system

Abstract

We provide the system. [Solution] A means of collecting and formatting image data, A means for learning using the aforementioned image data and past disaster data to construct a damage prediction model, A means for calculating the optimal evacuation route using the aforementioned damage prediction model, A means of providing calculated evacuation route information to a terminal, A means to make the evacuation route information available even when the terminal is offline, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Selecting an appropriate evacuation route during a disaster is often difficult due to insufficient information or network outages. In conventional evacuation guidance systems, it is difficult to quickly update routes considering real-time damage situations and terrain changes, and there are problems in terms of safety and convenience. Also, the provision of evacuation information available in an offline environment is not sufficient.

Means for Solving the Problems

[0005] This invention provides a system that enables real-time damage prediction and calculation of optimal evacuation routes during disasters. Specifically, it includes means for collecting and formatting image data, and means for an AI to learn from past disaster data based on this data and construct a damage prediction model. Furthermore, it includes means for calculating the optimal evacuation route using this model and distributing it to a terminal. In addition, even if the network is down, the evacuation route can be corrected in real time using evacuation information stored on the terminal. Furthermore, evacuation route guidance is provided using both voice and visual means, providing users with an intuitive and safe evacuation path.

[0006] "Image data" refers to visual information acquired using cameras, satellites, etc., recorded in digital format.

[0007] "Shaping" refers to a process or device that preprocesses collected data so that it can be efficiently processed by an AI model.

[0008] "Disaster data" refers to data that records information and damage situations related to natural disasters that have occurred in the past, such as earthquakes, floods, and typhoons.

[0009] "Means of learning" refers to the process by which an AI model uses input data to recognize patterns and features and improves its ability to predict future situations.

[0010] A "damage prediction model" is an AI algorithm that calculates potential future damage based on past disaster data and real-time information.

[0011] An "optimal evacuation route" is a calculated path designed to allow people to reach evacuation shelters or safe zones safely and quickly during a disaster.

[0012] "Means of distribution" refers to a process or device that transmits calculated information to a user's terminal via the internet or other means of communication.

[0013] "Network outage" refers to a state where communication is interrupted, making it impossible to send or receive data via the internet or other networks.

[0014] "Real-time correction" means performing calculations immediately based on the current situation and updating instructions and routes based on new information.

[0015] "Audio and visual guidance" refers to the process of providing information to users through audio and visual displays, used to aid intuitive understanding. [Brief explanation of the drawing]

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

Mode for Carrying Out the Invention

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

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

[0019] In the following embodiments, 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.

[0020] 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.

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

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

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

[0024] [First Embodiment]

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

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

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

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

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

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

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

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

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

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

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

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

[0037] This invention provides a system that enables safe and rapid evacuation during disasters. Through the cooperation of a server and terminals, this system provides real-time damage prediction and guidance on optimal evacuation routes based on the disaster situation.

[0038] The server acquires image data via the internet and uses this image data to analyze the terrain and building conditions. Furthermore, by utilizing past disaster data and training a generative AI model, it can predict damage. Based on the damage prediction model, the server calculates the optimal evacuation route in the event of a disaster and transmits this information to the terminal.

[0039] The device receives evacuation route information transmitted from the server and stores it in its storage so that it can be used offline. When a disaster occurs, the device prompts the user to evacuate using voice and visuals and guides them along the optimal evacuation route. This allows the user to intuitively begin evacuation.

[0040] For example, in the event of an earthquake, the server predicts damage based on the earthquake's epicenter and affected area, and uses that information to calculate evacuation routes. The terminal then uses the received information to guide the user to a safe route from their current location to a shelter, updating it in real time. In this way, the system balances real-time information with ensuring user safety.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The server periodically collects image data from the internet and formats it into a format that is easy for AI to process. This includes removing unnecessary data and extracting important features.

[0044] Step 2:

[0045] The server trains an AI model using formatted image data and historical disaster data. This training improves the AI ​​model's ability to predict damage and prepares it to calculate the optimal evacuation route during a disaster.

[0046] Step 3:

[0047] The server uses a trained AI model to predict damage in the event of a disaster and simulate the optimal evacuation route. This information is later delivered to the terminal.

[0048] Step 4:

[0049] The server sends calculated damage prediction information and evacuation route information to each user's terminal. To account for network outages, the data is saved to the terminal.

[0050] Step 5:

[0051] The device records received evacuation route information in its storage, preparing for any eventuality. The data is immediately available in the event of a disaster or network failure.

[0052] Step 6:

[0053] In the event of a disaster, the device will alert the user and immediately instruct them to evacuate safely. Route guidance will be displayed both audibly and visually to encourage the user to take swift action.

[0054] Step 7:

[0055] The user follows the instructions on the device and proceeds along the designated evacuation route. The device checks location information in real time and updates the information as needed to maintain a safe route.

[0056] (Example 1)

[0057] 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."

[0058] To ensure rapid and safe evacuation during disasters, real-time, highly accurate damage predictions and the provision of optimal evacuation routes are essential. However, the effectiveness of these systems is significantly reduced if networks are down or if evacuees are unable to intuitively initiate safe evacuation actions. Therefore, there is a need for technologies that provide evacuation information usable even in offline environments and enable dynamic route updates in response to disaster conditions.

[0059] 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.

[0060] In this invention, the server includes means for acquiring and processing video information, means for learning using the video information and past event information to construct an impact prediction model, and means for calculating the optimal movement path using the impact prediction model. This makes it possible to provide highly accurate evacuation information even when a network connection is not required, and to dynamically correct evacuation routes.

[0061] "Visual information" refers to visual data acquired by imaging devices such as cameras and satellites, and is used to evaluate the condition of terrain and buildings.

[0062] "Means of processing" refers to hardware and software used to analyze collected data and convert it into useful information, and computer programs are often used in this context.

[0063] "Past event information" refers to a collection of data on disasters and other important events that have occurred historically, and is used to build damage prediction models.

[0064] An "impact prediction model" refers to a mathematical or computational model that uses machine learning or statistical methods based on past data to estimate the impact of disasters and other events.

[0065] An "optimal route" is a route calculated to allow evacuees to reach their destination in the safest and fastest way possible, and is determined while taking into consideration the interests of all parties involved.

[0066] "A state where network connectivity is not required" refers to a state where the communication infrastructure is not functioning, meaning that normal internet and mobile phone communication are unavailable.

[0067] "Dynamically modifying evacuation routes" means continuously updating the routes provided to evacuees based on on-site conditions and new information, thereby presenting more appropriate routes.

[0068] This invention is a system that provides the optimal evacuation route in real time during a disaster, enabling rapid and safe evacuation. The server uses image acquisition devices such as cameras and satellites to acquire video information. The visual data obtained from these devices is stored in a database and used for later analysis.

[0069] The server uses image recognition libraries (e.g., TENSORFLOW® and OpenCV) to analyze collected video information and evaluate the terrain and building conditions. It also references historical data on disasters to compare it with past event information. Using this data, it constructs a generative AI model to predict the impact of disasters.

[0070] This generative AI model can generate prompt statements in various situations. For example, it might instruct the user to "predict the impact of an earthquake in this region." These prompt statements allow the AI ​​to obtain guidance for action under specific circumstances.

[0071] The server calculates the optimal travel route based on an impact prediction model. While GIS (Geographic Information System) is often used for this calculation, other geographic computing engines are also available. The calculated travel route information is provided to the terminal via a communication protocol (e.g., HTTP / HTTPS).

[0072] The device has a function to save received evacuation route information to its storage so that it can be used even in an offline environment. Furthermore, the device provides guidance on the evacuation route using voice and visuals, helping users to intuitively begin evacuation actions. This enables users to take appropriate actions intuitively.

[0073] For example, the terminal can display a prompt message to the user such as, "Please guide me to a safe route from my current location to the nearest evacuation shelter." In this way, the present invention realizes the provision of accurate and reliable information in emergencies.

[0074] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0075] Step 1:

[0076] The server acquires image information using cameras and satellites. The input is raw data from these image acquisition devices. Upon receiving this data, the server analyzes the images using an image recognition library. As a result, the terrain and building conditions are evaluated, and evaluation information is generated as output. This evaluation information includes the location of obstacles and the degree of building damage.

[0077] Step 2:

[0078] The server uses a generative AI model to predict impacts based on evaluation information and historical event data. The inputs are evaluation information and historical disaster data. Based on this, the AI ​​model calculates the impact and outputs a damage prediction. For example, it can predict which areas will suffer how much damage during an earthquake.

[0079] Step 3:

[0080] The server calculates the optimal evacuation route based on damage predictions. The input is the damage prediction results. Using GIS software, it outputs a safe evacuation route, not just the shortest route, while considering traffic congestion and road closures. This result is adjusted in real time according to changing conditions.

[0081] Step 4:

[0082] The server sends the calculated evacuation route information to the terminal. The input is the optimal evacuation route. This information is sent to the terminal using a communication protocol and delivered to the user. The output is the evacuation route information received by the user.

[0083] Step 5:

[0084] The terminal saves received evacuation route information to its storage so that it can be used offline. The input is evacuation route information sent from the server. After the saving process, the output is the saved evacuation route. This allows the terminal to be used even when the network is down.

[0085] Step 6:

[0086] The device provides the user with evacuation route guidance using both voice and visuals. The input is stored evacuation route information. Based on this information, the device uses its voice output device and display to present the information, generating visual and auditory instructions for the user as output. This allows the user to intuitively begin evacuation.

[0087] (Application Example 1)

[0088] 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."

[0089] Ensuring the safe and rapid evacuation of residents during a disaster has been difficult with conventional technology. In particular, when disaster information is not provided in real time, or when appropriate instructions are lacking based on local conditions, evacuation route options are often limited. Furthermore, responding to obstacles and changing conditions along actual evacuation routes remains a challenge.

[0090] 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.

[0091] In this invention, the server includes means for collecting and shaping image information; means for learning using the image information and past disaster information to construct a damage prediction model; means for calculating the optimal evacuation route using the damage prediction model; means for supplying the calculated evacuation route information to a user device; means for making the evacuation route information available even when the user device is offline; and means for overlaying and displaying obstacles on the evacuation route using augmented reality technology. This enables safe and rapid evacuation in the event of a disaster.

[0092] "Image information" refers to visual data acquired by cameras and sensors, which represents terrain, buildings, and the surrounding environment.

[0093] "Disaster information" refers to historical statistical data and real-time situational information regarding natural and man-made disasters, indicating the scale and scope of the disaster.

[0094] A "damage prediction model" is a model built using machine learning or artificial intelligence to predict the extent of damage in the event of a disaster.

[0095] An "evacuation route" refers to a path used by people to evacuate safely during a disaster, and it provides the most optimal route.

[0096] A "user device" refers to a device owned by the user, such as a smartphone or dedicated terminal, that receives and displays information and provides specific instructions to the user.

[0097] Augmented reality technology is a technique that overlays computer-generated information onto the real world's field of view, providing users with visual guidance.

[0098] This invention provides a system to support the safe evacuation of residents during disasters. The system mainly consists of a server and terminals. The server collects image information via the internet, formats it, and analyzes it. The hardware used is a cloud server, and the software used is OpenCV for image processing and TensorFlow for utilizing generative AI models. Based on the image information and past disaster information, the server constructs a damage prediction model and calculates the optimal evacuation route in the event of a disaster.

[0099] The terminal is a user device such as a smartphone or tablet that receives evacuation route information transmitted from a server. This information is stored on the terminal and can be used even when offline. The terminal also uses augmented reality technology to visually display obstacles and conditions along the actual evacuation route. Specifically, ARKit (iOS) and ARCore (Android®), which support AR technology, are used. Through the terminal, users can receive voice and visual guidance, enabling them to evacuate safely and intuitively.

[0100] For example, consider a scenario where an earthquake occurs and major evacuation routes are blocked in a certain area. The server quickly identifies the earthquake's epicenter and the extent of the damage, and calculates new evacuation routes using the latest damage prediction models. The calculated evacuation route information is transmitted to the terminal and clearly displayed to the user via augmented reality (AR) on the terminal. Through this process, the user can be sure to take the most appropriate evacuation action.

[0101] The generated AI model continuously improves the accuracy of damage predictions by incorporating new data during disasters. An example of a prompt message is, "Please re-evaluate evacuation routes within the town based on the latest disaster information." This allows the system to provide appropriate, situation-sensitive instructions in real time through its dedicated model.

[0102] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0103] Step 1:

[0104] The server collects image information from devices such as dedicated cameras and drones. The input consists of real-time visual data of terrain and buildings. This data is formatted using OpenCV, undergoing data processing such as noise reduction and cropping of necessary parts to generate foundational data for analysis.

[0105] Step 2:

[0106] The server trains a generative AI model using image data collected along with historical disaster information. The input is statistical data and simulation data from past disasters, and the output is a damage prediction model. This model is updated through an iterative learning process of loopback verification to more accurately predict the extent of damage during a disaster.

