System

Abstract

A system is provided.SOLUTION: The system includes a means for collecting text, voice, image, and moving image data, a means for analyzing the collected data and specifying a disaster occurrence point and a damage situation, a means for dispatching a robot to the specified disaster occurrence point and performing site investigation and rescue of a victim, and a means for generating an optimum evacuation route in real time and providing it to the victim.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] This invention aims to address the increasing number of disasters and their expanding impacts due to climate change by improving the situation where there is a lack of rapid and effective disaster information collection and response methods, as well as the need to provide appropriate evacuation routes and early detection of disaster victims. It also aims to provide a new method to address the shortage of rescue resources and the problem of rescue operations in dangerous environments. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for collecting text, audio, image, and video data, a means for analyzing the collected data to identify the location of a disaster and the extent of the damage, a means for dispatching a robot to the identified disaster location to conduct an on-site investigation and rescue of victims, and a means for generating optimal evacuation routes in real time and providing them to victims. Specifically, by combining these means, it is possible to realize quick and safe rescue operations, ensure the safety of victims, and improve the saving of lives.

[0006] "Text" is character string data expressed in natural language, and includes information such as disaster-related reports and instructions.

[0007] "Sound" refers to sound data that includes human speech and environmental sounds, such as explanations of the disaster situation and the voices of disaster victims.

[0008] "Images" are still image data that show visual information about the disaster site and the extent of the damage.

[0009] "Video" is composed of continuous image data and includes video information showing the dynamic situation of a disaster.

[0010] "Means of collection" refers to a combination of hardware and software for capturing text, audio, image, and video data and transmitting it to a server.

[0011] "Means of analysis" refers to algorithms and data processing technologies that process collected data and identify the location of the disaster and the extent of the damage.

[0012] "Means of identification" refers to methods for extracting important information based on the analyzed data and using it in disaster response.

[0013] A "robot" is an autonomous or remotely controlled mechanical device that is dispatched to a disaster site to conduct on-site investigations and rescue victims.

[0014] The "dispatch means" refers to the communications technology and control system used to send the robot to the identified disaster site and direct its operations.

[0015] "Field survey" is a series of processes in which a robot uses cameras and sensors to collect information on-site and then sends the data to a server.

[0016] "Rescue of disaster victims" refers to activities to rescue lives and provide necessary medical care and evacuation instructions at identified disaster sites.

[0017] "Real time" refers to a timeframe that minimizes delays and allows for immediate response to ongoing events.

[0018] An "evacuation route" is the optimal route for disaster victims to evacuate safely, and is a route that is set up to avoid obstacles and dangerous areas.

[0019] The "means of generation" is an algorithm for calculating the optimal evacuation route based on collected data and analysis results.

[0020] The "means for providing" refers to an interface technology for notifying the user of the generated evacuation route and presenting it in an intuitively understandable format. [Brief explanation of the drawings]

[0021] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5]FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram illustrating a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0022] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0023] First, the terms used in the following description will be explained.

[0024] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0025] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0026] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0027] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0028] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0029] [First embodiment]

[0030] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0031] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0032] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0033] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0034] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0035] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0036] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0037] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0038] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0039] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0040] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0041] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0042] This invention is a system that uses multimodal AI and robots for disaster prevention and rescue. This system collects and analyzes text, audio, images, and video to support rapid information gathering and rescue operations in the event of a disaster. It also identifies victims and ensures their safety by providing optimal evacuation routes.

[0043] System overview and main components

[0044] The entire system is mainly composed of a server, a terminal, and a user interface. The specific operation of each component is explained below.

[0045] Server side

[0046] 1. Data Collection Module

[0047] The server collects text, audio, image, and video data. The sources of data include reports from users and automatic transmissions from devices. This allows for the acquisition of a wide range of data in real time.

[0048] 2. Data Analysis Module

[0049] The collected data is analyzed on a server. This analysis identifies the type and scale of the disaster, the extent of the damage, etc. For example, image analysis can be used to pinpoint the location of collapsed buildings, and audio analysis can be used to determine the situation from the voices of victims.

[0050] 3. Rescue operation support module

[0051] Based on the analysis results, the server issues instructions to the rescue robots, including a specific action plan for dispatching them to the disaster site, as well as detailed instructions for investigating the site and rescuing victims.

[0052] 4. Evacuation route optimization module

[0053] The server uses the information collected in real time to calculate the optimal evacuation route, taking into account the current situation at the disaster site in order to select the safest and fastest route for the victims.

[0054] Terminal side

[0055] 1. Data Entry Module

[0056] The device sends text, voice, image, and video data from the user to the server in real time, allowing the server to quickly grasp the situation of the disaster based on this data.

[0057] 2. Robot Control Module

[0058] This module controls the rescue robot by receiving instructions from the server. It moves the robot to the designated location, conducts an on-site investigation, and sends the acquired data back to the server.

[0059] User side

[0060] 1. Disaster Information Provision Interface

[0061] Users can provide necessary information in the event of a disaster using a smartphone or a dedicated app. Voice commands and image posting are possible through this interface.

[0062] 2. Evacuation route generation interface

[0063] This is an interface that notifies the user of the evacuation route generated by the server, allowing the user to confirm the optimal evacuation route and evacuate according to the instructions.

[0064] Specific Example Embodiments

[0065] For example, suppose a large earthquake occurs and many buildings collapse in a certain city area.

[0066] 1. User Reports

[0067] A user uses a smartphone app to report by voice, "An earthquake has occurred and a building has collapsed." In addition, the user takes a photo of the collapsed building within the app and sends it to the server.

[0068] 2. Data Collection

[0069] Text, voice, and image data sent from the terminal are sent to the server in real time.

[0070] 3. Data Analysis

[0071] The server analyzes the data, identifies the location of the collapsed building from the image data, and confirms the condition of the victims from the audio data.

[0072] 4. Dispatch of rescue robots

[0073] Based on the analysis results, the server issues instructions to rescue robots and dispatches them to the collapsed site. After arriving, the robots use cameras and sensors to conduct on-site surveys and send the data back to the server.

[0074] 5. Identifying victims and providing evacuation routes

[0075] The server reanalyzes the data received from the robot to identify the location of the victims, calculates a safe evacuation route, and notifies the user's smartphone app.

[0076] In this way, the system of the present invention realizes rapid and efficient disaster response and rescue operations, significantly improving the safety of disaster victims and saving their lives.

[0077] The processing flow will be explained below.

[0078] Step 1:

[0079] Users can report the occurrence of a disaster using a smartphone app. For example, they can report by voice, "An earthquake has occurred and a building has collapsed," and take and send a photo of the collapsed building with their smartphone.

[0080] Step 2:

[0081] The device collects text, voice, and image data provided by the user and transmits it to the server in real time, allowing disaster conditions to be immediately communicated to the server.

[0082] Step 3:

[0083] The server receives the data sent from the device and begins analysis using the data analysis module. Text analysis identifies the type and scale of the disaster, image analysis identifies the location of collapsed buildings, and voice analysis determines the situation from the voices of the victims.

[0084] Step 4:

[0085] Based on the results of the data analysis, the server identifies disaster locations with the highest urgency and issues instructions to rescue robots, such as sending GPS information of identified collapsed areas to the robots.

[0086] Step 5:

[0087] The terminal receives instructions from the server and dispatches the rescue robot to the site. The robot control module moves the robot to the specified location.

[0088] Step 6:

[0089] The rescue robot arrives at the designated disaster site and uses its on-board cameras and sensors to conduct on-site surveys, sending the survey data to a server in real time.

[0090] Step 7:

[0091] The server re-analyzes the on-site survey data sent from the robot to determine the location and condition of the victims, which will then be used to determine the priority of rescue efforts.

[0092] Step 8:

[0093] Based on the analysis results, the server creates an optimal rescue plan through the rescue operation support module and sends instructions to the rescue team, including the location information of the victims and instructions on the necessary rescue equipment.

[0094] Step 9:

[0095] The server generates optimal evacuation routes based on real-time data. The evacuation route optimization module selects the safest and fastest route for disaster victims.

[0096] Step 10:

[0097] The device notifies the user of the evacuation route information sent from the server, and the smartphone app displays evacuation instructions to the user, and the voice assistant provides route guidance.

[0098] Step 11:

[0099] Users follow the instructions on the smartphone app and evacuate to a safe location using the evacuation route provided. By acting quickly based on the instructions, safety is ensured.

[0100] Step 12:

[0101] The server monitors all rescue and evacuation operations in real time and updates instructions based on new information as needed, ensuring that responses are always based on the most up-to-date information.

[0102] Example 1

[0103] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0104] When a disaster occurs, rapid information gathering and situation assessment are required, but in many cases, rescue efforts for victims are delayed due to a lack of necessary data or the inability to provide appropriate evacuation routes. Furthermore, ineffective provision of information by victims or the use of robots can lead to the spread of damage. The objective of this invention is to solve these problems.

[0105] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0106] In this invention, the server includes means for collecting text, audio, image, and video data, means for analyzing the collected data and identifying the location of the disaster and the extent of the damage, means for dispatching a robot to the identified disaster location to conduct an on-site investigation and rescue victims, means for generating optimal evacuation routes in real time and providing them to the victims, means for generating an action plan for the robot based on the analysis results and sending instructions, and means for collecting information and providing evacuation routes via the user's smart device. This makes it possible to quickly and efficiently grasp the disaster situation and realize appropriate rescue operations and evacuation support.

[0107] "Text, audio, image, and video data" refers to digital data collected from users and devices that includes information on the situation and damage caused by a disaster.

[0108] "Collection methods" are the mechanisms and infrastructure for obtaining text, audio, image, and video data reported by users or automatically transmitted from devices.

[0109] "Means of analysis" refers to algorithms and software that process collected data and identify the type, scale, and damage caused by a disaster.

[0110] The "disaster occurrence location" refers to the location where the disaster actually occurred, and is an area identified based on the analyzed data.

[0111] "Damage situation" refers to the scope and extent of physical or human damage caused by a disaster, and is assessed based on collected and analyzed data.

[0112] A "robot" is an autonomous or remotely operated mechanical device that is dispatched to a designated disaster site to conduct on-site investigations and rescue victims.

[0113] "Field survey" refers to the act of a robot using cameras and sensors at the disaster site to confirm the extent of the damage and collect data.

[0114] "Victim rescue" refers to the act of using robots or other means to safely evacuate people caught in disasters.

[0115] "Generating optimal evacuation routes in real time" is the process of calculating the quickest and safest route for disaster victims based on the latest data.

[0116] "Means to provide" refers to the communications infrastructure and interfaces for notifying disaster victims of the calculated evacuation routes and sending instructions.

