time video data from video acquisition devices such as street cameras and drones. This video data is analyzed using an AI analysis module to identify the progression of the disaster. Machine learning libraries such as TensorFlow and PyTorch can be used for this AI analysis. The server also collects location data from cell phone base stations and GPS devices and generates pedestrian flow information by analyzing people's movement patterns. This data is crucial for deriving optimal evacuation routes.

[0679] The server dynamically generates the optimal evacuation route based on the generated disaster progression information and human flow information. This route generation process can utilize real-time map data and traffic information. Map services such as the Google Maps API are used to adjust the route to avoid obstacles and hazardous areas.

[0680] The terminal receives evacuation route information transmitted from the server. Using this information, the terminal provides visual and audio route guidance to the user. It utilizes GPS functionality to track the user's current location in real time and displays the route on the screen. Furthermore, it uses an audio guidance function to appropriately guide the user.

[0681] Users evacuate safely based on information provided by their devices. After the evacuation is complete, the devices send user feedback to the server, which is used to improve the system. This feedback includes user opinions on evacuation routes and changes in the environment.

[0682] As a concrete example, during a flood, users can follow the instructions on their device to evacuate to a safe, non-flooded area. An example of a prompt message is, "Design a real-time evacuation route optimization algorithm for floods." In this way, the present invention provides a system that supports rapid and safe evacuation in real time during disasters.

[0683] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0684] Step 1:

[0685] The server first receives video data from street cameras and drones. This input video data is updated in real time to provide a detailed understanding of the disaster site. The video data is stored in a temporary storage device and then passed to an AI analysis module. This module detects disaster-related features in the video and outputs them as disaster progression identification information. For example, in flood areas, it identifies changes in water levels and generates information indicating dangerous areas.

[0686] Step 2:

[0687] The server acquires location data of people from cell phone base stations and GPS devices. This location data is used as input data, and movement pattern information is generated by analyzing pedestrian flow patterns. The server analyzes this information to identify the direction of group movements and evacuation. Based on this information, it predicts the congestion level of evacuation routes and outputs optimized evacuation route information.

[0688] Step 3:

[0689] The server integrates the generated disaster progression identification information and evacuation route optimization information to create the optimal evacuation route. Based on both input pieces of information, the server dynamically calculates a safe and efficient evacuation route by referring to current map data and real-time traffic information. In this process, a route optimization algorithm is employed to output route information that avoids obstacles and dangerous areas.

[0690] Step 4:

[0691] The server sends the generated evacuation route information to the terminal. The encrypted route information arrives at the terminal via normal communication methods. The terminal analyzes the received information and prepares to guide the user along the evacuation route visually and audibly. Here, the terminal utilizes the user's current location information to provide real-time updated navigation information.

[0692] Step 5:

[0693] The device displays an evacuation route on the screen and guides the user in the right direction via a voice assistant. This process utilizes GPS functionality, ensuring the user's current location on the map is constantly updated. The user follows the displayed route, along with the device's voice instructions, to ensure a safe evacuation.

[0694] Step 6:

[0695] After completing an evacuation, users input feedback into a terminal based on the condition of the evacuation route and their impressions. This feedback is sent from the terminal to the server and stored in a database. The server uses the collected feedback to improve the accuracy of future analyses and refine evacuation plans.

[0696] (Application Example 1)

[0697] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0698] During disasters, safe and efficient evacuation is crucial, but existing systems are insufficient for real-time monitoring of disaster progress and for issuing evacuation orders based on human movement information. Furthermore, information provided to users is limited, and a particular lack of visual navigation is a significant challenge.

[0699] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0700] In this invention, the server includes means for analyzing video information received from a video acquisition device and generating disaster progression identification information, means for analyzing human flow information acquired from a location data acquisition device and generating evacuation route optimization information, and means for generating safe evacuation route information based on the disaster progression identification information and the evacuation route optimization information. This makes it possible to visually present optimal evacuation route information, which is updated in real time, using augmented reality technology, and to provide dynamic navigation support for safe and efficient evacuation.

[0701] A "video acquisition device" is a device that acquires video data from cameras, drones, and other equipment installed in disaster areas.

[0702] "Disaster Progress Identification Information" refers to information that identifies the progress of a disaster using AI analysis based on acquired video data.

[0703] A "location data acquisition device" is a device that acquires people's location information from mobile phone base stations and GPS devices.

[0704] "Population flow information" refers to information about the movement and gatherings of people obtained through location data acquisition devices.