[0107] Step 3:

[0108] The server uses a damage prediction model to calculate the optimal evacuation route in the event of a disaster. It takes real-time earthquake and weather information as input and provides rapidly calculated evacuation route data as output. Using pathfinding algorithms such as the A algorithm, it evaluates multiple routes in a short time and selects the optimal one.

[0109] Step 4:

[0110] The server transmits the calculated evacuation route information to the user device. The input is the calculated evacuation route data, and the output is data converted to a format usable on the terminal. This information is optimized for storage for offline use on the terminal.

[0111] Step 5:

[0112] The terminal uses augmented reality technology to visually present the evacuation route to the user based on the received evacuation route information. Inputs include evacuation route data from the server and real-time video feeds from the terminal's camera. The output is an overlay of route information using AR display, showing the user a safe travel route within their field of view. By using ARKit or ARCore, virtual guidance displays are realized in the real world.

[0113] Step 6:

[0114] Users perform safe evacuation actions by following the voice and visual guidance displayed on the terminal. Input is visual and voice guidance from the terminal, and users complete a quick and safe evacuation by following these instructions. The system's guidance allows users to respond immediately to unexpected obstacles and changes.

[0115] 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.

[0116] This invention is a system that supports the safe evacuation of users during disasters, and in particular, provides evacuation guidance that takes into account the user's emotions. This system consists of a server, a terminal, and an emotion engine, and each part works closely together to provide the user with an optimal evacuation experience.

[0117] Under normal circumstances, the server collects image data and disaster data via the internet and uses this to build damage prediction models. The server also trains AI models to prepare to provide rapid and accurate evacuation routes in the event of a disaster.

[0118] The terminal uses evacuation route information received from the server to provide users with voice and visual guidance. Even when offline, it provides evacuation routes based on information stored on the terminal, allowing users to evacuate safely even when the network is down.

[0119] Furthermore, this system is equipped with an emotion engine that recognizes emotions from the user's facial expressions and voice. Based on the results of this emotion recognition, the device adjusts the tone of guidance and displayed content according to the user's level of stress and anxiety. For example, if the user is feeling anxious, the device will provide guidance in a calmer tone and display messages that promote relaxation, thereby increasing the user's sense of security.

[0120] As a concrete example, in the event of an earthquake, the server immediately predicts the damage and transmits the optimal evacuation route to the terminal. The user begins evacuating according to the terminal's instructions, but if the emotion engine detects the user's anxiety, more polite and calming evacuation instructions are provided. In this way, the system uses advanced technology to support safe evacuation while taking the user's emotions into consideration.

[0121] The following describes the processing flow.

[0122] Step 1:

[0123] The server periodically collects and formats image data and disaster-related data from the environment. This formatted data is then prepared for use in training AI models.

[0124] Step 2:

[0125] The server trains an AI model using formatted data. This model is designed to predict damage based on past disaster data and has the ability to quickly calculate evacuation routes.

[0126] Step 3:

[0127] In the event of a disaster, the server performs damage prediction and sends optimal evacuation route information, calculated based on this prediction, to the terminal. This information is updated in real time.

[0128] Step 4:

[0129] The terminal stores evacuation route information received from the server and is ready to present it to the user at any time. In the event of a network outage, the stored data can be used to allow the user to receive appropriate instructions even when offline.

[0130] Step 5:

[0131] The device uses the user's camera and microphone to recognize the user's emotional state through an emotion engine. This recognition is performed through facial expression analysis and voice intonation analysis.

[0132] Step 6:

[0133] When a user recognizes the need to evacuate, the device guides them to the optimal evacuation route using voice and visuals. The guidance tone and messages are adjusted according to the user's emotional state, as determined by the emotion engine, to reassure the user.

[0134] Step 7:

[0135] During evacuation, users follow instructions provided in a timely manner. Throughout this process, the device constantly monitors the user's emotions and updates information as needed. It provides users with a sense of security while offering flexible responses to ensure safe evacuation.

[0136] (Example 2)

[0137] 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".

[0138] Currently, route guidance for rapid and safe evacuation during disasters does not take into account the emotional state of users, and therefore fails to adequately address users who are experiencing fear or anxiety. Furthermore, there is a need for a system that can provide reliable evacuation instructions even in environments where communication is unavailable. These challenges need to be addressed.

[0139] 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.

[0140] In this invention, the server includes means for collecting and formatting image data, means for training with past disaster-related data to construct a damage prediction information processing model, and means for analyzing the user's emotional state and dynamically adjusting the content of evacuation guidance. This makes it possible to provide flexible and appropriate evacuation guidance that takes into account the user's emotions.

[0141] "Image data" refers to still images and videos that have been converted into a computer-processable format, representing a numerical representation of visual information.

[0142] "Disaster-related data" refers to information about natural and man-made disasters, including statistics and reports that are useful for past cases and predictions.

[0143] A "damage prediction information processing model" refers to a set of data analysis methods and algorithms trained to predict the impact and damage in the event of a disaster.

[0144] "Evacuation routes" refer to information that shows the optimal route for moving from danger to a safe place.

[0145] "Emotional state" refers to the psychological and physiological state that a user is experiencing at a particular moment, as assessed through facial expressions and voice data.

[0146] "Dynamic adjustment" refers to a process that automatically optimizes the content and expression of guidance in response to real-time changes in circumstances and input data.

[0147] "Wireless communication unavailable" refers to a state in which communication via the internet or mobile network is unavailable for any reason.

[0148] "Acoustic and visual information" refers to methods that include means of information transmission via sound or voice, and visually displayed information.

[0149] This disaster evacuation support system includes servers, terminals, and emotion recognition capabilities to provide users with safe and appropriate evacuation routes.

[0150] The server periodically collects disaster-related image and geographic data via the internet. This process uses APIs and scraping techniques to obtain data from meteorological agencies and geographic information systems. The collected data is stored in a database, and machine learning libraries (such as TensorFlow and PyTorch) are used to train disaster damage prediction information processing models.

[0151] The terminal receives information from the server to guide the user along an evacuation route. The terminal functions as a smartphone or a dedicated evacuation navigation device, combining map display and voice guidance. This utilizes common map information service APIs (e.g., Google® Maps API). Even in the event of communication failure, the terminal can provide guidance to the user based on pre-stored evacuation route information.

[0152] Furthermore, the device uses its built-in camera and microphone to analyze the user's emotional state. This emotion analysis utilizes image processing libraries (e.g., OpenCV) and speech analysis APIs (e.g., Google Cloud Speech-to-Text). Based on the analysis results, the device dynamically adjusts the tone of the evacuation guidance. Specifically, if it detects that the user is feeling anxious, it adds a calming message and softens the tone of the voice guidance.

[0153] As a concrete example, when an earthquake occurs, the server immediately predicts the damage and provides the terminal with the optimal evacuation route. The user begins evacuating according to the terminal's guidance, but at this time, the terminal detects the user's level of anxiety and provides more careful and calm guidance.

[0154] An example of a prompt message to be input into the generation AI model is: "In the event of an earthquake, generate quick and reassuring evacuation route guidance. Strive to alleviate user anxiety and ensure safe evacuation."

[0155] In this way, by adjusting the system according to the emotional state of the server, terminal, and user, the system provides effective and user-friendly evacuation guidance.

[0156] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0157] Step 1:

[0158] The server periodically collects disaster-related image and geographic data via the internet. Raw data obtained via API or web scraping is provided as input. This data is cleansed and formatted before being stored in the database. This process includes noise reduction and formatting standardization. The collected data is then used to produce clear information for later training of predictive models.

[0159] Step 2:

[0160] The server trains a generative AI model using the collected data. The inputs used are clean image data and historical disaster-related information stored in a database. This data is applied to the model using a machine learning framework (e.g., TensorFlow) to build an information processing model for predicting the occurrence and impact of disasters. The output is a trained, highly accurate damage prediction information processing model. This model is used to calculate rapid and accurate evacuation routes.

[0161] Step 3:

[0162] When a disaster is detected, the server uses a trained generative AI model to calculate the optimal evacuation route. The input to this process is real-time disaster information and geographical data. The output is the calculated evacuation route information. The server sends this information to terminals for use in issuing evacuation orders.

[0163] Step 4:

[0164] The terminal provides the user with audible and visual guidance based on evacuation route information received from the server. Inputs include evacuation information transmitted from the server and map data pre-installed on the terminal. Operationally, the terminal visually displays the route on a map and provides route guidance through speech synthesis. Output is evacuation instructions that the user can recognize visually and audibly.

[0165] Step 5:

[0166] The device uses emotion recognition technology to analyze the user's facial expressions and voice. Input is real-time data obtained from the camera and microphone. Based on this, it uses OpenCV and a voice analysis API to quantify the emotional state and determine what guidance tone is appropriate. Output is guidance content adjusted according to the user's psychological state. Specifically, if anxiety is detected, the device will repeat the explanation or provide guidance in a calmer tone.

[0167] This series of processes enables the system to provide user-friendly, safe, and reliable evacuation support.

[0168] (Application Example 2)

[0169] 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".

[0170] In times of disaster, a key challenge is ensuring that users can evacuate safely and quickly. In particular, in the chaotic conditions of a disaster, it is essential to provide appropriate evacuation route guidance that takes users' emotions into consideration. Furthermore, ensuring accurate and effective evacuation support even in situations where communication networks may be disrupted is another challenge.

[0171] 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.

[0172] In this invention, the server includes means for collecting and formatting image information, means for learning using the image information and past disaster information to construct a damage prediction structure, and means for calculating the optimal evacuation route. This makes it possible to provide evacuation route information offline even when the communication network is down, and to provide an environment in which people can evacuate with peace of mind by adjusting the guidance method according to the user's emotions.

[0173] "Image information" refers to visual data acquired in digital format, which is used for various purposes through analysis and processing.

[0174] "Disaster information" refers to data and history related to natural disasters and accidents, as well as information about the impacts and damages caused by them.

[0175] A "damage prediction structure" refers to a model used to estimate the nature and extent of potential future damage based on past data and current conditions.

[0176] An "evacuation route" refers to a path or route designed to allow people to evacuate safely in the event of a disaster.

[0177] A "terminal" refers to an information processing device used directly by the user, and includes smartphones and computers.

[0178] "Emotions" refer to the user's internal psychological state, including levels of stress and anxiety.

[0179] "Guidance methods" refer to the methods and formats used to convey instructions and information to users, and can include audio and visual methods.

[0180] In the system that implements this application example, a server plays a central role. The server collects image and disaster information via the internet before a disaster occurs and uses an AI model to build a damage prediction structure based on this information. This uses machine learning libraries such as Google's TensorFlow. The damage prediction structure is used to calculate evacuation routes that other devices can use.

[0181] Users receive evacuation guidance via devices such as smartphones. These devices receive evacuation route information from a server and utilize the Google Cloud Vision API and speech synthesis software to provide voice and visual guidance. Even offline, evacuation route guidance can be provided using information stored on the device.

[0182] Furthermore, the device uses its built-in camera and microphone to monitor and recognize the user's emotions. This allows it to display relaxing messages and adjust its guidance tone if the user's stress or anxiety levels are high. For example, if the emotion recognition engine detects anxiety during an evacuation, the device will display a message in a calm tone such as, "It's okay. We're guiding you to a safe route. Please stay calm."

[0183] This system can also utilize generative AI models to enhance user confidence and can be equipped with features to customize guidance based on user feedback.

[0184] Examples of prompt statements include the following:

[0185] Please write the program specifications for an app that reads the user's emotions during a disaster and guides them to a safe and reassuring evacuation route. Include appropriate voice tones and messages to alleviate user anxiety.

[0186] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0187] Step 1:

[0188] The server collects the latest image information and historical disaster information via the internet. Based on this input data, it uses image processing algorithms to format the data and convert it into a format suitable for training. The formatted data is then used as training data for the AI ​​model.

[0189] Step 2:

[0190] The server uses a generative AI model to construct a damage prediction structure based on formatted image information and disaster information as input. In this process, machine learning libraries such as TensorFlow are used to analyze the data and predict future damage. The output of this process is the risk level and recommended evacuation routes for each region.

[0191] Step 3:

[0192] The server sends the recommended evacuation route, which is the output of the AI ​​model, to the terminal. The terminal receives this information and prepares to provide the user with the most suitable evacuation route guidance.

[0193] Step 4:

[0194] The device uses a camera and microphone to capture the user's facial expressions and voice, and performs emotion recognition. It uses real-time video and audio data as input and analyzes it using an emotion analysis library. The output is a calculation of the user's stress and anxiety levels.

[0195] Step 5:

[0196] The device uses the output of sentiment analysis to adjust the voice tone and message content of evacuation route guidance. Specifically, it displays voice guidance in a calm tone to promote reassurance and messages with a relaxing effect. It also collects user feedback on an ongoing basis to improve the guidance methods.