[0117] The "means for generating a robot's action plan based on the analysis results and transmitting instructions" is a mechanism for creating a specific operation plan for the rescue robot based on data analysis and communicating those instructions to the robot.

[0118] "Means for collecting information and providing evacuation routes through users' smart devices" refers to a system for receiving data from users using portable electronic devices such as smartphones and tablets, and sending evacuation instructions and route guidance.

[0119] This invention is a system that uses multimodal AI and robots for disaster response and rescue, which collects and analyzes text, audio, image, and video data to support rapid information gathering and rescue operations. It also identifies victims and ensures their safety by providing optimal evacuation routes.

[0120] System configuration

[0121] The system is mainly composed of a server, a terminal, and a user interface. The operation and role of each component are explained below.

[0122] Server-side behavior

[0123] The server includes the following modules:

[0124] 1. Data Collection Module

[0125] The server receives voice, text, image, and video data reported by users in real time using a REST API. Users provide data through a smartphone app.

[0126] 2. Data Analysis Module

[0127] The server uses machine learning models such as TensorFlow to analyze image data and identify the location of collapsed buildings, and also uses a voice recognition system to analyze user reports and determine the status of victims.

[0128] 3. Rescue operation support module

[0129] Based on the results of the data analysis, the server generates an action plan for the rescue robot and sends instructions to the robot via Wi-Fi or LTE networks, including how to investigate the disaster site and how to rescue victims.

[0130] 4. Evacuation route optimization module

[0131] The server uses the Google Maps API and a proprietary route optimization algorithm to calculate the optimal evacuation route based on the latest disaster information, and the calculated route is notified to the user via a smartphone app.

[0132] Operation on the terminal side

[0133] The terminal includes the following modules:

[0134] 1. Data Entry Module

[0135] The device (smartphone or tablet) transmits text, voice, image, and video data provided by the user to the server in real time. This process uses a camera app and a voice recording app.

[0136] 2. Robot Control Module

[0137] The terminal receives instructions from the server and controls the rescue robot. The robot moves to the designated location, conducts an on-site investigation, and transmits data obtained from sensors and cameras back to the server.

[0138] User behavior

[0139] Users participate in the system through the following interfaces:

[0140] 1. Disaster Information Provision Interface

[0141] Users use a smartphone app to provide information in the event of a disaster by taking photos of the collapsed area or reporting the damage situation via voice.

[0142] 2. Evacuation route generation interface

[0143] The user receives the evacuation route generated by the server on their smartphone app and evacuates by following the displayed instructions, allowing the user to quickly confirm the optimal evacuation route.

[0144] Specific Example Embodiments

[0145] For example, the scenario is as follows when a large earthquake occurs in a city area and many buildings collapse.

[0146] 1. User Reports

[0147] A user uses a smartphone app to report by voice that "an earthquake has occurred and a building has collapsed," and sends a photo of the collapsed building to the server.

[0148] 2. Data Collection

[0149] The server receives text, voice, and image data sent by the user in real time.

[0150] 3. Data Analysis

[0151] The server analyzes image data to identify the location of collapsed buildings and analyzes audio data to understand the situation of victims.

[0152] 4. Dispatch of rescue robots

[0153] Based on the analysis results, the server issues specific instructions to the rescue robot and dispatches it to the collapsed site. The robot uses cameras and sensors to conduct on-site surveys and transmits the data to the server.

[0154] 5. Identifying victims and providing evacuation routes

[0155] The server reanalyzes the data obtained from the robot, locates the location of the victims, calculates safe evacuation routes, and notifies the user's smartphone app.

[0156] Example of input prompt for generative AI model

[0157] Prompt statement:

[0158] "We have a disaster response system in which users, terminals, and servers work together. Please explain in detail how this system enables quick and efficient disaster response."

[0159] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0160] Step 1:

[0161] The server receives reports from users and automatic transmissions from devices. Specifically, users provide disaster information in the form of text, audio, images, and videos through a smartphone app. This data is sent to the server and stored in the data collection module. The input is disaster information data from users, and the output is the collected, unanalyzed data.

[0162] Step 2:

[0163] The server analyzes the collected data. Specifically, it uses machine learning models such as TensorFlow to analyze image data and identify the location of collapsed buildings. It also uses voice recognition software to convert voice data into text and determine the status of victims. The input is the collected unanalyzed data, and the output is the analysis results (location of collapsed buildings, status of victims).

[0164] Step 3:

[0165] The server generates a behavior plan for the rescue robot based on the analysis results. Specifically, it uses a behavior plan generation algorithm to create an action plan to instruct the robot, including detailed steps and routes for the robot to take. The input is the analysis results, and the output is the robot's behavior plan.

[0166] Step 4:

[0167] The server sends the generated action plan to the rescue robot. Specifically, it sends instructions to the robot's control unit via Wi-Fi or LTE network. This causes the robot to move to the specified location and begin on-site investigation and rescue operations. The input is the robot's action plan, and the output is the instructions for the robot to initiate its actions.

[0168] Step 5:

[0169] The terminal then transmits the on-site data collected by the robot back to the server. Specifically, the data acquired by the robot using cameras and sensors is transmitted to the server via Wi-Fi or LTE networks. The input is the on-site data collected by the robot, and the output is the on-site data transmitted to the server.

[0170] Step 6:

[0171] The server re-analyzes the on-site data received from the robot. Specifically, as with the initial analysis, it uses machine learning models to identify the locations of victims and to confirm the on-site situation in detail. The input is the on-site data sent from the robot, and the output is the detailed analysis results.

[0172] Step 7:

[0173] The server generates the optimal evacuation route based on the detailed analysis results. Specifically, it uses the Google Maps API and a unique route optimization algorithm to calculate the optimal evacuation route based on the latest information. The input is the detailed analysis results, and the output is evacuation route information.

[0174] Step 8:

[0175] The server notifies the generated evacuation route to the user's smartphone app. Specifically, it uses the app's notification function to provide the user with the evacuation route in real time. The input is evacuation route information, and the output is the evacuation route notified to the user.

[0176] (Application example 1)

[0177] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0178] In conventional disaster response and rescue systems, it took time to gather information and rescue victims, which resulted in delays in providing appropriate evacuation routes. Furthermore, there was a lack of a comprehensive system that was integrated across different devices and applications, making it difficult for users to efficiently provide information and evacuate quickly.

[0179] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0180] In this invention, the server includes means for collecting text, audio, image, and video data, means for analyzing the collected data and identifying the location of a disaster and the extent of damage, means for dispatching a robot to the identified disaster location to conduct an on-site investigation and rescue victims, means for generating optimal evacuation routes in real time and providing them to victims, and means for operating as an application installed on a smartphone, smart glasses, a head-mounted display, or a robot. This allows for rapid and accurate information collection in the event of a disaster, smooth rescue operations on site, and immediate evacuation routes to be provided to users.

[0181] "Text" refers to written information expressed in a language.

[0182] "Speech" refers to the human voice and other acoustic information, including, in particular, linguistic information.

[0183] "Image" refers to still visual data, such as photographs or graphics.

[0184] "Video" refers to visual data made up of a series of frames, such as movies and animations.

[0185] A "collection means" is a method or device that collects information and captures it for use within the system.

[0186] An "analyzing means" is a method or device for analyzing collected data and extracting useful information.

[0187] "Means for identification" refers to a method or device for clarifying a specific location or situation based on the analysis results.

[0188] A "robot" is an automated machine, a device that is programmed to perform specific tasks.

[0189] A "dispatch means" is a method or means for sending a robot to a specific location.

[0190] "Field survey" refers to survey activities carried out to confirm the actual situation at the disaster site.

[0191] "Rescue" is the act or activity of helping people in difficult situations.

[0192] An "evacuation route" is a route to a safe place in the event of a disaster.

[0193] A "means for producing" is a method or device for producing a particular result or data.

[0194] The "means for providing" refers to a method or device for transmitting the generated information or data to the user.

[0195] A "system" is a set of devices or software in which multiple elements work together.

[0196] A "smartphone" is a portable electronic device that can run many applications in addition to the functions of a mobile phone.

[0197] "Smart glasses" are a wearable eyeglass-type device that has the function of displaying information.

[0198] A "head-mounted display" is a display device that is worn on the head.

[0199] An "installed application" is software that is pre-configured to run on a particular device.

[0200] This invention is a system that uses multimodal AI and robots for disaster prevention and rescue. Specifically, this invention collects text, audio, image, and video data and analyzes them to support rapid information gathering and rescue operations. It also ensures the safety of victims by identifying them and providing optimal evacuation routes.

[0201] This system operates in cooperation with the server, terminals, and users. The operation of each component is explained below.

[0202] Server side

[0203] The server consists of the following modules:

[0204] 1. Data Collection Module

[0205] The server collects text, voice, image, and video data sent from users and devices in real time using a communication module and a database management system.

[0206] 2. Data Analysis Module

[0207] The collected data is analyzed by an AI model (for example, a model trained with TensorFlow or PyTorch) to identify the type, scale, and extent of damage caused by the disaster.

[0208] 3. Rescue operation support module

[0209] Based on the analysis results, specific action plans and detailed instructions are given to the rescue robots using robot control software and communication protocols.

[0210] 4. Evacuation route generation module

[0211] The server calculates the optimal evacuation route based on the information collected in real time and provides it to the user. This function is realized using location calculation tools such as the geopy package.

[0212] Terminal side

[0213] The device consists of the following modules:

[0214] 1. Data Entry Module

[0215] The device transmits voice, text, image, and video data from the user to a server in real time through an application installed on a smartphone, smart glasses, head-mounted display, or robot.

[0216] 2. Robot Control Module

[0217] The system receives instructions from the server and controls the rescue robot. The robot is equipped with cameras and sensors, conducts on-site surveys, and sends the data to the server.

[0218] User side

[0219] The user interacts with the system through the following interfaces:

[0220] 1. Disaster Information Provision Interface

[0221] Users can report the damage situation using their smartphones or a dedicated app, and can use voice commands and post images.

[0222] 2. Evacuation route generation interface

[0223] The server notifies the user of the generated evacuation route, and the user evacuates by following the evacuation route based on this information.

[0224] Specific examples

[0225] For example, consider a case where a large earthquake occurs and many buildings collapse in a certain city. A user uses a smartphone app to report by voice that "an earthquake has occurred" and uploads photos and videos of the collapsed buildings. This data is sent to a server.

[0226] The server analyzes the received data and identifies the extent of the damage and the location of the victims. Based on the results of this analysis, rescue robots are dispatched to conduct on-site investigations. The data collected by the robots is also sent to the server for further analysis.

[0227] The calculated evacuation route is sent to the user's smartphone app, and the user follows the route to a safe location.