[0705] "Evacuation route optimization information" is information used to calculate safe and efficient evacuation routes based on human flow information and disaster progression identification information.

[0706] "Safe evacuation route information" refers to optimal evacuation route information generated based on disaster conditions and human movement data.

[0707] A "communication terminal device" refers to a device used by a user to receive and display information, such as a smartphone or smart glasses.

[0708] Augmented reality technology is a technique that overlays digital information onto the real world, and is used to present evacuation information in a visually easy-to-understand manner.

[0709] "Dynamic navigation assistance" is a function that provides optimal route guidance in real time according to the user's current location and disaster situation.

[0710] This invention is a system for supporting safe and efficient evacuation during disasters. The system mainly consists of a server, a video acquisition device, a location data acquisition device, and a communication terminal device.

[0711] The server receives video information from video acquisition devices such as cameras and drones installed in disaster areas. Then, using an AI analysis module, it generates disaster progression identification information to determine the progression of the disaster from the acquired video. Machine learning algorithms are used in this analysis to improve prediction accuracy.

[0712] Furthermore, the server uses location data acquired via cell phone base stations and GPS devices to analyze human flow information regarding people's movements and gatherings. Based on this analysis, it generates information to optimize evacuation routes. This makes it possible to integrate disaster progression identification information and human flow information to dynamically generate optimal evacuation route information that is safe and less congested.

[0713] The terminal device provides users with easily viewable evacuation route information. Specifically, it visually displays evacuation routes using augmented reality technology via smartphones or smart glasses, and provides dynamic navigation through voice guidance. By acquiring the user's current location in real time and constantly providing the most appropriate evacuation measures according to the situation, it supports safe evacuation.

[0714] As a concrete example, if a user in an area experiencing flooding due to heavy rain uses this system, wearing smart glasses will allow the system to accumulate new routes that avoid dangerous areas such as flooded roads, and this information will be visually presented using augmented reality (AR). An example of the prompt text in this case is as follows:

[0715] "Heavy rain is falling. Please generate an AR-based evacuation route from my current location (latitude: xx, longitude: xx) to the safest shelter, and provide audio guidance. Please also include information about surrounding hazards."

[0716] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0717] Step 1:

[0718] The server receives video data in real time from video acquisition devices installed in the disaster area. This includes street cameras and drones. The received video data is used as input, and an AI analysis module begins processing it, outputting information to identify the progression of the disaster. The AI ​​uses image analysis technology to identify things like rising water levels and the locations of fire trucks.

[0719] Step 2:

[0720] The server acquires pedestrian flow information via cell phone base stations and GPS devices. This provides real-time location data and movement patterns of users as input. By analyzing this information, the server identifies congestion levels and areas of stagnation, and performs pedestrian flow analysis to generate information for optimizing evacuation routes.

[0721] Step 3:

[0722] The server integrates disaster progression identification information from Step 1 and evacuation route optimization information from Step 2 to generate safe evacuation route information. This uses an algorithm that dynamically determines the optimal evacuation route in real time, taking into account road flooding and congestion information. The output evacuation route information is constantly updated according to the disaster situation.

[0723] Step 4:

[0724] The server distributes generated safe evacuation route information to the terminal device. The terminal device receives this information and provides visual and audio guidance to the user. This guides the user from their current location to the safest evacuation shelter. The entered evacuation route information is displayed overlaid on the user's actual field of view using augmented reality (AR) technology.

[0725] Step 5:

[0726] The user begins evacuating by following the route provided by the device. During the evacuation, the device continuously tracks the user's location and provides real-time notifications of new hazards that appear in Step 3 and the status of evacuation shelters. This allows the user to continue taking optimal evacuation actions.

[0727] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0728] The present invention aims to provide more personalized evacuation support by combining a system that assists with evacuation during disasters with an emotion engine that recognizes the user's emotions. The following describes the configuration of the system for implementing the present invention and the details of its operation.

[0729] The server acquires video data from the disaster site and surrounding areas, and uses an AI analysis module to identify the progression of the disaster. This analysis generates real-time disaster progression information, such as the direction of flooding and fires.

[0730] Furthermore, the server analyzes human flow information by collecting people's location data and designs the optimal evacuation route based on the results. This evacuation route optimization information is integrated with the generated disaster progression information to create safe evacuation route information.

[0731] Evacuation route information is transmitted to a communication terminal device, and the user's emotions are recognized by the emotion engine on the terminal. The emotion engine uses the user's voice input and facial recognition data to determine whether the user is feeling stressed or anxious.