[0197] Step 6:

[0198] Users will evacuate safely by following the instructions. Even when the device is offline, it will continue providing instructions using locally stored route information. When the network is restored, it will retrieve the latest evacuation route information from the server and update the instructions.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] [Second Embodiment]

[0203] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0204] 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.

[0205] 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).

[0206] 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.

[0207] 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.

[0208] 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).

[0209] 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.

[0210] 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.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] 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".

[0215] This invention provides a system that enables safe and rapid evacuation during disasters. Through the cooperation of a server and terminals, this system provides real-time damage prediction and guidance on optimal evacuation routes based on the disaster situation.

[0216] The server acquires image data via the internet and uses this image data to analyze the terrain and building conditions. Furthermore, by utilizing past disaster data and training a generative AI model, it can predict damage. Based on the damage prediction model, the server calculates the optimal evacuation route in the event of a disaster and transmits this information to the terminal.

[0217] The device receives evacuation route information transmitted from the server and stores it in its storage so that it can be used offline. When a disaster occurs, the device prompts the user to evacuate using voice and visuals and guides them along the optimal evacuation route. This allows the user to intuitively begin evacuation.

[0218] For example, in the event of an earthquake, the server predicts damage based on the earthquake's epicenter and affected area, and uses that information to calculate evacuation routes. The terminal then uses the received information to guide the user to a safe route from their current location to a shelter, updating it in real time. In this way, the system balances real-time information with ensuring user safety.

[0219] The following describes the processing flow.

[0220] Step 1:

[0221] The server periodically collects image data from the internet and formats it into a format that is easy for AI to process. This includes removing unnecessary data and extracting important features.

[0222] Step 2:

[0223] The server trains an AI model using formatted image data and historical disaster data. This training improves the AI ​​model's ability to predict damage and prepares it to calculate the optimal evacuation route during a disaster.

[0224] Step 3:

[0225] The server uses a trained AI model to predict damage in the event of a disaster and simulate the optimal evacuation route. This information is later delivered to the terminal.

[0226] Step 4:

[0227] The server sends calculated damage prediction information and evacuation route information to each user's terminal. To account for network outages, the data is saved to the terminal.

[0228] Step 5:

[0229] The device records received evacuation route information in its storage, preparing for any eventuality. The data is immediately available in the event of a disaster or network failure.

[0230] Step 6:

[0231] In the event of a disaster, the device will alert the user and immediately instruct them to evacuate safely. Route guidance will be displayed both audibly and visually to encourage the user to take swift action.

[0232] Step 7:

[0233] The user follows the instructions on the device and proceeds along the designated evacuation route. The device checks location information in real time and updates the information as needed to maintain a safe route.

[0234] (Example 1)

[0235] 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."

[0236] To ensure rapid and safe evacuation during disasters, real-time, highly accurate damage predictions and the provision of optimal evacuation routes are essential. However, the effectiveness of these systems is significantly reduced if networks are down or if evacuees are unable to intuitively initiate safe evacuation actions. Therefore, there is a need for technologies that provide evacuation information usable even in offline environments and enable dynamic route updates in response to disaster conditions.

[0237] 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.

[0238] In this invention, the server includes means for acquiring and processing video information, means for learning using the video information and past event information to construct an impact prediction model, and means for calculating the optimal movement path using the impact prediction model. This makes it possible to provide highly accurate evacuation information even when a network connection is not required, and to dynamically correct evacuation routes.

[0239] "Visual information" refers to visual data acquired by imaging devices such as cameras and satellites, and is used to evaluate the condition of terrain and buildings.

[0240] "Means of processing" refers to hardware and software used to analyze collected data and convert it into useful information, and computer programs are often used in this context.

[0241] "Past event information" refers to a collection of data on disasters and other important events that have occurred historically, and is used to build damage prediction models.

[0242] An "impact prediction model" refers to a mathematical or computational model that uses machine learning or statistical methods based on past data to estimate the impact of disasters and other events.

[0243] An "optimal route" is a route calculated to allow evacuees to reach their destination in the safest and fastest way possible, and is determined while taking into consideration the interests of all parties involved.

[0244] "A state where network connectivity is not required" refers to a state where the communication infrastructure is not functioning, meaning that normal internet and mobile phone communication are unavailable.

[0245] "Dynamically modifying evacuation routes" means continuously updating the routes provided to evacuees based on on-site conditions and new information, thereby presenting more appropriate routes.

[0246] This invention is a system that provides the optimal evacuation route in real time during a disaster, enabling rapid and safe evacuation. The server uses image acquisition devices such as cameras and satellites to acquire video information. The visual data obtained from these devices is stored in a database and used for later analysis.

[0247] The server uses image recognition libraries (e.g., TensorFlow and OpenCV) to analyze collected video information and evaluate the terrain and building conditions. It also references historical data related to disasters to compare it with past event information. Using this data, it builds a generative AI model to predict the impact of disasters.

[0248] This generative AI model can generate prompt statements in various situations. For example, it might instruct the user to "predict the impact of an earthquake in this region." These prompt statements allow the AI ​​to obtain guidance for action under specific circumstances.

[0249] The server calculates the optimal travel route based on an impact prediction model. While GIS (Geographic Information System) is often used for this calculation, other geographic computing engines are also available. The calculated travel route information is provided to the terminal via a communication protocol (e.g., HTTP / HTTPS).

[0250] The device has a function to save received evacuation route information to its storage so that it can be used even in an offline environment. Furthermore, the device provides guidance on the evacuation route using voice and visuals, helping users to intuitively begin evacuation actions. This enables users to take appropriate actions intuitively.

[0251] For example, the terminal can display a prompt message to the user such as, "Please guide me to a safe route from my current location to the nearest evacuation shelter." In this way, the present invention realizes the provision of accurate and reliable information in emergencies.

[0252] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0253] Step 1:

[0254] The server acquires image information using cameras and satellites. The input is raw data from these image acquisition devices. Upon receiving this data, the server analyzes the images using an image recognition library. As a result, the terrain and building conditions are evaluated, and evaluation information is generated as output. This evaluation information includes the location of obstacles and the degree of building damage.

[0255] Step 2:

[0256] The server uses a generative AI model to predict impacts based on evaluation information and historical event data. The inputs are evaluation information and historical disaster data. Based on this, the AI ​​model calculates the impact and outputs a damage prediction. For example, it can predict which areas will suffer how much damage during an earthquake.

[0257] Step 3:

[0258] The server calculates the optimal evacuation route based on damage predictions. The input is the damage prediction results. Using GIS software, it outputs a safe evacuation route, not just the shortest route, while considering traffic congestion and road closures. This result is adjusted in real time according to changing conditions.

[0259] Step 4:

[0260] The server sends the calculated evacuation route information to the terminal. The input is the optimal evacuation route. This information is sent to the terminal using a communication protocol and delivered to the user. The output is the evacuation route information received by the user.

[0261] Step 5:

[0262] The terminal saves received evacuation route information to its storage so that it can be used offline. The input is evacuation route information sent from the server. After the saving process, the output is the saved evacuation route. This allows the terminal to be used even when the network is down.

[0263] Step 6:

[0264] The device provides the user with evacuation route guidance using both voice and visuals. The input is stored evacuation route information. Based on this information, the device uses its voice output device and display to present the information, generating visual and auditory instructions for the user as output. This allows the user to intuitively begin evacuation.

[0265] (Application Example 1)

[0266] 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."

[0267] Ensuring the safe and rapid evacuation of residents during a disaster has been difficult with conventional technology. In particular, when disaster information is not provided in real time, or when appropriate instructions are lacking based on local conditions, evacuation route options are often limited. Furthermore, responding to obstacles and changing conditions along actual evacuation routes remains a challenge.

[0268] 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.

[0269] In this invention, the server includes means for collecting and shaping image information; means for learning using the image information and past disaster information to construct a damage prediction model; means for calculating the optimal evacuation route using the damage prediction model; means for supplying the calculated evacuation route information to a user device; means for making the evacuation route information available even when the user device is offline; and means for overlaying and displaying obstacles on the evacuation route using augmented reality technology. This enables safe and rapid evacuation in the event of a disaster.

[0270] "Image information" refers to visual data acquired by cameras and sensors, which represents terrain, buildings, and the surrounding environment.

[0271] "Disaster information" refers to historical statistical data and real-time situational information regarding natural and man-made disasters, indicating the scale and scope of the disaster.

[0272] A "damage prediction model" is a model built using machine learning or artificial intelligence to predict the extent of damage in the event of a disaster.

[0273] An "evacuation route" refers to a path used by people to evacuate safely during a disaster, and it provides the most optimal route.

[0274] A "user device" refers to a device owned by the user, such as a smartphone or dedicated terminal, that receives and displays information and provides specific instructions to the user.

[0275] Augmented reality technology is a technique that overlays computer-generated information onto the real world's field of view, providing users with visual guidance.

[0276] This invention provides a system to support the safe evacuation of residents during disasters. The system mainly consists of a server and terminals. The server collects image information via the internet, formats it, and analyzes it. The hardware used is a cloud server, and the software used is OpenCV for image processing and TensorFlow for utilizing generative AI models. Based on the image information and past disaster information, the server constructs a damage prediction model and calculates the optimal evacuation route in the event of a disaster.

[0277] The terminal is a user device such as a smartphone or tablet that receives evacuation route information transmitted from a server. This information is stored on the terminal and can be used even when offline. The terminal also uses augmented reality technology to visually display obstacles and conditions along the actual evacuation route. Specifically, ARKit (iOS) and ARCore (Android), which support AR technology, are used. Through the terminal, users can receive voice and visual guidance, enabling them to evacuate safely and intuitively.

[0278] For example, consider a scenario where an earthquake occurs and major evacuation routes are blocked in a certain area. The server quickly identifies the earthquake's epicenter and the extent of the damage, and calculates new evacuation routes using the latest damage prediction models. The calculated evacuation route information is transmitted to the terminal and clearly displayed to the user via augmented reality (AR) on the terminal. Through this process, the user can be sure to take the most appropriate evacuation action.

[0279] The generated AI model continuously improves the accuracy of damage predictions by incorporating new data during disasters. An example of a prompt message is, "Please re-evaluate evacuation routes within the town based on the latest disaster information." This allows the system to provide appropriate, situation-sensitive instructions in real time through its dedicated model.

[0280] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0281] Step 1:

[0282] The server collects image information from devices such as dedicated cameras and drones. As inputs, there are real-time visual data of terrain and buildings. This data is processed using OpenCV, and data processing such as noise removal and cropping of necessary parts is performed to generate basic data for analysis.

[0283] Step 2:

[0284] The server trains a generated AI model using the image information collected together with past disaster information. The inputs are statistical data and simulation data of past disasters, and as an output, a damage prediction model is obtained. This model is updated through an iterative learning process of cross-confirmation so that it can more accurately predict the damage situation during a disaster.

[0285] Step 3:

[0286] The server uses the damage prediction model to calculate the optimal evacuation route when a disaster occurs. As inputs, there are real-time earthquake and weather information, and as an output, quickly calculated evacuation route data is provided. Using a route search algorithm such as the A algorithm, multiple routes are evaluated in a short time, and the optimal one is selected.

[0287] Step 4:

[0288] The server transmits the calculated evacuation route information to the utilization device. The input is the calculated evacuation route data, and the output is data converted into a format that can be used on the terminal. This information is subjected to weight reduction processing in consideration of storage for offline use on the terminal.

[0289] Step 5:

[0290] The terminal uses augmented reality technology to visually present the evacuation route to the user based on the received evacuation route information. Inputs include evacuation route data from the server and real-time video feeds from the terminal's camera. The output is an overlay of route information using AR display, showing the user a safe travel route within their field of view. By using ARKit or ARCore, virtual guidance displays are realized in the real world.

[0291] Step 6:

[0292] Users perform safe evacuation actions by following the voice and visual guidance displayed on the terminal. Input is visual and voice guidance from the terminal, and users complete a quick and safe evacuation by following these instructions. The system's guidance allows users to respond immediately to unexpected obstacles and changes.

[0293] 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.

[0294] This invention is a system that supports the safe evacuation of users during disasters, and in particular, provides evacuation guidance that takes into account the user's emotions. This system consists of a server, a terminal, and an emotion engine, and each part works closely together to provide the user with an optimal evacuation experience.

[0295] Under normal circumstances, the server collects image data and disaster data via the internet and uses this to build damage prediction models. The server also trains AI models to prepare to provide rapid and accurate evacuation routes in the event of a disaster.

[0296] The terminal uses evacuation route information received from the server to provide users with voice and visual guidance. Even when offline, it provides evacuation routes based on information stored on the terminal, allowing users to evacuate safely even when the network is down.