[0228] Example prompt sentence:

[0229] "An earthquake has occurred. A building is collapsing. Many victims have been killed. Please analyze the situation based on audio, images, and video. Please suggest appropriate rescue actions. Text: An earthquake has occurred. Images: Photos of collapsed buildings. Video: Video of the collapsed area. Audio: Screams of victims."

[0230] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0231] Step 1:

[0232] Users report the disaster situation through a smartphone app. They report "an earthquake has occurred" using voice commands or text input, and also upload photos and videos of collapsed buildings. This data is collected by the data collection module of the present invention and sent to the server in real time.

[0233] Input: Voice commands, text, images, video data

[0234] Output: Disaster report data sent to the server

[0235] Step 2:

[0236] The server centrally manages the received voice, text, image, and video data in a data collection module, then passes it to a data analysis module, which uses software to convert the voice data into text and uses the image and video data to identify the extent of the damage and victims.

[0237] Input: Audio, text, image, video data

[0238] Output: Analyzed text, damage situation data, victim location data

[0239] What it does: The server uses voice recognition software to convert speech to text and image analysis software to identify the details of the damage.

[0240] Step 3:

[0241] The server identifies the location of the disaster and the extent of the damage based on the analyzed data, and issues instructions to the rescue robot via the rescue operation support module. The rescue robot is dispatched to the designated location, re-surveys the local situation using sensors and cameras, and sends additional data to the server.

[0242] Input: Analysis results (disaster location, damage situation)

[0243] Output: Instructions for rescue robots

[0244] Specific operation: The server calculates the location where the rescue robot should head based on GPS data, sends the instructions to the robot, and has it carry out the instructions.

[0245] Step 4:

[0246] The server then analyzes the newly collected data again using the data analysis module, and generates an evacuation route optimized for the location of the disaster victims. The evacuation route generation module uses location calculation tools such as geopy to calculate the safest evacuation route.

[0247] Input: Local data sent from the rescue robot

[0248] Output: Optimized evacuation route data

[0249] Specific operation: The server uses the geographic information system to recalculate evacuation routes based on the newly received local data.

[0250] Step 5:

[0251] The server then sends the calculated evacuation route data to the user's smartphone app. The user can then check the optimal evacuation route through the app and follow the displayed instructions to evacuate. The app continues to update the evacuation route information in real time.

[0252] Input: Optimized evacuation route data

[0253] Output: Evacuation route information sent to the user's smartphone app

[0254] Specific operation: The server sends the calculated evacuation route to the user's smartphone and displays it on the app screen.

[0255] Example prompt sentence:

[0256] "An earthquake has occurred. A building is collapsing. Many victims have been killed. Please analyze the situation based on audio, images, and video. Please suggest appropriate rescue actions. Text: An earthquake has occurred. Images: Photos of collapsed buildings. Video: Video of the collapsed area. Audio: Screams of victims."

[0257] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0258] This invention is a system that improves the quality of rescue operations by combining a system that uses multimodal AI and robots for disaster prevention and rescue operations with an emotion engine that recognizes user emotions. This system not only supports rapid information gathering and rescue operations when a disaster occurs by collecting and analyzing text, audio, images, and videos, but also uses the emotion engine to analyze user emotions and take optimal responses based on those analysis results.

[0259] System overview and main components

[0260] The entire system is composed of a server, a terminal, a user interface, and an emotion engine. The specific operation of each component is explained below.

[0261] Server side

[0262] 1. Data Collection Module

[0263] The server collects text, audio, image, and video data. The data sources include user reports and automatic transmissions from devices. It also works with an emotion engine to collect data based on user emotions.

[0264] 2. Data Analysis Module

[0265] The collected data is analyzed on a server. This analysis identifies the type and scale of the disaster, the extent of the damage, etc. For example, image analysis can be used to pinpoint the location of collapsed buildings, and audio analysis can be used to determine the situation from the voices of victims.

[0266] 3. Rescue operation support module

[0267] Based on the analysis results, the server issues instructions to the rescue robots, including a specific action plan for dispatching them to the disaster site, detailed instructions for investigating the site and rescuing victims, and also takes into account the emotion data analyzed by the emotion engine.

[0268] 4. Evacuation route optimization module

[0269] The server uses the information collected in real time to calculate the optimal evacuation route, taking into account the current situation at the disaster site and the user's emotional state in order to select the safest and fastest route for the victims.

[0270] Terminal side

[0271] 1. Data Entry Module

[0272] The device sends text, voice, image, and video data from the user to the server in real time, and the server quickly grasps the disaster situation based on this data.

[0273] 2. Robot Control Module

[0274] This module controls the rescue robot by receiving instructions from the server. It moves the robot to the designated location, conducts an on-site investigation, and sends the acquired data back to the server.

[0275] User side

[0276] 1. Disaster Information Provision Interface

[0277] Users can provide necessary information in the event of a disaster using a smartphone or a dedicated app. Voice commands and images can be posted through this interface. The emotion engine also analyzes emotions from user speech and input text.

[0278] 2. Evacuation route generation interface

[0279] This is an interface that notifies the user of the evacuation route generated by the server, allowing the user to confirm the optimal evacuation route and evacuate according to the instructions.

[0280] Emotion Engine

[0281] 1. Sentiment Analysis Module

[0282] The emotion engine analyzes the voice and text data to identify the user's emotions, such as whether they are feeling anxious or scared, and notifies the server of the appropriate response.

[0283] 2. Emotion Data Linkage Module

[0284] It works in conjunction with a server and sends emotion-based data to other modules, allowing emotion data to be reflected in rescue operations and the optimization of evacuation routes.

[0285] Specific Example Embodiments

[0286] For example, suppose a large earthquake occurs and many buildings collapse in a certain city area.

[0287] 1. User Reports

[0288] A user uses a smartphone app to report by voice, "An earthquake has occurred and a building has collapsed." In addition, the user takes a photo of the collapsed building within the app and sends it to the server. The emotion engine analyzes emotions such as anxiety and fear from the user's voice.

[0289] 2. Data Collection

[0290] Text, voice, and image data sent from the device are sent to the server in real time, and emotional data is also collected.

[0291] 3. Data Analysis

[0292] The server analyzes the data, pinpoints the location of collapsed buildings from image data, and checks the status of victims from voice data. It also takes into account emotional data to understand the emotional state of the victims.

[0293] 4. Dispatch of rescue robots

[0294] The server issues instructions to rescue robots based on the analysis results and dispatches them to the collapsed site. After the robots arrive, they use cameras and sensors to conduct on-site surveys and send the data to the server. Based on the emotional data, the robots' behavior is also considered.

[0295] 5. Identifying victims and providing evacuation routes

[0296] The server reanalyzes the data received from the robot to identify the location of the victim. It then calculates a safe evacuation route and notifies the user's smartphone app. The evacuation route guidance is adjusted based on the emotion data.

[0297] In this way, the system of the present invention realizes rapid and efficient disaster response and rescue operations. By combining it with an emotion engine, it becomes possible to provide support that takes into consideration the psychological state of the victims, significantly improving the safety of victims and the rescue of their lives.

[0298] The processing flow will be explained below.

[0299] Step 1:

[0300] Users report the occurrence of a disaster using a smartphone app. For example, they report by voice, "An earthquake occurred and a building collapsed," and take and send a photo of the collapsed building with their smartphone. The emotion engine analyzes emotions such as anxiety and fear from the user's voice.

[0301] Step 2:

[0302] The device collects text, voice, and image data provided by the user and transmits them to the server in real time, along with analyzed emotional data.

[0303] Step 3:

[0304] The server receives the data sent from the device and begins analysis using the data analysis module. Text analysis identifies the type and scale of the disaster, image analysis identifies the location of collapsed buildings, and voice analysis determines the situation from the voices of the victims.

[0305] Step 4:

[0306] The server identifies disaster locations with high urgency based on the data analysis results and emotion data, and issues instructions to rescue robots. For example, it sends the robot a specific action plan based on the GPS information of the identified collapsed area and the user's emotional state.

[0307] Step 5:

[0308] The terminal receives instructions from the server and dispatches the rescue robot to the site. The robot control module moves the robot to the specified location.

[0309] Step 6:

[0310] The rescue robot arrives at the designated disaster site and uses its on-board cameras and sensors to conduct on-site surveys, sending the survey data to a server in real time.

[0311] Step 7:

[0312] The server reanalyzes the on-site survey data sent from the robot to identify the location and condition of the victims, and also takes into account the emotional data to understand the psychological state of the victims.

[0313] Step 8:

[0314] Based on the analysis results and emotional data, the server creates an optimal rescue plan through the rescue operation support module and sends instructions to the rescue team, including the location information of the victims and instructions on the necessary rescue equipment. Based on the emotional data, the rescue team is also instructed to take psychological considerations into account.

[0315] Step 9:

[0316] The server generates optimal evacuation routes based on real-time data. The evacuation route optimization module selects the safest and quickest route for disaster victims. It also takes into account emotional data and provides appropriate explanations for evacuation routes.

[0317] Step 10:

[0318] The device notifies the user of the evacuation route information sent from the server. The smartphone app displays evacuation instructions to the user, and the voice assistant guides the user along the evacuation route. The voice assistant provides guidance in a calm voice that adapts to the user's emotional state.

[0319] Step 11:

[0320] Users follow the instructions on the smartphone app and evacuate to a safe location using the evacuation route provided. By acting quickly and calmly based on the instructions, safety is ensured.

[0321] Step 12:

[0322] The server monitors all rescue operations and evacuation situations in real time and updates instructions as new information becomes available, ensuring that responses are always based on the latest information. It also references emotion data and provides enhanced support to users as needed.

[0323] Example 2

[0324] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0325] Current disaster response systems are capable of rapidly collecting and analyzing disaster information, but there are limitations to improving the quality of rescue operations by taking into account the emotional and psychological states of victims. A system that can quickly respond to the anxiety and fear of victims is needed. Furthermore, a system that comprehensively considers current disaster information and the psychological states of victims is also needed to provide optimal evacuation routes in real time.

[0326] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0327] In this invention, the server includes means for collecting text, voice, image, and video data, means for analyzing the collected data and identifying the location of the disaster and the extent of the damage, means for analyzing emotions from the user's voice and text and reflecting the data, means for dispatching a robot to the identified disaster location to conduct an on-site investigation and rescue of victims, and means for generating optimal evacuation routes in real time and providing them to the victims, thereby enabling rapid and efficient disaster response and rescue operations that take into account the emotional state of the victims.

[0328] "Text data" refers to data that includes text information such as sentences and words.

[0329] "Audio data" refers to data in which an audio signal is recorded in digital format.

[0330] "Image data" refers to still image information recorded in digital format.

[0331] "Video data" refers to data that records dynamic video in digital format.

[0332] "Sentiment analysis" refers to the process of identifying a user's emotional state from speech or text.