[0732] The device adjusts the displayed evacuation route information and notification methods according to the user's emotions. For example, if the device determines that the user is experiencing high levels of stress, it will emphasize visual instructions in addition to voice guidance to provide simpler and clearer directions.

[0733] Users move along the designated evacuation route and perform evacuation actions according to the instructions on the device. After the evacuation is complete, the device sends feedback on the user's evacuation method and route to the server. This will contribute to improving the accuracy of support during future disasters.

[0734] Thus, the present invention provides a system that reduces the stress of evacuation and supports safer and smoother evacuations by personalizing evacuation during disasters and enabling the provision of information according to the user's emotional state.

[0735] The following describes the processing flow.

[0736] Step 1:

[0737] The server receives video data from street cameras and drones. This data reflects the real-time situation at disaster sites.

[0738] Step 2:

[0739] The server processes the received video data using an AI analysis module to generate disaster progression identification information. This allows for the identification of the disaster's progress and affected area.

[0740] Step 3:

[0741] The server receives and analyzes human flow information from location data acquisition devices. This allows for understanding the movements and density of evacuees.

[0742] Step 4:

[0743] Based on disaster progression identification information and human flow information, the server calculates the safest and most efficient evacuation route and generates evacuation route optimization information.

[0744] Step 5:

[0745] The server transmits the generated safe evacuation route information to the communication terminal device. This information includes real-time evacuation route guidance.

[0746] Step 6:

[0747] The device receives information sent from the server and uses its built-in emotion engine to recognize the user's emotions. It uses the user's voice input and camera to determine their current emotional state.

[0748] Step 7:

[0749] The device adjusts evacuation route information appropriately according to the user's emotional state, as determined by the emotion engine. For example, if the user is feeling anxious, the instructions are simplified and visually emphasized.

[0750] Step 8:

[0751] Users follow the instructions on their devices and move along the provided evacuation routes. They evacuate safely while receiving instructions and emotional feedback from the devices as needed.

[0752] Step 9:

[0753] The terminal sends user feedback information to the server. This allows the system to use the feedback to improve evacuation routes and enhance the accuracy of emotion recognition.

[0754] (Example 2)

[0755] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0756] Conventional disaster evacuation support systems provide information on the progression of the disaster and evacuation routes without considering the user's emotional state, which can lead to users panicking or feeling anxious. Furthermore, because evacuation information is not updated in real time, responses to rapidly changing disaster situations may be delayed. It is necessary to solve these problems and provide safe, efficient, and personalized evacuation information.

[0757] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0758] In this invention, the server includes means for analyzing visual information received from video collection means and generating disaster progression information, means for analyzing human flow data acquired from location information collection means and generating evacuation route design information, and means for generating safe evacuation route information based on the disaster progression information and evacuation route design information. This makes it possible to safely and accurately provide evacuation information that is updated in real time, taking into account the emotional state of the user.

[0759] "Image acquisition means" refers to equipment or technology for obtaining visual information from disaster sites and surrounding areas, and includes cameras and other visual sensors.

[0760] "Visual information" refers to image data acquired by cameras and other video acquisition devices, and is used to identify the progression of a disaster.

[0761] "Disaster progress information" refers to data generated to identify the degree of the crisis and assess the situation, including the type of disaster, its direction of progression, and the scope of its impact.

[0762] "Location information collection means" refers to devices or technologies for collecting data on the location of people, and includes GPS and other location tracking technologies.

[0763] "Human flow data" refers to data showing the movement and number of people staying in a specific area, and is used to optimize evacuation routes.

[0764] "Evacuation route design information" refers to data that includes proposals for safe and efficient evacuation routes, designed based on disaster conditions and human flow data.

[0765] "Communication equipment" refers to devices used for sending and receiving information, and includes mobile terminals and smart devices.

[0766] "Emotional state" refers to the psychological state a user experiences in a particular situation, such as stress, anxiety, or relief, and it influences the user's reactions and judgments.

[0767] "Information display method" refers to the method of presenting information to users, and includes visual, auditory, or a combination thereof.

[0768] "Artificial intelligence algorithms" refer to computational methods and models used to analyze video information and location data, and include deep learning and machine learning techniques.

[0769] This invention aims to enhance disaster evacuation support and realize a system that provides personalized information to users. This system identifies the progression of a disaster in real time and provides optimal evacuation support according to the emotional state of each individual user.