[0297] Furthermore, this system is equipped with an emotion engine that recognizes emotions from the user's facial expressions and voice. Based on the results of this emotion recognition, the device adjusts the tone of guidance and displayed content according to the user's level of stress and anxiety. For example, if the user is feeling anxious, the device will provide guidance in a calmer tone and display messages that promote relaxation, thereby increasing the user's sense of security.

[0298] As a concrete example, in the event of an earthquake, the server immediately predicts the damage and transmits the optimal evacuation route to the terminal. The user begins evacuating according to the terminal's instructions, but if the emotion engine detects the user's anxiety, more polite and calming evacuation instructions are provided. In this way, the system uses advanced technology to support safe evacuation while taking the user's emotions into consideration.

[0299] The following describes the processing flow.

[0300] Step 1:

[0301] The server periodically collects and formats image data and disaster-related data from the environment. This formatted data is then prepared for use in training AI models.

[0302] Step 2:

[0303] The server trains an AI model using formatted data. This model is designed to predict damage based on past disaster data and has the ability to quickly calculate evacuation routes.

[0304] Step 3:

[0305] In the event of a disaster, the server performs damage prediction and sends optimal evacuation route information, calculated based on this prediction, to the terminal. This information is updated in real time.

[0306] Step 4:

[0307] The terminal saves the evacuation route information received from the server and makes preparations to be able to present it to the user at any time. When the network is down, by using the saved data, it is possible for the user to receive appropriate instructions even in an offline situation.

[0308] Step 5:

[0309] The terminal recognizes the user's emotional state through the user's camera and microphone by means of an emotion engine. This recognition is carried out through facial expression analysis and intonation analysis of the voice.

[0310] Step 6:

[0311] When the user recognizes the need for evacuation, the terminal guides the user to the optimal evacuation route both audibly and visually. By adjusting the tone and message of the guidance according to the user's emotional state obtained from the emotion engine, the user is reassured.

[0312] Step 7:

[0313] During evacuation, the user follows the instructions provided in a timely manner. In this process, the terminal constantly monitors the user's emotions and continues to update the information as necessary. It makes flexible responses to ensure a safe evacuation while providing the user with a sense of security.

[0314] (Example 2)

[0315] Next, Example 2 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0316] Currently, the route guidance for evacuating quickly and safely during a disaster does not take into account the emotional state of the users, so it cannot adequately respond to users who are feeling fear or anxiety. Also, there is a need for a system that can provide reliable evacuation instructions even in an environment where communication is not possible. It is necessary to solve these problems.

[0317] 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.

[0318] In this invention, the server includes means for collecting and formatting image data, means for training with past disaster-related data to construct a damage prediction information processing model, and means for analyzing the user's emotional state and dynamically adjusting the content of evacuation guidance. This makes it possible to provide flexible and appropriate evacuation guidance that takes into account the user's emotions.

[0319] "Image data" refers to still images and videos that have been converted into a computer-processable format, representing a numerical representation of visual information.

[0320] "Disaster-related data" refers to information about natural and man-made disasters, including statistics and reports that are useful for past cases and predictions.

[0321] A "damage prediction information processing model" refers to a set of data analysis methods and algorithms trained to predict the impact and damage in the event of a disaster.

[0322] "Evacuation routes" refer to information that shows the optimal route for moving from danger to a safe place.

[0323] "Emotional state" refers to the psychological and physiological state that a user is experiencing at a particular moment, as assessed through facial expressions and voice data.

[0324] "Dynamic adjustment" refers to a process that automatically optimizes the content and expression of guidance in response to real-time changes in circumstances and input data.

[0325] "Wireless communication unavailable" refers to a state in which communication via the internet or mobile network is unavailable for any reason.

[0326] "Acoustic and visual information" refers to methods that include means of information transmission via sound or voice, and visually displayed information.

[0327] This disaster evacuation support system includes servers, terminals, and emotion recognition capabilities to provide users with safe and appropriate evacuation routes.

[0328] The server periodically collects disaster-related image and geographic data via the internet. This process uses APIs and scraping techniques to obtain data from meteorological agencies and geographic information systems. The collected data is stored in a database, and machine learning libraries (such as TensorFlow and PyTorch) are used to train disaster damage prediction information processing models.

[0329] The terminal receives information from the server to guide the user along an evacuation route. The terminal functions as a smartphone or a dedicated evacuation navigation device, combining map display and voice guidance. This utilizes common map information service APIs (such as the Google Maps API). Even in the event of communication failure, the terminal can provide guidance to the user based on pre-stored evacuation route information.

[0330] Furthermore, the device uses its built-in camera and microphone to analyze the user's emotional state. This emotion analysis utilizes image processing libraries (e.g., OpenCV) and speech analysis APIs (e.g., Google Cloud Speech-to-Text). Based on the analysis results, the device dynamically adjusts the tone of the evacuation guidance. Specifically, if it detects that the user is feeling anxious, it adds a calming message and softens the tone of the voice guidance.

[0331] As a concrete example, when an earthquake occurs, the server immediately predicts the damage and provides the terminal with the optimal evacuation route. The user begins evacuating according to the terminal's guidance, but at this time, the terminal detects the user's level of anxiety and provides more careful and calm guidance.

[0332] An example of a prompt message to be input into the generation AI model is: "In the event of an earthquake, generate quick and reassuring evacuation route guidance. Strive to alleviate user anxiety and ensure safe evacuation."

[0333] In this way, by adjusting the system according to the emotional state of the server, terminal, and user, the system provides effective and user-friendly evacuation guidance.

[0334] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0335] Step 1:

[0336] The server periodically collects disaster-related image and geographic data via the internet. Raw data obtained via API or web scraping is provided as input. This data is cleansed and formatted before being stored in the database. This process includes noise reduction and formatting standardization. The collected data is then used to produce clear information for later training of predictive models.

[0337] Step 2:

[0338] The server trains a generative AI model using the collected data. The inputs used are clean image data and historical disaster-related information stored in a database. This data is applied to the model using a machine learning framework (e.g., TensorFlow) to build an information processing model for predicting the occurrence and impact of disasters. The output is a trained, highly accurate damage prediction information processing model. This model is used to calculate rapid and accurate evacuation routes.

[0339] Step 3:

[0340] When a disaster is detected, the server uses a trained generative AI model to calculate the optimal evacuation route. The input to this process is real-time disaster information and geographical data. The output is the calculated evacuation route information. The server sends this information to terminals for use in issuing evacuation orders.

[0341] Step 4:

[0342] The terminal provides the user with audible and visual guidance based on evacuation route information received from the server. Inputs include evacuation information transmitted from the server and map data pre-installed on the terminal. Operationally, the terminal visually displays the route on a map and provides route guidance through speech synthesis. Output is evacuation instructions that the user can recognize visually and audibly.

[0343] Step 5:

[0344] The device uses emotion recognition technology to analyze the user's facial expressions and voice. Input is real-time data obtained from the camera and microphone. Based on this, it uses OpenCV and a voice analysis API to quantify the emotional state and determine what guidance tone is appropriate. Output is guidance content adjusted according to the user's psychological state. Specifically, if anxiety is detected, the device will repeat the explanation or provide guidance in a calmer tone.

[0345] This series of processes enables the system to provide user-friendly, safe, and reliable evacuation support.

[0346] (Application Example 2)

[0347] 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."

[0348] In times of disaster, a key challenge is ensuring that users can evacuate safely and quickly. In particular, in the chaotic conditions of a disaster, it is essential to provide appropriate evacuation route guidance that takes users' emotions into consideration. Furthermore, ensuring accurate and effective evacuation support even in situations where communication networks may be disrupted is another challenge.

[0349] 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.

[0350] In this invention, the server includes means for collecting and formatting image information, means for learning using the image information and past disaster information to construct a damage prediction structure, and means for calculating the optimal evacuation route. This makes it possible to provide evacuation route information offline even when the communication network is down, and to provide an environment in which people can evacuate with peace of mind by adjusting the guidance method according to the user's emotions.

[0351] "Image information" refers to visual data acquired in digital format, which is used for various purposes through analysis and processing.

[0352] "Disaster information" refers to data and history related to natural disasters and accidents, as well as information about the impacts and damages caused by them.

[0353] A "damage prediction structure" refers to a model used to estimate the nature and extent of potential future damage based on past data and current conditions.

[0354] An "evacuation route" refers to a path or route designed to allow people to evacuate safely in the event of a disaster.

[0355] A "terminal" refers to an information processing device used directly by the user, and includes smartphones and computers.

[0356] "Emotions" refer to the user's internal psychological state, including levels of stress and anxiety.

[0357] "Guidance methods" refer to the methods and formats used to convey instructions and information to users, and can include audio and visual methods.

[0358] In the system that implements this application example, a server plays a central role. The server collects image and disaster information via the internet before a disaster occurs and uses an AI model to build a damage prediction structure based on this information. This uses machine learning libraries such as Google's TensorFlow. The damage prediction structure is used to calculate evacuation routes that other devices can use.

[0359] Users receive evacuation guidance via devices such as smartphones. These devices receive evacuation route information from a server and utilize the Google Cloud Vision API and speech synthesis software to provide voice and visual guidance. Even offline, evacuation route guidance can be provided using information stored on the device.

[0360] Furthermore, the device uses its built-in camera and microphone to monitor and recognize the user's emotions. This allows it to display relaxing messages and adjust its guidance tone if the user's stress or anxiety levels are high. For example, if the emotion recognition engine detects anxiety during an evacuation, the device will display a message in a calm tone such as, "It's okay. We're guiding you to a safe route. Please stay calm."

[0361] This system can also utilize generative AI models to enhance user confidence and can be equipped with features to customize guidance based on user feedback.

[0362] Examples of prompt statements include the following:

[0363] Please write the program specifications for an app that reads the user's emotions during a disaster and guides them to a safe and reassuring evacuation route. Include appropriate voice tones and messages to alleviate user anxiety.

[0364] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0365] Step 1:

[0366] The server collects the latest image information and historical disaster information via the internet. Based on this input data, it uses image processing algorithms to format the data and convert it into a format suitable for training. The formatted data is then used as training data for the AI ​​model.

[0367] Step 2:

[0368] The server uses a generative AI model to construct a damage prediction structure based on formatted image information and disaster information as input. In this process, machine learning libraries such as TensorFlow are used to analyze the data and predict future damage. The output of this process is the risk level and recommended evacuation routes for each region.

[0369] Step 3:

[0370] The server sends the recommended evacuation route, which is the output of the AI ​​model, to the terminal. The terminal receives this information and prepares to provide the user with the most suitable evacuation route guidance.

[0371] Step 4:

[0372] The device uses a camera and microphone to capture the user's facial expressions and voice, and performs emotion recognition. It uses real-time video and audio data as input and analyzes it using an emotion analysis library. The output is a calculation of the user's stress and anxiety levels.

[0373] Step 5:

[0374] The device uses the output of sentiment analysis to adjust the voice tone and message content of evacuation route guidance. Specifically, it displays voice guidance in a calm tone to promote reassurance and messages with a relaxing effect. It also collects user feedback on an ongoing basis to improve the guidance methods.

[0375] Step 6:

[0376] Users will evacuate safely by following the instructions. Even when the device is offline, it will continue providing instructions using locally stored route information. When the network is restored, it will retrieve the latest evacuation route information from the server and update the instructions.

[0377] 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.

[0378] 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.

[0379] 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.

[0380] [Third Embodiment]

[0381] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0382] 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.

[0383] 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).

[0384] 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.

[0385] 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.

[0386] 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).

[0387] 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.

[0388] 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.

[0389] 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.

[0390] 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.

[0391] 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.

[0392] 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".

[0393] This invention provides a system that enables safe and rapid evacuation during disasters. Through the cooperation of a server and terminals, this system provides real-time damage prediction and guidance on optimal evacuation routes based on the disaster situation.

[0394] The server acquires image data via the internet and uses this image data to analyze the terrain and building conditions. Furthermore, by utilizing past disaster data and training a generative AI model, it can predict damage. Based on the damage prediction model, the server calculates the optimal evacuation route in the event of a disaster and transmits this information to the terminal.

[0395] The device receives evacuation route information transmitted from the server and stores it in its storage so that it can be used offline. When a disaster occurs, the device prompts the user to evacuate using voice and visuals and guides them along the optimal evacuation route. This allows the user to intuitively begin evacuation.

[0396] For example, in the event of an earthquake, the server predicts damage based on the earthquake's epicenter and affected area, and uses that information to calculate evacuation routes. The terminal then uses the received information to guide the user to a safe route from their current location to a shelter, updating it in real time. In this way, the system balances real-time information with ensuring user safety.

[0397] The following describes the processing flow.

[0398] Step 1:

[0399] The server periodically collects image data from the internet and formats it into a format that is easy for AI to process. This includes removing unnecessary data and extracting important features.