[0333] "Robot" refers to a mechanical device that can perform designated tasks automatically.

[0334] "Camera" means a device that records still or moving images.

[0335] "Sensor" refers to a device for collecting information about the physical environment.

[0336] An "evacuation route" refers to the geographical route that disaster victims can take to evacuate safely.

[0337] "Server" refers to a computer system for collecting, analyzing, and storing data.

[0338] "User" refers to a person who utilizes the system to provide information and receive instructions.

[0339] "Collection means" refers to the device or method used to obtain data.

[0340] "Analysis means" refers to devices and methods for processing collected data to extract useful information.

[0341] "Dispatch means" refers to a method or device for sending a robot or other device to a specific destination.

[0342] "Real-time" refers to time characteristics in which processing and response occur almost instantaneously.

[0343] This invention is a system for disaster prevention and rescue, and in particular improves the quality of rescue operations by combining an emotion engine that recognizes the user's emotions. The entire system consists of a server, a terminal, a user interface, and an emotion engine.

[0344] server

[0345] The server plays a central role in collecting and analyzing various data. Specifically, it uses the following hardware and software:

[0346] Data Collection Module

[0347] The server collects text, audio, image, and video data reported by users or automatically sent from devices using natural language processing and speech recognition technologies, such as the Google Cloud Speech-to-Text API.

[0348] Data Analysis Module

[0349] The server analyzes the collected data, using Google Cloud Natural Language API for natural language processing (NLP) of text data, Convolutional Neural Network (CNN) technology for image analysis, and the YOLO (You Only Look Once) object recognition algorithm, to identify the type, scale, and damage of the disaster.

[0350] Rescue operation support module

[0351] Based on the analysis results, the server sends specific instructions to the rescue robot, such as instructing it to search for collapsed buildings in the city and formulating a rescue plan for victims. The robot is then dispatched to a designated location to investigate the situation and rescue victims.

[0352] Evacuation route optimization module

[0353] The server uses the Dijkstra algorithm to calculate the optimal evacuation route based on the information and emotion data collected in real time, providing an evacuation route that takes into account the user's psychological state.

[0354] Terminal

[0355] The terminal is responsible for exchanging data between the user and the server. Specifically, a smartphone or a dedicated app is used.

[0356] Data Entry Module

[0357] Users use a smartphone app to input text, voice, image, and video data, which is then sent in real time to a server, where Google Cloud Speech-to-Text is used to convert the voice data into text.

[0358] Robot Control Module

[0359] This module controls the rescue robot by receiving instructions from the server. It is responsible for sending commands to move the robot to a specified location, conducting on-site investigations, and sending the acquired data back to the server.

[0360] User

[0361] Users are responsible for providing disaster information and receiving evacuation route instructions. Specifically, information is exchanged via smartphones and dedicated apps.

[0362] Disaster information provision interface

[0363] Users can provide necessary information in the event of a disaster using a smartphone or a dedicated app. This allows them to send voice commands and post images. The emotion engine also analyzes emotions from the user's speech and input text.

[0364] Evacuation route generation interface

[0365] This is an interface that notifies the user of the evacuation route generated by the server, allowing the user to confirm the optimal evacuation route and evacuate according to the instructions.

[0366] Emotion Engine

[0367] Sentiment Analysis Module

[0368] The emotion engine analyzes voice and text data to identify the user's emotions. This uses IBM Watson's Tone Analyzer technology, which determines emotions such as anxiety or fear, and notifies the server of the appropriate response.

[0369] Emotion data linking module

[0370] It works in conjunction with a server and sends emotion-based data to other modules, allowing emotion data to be reflected in rescue operations and the optimization of evacuation routes.

[0371] Specific Example Embodiments

[0372] For example, suppose a large earthquake occurs and many buildings collapse in a certain city area.

[0373] User Reports

[0374] A user uses a smartphone app to report by voice, "An earthquake has occurred and a building has collapsed." In addition, the user takes a photo of the collapsed building within the app and sends it to the server. The emotion engine analyzes emotions such as anxiety and fear from the user's voice.

[0375] Data collection

[0376] Text, voice, and image data sent from the device are sent to the server in real time, and emotional data is also collected.

[0377] Data analysis

[0378] The server analyzes the data, pinpoints the location of collapsed buildings from image data, and checks the status of victims from voice data. It also takes into account emotional data to understand the emotional state of the victims.

[0379] Dispatch of rescue robots

[0380] The server issues instructions to rescue robots based on the analysis results and dispatches them to the collapsed site. After the robots arrive, they use cameras and sensors to conduct on-site surveys and send the data to the server. Based on the emotional data, the robots' behavior is also considered.

[0381] Identifying victims and providing evacuation routes

[0382] The server reanalyzes the data received from the robot to identify the location of the victim, calculates a safe evacuation route, and notifies the user's smartphone app. The evacuation route guidance is adjusted based on the emotion data.

[0383] Prompt Sentence Examples

[0384] By inputting the following prompt sentence into the generative AI model, an explanation of evacuation route optimization using the emotion engine can be obtained.

[0385] "An earthquake occurred and a building collapsed. I'm very worried. Which evacuation route is safe?"

[0386] Based on this prompt, the system generates the optimal evacuation route and notifies the user.

[0387] In this way, the system of the present invention realizes rapid and efficient disaster response and rescue operations. By combining it with an emotion engine, it becomes possible to provide support that takes into consideration the psychological state of the victims, greatly improving the safety of victims and the ability to save their lives.

[0388] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0389] Step 1:

[0390] Data collection

[0391] Input: A user reports a disaster using a smartphone app. This report can include text, audio, images, and video. For example, a voice message saying "An earthquake has occurred and buildings have collapsed" and a photo of a collapsed building.

[0392] How it works: The device receives user input and converts voice data to text using the Google Cloud Speech-to-Text API. It also uploads image data to cloud storage and processes video data in the same way.

[0393] Output: Text, audio, image, and video data sent from the device to the server.

[0394] Step 2:

[0395] Data analysis

[0396] Input: Text, audio, image, and video data sent from your device to the server.

[0397] How it works: The server analyzes the text data using the Google Cloud Natural Language API to identify the type and scale of the disaster. Image data is analyzed using the YOLO algorithm to identify the state of building collapse, and video data is also analyzed. Audio data is again analyzed using natural language processing.

[0398] Output: Various analyzed data (type of disaster, scale, damage situation, collapsed location, etc.).

[0399] Step 3:

[0400] Emotion analysis

[0401] Input: Voice and text data from the user.

[0402] How it works: The server uses IBM Watson's Tone Analyzer to analyze the user's emotions, extracting emotions such as anxiety or fear from voice and determining similar emotions from text data.

[0403] Output: Analyzed emotion data (user's psychological state such as anxiety or fear).

[0404] Step 4:

[0405] Dispatch and control of rescue robots

[0406] Input: Data analysis results and sentiment analysis results.

[0407] Operation: The server issues instructions to the rescue robot based on the analysis results. Specifically, it instructs it to head to the collapsed area and conduct an on-site investigation using cameras and sensors. The robot collects data and sends it to the server.

[0408] Output: Field survey data (images, videos, sensor data, etc.).

[0409] Step 5:

[0410] Optimizing evacuation routes

[0411] Input: Field survey data and sentiment data collected in real time.

[0412] How it works: The server uses the Dijkstra algorithm to calculate the optimal evacuation route based on the latest collected data, taking into account the current state of the disaster and the user's psychological state.

[0413] Output: Optimal evacuation route.

[0414] Step 6:

[0415] Interface Notifications

[0416] Input: The calculated optimal evacuation route.

[0417] How it works: The server notifies the user's smartphone app of the optimal evacuation route. The user receives the information through the app and follows the evacuation route. The app also provides audio guidance and visual navigation.

[0418] Output: Information to assist the user in evacuation actions.

[0419] In this way, disaster response and rescue operations can be carried out quickly and efficiently through each step. By incorporating an emotion engine, evacuation instructions and rescue operations can be carried out taking into account the psychological state of the victims, further ensuring their safety.

[0420] (Application example 2)

[0421] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0422] In disasters and emergencies, rescue of victims and provision of evacuation routes must be prompt and accurate. However, the current system makes it difficult to respond while taking into account the psychological state of the victims, which may result in inappropriate instructions being given. In particular, in emergencies such as fires and chemical leaks in factories, it is necessary to quickly gather information and provide evacuation instructions that take into account the emotions of workers, so there is room for improvement in the current system.

[0423] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0424] In this invention, the server includes means for collecting text, audio, image, and video data, means for analyzing the collected data and identifying the disaster site and damage status, means for dispatching a robot to the identified disaster site to conduct an on-site investigation and rescue victims, an emotion recognition engine for analyzing the user's emotions and means for adjusting and providing evacuation routes taking the data into consideration, and means for generating optimal evacuation routes in real time and providing them to victims. This enables rapid and accurate disaster response and supports safe evacuation behavior while taking into consideration the psychological state of the victims.

[0425] "Text data" refers to textual information from users, including reports on disasters and emergencies.

[0426] "Voice data" refers to voice information from users, and is used to report or explain the situation in the event of a disaster or emergency.

[0427] "Image data" refers to photographs and image information sent by users, and is used to understand the situation on site and confirm damage.

[0428] "Video data" refers to video footage sent by users and is used to grasp the real-time situation at disaster sites.

[0429] "Data analysis means" refers to the technical means of analyzing collected text, audio, image, and video data to identify the location of the disaster and the extent of the damage.

[0430] "Robot dispatch means" refers to a technical means of dispatching a robot to a specified disaster site to conduct an on-site investigation and rescue victims.

[0431] An "emotion recognition engine" is a technological means of analyzing a user's voice and text data to identify and evaluate their emotional state.

[0432] An "evacuation route adjustment means" is a technical means that takes into account the user's emotional data and generates and provides a safe and optimal evacuation route in real time.

[0433] The system for realizing this application example mainly consists of the following elements.

[0434] Data collection

[0435] The server collects text, audio, image, and video data. These data are transmitted in real time from users' smartphones, head-mounted displays, and other communication devices. The data is mainly collected from user reports.

[0436] Data analysis

[0437] The server analyzes the collected data to identify the location of the disaster and the extent of the damage. This analysis uses techniques such as image analysis, audio analysis, and text analysis. Specific software used includes image analysis tools (e.g., OpenCV), audio analysis tools (e.g., LibROSA), and text analysis tools (e.g., NLTK).

[0438] Emotion Recognition Engine

[0439] The server uses an emotion recognition engine that analyzes voice and text data to identify the user's emotional state and evaluate emotions such as fear and anxiety. The analysis results are used to generate evacuation routes.