[0770] The server uses visual devices such as surveillance cameras and drones to acquire video from the disaster site and its surroundings. The acquired visual information is then analyzed by an AI analysis module. This module typically uses machine learning frameworks such as TensorFlow or PyTorch to process the data in order to identify the direction of the disaster's progression and the extent of its impact.

[0771] The server also analyzes people's movements using location data obtained from smartphones and GPS devices. In this process, location information service APIs are used to design optimal evacuation routes based on people flow data. Algorithms such as Dijkstra's algorithm are used for route planning.

[0772] The generated safe evacuation route information is distributed to the terminal via a communication device. Based on the information received from the server, the terminal's emotion engine determines the user's emotional state. The emotion engine utilizes speech recognition and facial recognition technologies to evaluate the user's stress and anxiety levels. Libraries such as OpenCV may be used for this evaluation.

[0773] The device customizes how information is provided based on the emotional data it receives. For example, it presents information in a way that is easy for the user to understand by combining visual and audio guidance. A specific example is inputting a prompt sentence such as "Tell me the best route to evacuate safely as quickly as possible from the flood" into a generating AI model, which then provides information that is immediately relevant to the user.

[0774] Users can evacuate safely by following these instructions and provide feedback via their device after completing the evacuation. This feedback will be used to improve the accuracy of future evacuation assistance.

[0775] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0776] Step 1:

[0777] The server acquires video data from the disaster site and its surroundings. This video data is collected using visual devices such as surveillance cameras and drones. The video data is passed as input to an AI analysis module, which performs analysis to identify the progression of the disaster. Disaster progression information is generated as output. In this step, machine learning techniques are used to perform specific actions to detect changes and anomalies in the video.

[0778] Step 2:

[0779] The server analyzes location information obtained from smartphones and GPS devices to generate pedestrian flow data. By analyzing the location information received as input, it identifies the movement and concentration points of people within a specific area. As output, pedestrian flow analysis data is generated. Specifically, a location information service API is used to aggregate and visualize a large amount of location data.

[0780] Step 3:

[0781] The server integrates disaster progress information and human flow analysis data to design the optimal evacuation route. The inputs used are real-time updated disaster information and human flow data. Based on this, algorithms such as Dijkstra's algorithm are used to calculate the shortest and safest evacuation route and generate evacuation route information. In this step, multiple routes are compared, and specific routes are generated considering safety and time efficiency.

[0782] Step 4:

[0783] The server transmits the generated safe evacuation route information to the terminal via a communication device. The terminal receives the evacuation route information as output and presents it to the user. In this step, a network communication protocol is used to enable real-time information transmission.

[0784] Step 5:

[0785] The device uses an emotion engine to determine the user's emotional state based on the received evacuation route information. Inputs include data obtained from the user's voice and facial expressions. Outputs include the user's stress level and emotional state. Specific operations include voice analysis and facial recognition using TensorFlow and OpenCV.

[0786] Step 6:

[0787] The device adjusts its display method according to the user's emotional state. For example, if the user is in a high-stress state, visual guidance is increased and audio guidance is emphasized. Based on emotional data as input, adjusted information is presented to the user as output. In this step, specific methods for presenting information clearly to the user are applied using UI / UX design tools.

[0788] Step 7:

[0789] Users evacuate based on instructions from their devices and provide feedback after completing the evacuation. Data regarding the user's movement route and speed are considered unnecessary input, while feedback data is sent to the server as output. This feedback includes specific opinions on the appropriateness of the evacuation route and the effectiveness of the instructions.

[0790] (Application Example 2)

[0791] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0792] In times of disaster, supporting swift and accurate evacuation is extremely important, but conventional evacuation support systems do not adequately consider real-time disaster progress information or people's emotional states, making it difficult to evacuate safely while reducing stress.

[0793] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0794] In this invention, the server includes means for analyzing video data acquired from a video analysis device and generating disaster progression information, means for analyzing human flow analysis data obtained from a position sensor device and generating evacuation route suggestion information, and means for evaluating the emotional state using the user's voice information and image recognition data and adjusting the information presentation method based on that evaluation. This makes it possible to provide appropriate evacuation support according to the individual emotional state during a disaster.

[0795] A "video analysis device" is a device used to acquire video data and analyze its contents.

[0796] "Disaster progress information" refers to information generated to identify and understand the progress of a disaster.

[0797] A "position sensor device" is a device used to determine the position of a moving object.

[0798] "Human flow analysis data" refers to data used to analyze the movement patterns of groups and individuals.