[0400] Step 2:

[0401] The server trains an AI model using formatted image data and historical disaster data. This training improves the AI ​​model's ability to predict damage and prepares it to calculate the optimal evacuation route during a disaster.

[0402] Step 3:

[0403] The server uses a trained AI model to predict damage in the event of a disaster and simulate the optimal evacuation route. This information is later delivered to the terminal.

[0404] Step 4:

[0405] The server sends calculated damage prediction information and evacuation route information to each user's terminal. To account for network outages, the data is saved to the terminal.

[0406] Step 5:

[0407] The device records received evacuation route information in its storage, preparing for any eventuality. The data is immediately available in the event of a disaster or network failure.

[0408] Step 6:

[0409] In the event of a disaster, the device will alert the user and immediately instruct them to evacuate safely. Route guidance will be displayed both audibly and visually to encourage the user to take swift action.

[0410] Step 7:

[0411] The user follows the instructions on the device and proceeds along the designated evacuation route. The device checks location information in real time and updates the information as needed to maintain a safe route.

[0412] (Example 1)

[0413] 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."

[0414] To ensure rapid and safe evacuation during disasters, real-time, highly accurate damage predictions and the provision of optimal evacuation routes are essential. However, the effectiveness of these systems is significantly reduced if networks are down or if evacuees are unable to intuitively initiate safe evacuation actions. Therefore, there is a need for technologies that provide evacuation information usable even in offline environments and enable dynamic route updates in response to disaster conditions.

[0415] 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.

[0416] In this invention, the server includes means for acquiring and processing video information, means for learning using the video information and past event information to construct an impact prediction model, and means for calculating the optimal movement path using the impact prediction model. This makes it possible to provide highly accurate evacuation information even when a network connection is not required, and to dynamically correct evacuation routes.

[0417] "Visual information" refers to visual data acquired by imaging devices such as cameras and satellites, and is used to evaluate the condition of terrain and buildings.

[0418] "Means of processing" refers to hardware and software used to analyze collected data and convert it into useful information, and computer programs are often used in this context.

[0419] "Past event information" refers to a collection of data on disasters and other important events that have occurred historically, and is used to build damage prediction models.

[0420] An "impact prediction model" refers to a mathematical or computational model that uses machine learning or statistical methods based on past data to estimate the impact of disasters and other events.

[0421] An "optimal route" is a route calculated to allow evacuees to reach their destination in the safest and fastest way possible, and is determined while taking into consideration the interests of all parties involved.

[0422] "A state where network connectivity is not required" refers to a state where the communication infrastructure is not functioning, meaning that normal internet and mobile phone communication are unavailable.

[0423] "Dynamically modifying evacuation routes" means continuously updating the routes provided to evacuees based on on-site conditions and new information, thereby presenting more appropriate routes.

[0424] This invention is a system that provides the optimal evacuation route in real time during a disaster, enabling rapid and safe evacuation. The server uses image acquisition devices such as cameras and satellites to acquire video information. The visual data obtained from these devices is stored in a database and used for later analysis.

[0425] The server uses image recognition libraries (e.g., TensorFlow and OpenCV) to analyze collected video information and evaluate the terrain and building conditions. It also references historical data related to disasters to compare it with past event information. Using this data, it builds a generative AI model to predict the impact of disasters.

[0426] This generative AI model can generate prompt statements in various situations. For example, it might instruct the user to "predict the impact of an earthquake in this region." These prompt statements allow the AI ​​to obtain guidance for action under specific circumstances.

[0427] The server calculates the optimal travel route based on an impact prediction model. While GIS (Geographic Information System) is often used for this calculation, other geographic computing engines are also available. The calculated travel route information is provided to the terminal via a communication protocol (e.g., HTTP / HTTPS).

[0428] The device has a function to save received evacuation route information to its storage so that it can be used even in an offline environment. Furthermore, the device provides guidance on the evacuation route using voice and visuals, helping users to intuitively begin evacuation actions. This enables users to take appropriate actions intuitively.

[0429] For example, the terminal can display a prompt message to the user such as, "Please guide me to a safe route from my current location to the nearest evacuation shelter." In this way, the present invention realizes the provision of accurate and reliable information in emergencies.

[0430] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0431] Step 1:

[0432] The server acquires image information using cameras and satellites. The input is raw data from these image acquisition devices. Upon receiving this data, the server analyzes the images using an image recognition library. As a result, the terrain and building conditions are evaluated, and evaluation information is generated as output. This evaluation information includes the location of obstacles and the degree of building damage.

[0433] Step 2:

[0434] The server uses a generative AI model to predict impacts based on evaluation information and historical event data. The inputs are evaluation information and historical disaster data. Based on this, the AI ​​model calculates the impact and outputs a damage prediction. For example, it can predict which areas will suffer how much damage during an earthquake.

[0435] Step 3:

[0436] The server calculates the optimal evacuation route based on damage predictions. The input is the damage prediction results. Using GIS software, it outputs a safe evacuation route, not just the shortest route, while considering traffic congestion and road closures. This result is adjusted in real time according to changing conditions.

[0437] Step 4:

[0438] The server sends the calculated evacuation route information to the terminal. The input is the optimal evacuation route. This information is sent to the terminal using a communication protocol and delivered to the user. The output is the evacuation route information received by the user.

[0439] Step 5:

[0440] The terminal saves received evacuation route information to its storage so that it can be used offline. The input is evacuation route information sent from the server. After the saving process, the output is the saved evacuation route. This allows the terminal to be used even when the network is down.

[0441] Step 6:

[0442] The device provides the user with evacuation route guidance using both voice and visuals. The input is stored evacuation route information. Based on this information, the device uses its voice output device and display to present the information, generating visual and auditory instructions for the user as output. This allows the user to intuitively begin evacuation.

[0443] (Application Example 1)

[0444] 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."

[0445] Ensuring the safe and rapid evacuation of residents during a disaster has been difficult with conventional technology. In particular, when disaster information is not provided in real time, or when appropriate instructions are lacking based on local conditions, evacuation route options are often limited. Furthermore, responding to obstacles and changing conditions along actual evacuation routes remains a challenge.

[0446] 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.

[0447] In this invention, the server includes means for collecting and shaping image information; means for learning using the image information and past disaster information to construct a damage prediction model; means for calculating the optimal evacuation route using the damage prediction model; means for supplying the calculated evacuation route information to a user device; means for making the evacuation route information available even when the user device is offline; and means for overlaying and displaying obstacles on the evacuation route using augmented reality technology. This enables safe and rapid evacuation in the event of a disaster.

[0448] "Image information" refers to visual data acquired by cameras and sensors, which represents terrain, buildings, and the surrounding environment.

[0449] "Disaster information" refers to historical statistical data and real-time situational information regarding natural and man-made disasters, indicating the scale and scope of the disaster.

[0450] A "damage prediction model" is a model built using machine learning or artificial intelligence to predict the extent of damage in the event of a disaster.

[0451] An "evacuation route" refers to a path used by people to evacuate safely during a disaster, and it provides the most optimal route.

[0452] A "user device" refers to a device owned by the user, such as a smartphone or dedicated terminal, that receives and displays information and provides specific instructions to the user.

[0453] Augmented reality technology is a technique that overlays computer-generated information onto the real world's field of view, providing users with visual guidance.

[0454] This invention provides a system to support the safe evacuation of residents during disasters. The system mainly consists of a server and terminals. The server collects image information via the internet, formats it, and analyzes it. The hardware used is a cloud server, and the software used is OpenCV for image processing and TensorFlow for utilizing generative AI models. Based on the image information and past disaster information, the server constructs a damage prediction model and calculates the optimal evacuation route in the event of a disaster.

[0455] The terminal is a user device such as a smartphone or tablet that receives evacuation route information transmitted from a server. This information is stored on the terminal and can be used even when offline. The terminal also uses augmented reality technology to visually display obstacles and conditions along the actual evacuation route. Specifically, ARKit (iOS) and ARCore (Android), which support AR technology, are used. Through the terminal, users can receive voice and visual guidance, enabling them to evacuate safely and intuitively.

[0456] For example, consider a scenario where an earthquake occurs and major evacuation routes are blocked in a certain area. The server quickly identifies the earthquake's epicenter and the extent of the damage, and calculates new evacuation routes using the latest damage prediction models. The calculated evacuation route information is transmitted to the terminal and clearly displayed to the user via augmented reality (AR) on the terminal. Through this process, the user can be sure to take the most appropriate evacuation action.

[0457] The generated AI model continuously improves the accuracy of damage predictions by incorporating new data during disasters. An example of a prompt message is, "Please re-evaluate evacuation routes within the town based on the latest disaster information." This allows the system to provide appropriate, situation-sensitive instructions in real time through its dedicated model.

[0458] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0459] Step 1:

[0460] The server collects image information from devices such as dedicated cameras and drones. The input consists of real-time visual data of terrain and buildings. This data is formatted using OpenCV, undergoing data processing such as noise reduction and cropping of necessary parts to generate foundational data for analysis.

[0461] Step 2:

[0462] The server trains a generative AI model using image data collected along with historical disaster information. The input is statistical data and simulation data from past disasters, and the output is a damage prediction model. This model is updated through an iterative learning process of loopback verification to more accurately predict the extent of damage during a disaster.

[0463] Step 3:

[0464] The server uses a damage prediction model to calculate the optimal evacuation route in the event of a disaster. It takes real-time earthquake and weather information as input and provides rapidly calculated evacuation route data as output. Using pathfinding algorithms such as the A algorithm, it evaluates multiple routes in a short time and selects the optimal one.

[0465] Step 4:

[0466] The server transmits the calculated evacuation route information to the user device. The input is the calculated evacuation route data, and the output is data converted to a format usable on the terminal. This information is optimized for storage for offline use on the terminal.

[0467] Step 5:

[0468] The terminal uses augmented reality technology to visually present the evacuation route to the user based on the received evacuation route information. Inputs include evacuation route data from the server and real-time video feeds from the terminal's camera. The output is an overlay of route information using AR display, showing the user a safe travel route within their field of view. By using ARKit or ARCore, virtual guidance displays are realized in the real world.

[0469] Step 6:

[0470] Users perform safe evacuation actions by following the voice and visual guidance displayed on the terminal. Input is visual and voice guidance from the terminal, and users complete a quick and safe evacuation by following these instructions. The system's guidance allows users to respond immediately to unexpected obstacles and changes.

[0471] 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.

[0472] This invention is a system that supports the safe evacuation of users during disasters, and in particular, provides evacuation guidance that takes into account the user's emotions. This system consists of a server, a terminal, and an emotion engine, and each part works closely together to provide the user with an optimal evacuation experience.

[0473] Under normal circumstances, the server collects image data and disaster data via the internet and uses this to build damage prediction models. The server also trains AI models to prepare to provide rapid and accurate evacuation routes in the event of a disaster.

[0474] The terminal uses evacuation route information received from the server to provide users with voice and visual guidance. Even when offline, it provides evacuation routes based on information stored on the terminal, allowing users to evacuate safely even when the network is down.

[0475] Furthermore, this system is equipped with an emotion engine that recognizes emotions from the user's facial expressions and voice. Based on the results of this emotion recognition, the device adjusts the tone of guidance and displayed content according to the user's level of stress and anxiety. For example, if the user is feeling anxious, the device will provide guidance in a calmer tone and display messages that promote relaxation, thereby increasing the user's sense of security.

[0476] As a concrete example, in the event of an earthquake, the server immediately predicts the damage and transmits the optimal evacuation route to the terminal. The user begins evacuating according to the terminal's instructions, but if the emotion engine detects the user's anxiety, more polite and calming evacuation instructions are provided. In this way, the system uses advanced technology to support safe evacuation while taking the user's emotions into consideration.

[0477] The following describes the processing flow.

[0478] Step 1:

[0479] The server periodically collects and formats image data and disaster-related data from the environment. This formatted data is then prepared for use in training AI models.

[0480] Step 2:

[0481] The server trains an AI model using formatted data. This model is designed to predict damage based on past disaster data and has the ability to quickly calculate evacuation routes.

[0482] Step 3:

[0483] In the event of a disaster, the server performs damage prediction and sends optimal evacuation route information, calculated based on this prediction, to the terminal. This information is updated in real time.

[0484] Step 4:

[0485] The terminal stores evacuation route information received from the server and is ready to present it to the user at any time. In the event of a network outage, the stored data can be used to allow the user to receive appropriate instructions even when offline.

[0486] Step 5:

[0487] The device uses the user's camera and microphone to recognize the user's emotional state through an emotion engine. This recognition is performed through facial expression analysis and voice intonation analysis.

[0488] Step 6:

[0489] When a user recognizes the need to evacuate, the device guides them to the optimal evacuation route using voice and visuals. The guidance tone and messages are adjusted according to the user's emotional state, as determined by the emotion engine, to reassure the user.