[0440] Robot Dispatch

[0441] The server dispatches the robot to the identified disaster site to conduct on-site investigations and rescue victims. The robot is equipped with a camera and sensors, and transmits data collected on-site to the server in real time, enabling a detailed understanding of the situation on-site.

[0442] Evacuation route generation

[0443] The server generates optimal evacuation routes in real time and provides them to disaster victims. The generated evacuation routes are notified to users via their smartphone apps or head-mounted displays. Emotion data from the emotion recognition engine is also taken into account, providing users with optimal and reassuring evacuation instructions.

[0444] Specific examples

[0445] For example, if a fire breaks out in a factory, workers can report the situation using their smartphones or head-mounted displays. They can report, for example, "There's a fire. I want to escape quickly," and send image data to the server. The system collects and analyzes this data. If the emotion recognition engine determines that a worker is feeling strong fear, the server uses that information to generate the optimal evacuation route and alerts the worker to evacuate calmly.

[0446] Prompt Sentence Examples

[0447] User input: "There's a fire and I want to get out quickly."

[0448] System: "You seem scared and anxious. Calmly direct the evacuation route."

[0449] Hardware and software used

[0450] Smartphone / head-mounted display: Used for data collection and evacuation route display

[0451] Server: Responsible for data analysis and evacuation route generation

[0452] Robots: Used for disaster site surveys and rescue operations

[0453] Analysis tools:

[0454] Image analysis tool: OpenCV

[0455] Audio analysis tool: LibROSA

[0456] Text analysis tool: NLTK

[0457] Emotion Recognition Engine: An AI engine that analyzes the user's emotional state

[0458] In this way, the system enables rapid and appropriate disaster response and provides safe evacuation routes that take into account the psychological state of users.

[0459] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0460] Step 1:

[0461] Users can use their smartphones or head-mounted displays to report disasters and emergencies by voice or text. For example, they can report, "There's a fire. I want to escape quickly." At this time, they can also upload images and videos as needed.

[0462] Input: User-generated voice, text, image, and video data

[0463] Output: Report data sent to the server

[0464] Step 2:

[0465] The device transmits the voice, text, image, and video data collected from the user to the server in real time, where the data is packaged according to a specific format.

[0466] Input: Reported data collected from users

[0467] Output: Packaged data sent to the server

[0468] Step 3:

[0469] The server analyzes the received data to identify the location of the disaster and the extent of the damage. It uses a text analysis tool (e.g., NLTK) to convert the speech into text and analyzes the content of the text. It uses an image analysis tool (e.g., OpenCV) to analyze the image data and confirm the specific state of the disaster.

[0470] Input: Data sent from the terminal

[0471] Output: Identification of disaster location and damage status

[0472] Step 4:

[0473] The server uses an emotion recognition engine to identify the user's emotional state based on the analyzed data. Voice and text data are input into the emotion recognition engine, which calculates an emotion score such as fear or anxiety.

[0474] Input: Parsed audio and text data

[0475] Output: User sentiment score

[0476] Step 5:

[0477] The server issues instructions to dispatch robots to identified disaster sites. The robots are equipped with cameras and sensors to conduct on-site surveys and rescue victims. Data collected on-site is sent to the server in real time.

[0478] Input: Identification of disaster location and damage status

[0479] Output: Robot dispatch instructions and on-site investigation data

[0480] Step 6:

[0481] The server re-analyzes the on-site data sent from the robot and identifies the location of the victims. Based on this information, a safe and optimal evacuation route is generated. The user's emotion score is also taken into consideration, and appropriate evacuation instructions are given. The evacuation route is calculated using the NetworkX library, etc.

[0482] Input: Field survey data and emotion scores from the robot

[0483] Output: Optimal evacuation route and evacuation guidance information

[0484] Step 7:

[0485] The server notifies the user of the generated optimal evacuation route via a smartphone app or head-mounted display, displaying a message according to the user's emotional state.

[0486] Input: Optimal evacuation route and evacuation guidance information

[0487] Output: Evacuation route notification and evacuation instruction message to the user

[0488] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0489] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0490] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0491] [Second embodiment]

[0492] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0493] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0494] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0495] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0496] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0497] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0498] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0499] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0500] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0501] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0502] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0503] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0504] This invention is a system that uses multimodal AI and robots for disaster prevention and rescue. This system collects and analyzes text, audio, images, and video to support rapid information gathering and rescue operations in the event of a disaster. It also identifies victims and ensures their safety by providing optimal evacuation routes.

[0505] System overview and main components

[0506] The entire system is mainly composed of a server, a terminal, and a user interface. The specific operation of each component is explained below.

[0507] Server side

[0508] 1. Data Collection Module

[0509] The server collects text, audio, image, and video data. The sources of data include reports from users and automatic transmissions from devices. This allows for the acquisition of a wide range of data in real time.

[0510] 2. Data Analysis Module

[0511] The collected data is analyzed on a server. This analysis identifies the type and scale of the disaster, the extent of the damage, etc. For example, image analysis can be used to pinpoint the location of collapsed buildings, and audio analysis can be used to determine the situation from the voices of victims.

[0512] 3. Rescue operation support module

[0513] Based on the analysis results, the server issues instructions to the rescue robots, including a specific action plan for dispatching them to the disaster site, as well as detailed instructions for investigating the site and rescuing victims.

[0514] 4. Evacuation route optimization module

[0515] The server uses the information collected in real time to calculate the optimal evacuation route, taking into account the current situation at the disaster site in order to select the safest and fastest route for the victims.

[0516] Terminal side

[0517] 1. Data Entry Module

[0518] The device sends text, voice, image, and video data from the user to the server in real time, allowing the server to quickly grasp the situation of the disaster based on this data.

[0519] 2. Robot Control Module

[0520] This module controls the rescue robot by receiving instructions from the server. It moves the robot to the designated location, conducts an on-site investigation, and sends the acquired data back to the server.

[0521] User side

[0522] 1. Disaster Information Provision Interface

[0523] Users can provide necessary information in the event of a disaster using a smartphone or a dedicated app. Voice commands and image posting are possible through this interface.

[0524] 2. Evacuation route generation interface

[0525] This is an interface that notifies the user of the evacuation route generated by the server, allowing the user to confirm the optimal evacuation route and evacuate according to the instructions.

[0526] Specific Example Embodiments

[0527] For example, suppose a large earthquake occurs and many buildings collapse in a certain city area.

[0528] 1. User Reports

[0529] A user uses a smartphone app to report by voice, "An earthquake has occurred and a building has collapsed." In addition, the user takes a photo of the collapsed building within the app and sends it to the server.

[0530] 2. Data Collection

[0531] Text, voice, and image data sent from the terminal are sent to the server in real time.

[0532] 3. Data Analysis

[0533] The server analyzes the data, identifies the location of the collapsed building from the image data, and confirms the condition of the victims from the audio data.

[0534] 4. Dispatch of rescue robots

[0535] Based on the analysis results, the server issues instructions to rescue robots and dispatches them to the collapsed site. After arriving, the robots use cameras and sensors to conduct on-site surveys and send the data back to the server.

[0536] 5. Identifying victims and providing evacuation routes

[0537] The server reanalyzes the data received from the robot to identify the location of the victims, calculates a safe evacuation route, and notifies the user's smartphone app.

[0538] In this way, the system of the present invention realizes rapid and efficient disaster response and rescue operations, significantly improving the safety of disaster victims and saving their lives.

[0539] The processing flow will be explained below.

[0540] Step 1:

[0541] Users can report the occurrence of a disaster using a smartphone app. For example, they can report by voice, "An earthquake has occurred and a building has collapsed," and take and send a photo of the collapsed building with their smartphone.

[0542] Step 2:

[0543] The device collects text, voice, and image data provided by the user and transmits it to the server in real time, allowing disaster conditions to be immediately communicated to the server.

[0544] Step 3:

[0545] The server receives the data sent from the device and begins analysis using the data analysis module. Text analysis identifies the type and scale of the disaster, image analysis identifies the location of collapsed buildings, and voice analysis determines the situation from the voices of the victims.

[0546] Step 4:

[0547] Based on the results of the data analysis, the server identifies disaster locations with the highest urgency and issues instructions to rescue robots, such as sending GPS information of identified collapsed areas to the robots.

[0548] Step 5:

[0549] The terminal receives instructions from the server and dispatches the rescue robot to the site. The robot control module moves the robot to the specified location.

[0550] Step 6:

[0551] The rescue robot arrives at the designated disaster site and uses its on-board cameras and sensors to conduct on-site surveys, sending the survey data to a server in real time.

[0552] Step 7:

[0553] The server re-analyzes the on-site survey data sent from the robot to determine the location and condition of the victims, which will then be used to determine the priority of rescue efforts.

[0554] Step 8:

[0555] Based on the analysis results, the server creates an optimal rescue plan through the rescue operation support module and sends instructions to the rescue team, including the location information of the victims and instructions on the necessary rescue equipment.

[0556] Step 9:

[0557] The server generates optimal evacuation routes based on real-time data. The evacuation route optimization module selects the safest and fastest route for disaster victims.

[0558] Step 10:

[0559] The device notifies the user of the evacuation route information sent from the server, and the smartphone app displays evacuation instructions to the user, and the voice assistant provides route guidance.

[0560] Step 11:

[0561] Users follow the instructions on the smartphone app and evacuate to a safe location using the evacuation route provided. By acting quickly based on the instructions, safety is ensured.

[0562] Step 12:

[0563] The server monitors all rescue and evacuation operations in real time and updates instructions based on new information as needed, ensuring that responses are always based on the most up-to-date information.

[0564] Example 1

[0565] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0566] When a disaster occurs, rapid information gathering and situation assessment are required, but in many cases, rescue efforts for victims are delayed due to a lack of necessary data or the inability to provide appropriate evacuation routes. Furthermore, ineffective provision of information by victims or the use of robots can lead to the spread of damage. The objective of this invention is to solve these problems.

[0567] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0568] In this invention, the server includes means for collecting text, audio, image, and video data, means for analyzing the collected data and identifying the location of the disaster and the extent of the damage, means for dispatching a robot to the identified disaster location to conduct an on-site investigation and rescue victims, means for generating optimal evacuation routes in real time and providing them to the victims, means for generating an action plan for the robot based on the analysis results and sending instructions, and means for collecting information and providing evacuation routes via the user's smart device. This makes it possible to quickly and efficiently grasp the disaster situation and realize appropriate rescue operations and evacuation support.

[0569] "Text, audio, image, and video data" refers to digital data collected from users and devices that includes information on the situation and damage caused by a disaster.

[0570] "Collection methods" are the mechanisms and infrastructure for obtaining text, audio, image, and video data reported by users or automatically transmitted from devices.

[0571] "Means of analysis" refers to algorithms and software that process collected data and identify the type, scale, and damage caused by a disaster.