[0799] "Evacuation route suggestion information" refers to information used to suggest routes optimized for evacuation.

[0800] A "mobile communication terminal" is a device equipped with communication functions used in a mobile environment.

[0801] "Voice information" refers to data related to voice obtained from the user.

[0802] "Image recognition data" refers to information recognized based on the analysis of an image.

[0803] "Emotional state" refers to the user's emotions and psychological condition.

[0804] "Information presentation method" refers to the method of how information is presented to the user.

[0805] In this invention, three main elements—a server, a mobile communication terminal, and a user—interact with each other to achieve optimal evacuation support.

[0806] server:

[0807] The server uses video analysis equipment to receive video data from disaster sites and generates disaster progression information using an AI analysis module. Furthermore, it generates evacuation route suggestion information based on human flow analysis data from location sensor devices. This information is processed in real time, and data on disaster progression and evacuation routes is updated immediately. Machine learning frameworks such as TensorFlow and OpenCV are used for processing.

[0808] Mobile communication terminals:

[0809] The mobile communication terminal receives secure evacuation route data transmitted from the server and analyzes the user's emotional state using voice information and image recognition data. Based on the evaluation obtained by the emotion engine, it selects an appropriate method of presenting information. This makes it possible to reduce user anxiety while facilitating a smooth evacuation. The application can run on Android and iOS environments.

[0810] User:

[0811] Users take evacuation actions according to instructions from their mobile communication terminals. Emotional states are collected and analyzed in real time using voice input and cameras. For example, in the event of a disaster, a glasses-type device scans the user's facial expressions, and if it determines that the user is in an anxious state, the device provides vivid visual instructions.

[0812] For example, in a flood-stricken city, the system displays the user an evacuation route to the safest high ground, and if the emotion engine detects high stress levels, a visually clear interface is highlighted. Queries such as "How should the evacuation route presentation be adjusted if the user is confused?" can be used as prompts for the generative AI model.

[0813] This configuration enables safe and efficient evacuation during disasters.

[0814] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0815] Step 1:

[0816] The server receives video data from the disaster site from the video analysis device and processes it with an AI analysis module. Based on this input data, it generates disaster progression information to identify the progression of the disaster (e.g., the expansion of the flood area). In this process, an image analysis algorithm is applied to the video data to extract the characteristics of the disaster.

[0817] Step 2:

[0818] The server receives pedestrian flow analysis data from location sensor devices, processes it, and generates evacuation route suggestion information. By analyzing the input location data and determining the current location and movement speed of the crowd, it calculates the optimal evacuation route for the user. In this process, machine learning algorithms are used to model the fluctuation patterns of pedestrian flow data.

[0819] Step 3:

[0820] The server integrates disaster progression information and evacuation route suggestion information to generate safe evacuation route data. This data generation includes a risk assessment of available evacuation routes, and the safest route is selected. The integration process is updated in real time.

[0821] Step 4:

[0822] The device receives safe evacuation route data provided by the server. Next, it collects voice information from the user and images from the camera as input, which is then analyzed by an emotion engine. The user's emotional state (e.g., stress level) is evaluated, and based on this result, the method of presenting evacuation information is adjusted. For example, if stress levels are high, visual feedback is highlighted.

[0823] Step 5:

[0824] The user initiates actual evacuation based on the evacuation route information presented on the device. The device continuously provides real-time navigation in accordance with the user's movement. Navigation updates are constantly adapted to the latest disaster situation and the user's emotional state.

[0825] Step 6:

[0826] After evacuation is complete, the terminal sends feedback to the server regarding the evacuation route and method. This feedback, based on the user's experience, helps improve the system. The collected data is anonymized and used to train AI models for future disaster relief.

[0827] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0828] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0829] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0830] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0831] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0832] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0833] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0834] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0835] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0836] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0837] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0838] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0839] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0840] 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.

[0841] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0842] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0843] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0844] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0845] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0846] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0847] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0848] The following is further disclosed regarding the embodiments described above.

[0849] (Claim 1)

[0850] A means for analyzing video information received from a video acquisition device and generating disaster progression identification information,

[0851] A means for analyzing pedestrian flow information acquired from a location data acquisition device and generating information for optimizing evacuation routes,

[0852] A means for generating safe evacuation route information based on disaster progression identification information and evacuation route optimization information,

[0853] A means for distributing the aforementioned safe evacuation route information to a communication terminal device,

[0854] A system that includes this.