[0490] Step 7:

[0491] During evacuation, users follow instructions provided in a timely manner. Throughout this process, the device constantly monitors the user's emotions and updates information as needed. It provides users with a sense of security while offering flexible responses to ensure safe evacuation.

[0492] (Example 2)

[0493] 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."

[0494] Currently, route guidance for rapid and safe evacuation during disasters does not take into account the emotional state of users, and therefore fails to adequately address users who are experiencing fear or anxiety. Furthermore, there is a need for a system that can provide reliable evacuation instructions even in environments where communication is unavailable. These challenges need to be addressed.

[0495] 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.

[0496] In this invention, the server includes means for collecting and formatting image data, means for training with past disaster-related data to construct a damage prediction information processing model, and means for analyzing the user's emotional state and dynamically adjusting the content of evacuation guidance. This makes it possible to provide flexible and appropriate evacuation guidance that takes into account the user's emotions.

[0497] "Image data" refers to still images and videos that have been converted into a computer-processable format, representing a numerical representation of visual information.

[0498] "Disaster-related data" refers to information about natural and man-made disasters, including statistics and reports that are useful for past cases and predictions.

[0499] A "damage prediction information processing model" refers to a set of data analysis methods and algorithms trained to predict the impact and damage in the event of a disaster.

[0500] "Evacuation routes" refer to information that shows the optimal route for moving from danger to a safe place.

[0501] "Emotional state" refers to the psychological and physiological state that a user is experiencing at a particular moment, as assessed through facial expressions and voice data.

[0502] "Dynamic adjustment" refers to a process that automatically optimizes the content and expression of guidance in response to real-time changes in circumstances and input data.

[0503] "Wireless communication unavailable" refers to a state in which communication via the internet or mobile network is unavailable for any reason.

[0504] "Acoustic and visual information" refers to methods that include means of information transmission via sound or voice, and visually displayed information.

[0505] This disaster evacuation support system includes servers, terminals, and emotion recognition capabilities to provide users with safe and appropriate evacuation routes.

[0506] The server periodically collects disaster-related image and geographic data via the internet. This process uses APIs and scraping techniques to obtain data from meteorological agencies and geographic information systems. The collected data is stored in a database, and machine learning libraries (such as TensorFlow and PyTorch) are used to train disaster damage prediction information processing models.

[0507] The terminal receives information from the server to guide the user along an evacuation route. The terminal functions as a smartphone or a dedicated evacuation navigation device, combining map display and voice guidance. This utilizes common map information service APIs (such as the Google Maps API). Even in the event of communication failure, the terminal can provide guidance to the user based on pre-stored evacuation route information.

[0508] Furthermore, the device uses its built-in camera and microphone to analyze the user's emotional state. This emotion analysis utilizes image processing libraries (e.g., OpenCV) and speech analysis APIs (e.g., Google Cloud Speech-to-Text). Based on the analysis results, the device dynamically adjusts the tone of the evacuation guidance. Specifically, if it detects that the user is feeling anxious, it adds a calming message and softens the tone of the voice guidance.

[0509] As a concrete example, when an earthquake occurs, the server immediately predicts the damage and provides the terminal with the optimal evacuation route. The user begins evacuating according to the terminal's guidance, but at this time, the terminal detects the user's level of anxiety and provides more careful and calm guidance.

[0510] An example of a prompt message to be input into the generation AI model is: "In the event of an earthquake, generate quick and reassuring evacuation route guidance. Strive to alleviate user anxiety and ensure safe evacuation."

[0511] In this way, by adjusting the system according to the emotional state of the server, terminal, and user, the system provides effective and user-friendly evacuation guidance.

[0512] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0513] Step 1:

[0514] The server periodically collects disaster-related image and geographic data via the internet. Raw data obtained via API or web scraping is provided as input. This data is cleansed and formatted before being stored in the database. This process includes noise reduction and formatting standardization. The collected data is then used to produce clear information for later training of predictive models.

[0515] Step 2:

[0516] The server trains a generative AI model using the collected data. The inputs used are clean image data and historical disaster-related information stored in a database. This data is applied to the model using a machine learning framework (e.g., TensorFlow) to build an information processing model for predicting the occurrence and impact of disasters. The output is a trained, highly accurate damage prediction information processing model. This model is used to calculate rapid and accurate evacuation routes.

[0517] Step 3:

[0518] When a disaster is detected, the server uses a trained generative AI model to calculate the optimal evacuation route. The input to this process is real-time disaster information and geographical data. The output is the calculated evacuation route information. The server sends this information to terminals for use in issuing evacuation orders.

[0519] Step 4:

[0520] The terminal provides the user with audible and visual guidance based on evacuation route information received from the server. Inputs include evacuation information transmitted from the server and map data pre-installed on the terminal. Operationally, the terminal visually displays the route on a map and provides route guidance through speech synthesis. Output is evacuation instructions that the user can recognize visually and audibly.

[0521] Step 5:

[0522] The device uses emotion recognition technology to analyze the user's facial expressions and voice. Input is real-time data obtained from the camera and microphone. Based on this, it uses OpenCV and a voice analysis API to quantify the emotional state and determine what guidance tone is appropriate. Output is guidance content adjusted according to the user's psychological state. Specifically, if anxiety is detected, the device will repeat the explanation or provide guidance in a calmer tone.

[0523] This series of processes enables the system to provide user-friendly, safe, and reliable evacuation support.

[0524] (Application Example 2)

[0525] 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."

[0526] In times of disaster, a key challenge is ensuring that users can evacuate safely and quickly. In particular, in the chaotic conditions of a disaster, it is essential to provide appropriate evacuation route guidance that takes users' emotions into consideration. Furthermore, ensuring accurate and effective evacuation support even in situations where communication networks may be disrupted is another challenge.

[0527] 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.

[0528] In this invention, the server includes means for collecting and formatting image information, means for learning using the image information and past disaster information to construct a damage prediction structure, and means for calculating the optimal evacuation route. This makes it possible to provide evacuation route information offline even when the communication network is down, and to provide an environment in which people can evacuate with peace of mind by adjusting the guidance method according to the user's emotions.

[0529] "Image information" refers to visual data acquired in digital format, which is used for various purposes through analysis and processing.

[0530] "Disaster information" refers to data and history related to natural disasters and accidents, as well as information about the impacts and damages caused by them.

[0531] A "damage prediction structure" refers to a model used to estimate the nature and extent of potential future damage based on past data and current conditions.

[0532] An "evacuation route" refers to a path or route designed to allow people to evacuate safely in the event of a disaster.

[0533] A "terminal" refers to an information processing device used directly by the user, and includes smartphones and computers.

[0534] "Emotions" refer to the user's internal psychological state, including levels of stress and anxiety.

[0535] "Guidance methods" refer to the methods and formats used to convey instructions and information to users, and can include audio and visual methods.

[0536] In the system that implements this application example, a server plays a central role. The server collects image and disaster information via the internet before a disaster occurs and uses an AI model to build a damage prediction structure based on this information. This uses machine learning libraries such as Google's TensorFlow. The damage prediction structure is used to calculate evacuation routes that other devices can use.

[0537] Users receive evacuation guidance via devices such as smartphones. These devices receive evacuation route information from a server and utilize the Google Cloud Vision API and speech synthesis software to provide voice and visual guidance. Even offline, evacuation route guidance can be provided using information stored on the device.

[0538] Furthermore, the device uses its built-in camera and microphone to monitor and recognize the user's emotions. This allows it to display relaxing messages and adjust its guidance tone if the user's stress or anxiety levels are high. For example, if the emotion recognition engine detects anxiety during an evacuation, the device will display a message in a calm tone such as, "It's okay. We're guiding you to a safe route. Please stay calm."

[0539] This system can also utilize generative AI models to enhance user confidence and can be equipped with features to customize guidance based on user feedback.

[0540] Examples of prompt statements include the following:

[0541] Please write the program specifications for an app that reads the user's emotions during a disaster and guides them to a safe and reassuring evacuation route. Include appropriate voice tones and messages to alleviate user anxiety.

[0542] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0543] Step 1:

[0544] The server collects the latest image information and historical disaster information via the internet. Based on this input data, it uses image processing algorithms to format the data and convert it into a format suitable for training. The formatted data is then used as training data for the AI ​​model.

[0545] Step 2:

[0546] The server uses a generative AI model to construct a damage prediction structure based on formatted image information and disaster information as input. In this process, machine learning libraries such as TensorFlow are used to analyze the data and predict future damage. The output of this process is the risk level and recommended evacuation routes for each region.

[0547] Step 3:

[0548] The server sends the recommended evacuation route, which is the output of the AI ​​model, to the terminal. The terminal receives this information and prepares to provide the user with the most suitable evacuation route guidance.

[0549] Step 4:

[0550] The device uses a camera and microphone to capture the user's facial expressions and voice, and performs emotion recognition. It uses real-time video and audio data as input and analyzes it using an emotion analysis library. The output is a calculation of the user's stress and anxiety levels.

[0551] Step 5:

[0552] The device uses the output of sentiment analysis to adjust the voice tone and message content of evacuation route guidance. Specifically, it displays voice guidance in a calm tone to promote reassurance and messages with a relaxing effect. It also collects user feedback on an ongoing basis to improve the guidance methods.

[0553] Step 6:

[0554] Users will evacuate safely by following the instructions. Even when the device is offline, it will continue providing instructions using locally stored route information. When the network is restored, it will retrieve the latest evacuation route information from the server and update the instructions.

[0555] 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.

[0556] 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.

[0557] 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.

[0558] [Fourth Embodiment]

[0559] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0560] 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.

[0561] 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).

[0562] 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.

[0563] 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.

[0564] 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).

[0565] 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.

[0566] 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.

[0567] 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.

[0568] 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.

[0569] 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.

[0570] 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.

[0571] 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".

[0572] This invention provides a system that enables safe and rapid evacuation during disasters. Through the cooperation of a server and terminals, this system provides real-time damage prediction and guidance on optimal evacuation routes based on the disaster situation.

[0573] The server acquires image data via the internet and uses this image data to analyze the terrain and building conditions. Furthermore, by utilizing past disaster data and training a generative AI model, it can predict damage. Based on the damage prediction model, the server calculates the optimal evacuation route in the event of a disaster and transmits this information to the terminal.

[0574] The device receives evacuation route information transmitted from the server and stores it in its storage so that it can be used offline. When a disaster occurs, the device prompts the user to evacuate using voice and visuals and guides them along the optimal evacuation route. This allows the user to intuitively begin evacuation.

[0575] For example, in the event of an earthquake, the server predicts damage based on the earthquake's epicenter and affected area, and uses that information to calculate evacuation routes. The terminal then uses the received information to guide the user to a safe route from their current location to a shelter, updating it in real time. In this way, the system balances real-time information with ensuring user safety.

[0576] The following describes the processing flow.

[0577] Step 1:

[0578] The server periodically collects image data from the internet and formats it into a format that is easy for AI to process. This includes removing unnecessary data and extracting important features.

[0579] Step 2:

[0580] The server trains an AI model using formatted image data and historical disaster data. This training improves the AI ​​model's ability to predict damage and prepares it to calculate the optimal evacuation route during a disaster.

[0581] Step 3:

[0582] The server uses a trained AI model to predict damage in the event of a disaster and simulate the optimal evacuation route. This information is later delivered to the terminal.

[0583] Step 4:

[0584] The server sends calculated damage prediction information and evacuation route information to each user's terminal. To account for network outages, the data is saved to the terminal.

[0585] Step 5:

[0586] The device records received evacuation route information in its storage, preparing for any eventuality. The data is immediately available in the event of a disaster or network failure.

[0587] Step 6:

[0588] In the event of a disaster, the device will alert the user and immediately instruct them to evacuate safely. Route guidance will be displayed both audibly and visually to encourage the user to take swift action.

[0589] Step 7:

[0590] The user follows the instructions on the device and proceeds along the designated evacuation route. The device checks location information in real time and updates the information as needed to maintain a safe route.

[0591] (Example 1)

[0592] 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".

[0593] To ensure rapid and safe evacuation during disasters, real-time, highly accurate damage predictions and the provision of optimal evacuation routes are essential. However, the effectiveness of these systems is significantly reduced if networks are down or if evacuees are unable to intuitively initiate safe evacuation actions. Therefore, there is a need for technologies that provide evacuation information usable even in offline environments and enable dynamic route updates in response to disaster conditions.

[0594] 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.

[0595] In this invention, the server includes means for acquiring and processing video information, means for learning using the video information and past event information to construct an impact prediction model, and means for calculating the optimal movement path using the impact prediction model. This makes it possible to provide highly accurate evacuation information even when a network connection is not required, and to dynamically correct evacuation routes.

[0596] "Visual information" refers to visual data acquired by imaging devices such as cameras and satellites, and is used to evaluate the condition of terrain and buildings.