[0572] The "disaster occurrence location" refers to the location where the disaster actually occurred, and is an area identified based on the analyzed data.

[0573] "Damage situation" refers to the scope and extent of physical or human damage caused by a disaster, and is assessed based on collected and analyzed data.

[0574] A "robot" is an autonomous or remotely operated mechanical device that is dispatched to a designated disaster site to conduct on-site investigations and rescue victims.

[0575] "Field survey" refers to the act of a robot using cameras and sensors at the disaster site to confirm the extent of the damage and collect data.

[0576] "Victim rescue" refers to the act of using robots or other means to safely evacuate people caught in disasters.

[0577] "Generating optimal evacuation routes in real time" is the process of calculating the quickest and safest route for disaster victims based on the latest data.

[0578] "Means to provide" refers to the communications infrastructure and interfaces for notifying disaster victims of the calculated evacuation routes and sending instructions.

[0579] The "means for generating a robot's action plan based on the analysis results and transmitting instructions" is a mechanism for creating a specific operation plan for the rescue robot based on data analysis and communicating those instructions to the robot.

[0580] "Means for collecting information and providing evacuation routes through users' smart devices" refers to a system for receiving data from users using portable electronic devices such as smartphones and tablets, and sending evacuation instructions and route guidance.

[0581] This invention is a system that uses multimodal AI and robots for disaster response and rescue, which collects and analyzes text, audio, image, and video data to support rapid information gathering and rescue operations. It also identifies victims and ensures their safety by providing optimal evacuation routes.

[0582] System configuration

[0583] The system is mainly composed of a server, a terminal, and a user interface. The operation and role of each component are explained below.

[0584] Server-side behavior

[0585] The server includes the following modules:

[0586] 1. Data Collection Module

[0587] The server receives voice, text, image, and video data reported by users in real time using a REST API. Users provide data through a smartphone app.

[0588] 2. Data Analysis Module

[0589] The server uses machine learning models such as TensorFlow to analyze image data and identify the location of collapsed buildings, and also uses a voice recognition system to analyze user reports and determine the status of victims.

[0590] 3. Rescue operation support module

[0591] Based on the results of the data analysis, the server generates an action plan for the rescue robot and sends instructions to the robot via Wi-Fi or LTE networks, including how to investigate the disaster site and how to rescue victims.

[0592] 4. Evacuation route optimization module

[0593] The server uses the Google Maps API and a proprietary route optimization algorithm to calculate the optimal evacuation route based on the latest disaster information, and the calculated route is notified to the user via a smartphone app.

[0594] Operation on the terminal side

[0595] The terminal includes the following modules:

[0596] 1. Data Entry Module

[0597] The device (smartphone or tablet) transmits text, voice, image, and video data provided by the user to the server in real time. This process uses a camera app and a voice recording app.

[0598] 2. Robot Control Module

[0599] The terminal receives instructions from the server and controls the rescue robot. The robot moves to the designated location, conducts an on-site investigation, and transmits data obtained from sensors and cameras back to the server.

[0600] User behavior

[0601] Users participate in the system through the following interfaces:

[0602] 1. Disaster Information Provision Interface

[0603] Users use a smartphone app to provide information in the event of a disaster by taking photos of the collapsed area or reporting the damage situation via voice.

[0604] 2. Evacuation route generation interface

[0605] The user receives the evacuation route generated by the server on their smartphone app and evacuates by following the displayed instructions, allowing the user to quickly confirm the optimal evacuation route.

[0606] Specific Example Embodiments

[0607] For example, the scenario is as follows when a large earthquake occurs in a city area and many buildings collapse.

[0608] 1. User Reports

[0609] A user uses a smartphone app to report by voice that "an earthquake has occurred and a building has collapsed," and sends a photo of the collapsed building to the server.

[0610] 2. Data Collection

[0611] The server receives text, voice, and image data sent by the user in real time.

[0612] 3. Data Analysis

[0613] The server analyzes image data to identify the location of collapsed buildings and analyzes audio data to understand the situation of victims.

[0614] 4. Dispatch of rescue robots

[0615] Based on the analysis results, the server issues specific instructions to the rescue robot and dispatches it to the collapsed site. The robot uses cameras and sensors to conduct on-site surveys and transmits the data to the server.

[0616] 5. Identifying victims and providing evacuation routes

[0617] The server reanalyzes the data obtained from the robot, locates the location of the victims, calculates safe evacuation routes, and notifies the user's smartphone app.

[0618] Example of input prompt for generative AI model

[0619] Prompt statement:

[0620] "We have a disaster response system in which users, terminals, and servers work together. Please explain in detail how this system enables quick and efficient disaster response."

[0621] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0622] Step 1:

[0623] The server receives reports from users and automatic transmissions from devices. Specifically, users provide disaster information in the form of text, audio, images, and videos through a smartphone app. This data is sent to the server and stored in the data collection module. The input is disaster information data from users, and the output is the collected, unanalyzed data.

[0624] Step 2:

[0625] The server analyzes the collected data. Specifically, it uses machine learning models such as TensorFlow to analyze image data and identify the location of collapsed buildings. It also uses voice recognition software to convert voice data into text and determine the status of victims. The input is the collected unanalyzed data, and the output is the analysis results (location of collapsed buildings, status of victims).

[0626] Step 3:

[0627] The server generates a behavior plan for the rescue robot based on the analysis results. Specifically, it uses a behavior plan generation algorithm to create an action plan to instruct the robot, including detailed steps and routes for the robot to take. The input is the analysis results, and the output is the robot's behavior plan.

[0628] Step 4:

[0629] The server sends the generated action plan to the rescue robot. Specifically, it sends instructions to the robot's control unit via Wi-Fi or LTE network. This causes the robot to move to the specified location and begin on-site investigation and rescue operations. The input is the robot's action plan, and the output is the instructions for the robot to initiate its actions.

[0630] Step 5:

[0631] The terminal then transmits the on-site data collected by the robot back to the server. Specifically, the data acquired by the robot using cameras and sensors is transmitted to the server via Wi-Fi or LTE networks. The input is the on-site data collected by the robot, and the output is the on-site data transmitted to the server.

[0632] Step 6:

[0633] The server re-analyzes the on-site data received from the robot. Specifically, as with the initial analysis, it uses machine learning models to identify the locations of victims and to confirm the on-site situation in detail. The input is the on-site data sent from the robot, and the output is the detailed analysis results.

[0634] Step 7:

[0635] The server generates the optimal evacuation route based on the detailed analysis results. Specifically, it uses the Google Maps API and a unique route optimization algorithm to calculate the optimal evacuation route based on the latest information. The input is the detailed analysis results, and the output is evacuation route information.

[0636] Step 8:

[0637] The server notifies the generated evacuation route to the user's smartphone app. Specifically, it uses the app's notification function to provide the user with the evacuation route in real time. The input is evacuation route information, and the output is the evacuation route notified to the user.

[0638] (Application example 1)

[0639] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0640] In conventional disaster response and rescue systems, it took time to gather information and rescue victims, which resulted in delays in providing appropriate evacuation routes. Furthermore, there was a lack of a comprehensive system that was integrated across different devices and applications, making it difficult for users to efficiently provide information and evacuate quickly.

[0641] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0642] In this invention, the server includes means for collecting text, audio, image, and video data, means for analyzing the collected data and identifying the location of a disaster and the extent of damage, means for dispatching a robot to the identified disaster location to conduct an on-site investigation and rescue victims, means for generating optimal evacuation routes in real time and providing them to victims, and means for operating as an application installed on a smartphone, smart glasses, a head-mounted display, or a robot. This allows for rapid and accurate information collection in the event of a disaster, smooth rescue operations on site, and immediate evacuation routes to be provided to users.

[0643] "Text" refers to written information expressed in a language.

[0644] "Speech" refers to the human voice and other acoustic information, including, in particular, linguistic information.

[0645] "Image" refers to still visual data, such as photographs or graphics.

[0646] "Video" refers to visual data made up of a series of frames, such as movies and animations.

[0647] A "collection means" is a method or device that collects information and captures it for use within the system.

[0648] An "analyzing means" is a method or device for analyzing collected data and extracting useful information.

[0649] "Means for identification" refers to a method or device for clarifying a specific location or situation based on the analysis results.

[0650] A "robot" is an automated machine, a device that is programmed to perform specific tasks.

[0651] A "dispatch means" is a method or means for sending a robot to a specific location.

[0652] "Field survey" refers to survey activities carried out to confirm the actual situation at the disaster site.

[0653] "Rescue" is the act or activity of helping people in difficult situations.

[0654] An "evacuation route" is a route to a safe place in the event of a disaster.

[0655] A "means for producing" is a method or device for producing a particular result or data.

[0656] The "means for providing" refers to a method or device for transmitting the generated information or data to the user.

[0657] A "system" is a set of devices or software in which multiple elements work together.

[0658] A "smartphone" is a portable electronic device that can run many applications in addition to the functions of a mobile phone.

[0659] "Smart glasses" are a wearable eyeglass-type device that has the function of displaying information.

[0660] A "head-mounted display" is a display device that is worn on the head.

[0661] An "installed application" is software that is pre-configured to run on a particular device.

[0662] This invention is a system that uses multimodal AI and robots for disaster prevention and rescue. Specifically, this invention collects text, audio, image, and video data and analyzes them to support rapid information gathering and rescue operations. It also ensures the safety of victims by identifying them and providing optimal evacuation routes.

[0663] This system operates in cooperation with the server, terminals, and users. The operation of each component is explained below.

[0664] Server side

[0665] The server consists of the following modules:

[0666] 1. Data Collection Module

[0667] The server collects text, voice, image, and video data sent from users and devices in real time using a communication module and a database management system.

[0668] 2. Data Analysis Module

[0669] The collected data is analyzed by an AI model (for example, a model trained with TensorFlow or PyTorch) to identify the type, scale, and extent of damage caused by the disaster.

[0670] 3. Rescue operation support module

[0671] Based on the analysis results, specific action plans and detailed instructions are given to the rescue robots using robot control software and communication protocols.

[0672] 4. Evacuation route generation module

[0673] The server calculates the optimal evacuation route based on the information collected in real time and provides it to the user. This function is realized using location calculation tools such as the geopy package.

[0674] Terminal side

[0675] The device consists of the following modules:

[0676] 1. Data Entry Module

[0677] The device transmits voice, text, image, and video data from the user to a server in real time through an application installed on a smartphone, smart glasses, head-mounted display, or robot.

[0678] 2. Robot Control Module

[0679] The system receives instructions from the server and controls the rescue robot. The robot is equipped with cameras and sensors, conducts on-site surveys, and sends the data to the server.