[0855] (Claim 2)

[0856] The system according to claim 1, characterized in that the safe evacuation route information is configured to be updated in real time.

[0857] (Claim 3)

[0858] The system according to claim 1, characterized in that a machine learning algorithm is used to generate the disaster progression identification information.

[0859] "Example 1"

[0860] (Claim 1)

[0861] A means for analyzing video information received from a video acquisition device and generating disaster progression identification information,

[0862] A means for analyzing movement pattern information acquired from a location data acquisition device and generating evacuation route optimization information,

[0863] A means for dynamically generating safe evacuation route information based on disaster progression identification information and evacuation route optimization information,

[0864] A means for distributing the aforementioned safe evacuation route information to a communication terminal device and providing route guidance to the user visually and audibly,

[0865] A means of collecting feedback information from users and using it to improve system accuracy,

[0866] A system that includes this.

[0867] (Claim 2)

[0868] The system according to claim 1, configured to provide real-time navigation guidance based on the aforementioned safe evacuation route information and the user's current location.

[0869] (Claim 3)

[0870] The system according to claim 1, characterized in that it uses a generation AI model to generate the disaster progression identification information.

[0871] "Application Example 1"

[0872] (Claim 1)

[0873] A means for analyzing video information received from a video acquisition device and generating disaster progression identification information,

[0874] A means for analyzing pedestrian flow information acquired from a location data acquisition device and generating information for optimizing evacuation routes,

[0875] A means for generating safe evacuation route information based on disaster progression identification information and evacuation route optimization information,

[0876] The means for distributing the aforementioned safe evacuation route information to a communication terminal device and presenting that information visually and audibly,

[0877] The means for visually displaying the aforementioned safe evacuation route information using augmented reality technology,

[0878] A means for acquiring real-time location information of a terminal device and providing dynamic navigation support,

[0879] A system that includes this.

[0880] (Claim 2)

[0881] The system according to claim 1, characterized in that the safe evacuation route information is updated in real time and configured to always provide the latest safety information.

[0882] (Claim 3)

[0883] The system according to claim 1, characterized in that a machine learning algorithm is used to generate the aforementioned disaster progression identification information in order to improve prediction accuracy.

[0884] "Example 2 of combining an emotion engine"

[0885] (Claim 1)

[0886] A means for analyzing visual information received from video collection means and generating disaster progress information,

[0887] A means for analyzing pedestrian flow data obtained from location information collection means and generating evacuation route design information,

[0888] A means for generating safe evacuation route information based on disaster progression information and evacuation route design information,

[0889] The means for providing the aforementioned safe evacuation route information to the communication device,

[0890] A means for determining the user's emotional state by analyzing voice data and facial recognition data,

[0891] A means of adjusting the information display method according to the user's emotional state,

[0892] A system that includes this.

[0893] (Claim 2)

[0894] The system according to claim 1, characterized in that the aforementioned safe evacuation route information is updated in real time.

[0895] (Claim 3)

[0896] The system according to claim 1, characterized in that an artificial intelligence algorithm is used to generate the disaster progress information.

[0897] "Application example 2 when combining with an emotional engine"

[0898] (Claim 1)

[0899] A means for analyzing video data acquired from a video analysis device and generating disaster progression information,

[0900] A means for analyzing pedestrian flow analysis data obtained from a position sensor device and generating evacuation route suggestion information,

[0901] A means for generating safe evacuation route data based on disaster progression information and evacuation route suggestion information,

[0902] A means for distributing the aforementioned safe evacuation route data to a mobile communication terminal,

[0903] A means for evaluating the emotional state of users using voice information and image recognition data, and for adjusting the information presentation method based on that evaluation,

[0904] A system that includes this.

[0905] (Claim 2)

[0906] The system according to claim 1, characterized in that the safe evacuation route data is updated immediately.

[0907] (Claim 3)

[0908] The system according to claim 1, characterized in that machine learning techniques are used to generate the disaster progression information. [Explanation of symbols]

[0909] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for analyzing video information received from a video acquisition device and generating disaster progression identification information, A means for analyzing pedestrian flow information acquired from a location data acquisition device and generating information for optimizing evacuation routes, A means for generating safe evacuation route information based on disaster progression identification information and evacuation route optimization information, A means for distributing the aforementioned safe evacuation route information to a communication terminal device, A system that includes this.

2. The system according to claim 1, characterized in that the safe evacuation route information is configured to be updated in real time.

3. The system according to claim 1, characterized in that a machine learning algorithm is used to generate the disaster progression identification information.

Images