[0597] "Means of processing" refers to hardware and software used to analyze collected data and convert it into useful information, and computer programs are often used in this context.

[0598] "Past event information" refers to a collection of data on disasters and other important events that have occurred historically, and is used to build damage prediction models.

[0599] An "impact prediction model" refers to a mathematical or computational model that uses machine learning or statistical methods based on past data to estimate the impact of disasters and other events.

[0600] An "optimal route" is a route calculated to allow evacuees to reach their destination in the safest and fastest way possible, and is determined while taking into consideration the interests of all parties involved.

[0601] "A state where network connectivity is not required" refers to a state where the communication infrastructure is not functioning, meaning that normal internet and mobile phone communication are unavailable.

[0602] "Dynamically modifying evacuation routes" means continuously updating the routes provided to evacuees based on on-site conditions and new information, thereby presenting more appropriate routes.

[0603] This invention is a system that provides the optimal evacuation route in real time during a disaster, enabling rapid and safe evacuation. The server uses image acquisition devices such as cameras and satellites to acquire video information. The visual data obtained from these devices is stored in a database and used for later analysis.

[0604] The server uses image recognition libraries (e.g., TensorFlow and OpenCV) to analyze collected video information and evaluate the terrain and building conditions. It also references historical data related to disasters to compare it with past event information. Using this data, it builds a generative AI model to predict the impact of disasters.

[0605] This generative AI model can generate prompt statements in various situations. For example, it might instruct the user to "predict the impact of an earthquake in this region." These prompt statements allow the AI ​​to obtain guidance for action under specific circumstances.

[0606] The server calculates the optimal travel route based on an impact prediction model. While GIS (Geographic Information System) is often used for this calculation, other geographic computing engines are also available. The calculated travel route information is provided to the terminal via a communication protocol (e.g., HTTP / HTTPS).

[0607] The device has a function to save received evacuation route information to its storage so that it can be used even in an offline environment. Furthermore, the device provides guidance on the evacuation route using voice and visuals, helping users to intuitively begin evacuation actions. This enables users to take appropriate actions intuitively.

[0608] For example, the terminal can display a prompt message to the user such as, "Please guide me to a safe route from my current location to the nearest evacuation shelter." In this way, the present invention realizes the provision of accurate and reliable information in emergencies.

[0609] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0610] Step 1:

[0611] The server acquires image information using cameras and satellites. The input is raw data from these image acquisition devices. Upon receiving this data, the server analyzes the images using an image recognition library. As a result, the terrain and building conditions are evaluated, and evaluation information is generated as output. This evaluation information includes the location of obstacles and the degree of building damage.

[0612] Step 2:

[0613] The server uses a generative AI model to predict impacts based on evaluation information and historical event data. The inputs are evaluation information and historical disaster data. Based on this, the AI ​​model calculates the impact and outputs a damage prediction. For example, it can predict which areas will suffer how much damage during an earthquake.

[0614] Step 3:

[0615] The server calculates the optimal evacuation route based on damage predictions. The input is the damage prediction results. Using GIS software, it outputs a safe evacuation route, not just the shortest route, while considering traffic congestion and road closures. This result is adjusted in real time according to changing conditions.

[0616] Step 4:

[0617] The server sends the calculated evacuation route information to the terminal. The input is the optimal evacuation route. This information is sent to the terminal using a communication protocol and delivered to the user. The output is the evacuation route information received by the user.

[0618] Step 5:

[0619] The terminal saves received evacuation route information to its storage so that it can be used offline. The input is evacuation route information sent from the server. After the saving process, the output is the saved evacuation route. This allows the terminal to be used even when the network is down.

[0620] Step 6:

[0621] The device provides the user with evacuation route guidance using both voice and visuals. The input is stored evacuation route information. Based on this information, the device uses its voice output device and display to present the information, generating visual and auditory instructions for the user as output. This allows the user to intuitively begin evacuation.

[0622] (Application Example 1)

[0623] 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".

[0624] Ensuring the safe and rapid evacuation of residents during a disaster has been difficult with conventional technology. In particular, when disaster information is not provided in real time, or when appropriate instructions are lacking based on local conditions, evacuation route options are often limited. Furthermore, responding to obstacles and changing conditions along actual evacuation routes remains a challenge.

[0625] 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.

[0626] In this invention, the server includes means for collecting and shaping image information; means for learning using the image information and past disaster information to construct a damage prediction model; means for calculating the optimal evacuation route using the damage prediction model; means for supplying the calculated evacuation route information to a user device; means for making the evacuation route information available even when the user device is offline; and means for overlaying and displaying obstacles on the evacuation route using augmented reality technology. This enables safe and rapid evacuation in the event of a disaster.

[0627] "Image information" refers to visual data acquired by cameras and sensors, which represents terrain, buildings, and the surrounding environment.

[0628] "Disaster information" refers to historical statistical data and real-time situational information regarding natural and man-made disasters, indicating the scale and scope of the disaster.

[0629] A "damage prediction model" is a model built using machine learning or artificial intelligence to predict the extent of damage in the event of a disaster.

[0630] An "evacuation route" refers to a path used by people to evacuate safely during a disaster, and it provides the most optimal route.

[0631] A "user device" refers to a device owned by the user, such as a smartphone or dedicated terminal, that receives and displays information and provides specific instructions to the user.

[0632] Augmented reality technology is a technique that overlays computer-generated information onto the real world's field of view, providing users with visual guidance.

[0633] This invention provides a system to support the safe evacuation of residents during disasters. The system mainly consists of a server and terminals. The server collects image information via the internet, formats it, and analyzes it. The hardware used is a cloud server, and the software used is OpenCV for image processing and TensorFlow for utilizing generative AI models. Based on the image information and past disaster information, the server constructs a damage prediction model and calculates the optimal evacuation route in the event of a disaster.

[0634] The terminal is a user device such as a smartphone or tablet that receives evacuation route information transmitted from a server. This information is stored on the terminal and can be used even when offline. The terminal also uses augmented reality technology to visually display obstacles and conditions along the actual evacuation route. Specifically, ARKit (iOS) and ARCore (Android), which support AR technology, are used. Through the terminal, users can receive voice and visual guidance, enabling them to evacuate safely and intuitively.

[0635] For example, consider a scenario where an earthquake occurs and major evacuation routes are blocked in a certain area. The server quickly identifies the earthquake's epicenter and the extent of the damage, and calculates new evacuation routes using the latest damage prediction models. The calculated evacuation route information is transmitted to the terminal and clearly displayed to the user via augmented reality (AR) on the terminal. Through this process, the user can be sure to take the most appropriate evacuation action.

[0636] The generated AI model continuously improves the accuracy of damage predictions by incorporating new data during disasters. An example of a prompt message is, "Please re-evaluate evacuation routes within the town based on the latest disaster information." This allows the system to provide appropriate, situation-sensitive instructions in real time through its dedicated model.

[0637] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0638] Step 1:

[0639] The server collects image information from devices such as dedicated cameras and drones. The input consists of real-time visual data of terrain and buildings. This data is formatted using OpenCV, undergoing data processing such as noise reduction and cropping of necessary parts to generate foundational data for analysis.

[0640] Step 2:

[0641] The server trains a generative AI model using image data collected along with historical disaster information. The input is statistical data and simulation data from past disasters, and the output is a damage prediction model. This model is updated through an iterative learning process of loopback verification to more accurately predict the extent of damage during a disaster.

[0642] Step 3:

[0643] The server uses a damage prediction model to calculate the optimal evacuation route in the event of a disaster. It takes real-time earthquake and weather information as input and provides rapidly calculated evacuation route data as output. Using pathfinding algorithms such as the A algorithm, it evaluates multiple routes in a short time and selects the optimal one.

[0644] Step 4:

[0645] The server transmits the calculated evacuation route information to the user device. The input is the calculated evacuation route data, and the output is data converted to a format usable on the terminal. This information is optimized for storage for offline use on the terminal.

[0646] Step 5:

[0647] The terminal uses augmented reality technology to visually present the evacuation route to the user based on the received evacuation route information. Inputs include evacuation route data from the server and real-time video feeds from the terminal's camera. The output is an overlay of route information using AR display, showing the user a safe travel route within their field of view. By using ARKit or ARCore, virtual guidance displays are realized in the real world.

[0648] Step 6:

[0649] Users perform safe evacuation actions by following the voice and visual guidance displayed on the terminal. Input is visual and voice guidance from the terminal, and users complete a quick and safe evacuation by following these instructions. The system's guidance allows users to respond immediately to unexpected obstacles and changes.

[0650] 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.

[0651] This invention is a system that supports the safe evacuation of users during disasters, and in particular, provides evacuation guidance that takes into account the user's emotions. This system consists of a server, a terminal, and an emotion engine, and each part works closely together to provide the user with an optimal evacuation experience.

[0652] Under normal circumstances, the server collects image data and disaster data via the internet and uses this to build damage prediction models. The server also trains AI models to prepare to provide rapid and accurate evacuation routes in the event of a disaster.

[0653] The terminal uses evacuation route information received from the server to provide users with voice and visual guidance. Even when offline, it provides evacuation routes based on information stored on the terminal, allowing users to evacuate safely even when the network is down.

[0654] Furthermore, this system is equipped with an emotion engine that recognizes emotions from the user's facial expressions and voice. Based on the results of this emotion recognition, the device adjusts the tone of guidance and displayed content according to the user's level of stress and anxiety. For example, if the user is feeling anxious, the device will provide guidance in a calmer tone and display messages that promote relaxation, thereby increasing the user's sense of security.

[0655] As a concrete example, in the event of an earthquake, the server immediately predicts the damage and transmits the optimal evacuation route to the terminal. The user begins evacuating according to the terminal's instructions, but if the emotion engine detects the user's anxiety, more polite and calming evacuation instructions are provided. In this way, the system uses advanced technology to support safe evacuation while taking the user's emotions into consideration.

[0656] The following describes the processing flow.

[0657] Step 1:

[0658] The server periodically collects and formats image data and disaster-related data from the environment. This formatted data is then prepared for use in training AI models.

[0659] Step 2:

[0660] The server trains an AI model using formatted data. This model is designed to predict damage based on past disaster data and has the ability to quickly calculate evacuation routes.

[0661] Step 3:

[0662] In the event of a disaster, the server performs damage prediction and sends optimal evacuation route information, calculated based on this prediction, to the terminal. This information is updated in real time.

[0663] Step 4:

[0664] The terminal stores evacuation route information received from the server and is ready to present it to the user at any time. In the event of a network outage, the stored data can be used to allow the user to receive appropriate instructions even when offline.

[0665] Step 5:

[0666] The device uses the user's camera and microphone to recognize the user's emotional state through an emotion engine. This recognition is performed through facial expression analysis and voice intonation analysis.

[0667] Step 6:

[0668] When a user recognizes the need to evacuate, the device guides them to the optimal evacuation route using voice and visuals. The guidance tone and messages are adjusted according to the user's emotional state, as determined by the emotion engine, to reassure the user.

[0669] Step 7:

[0670] During evacuation, users follow instructions provided in a timely manner. Throughout this process, the device constantly monitors the user's emotions and updates information as needed. It provides users with a sense of security while offering flexible responses to ensure safe evacuation.

[0671] (Example 2)

[0672] 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".

[0673] Currently, route guidance for rapid and safe evacuation during disasters does not take into account the emotional state of users, and therefore fails to adequately address users who are experiencing fear or anxiety. Furthermore, there is a need for a system that can provide reliable evacuation instructions even in environments where communication is unavailable. These challenges need to be addressed.

[0674] 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.

[0675] In this invention, the server includes means for collecting and formatting image data, means for training with past disaster-related data to construct a damage prediction information processing model, and means for analyzing the user's emotional state and dynamically adjusting the content of evacuation guidance. This makes it possible to provide flexible and appropriate evacuation guidance that takes into account the user's emotions.

[0676] "Image data" refers to still images and videos that have been converted into a computer-processable format, representing a numerical representation of visual information.

[0677] "Disaster-related data" refers to information about natural and man-made disasters, including statistics and reports that are useful for past cases and predictions.

[0678] A "damage prediction information processing model" refers to a set of data analysis methods and algorithms trained to predict the impact and damage in the event of a disaster.

[0679] "Evacuation routes" refer to information that shows the optimal route for moving from danger to a safe place.

[0680] "Emotional state" refers to the psychological and physiological state that a user is experiencing at a particular moment, as assessed through facial expressions and voice data.

[0681] "Dynamic adjustment" refers to a process that automatically optimizes the content and expression of guidance in response to real-time changes in circumstances and input data.

[0682] "Wireless communication unavailable" refers to a state in which communication via the internet or mobile network is unavailable for any reason.

[0683] "Acoustic and visual information" refers to methods that include means of information transmission via sound or voice, and visually displayed information.