[0680] User side

[0681] The user interacts with the system through the following interfaces:

[0682] 1. Disaster Information Provision Interface

[0683] Users can report the damage situation using their smartphones or a dedicated app, and can use voice commands and post images.

[0684] 2. Evacuation route generation interface

[0685] The server notifies the user of the generated evacuation route, and the user evacuates by following the evacuation route based on this information.

[0686] Specific examples

[0687] For example, consider a case where a large earthquake occurs and many buildings collapse in a certain city. A user uses a smartphone app to report by voice that "an earthquake has occurred" and uploads photos and videos of the collapsed buildings. This data is sent to a server.

[0688] The server analyzes the received data and identifies the extent of the damage and the location of the victims. Based on the results of this analysis, rescue robots are dispatched to conduct on-site investigations. The data collected by the robots is also sent to the server for further analysis.

[0689] The calculated evacuation route is sent to the user's smartphone app, and the user follows the route to a safe location.

[0690] Example prompt sentence:

[0691] "An earthquake has occurred. A building is collapsing. Many victims have been killed. Please analyze the situation based on audio, images, and video. Please suggest appropriate rescue actions. Text: An earthquake has occurred. Images: Photos of collapsed buildings. Video: Video of the collapsed area. Audio: Screams of victims."

[0692] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0693] Step 1:

[0694] Users report the disaster situation through a smartphone app. They report "an earthquake has occurred" using voice commands or text input, and also upload photos and videos of collapsed buildings. This data is collected by the data collection module of the present invention and sent to the server in real time.

[0695] Input: Voice commands, text, images, video data

[0696] Output: Disaster report data sent to the server

[0697] Step 2:

[0698] The server centrally manages the received voice, text, image, and video data in a data collection module, then passes it to a data analysis module, which uses software to convert the voice data into text and uses the image and video data to identify the extent of the damage and victims.

[0699] Input: Audio, text, image, video data

[0700] Output: Analyzed text, damage situation data, victim location data

[0701] What it does: The server uses voice recognition software to convert speech to text and image analysis software to identify the details of the damage.

[0702] Step 3:

[0703] The server identifies the location of the disaster and the extent of the damage based on the analyzed data, and issues instructions to the rescue robot via the rescue operation support module. The rescue robot is dispatched to the designated location, re-surveys the local situation using sensors and cameras, and sends additional data to the server.

[0704] Input: Analysis results (disaster location, damage situation)

[0705] Output: Instructions for rescue robots

[0706] Specific operation: The server calculates the location where the rescue robot should head based on GPS data, sends the instructions to the robot, and has it carry out the instructions.

[0707] Step 4:

[0708] The server then analyzes the newly collected data again using the data analysis module, and generates an evacuation route optimized for the location of the disaster victims. The evacuation route generation module uses location calculation tools such as geopy to calculate the safest evacuation route.

[0709] Input: Local data sent from the rescue robot

[0710] Output: Optimized evacuation route data

[0711] Specific operation: The server uses the geographic information system to recalculate evacuation routes based on the newly received local data.

[0712] Step 5:

[0713] The server then sends the calculated evacuation route data to the user's smartphone app. The user can then check the optimal evacuation route through the app and follow the displayed instructions to evacuate. The app continues to update the evacuation route information in real time.

[0714] Input: Optimized evacuation route data

[0715] Output: Evacuation route information sent to the user's smartphone app

[0716] Specific operation: The server sends the calculated evacuation route to the user's smartphone and displays it on the app screen.

[0717] Example prompt sentence:

[0718] "An earthquake has occurred. A building is collapsing. Many victims have been killed. Please analyze the situation based on audio, images, and video. Please suggest appropriate rescue actions. Text: An earthquake has occurred. Images: Photos of collapsed buildings. Video: Video of the collapsed area. Audio: Screams of victims."

[0719] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0720] This invention is a system that improves the quality of rescue operations by combining a system that uses multimodal AI and robots for disaster prevention and rescue operations with an emotion engine that recognizes user emotions. This system not only supports rapid information gathering and rescue operations when a disaster occurs by collecting and analyzing text, audio, images, and videos, but also uses the emotion engine to analyze user emotions and take optimal responses based on those analysis results.

[0721] System overview and main components

[0722] The entire system is composed of a server, a terminal, a user interface, and an emotion engine. The specific operation of each component is explained below.

[0723] Server side

[0724] 1. Data Collection Module

[0725] The server collects text, audio, image, and video data. The data sources include user reports and automatic transmissions from devices. It also works with an emotion engine to collect data based on user emotions.

[0726] 2. Data Analysis Module

[0727] The collected data is analyzed on a server. This analysis identifies the type and scale of the disaster, the extent of the damage, etc. For example, image analysis can be used to pinpoint the location of collapsed buildings, and audio analysis can be used to determine the situation from the voices of victims.

[0728] 3. Rescue operation support module

[0729] Based on the analysis results, the server issues instructions to the rescue robots, including a specific action plan for dispatching them to the disaster site, detailed instructions for investigating the site and rescuing victims, and also takes into account the emotion data analyzed by the emotion engine.

[0730] 4. Evacuation route optimization module

[0731] The server uses the information collected in real time to calculate the optimal evacuation route, taking into account the current situation at the disaster site and the user's emotional state in order to select the safest and fastest route for the victims.

[0732] Terminal side

[0733] 1. Data Entry Module

[0734] The device sends text, voice, image, and video data from the user to the server in real time, and the server quickly grasps the disaster situation based on this data.

[0735] 2. Robot Control Module

[0736] This module controls the rescue robot by receiving instructions from the server. It moves the robot to the designated location, conducts an on-site investigation, and sends the acquired data back to the server.

[0737] User side

[0738] 1. Disaster Information Provision Interface

[0739] Users can provide necessary information in the event of a disaster using a smartphone or a dedicated app. Voice commands and images can be posted through this interface. The emotion engine also analyzes emotions from user speech and input text.

[0740] 2. Evacuation route generation interface

[0741] This is an interface that notifies the user of the evacuation route generated by the server, allowing the user to confirm the optimal evacuation route and evacuate according to the instructions.

[0742] Emotion Engine

[0743] 1. Sentiment Analysis Module

[0744] The emotion engine analyzes the voice and text data to identify the user's emotions, such as whether they are feeling anxious or scared, and notifies the server of the appropriate response.

[0745] 2. Emotion Data Linkage Module

[0746] It works in conjunction with a server and sends emotion-based data to other modules, allowing emotion data to be reflected in rescue operations and the optimization of evacuation routes.

[0747] Specific Example Embodiments

[0748] For example, suppose a large earthquake occurs and many buildings collapse in a certain city area.

[0749] 1. User Reports

[0750] A user uses a smartphone app to report by voice, "An earthquake has occurred and a building has collapsed." In addition, the user takes a photo of the collapsed building within the app and sends it to the server. The emotion engine analyzes emotions such as anxiety and fear from the user's voice.

[0751] 2. Data Collection

[0752] Text, voice, and image data sent from the device are sent to the server in real time, and emotional data is also collected.

[0753] 3. Data Analysis

[0754] The server analyzes the data, pinpoints the location of collapsed buildings from image data, and checks the status of victims from voice data. It also takes into account emotional data to understand the emotional state of the victims.

[0755] 4. Dispatch of rescue robots

[0756] The server issues instructions to rescue robots based on the analysis results and dispatches them to the collapsed site. After the robots arrive, they use cameras and sensors to conduct on-site surveys and send the data to the server. Based on the emotional data, the robots' behavior is also considered.

[0757] 5. Identifying victims and providing evacuation routes

[0758] The server reanalyzes the data received from the robot to identify the location of the victim. It then calculates a safe evacuation route and notifies the user's smartphone app. The evacuation route guidance is adjusted based on the emotion data.

[0759] In this way, the system of the present invention realizes rapid and efficient disaster response and rescue operations. By combining it with an emotion engine, it becomes possible to provide support that takes into consideration the psychological state of the victims, significantly improving the safety of victims and the rescue of their lives.

[0760] The processing flow will be explained below.

[0761] Step 1:

[0762] Users report the occurrence of a disaster using a smartphone app. For example, they report by voice, "An earthquake occurred and a building collapsed," and take and send a photo of the collapsed building with their smartphone. The emotion engine analyzes emotions such as anxiety and fear from the user's voice.

[0763] Step 2:

[0764] The device collects text, voice, and image data provided by the user and transmits them to the server in real time, along with analyzed emotional data.

[0765] Step 3:

[0766] The server receives the data sent from the device and begins analysis using the data analysis module. Text analysis identifies the type and scale of the disaster, image analysis identifies the location of collapsed buildings, and voice analysis determines the situation from the voices of the victims.

[0767] Step 4:

[0768] The server identifies disaster locations with high urgency based on the data analysis results and emotion data, and issues instructions to rescue robots. For example, it sends the robot a specific action plan based on the GPS information of the identified collapsed area and the user's emotional state.

[0769] Step 5:

[0770] The terminal receives instructions from the server and dispatches the rescue robot to the site. The robot control module moves the robot to the specified location.

[0771] Step 6:

[0772] The rescue robot arrives at the designated disaster site and uses its on-board cameras and sensors to conduct on-site surveys, sending the survey data to a server in real time.

[0773] Step 7:

[0774] The server reanalyzes the on-site survey data sent from the robot to identify the location and condition of the victims, and also takes into account the emotional data to understand the psychological state of the victims.

[0775] Step 8:

[0776] Based on the analysis results and emotional data, the server creates an optimal rescue plan through the rescue operation support module and sends instructions to the rescue team, including the location information of the victims and instructions on the necessary rescue equipment. Based on the emotional data, the rescue team is also instructed to take psychological considerations into account.

[0777] Step 9:

[0778] The server generates optimal evacuation routes based on real-time data. The evacuation route optimization module selects the safest and quickest route for disaster victims. It also takes into account emotional data and provides appropriate explanations for evacuation routes.

[0779] Step 10:

[0780] The device notifies the user of the evacuation route information sent from the server. The smartphone app displays evacuation instructions to the user, and the voice assistant guides the user along the evacuation route. The voice assistant provides guidance in a calm voice that adapts to the user's emotional state.

[0781] Step 11:

[0782] Users follow the instructions on the smartphone app and evacuate to a safe location using the evacuation route provided. By acting quickly and calmly based on the instructions, safety is ensured.

[0783] Step 12:

[0784] The server monitors all rescue operations and evacuation situations in real time and updates instructions as new information becomes available, ensuring that responses are always based on the latest information. It also references emotion data and provides enhanced support to users as needed.

[0785] Example 2

[0786] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0787] Current disaster response systems are capable of rapidly collecting and analyzing disaster information, but there are limitations to improving the quality of rescue operations by taking into account the emotional and psychological states of victims. A system that can quickly respond to the anxiety and fear of victims is needed. Furthermore, a system that comprehensively considers current disaster information and the psychological states of victims is also needed to provide optimal evacuation routes in real time.