[0684] This disaster evacuation support system includes servers, terminals, and emotion recognition capabilities to provide users with safe and appropriate evacuation routes.

[0685] The server periodically collects disaster-related image and geographic data via the internet. This process uses APIs and scraping techniques to obtain data from meteorological agencies and geographic information systems. The collected data is stored in a database, and machine learning libraries (such as TensorFlow and PyTorch) are used to train disaster damage prediction information processing models.

[0686] The terminal receives information from the server to guide the user along an evacuation route. The terminal functions as a smartphone or a dedicated evacuation navigation device, combining map display and voice guidance. This utilizes common map information service APIs (such as the Google Maps API). Even in the event of communication failure, the terminal can provide guidance to the user based on pre-stored evacuation route information.

[0687] Furthermore, the device uses its built-in camera and microphone to analyze the user's emotional state. This emotion analysis utilizes image processing libraries (e.g., OpenCV) and speech analysis APIs (e.g., Google Cloud Speech-to-Text). Based on the analysis results, the device dynamically adjusts the tone of the evacuation guidance. Specifically, if it detects that the user is feeling anxious, it adds a calming message and softens the tone of the voice guidance.

[0688] As a concrete example, when an earthquake occurs, the server immediately predicts the damage and provides the terminal with the optimal evacuation route. The user begins evacuating according to the terminal's guidance, but at this time, the terminal detects the user's level of anxiety and provides more careful and calm guidance.

[0689] An example of a prompt message to be input into the generation AI model is: "In the event of an earthquake, generate quick and reassuring evacuation route guidance. Strive to alleviate user anxiety and ensure safe evacuation."

[0690] In this way, by adjusting the system according to the emotional state of the server, terminal, and user, the system provides effective and user-friendly evacuation guidance.

[0691] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0692] Step 1:

[0693] The server periodically collects disaster-related image and geographic data via the internet. Raw data obtained via API or web scraping is provided as input. This data is cleansed and formatted before being stored in the database. This process includes noise reduction and formatting standardization. The collected data is then used to produce clear information for later training of predictive models.

[0694] Step 2:

[0695] The server trains a generative AI model using the collected data. The inputs used are clean image data and historical disaster-related information stored in a database. This data is applied to the model using a machine learning framework (e.g., TensorFlow) to build an information processing model for predicting the occurrence and impact of disasters. The output is a trained, highly accurate damage prediction information processing model. This model is used to calculate rapid and accurate evacuation routes.

[0696] Step 3:

[0697] When a disaster is detected, the server uses a trained generative AI model to calculate the optimal evacuation route. The input to this process is real-time disaster information and geographical data. The output is the calculated evacuation route information. The server sends this information to terminals for use in issuing evacuation orders.

[0698] Step 4:

[0699] The terminal provides the user with audible and visual guidance based on evacuation route information received from the server. Inputs include evacuation information transmitted from the server and map data pre-installed on the terminal. Operationally, the terminal visually displays the route on a map and provides route guidance through speech synthesis. Output is evacuation instructions that the user can recognize visually and audibly.

[0700] Step 5:

[0701] The device uses emotion recognition technology to analyze the user's facial expressions and voice. Input is real-time data obtained from the camera and microphone. Based on this, it uses OpenCV and a voice analysis API to quantify the emotional state and determine what guidance tone is appropriate. Output is guidance content adjusted according to the user's psychological state. Specifically, if anxiety is detected, the device will repeat the explanation or provide guidance in a calmer tone.

[0702] This series of processes enables the system to provide user-friendly, safe, and reliable evacuation support.

[0703] (Application Example 2)

[0704] 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".

[0705] In times of disaster, a key challenge is ensuring that users can evacuate safely and quickly. In particular, in the chaotic conditions of a disaster, it is essential to provide appropriate evacuation route guidance that takes users' emotions into consideration. Furthermore, ensuring accurate and effective evacuation support even in situations where communication networks may be disrupted is another challenge.

[0706] 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.

[0707] In this invention, the server includes means for collecting and formatting image information, means for learning using the image information and past disaster information to construct a damage prediction structure, and means for calculating the optimal evacuation route. This makes it possible to provide evacuation route information offline even when the communication network is down, and to provide an environment in which people can evacuate with peace of mind by adjusting the guidance method according to the user's emotions.

[0708] "Image information" refers to visual data acquired in digital format, which is used for various purposes through analysis and processing.

[0709] "Disaster information" refers to data and history related to natural disasters and accidents, as well as information about the impacts and damages caused by them.

[0710] A "damage prediction structure" refers to a model used to estimate the nature and extent of potential future damage based on past data and current conditions.

[0711] An "evacuation route" refers to a path or route designed to allow people to evacuate safely in the event of a disaster.

[0712] A "terminal" refers to an information processing device used directly by the user, and includes smartphones and computers.

[0713] "Emotions" refer to the user's internal psychological state, including levels of stress and anxiety.

[0714] "Guidance methods" refer to the methods and formats used to convey instructions and information to users, and can include audio and visual methods.

[0715] In the system that implements this application example, a server plays a central role. The server collects image and disaster information via the internet before a disaster occurs and uses an AI model to build a damage prediction structure based on this information. This uses machine learning libraries such as Google's TensorFlow. The damage prediction structure is used to calculate evacuation routes that other devices can use.

[0716] Users receive evacuation guidance via devices such as smartphones. These devices receive evacuation route information from a server and utilize the Google Cloud Vision API and speech synthesis software to provide voice and visual guidance. Even offline, evacuation route guidance can be provided using information stored on the device.

[0717] Furthermore, the device uses its built-in camera and microphone to monitor and recognize the user's emotions. This allows it to display relaxing messages and adjust its guidance tone if the user's stress or anxiety levels are high. For example, if the emotion recognition engine detects anxiety during an evacuation, the device will display a message in a calm tone such as, "It's okay. We're guiding you to a safe route. Please stay calm."

[0718] This system can also utilize generative AI models to enhance user confidence and can be equipped with features to customize guidance based on user feedback.

[0719] Examples of prompt statements include the following:

[0720] Please write the program specifications for an app that reads the user's emotions during a disaster and guides them to a safe and reassuring evacuation route. Include appropriate voice tones and messages to alleviate user anxiety.

[0721] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0722] Step 1:

[0723] The server collects the latest image information and historical disaster information via the internet. Based on this input data, it uses image processing algorithms to format the data and convert it into a format suitable for training. The formatted data is then used as training data for the AI ​​model.

[0724] Step 2:

[0725] The server uses a generative AI model to construct a damage prediction structure based on formatted image information and disaster information as input. In this process, machine learning libraries such as TensorFlow are used to analyze the data and predict future damage. The output of this process is the risk level and recommended evacuation routes for each region.

[0726] Step 3:

[0727] The server sends the recommended evacuation route, which is the output of the AI ​​model, to the terminal. The terminal receives this information and prepares to provide the user with the most suitable evacuation route guidance.

[0728] Step 4:

[0729] The device uses a camera and microphone to capture the user's facial expressions and voice, and performs emotion recognition. It uses real-time video and audio data as input and analyzes it using an emotion analysis library. The output is a calculation of the user's stress and anxiety levels.

[0730] Step 5:

[0731] The device uses the output of sentiment analysis to adjust the voice tone and message content of evacuation route guidance. Specifically, it displays voice guidance in a calm tone to promote reassurance and messages with a relaxing effect. It also collects user feedback on an ongoing basis to improve the guidance methods.

[0732] Step 6:

[0733] Users will evacuate safely by following the instructions. Even when the device is offline, it will continue providing instructions using locally stored route information. When the network is restored, it will retrieve the latest evacuation route information from the server and update the instructions.

[0734] 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.

[0735] 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.

[0736] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0737] 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.

[0738] 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.

[0739] 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.

[0740] 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.

[0741] 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.

[0742] 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."

[0743] 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.

[0744] 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.

[0745] 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.

[0746] 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.

[0747] 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.

[0748] 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.

[0749] 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 this memory.

[0750] 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.

[0751] 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.

[0752] 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.

[0753] 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.

[0754] 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.

[0755] The following is further disclosed regarding the embodiments described above.

[0756] (Claim 1)

[0757] A means of collecting and formatting image data,

[0758] A means for learning using the aforementioned image data and past disaster data to construct a damage prediction model,

[0759] A means for calculating the optimal evacuation route using the aforementioned damage prediction model,

[0760] A means of providing calculated evacuation route information to a terminal,

[0761] A means to make the evacuation route information available even when the terminal is offline,

[0762] A system that includes this.

[0763] (Claim 2)

[0764] The system according to claim 1, characterized in that it includes means for correcting evacuation routes in real time using evacuation route information stored on a terminal when the network is down.

[0765] (Claim 3)

[0766] The system according to claim 1, characterized by comprising means for providing evacuation route guidance in audio and visual form.

[0767] "Example 1"

[0768] (Claim 1)

[0769] A means of acquiring and processing video information,

[0770] A means for learning using the aforementioned video information and past event information to construct an impact prediction model,

[0771] A means for calculating the optimal travel route using the aforementioned impact prediction model,

[0772] Means for providing the calculated travel path information to an information processing device,

[0773] The information processing device provides means to enable the use of the travel route information even when a network connection is not required,

[0774] Means to encourage intuitive operation for the user,

[0775] A system that includes this.

[0776] (Claim 2)

[0777] The system according to claim 1, characterized in that it includes means for dynamically correcting the travel route using travel route information stored in an information processing device when the communication network is down.

[0778] (Claim 3)

[0779] The system according to claim 1, characterized by comprising means for providing travel route guidance using voice and visual representation.

[0780] "Application Example 1"

[0781] (Claim 1)

[0782] Means for collecting and shaping image information,

[0783] A means for constructing a damage prediction model by learning from the aforementioned image information and past disaster information,

[0784] A means for calculating the optimal evacuation route using the damage prediction model,

[0785] Means for supplying calculated evacuation route information to the user device,

[0786] Means for making the evacuation route information available even when the user device is offline,

[0787] A means of displaying obstacles along an evacuation route by overlaying them using augmented reality technology,

[0788] A system that includes this.

[0789] (Claim 2)

[0790] The system according to claim 1, characterized in that it includes means for correcting the evacuation route in real time using evacuation route information stored in the user device when the communication network is down.

[0791] (Claim 3)

[0792] The system according to claim 1, characterized by comprising means for providing evacuation route guidance using voice and visual information.

[0793] "Example 2 of combining an emotion engine"

[0794] (Claim 1)

[0795] A device for collecting and formatting image data,

[0796] A device that uses the aforementioned image data and past disaster-related data to train and construct a damage prediction information processing model,

[0797] A device that calculates the optimal evacuation route using the aforementioned damage prediction information processing model,

[0798] A device that analyzes the emotional state of users and dynamically adjusts the content of evacuation instructions,

[0799] A device that provides calculated evacuation route information to a terminal,

[0800] A device that makes the evacuation route information available even when the terminal is unable to communicate wirelessly,

[0801] A system that includes this.

[0802] (Claim 2)

[0803] The system according to claim 1, characterized in that it includes a device that, when wireless communication is impossible, uses evacuation route information stored in the terminal to correct the evacuation route in real time.

[0804] (Claim 3)

[0805] The system according to claim 1, characterized by comprising a device that provides evacuation route guidance using audible and visual information.

[0806] "Application example 2 when combining with an emotional engine"

[0807] (Claim 1)

[0808] Means for collecting and shaping image information,

[0809] A means for learning using the aforementioned image information and past disaster information to construct a damage prediction structure,

[0810] A means for calculating the optimal evacuation route using the damage prediction structure described above,

[0811] A means of providing calculated evacuation route information to a terminal,

[0812] A means to make the evacuation route information available even when the terminal is offline,

[0813] A means of recognizing the user's emotions and adjusting the evacuation route guidance method based on the results,

[0814] A system that includes this.

[0815] (Claim 2)

[0816] The system according to claim 1, characterized in that it includes means for correcting evacuation routes in real time using evacuation route information stored on a terminal when the network is down.

[0817] (Claim 3)

[0818] The system according to claim 1, characterized in that it provides evacuation route guidance using voice and visuals, and includes means for selecting an optimal guidance tone according to the user's stress or anxiety level. [Explanation of Symbols]

[0819] 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 of collecting and formatting image data, A means for learning using the aforementioned image data and past disaster data to construct a damage prediction model, A means for calculating the optimal evacuation route using the aforementioned damage prediction model, A means of providing calculated evacuation route information to a terminal, A means to make the evacuation route information available even when the terminal is offline, A system that includes this.

2. The system according to claim 1, characterized in that it includes means for correcting evacuation routes in real time using evacuation route information stored on a terminal when the network is down.

3. The system according to claim 1, characterized by comprising means for providing evacuation route guidance in audio and visual form.

Images