[0788] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0789] In this invention, the server includes means for collecting text, voice, image, and video data, means for analyzing the collected data and identifying the location of the disaster and the extent of the damage, means for analyzing emotions from the user's voice and text and reflecting the data, means for dispatching a robot to the identified disaster location to conduct an on-site investigation and rescue of victims, and means for generating optimal evacuation routes in real time and providing them to the victims, thereby enabling rapid and efficient disaster response and rescue operations that take into account the emotional state of the victims.

[0790] "Text data" refers to data that includes text information such as sentences and words.

[0791] "Audio data" refers to data in which an audio signal is recorded in digital format.

[0792] "Image data" refers to still image information recorded in digital format.

[0793] "Video data" refers to data that records dynamic video in digital format.

[0794] "Sentiment analysis" refers to the process of identifying a user's emotional state from speech or text.

[0795] "Robot" refers to a mechanical device that can perform designated tasks automatically.

[0796] "Camera" means a device that records still or moving images.

[0797] "Sensor" refers to a device for collecting information about the physical environment.

[0798] An "evacuation route" refers to the geographical route that disaster victims can take to evacuate safely.

[0799] "Server" refers to a computer system for collecting, analyzing, and storing data.

[0800] "User" refers to a person who utilizes the system to provide information and receive instructions.

[0801] "Collection means" refers to the device or method used to obtain data.

[0802] "Analysis means" refers to devices and methods for processing collected data to extract useful information.

[0803] "Dispatch means" refers to a method or device for sending a robot or other device to a specific destination.

[0804] "Real-time" refers to time characteristics in which processing and response occur almost instantaneously.

[0805] This invention is a system for disaster prevention and rescue, and in particular improves the quality of rescue operations by combining an emotion engine that recognizes the user's emotions. The entire system consists of a server, a terminal, a user interface, and an emotion engine.

[0806] server

[0807] The server plays a central role in collecting and analyzing various data. Specifically, it uses the following hardware and software:

[0808] Data Collection Module

[0809] The server collects text, audio, image, and video data reported by users or automatically sent from devices using natural language processing and speech recognition technologies, such as the Google Cloud Speech-to-Text API.

[0810] Data Analysis Module

[0811] The server analyzes the collected data, using Google Cloud Natural Language API for natural language processing (NLP) of text data, Convolutional Neural Network (CNN) technology for image analysis, and the YOLO (You Only Look Once) object recognition algorithm, to identify the type, scale, and damage of the disaster.

[0812] Rescue operation support module

[0813] Based on the analysis results, the server sends specific instructions to the rescue robot, such as instructing it to search for collapsed buildings in the city and formulating a rescue plan for victims. The robot is then dispatched to a designated location to investigate the situation and rescue victims.

[0814] Evacuation route optimization module

[0815] The server uses the Dijkstra algorithm to calculate the optimal evacuation route based on the information and emotion data collected in real time, providing an evacuation route that takes into account the user's psychological state.

[0816] Terminal

[0817] The terminal is responsible for exchanging data between the user and the server. Specifically, a smartphone or a dedicated app is used.

[0818] Data Entry Module

[0819] Users use a smartphone app to input text, voice, image, and video data, which is then sent in real time to a server, where Google Cloud Speech-to-Text is used to convert the voice data into text.

[0820] Robot Control Module

[0821] This module controls the rescue robot by receiving instructions from the server. It is responsible for sending commands to move the robot to a specified location, conducting on-site investigations, and sending the acquired data back to the server.

[0822] User

[0823] Users are responsible for providing disaster information and receiving evacuation route instructions. Specifically, information is exchanged via smartphones and dedicated apps.

[0824] Disaster information provision interface

[0825] Users can provide necessary information in the event of a disaster using a smartphone or a dedicated app. This allows them to send voice commands and post images. The emotion engine also analyzes emotions from the user's speech and input text.

[0826] Evacuation route generation interface

[0827] This is an interface that notifies the user of the evacuation route generated by the server, allowing the user to confirm the optimal evacuation route and evacuate according to the instructions.

[0828] Emotion Engine

[0829] Sentiment Analysis Module

[0830] The emotion engine analyzes voice and text data to identify the user's emotions. This uses IBM Watson's Tone Analyzer technology, which determines emotions such as anxiety or fear, and notifies the server of the appropriate response.

[0831] Emotion data linking module

[0832] It works in conjunction with a server and sends emotion-based data to other modules, allowing emotion data to be reflected in rescue operations and the optimization of evacuation routes.

[0833] Specific Example Embodiments

[0834] For example, suppose a large earthquake occurs and many buildings collapse in a certain city area.

[0835] User Reports

[0836] A user uses a smartphone app to report by voice, "An earthquake has occurred and a building has collapsed." In addition, the user takes a photo of the collapsed building within the app and sends it to the server. The emotion engine analyzes emotions such as anxiety and fear from the user's voice.

[0837] Data collection

[0838] Text, voice, and image data sent from the device are sent to the server in real time, and emotional data is also collected.

[0839] Data analysis

[0840] The server analyzes the data, pinpoints the location of collapsed buildings from image data, and checks the status of victims from voice data. It also takes into account emotional data to understand the emotional state of the victims.

[0841] Dispatch of rescue robots

[0842] The server issues instructions to rescue robots based on the analysis results and dispatches them to the collapsed site. After the robots arrive, they use cameras and sensors to conduct on-site surveys and send the data to the server. Based on the emotional data, the robots' behavior is also considered.

[0843] Identifying victims and providing evacuation routes

[0844] The server reanalyzes the data received from the robot to identify the location of the victim, calculates a safe evacuation route, and notifies the user's smartphone app. The evacuation route guidance is adjusted based on the emotion data.

[0845] Prompt Sentence Examples

[0846] By inputting the following prompt sentence into the generative AI model, an explanation of evacuation route optimization using the emotion engine can be obtained.

[0847] "An earthquake occurred and a building collapsed. I'm very worried. Which evacuation route is safe?"

[0848] Based on this prompt, the system generates the optimal evacuation route and notifies the user.

[0849] In this way, the system of the present invention realizes rapid and efficient disaster response and rescue operations. By combining it with an emotion engine, it becomes possible to provide support that takes into consideration the psychological state of the victims, greatly improving the safety of victims and the ability to save their lives.

[0850] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0851] Step 1:

[0852] Data collection

[0853] Input: A user reports a disaster using a smartphone app. This report can include text, audio, images, and video. For example, a voice message saying "An earthquake has occurred and buildings have collapsed" and a photo of a collapsed building.

[0854] How it works: The device receives user input and converts voice data to text using the Google Cloud Speech-to-Text API. It also uploads image data to cloud storage and processes video data in the same way.

[0855] Output: Text, audio, image, and video data sent from the device to the server.

[0856] Step 2:

[0857] Data analysis

[0858] Input: Text, audio, image, and video data sent from your device to the server.

[0859] How it works: The server analyzes the text data using the Google Cloud Natural Language API to identify the type and scale of the disaster. Image data is analyzed using the YOLO algorithm to identify the state of building collapse, and video data is also analyzed. Audio data is again analyzed using natural language processing.

[0860] Output: Various analyzed data (type of disaster, scale, damage situation, collapsed location, etc.).

[0861] Step 3:

[0862] Emotion analysis

[0863] Input: Voice and text data from the user.

[0864] How it works: The server uses IBM Watson's Tone Analyzer to analyze the user's emotions, extracting emotions such as anxiety or fear from voice and determining similar emotions from text data.

[0865] Output: Analyzed emotion data (user's psychological state such as anxiety or fear).

[0866] Step 4:

[0867] Dispatch and control of rescue robots

[0868] Input: Data analysis results and sentiment analysis results.

[0869] Operation: The server issues instructions to the rescue robot based on the analysis results. Specifically, it instructs it to head to the collapsed area and conduct an on-site investigation using cameras and sensors. The robot collects data and sends it to the server.

[0870] Output: Field survey data (images, videos, sensor data, etc.).

[0871] Step 5:

[0872] Optimizing evacuation routes

[0873] Input: Field survey data and sentiment data collected in real time.

[0874] How it works: The server uses the Dijkstra algorithm to calculate the optimal evacuation route based on the latest collected data, taking into account the current state of the disaster and the user's psychological state.

[0875] Output: Optimal evacuation route.

[0876] Step 6:

[0877] Interface Notifications

[0878] Input: The calculated optimal evacuation route.

[0879] How it works: The server notifies the user's smartphone app of the optimal evacuation route. The user receives the information through the app and follows the evacuation route. The app also provides audio guidance and visual navigation.

[0880] Output: Information to assist the user in evacuation actions.

[0881] In this way, disaster response and rescue operations can be carried out quickly and efficiently through each step. By incorporating an emotion engine, evacuation instructions and rescue operations can be carried out taking into account the psychological state of the victims, further ensuring their safety.

[0882] (Application example 2)

[0883] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0884] In disasters and emergencies, rescue of victims and provision of evacuation routes must be prompt and accurate. However, the current system makes it difficult to respond while taking into account the psychological state of the victims, which may result in inappropriate instructions being given. In particular, in emergencies such as fires and chemical leaks in factories, it is necessary to quickly gather information and provide evacuation instructions that take into account the emotions of workers, so there is room for improvement in the current system.

[0885] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0886] In this invention, the server includes means for collecting text, audio, image, and video data, means for analyzing the collected data and identifying the disaster site and damage status, means for dispatching a robot to the identified disaster site to conduct an on-site investigation and rescue victims, an emotion recognition engine for analyzing the user's emotions and means for adjusting and providing evacuation routes taking the data into consideration, and means for generating optimal evacuation routes in real time and providing them to victims. This enables rapid and accurate disaster response and supports safe evacuation behavior while taking into consideration the psychological state of the victims.

[0887] "Text data" refers to textual information from users, including reports on disasters and emergencies.

[0888] "Voice data" refers to voice information from users, and is used to report or explain the situation in the event of a disaster or emergency.

[0889] "Image data" refers to photographs and image information sent by users, and is used to understand the situation on site and confirm damage.

[0890] "Video data" refers to video footage sent by users and is used to grasp the real-time situation at disaster sites.

[0891] "Data analysis means" refers to the technical means of analyzing collected text, audio, image, and video data to identify the location of the disaster and the extent of the damage.

[0892] "Robot dispatch means" refers to a technical means of dispatching a robot to a specified disaster site to conduct an on-site investigation and rescue victims.

[0893] An "emotion recognition engine" is a technological means of analyzing a user's voice and text data to identify and evaluate their emotional state.

[0894] An "evacuation route adjustment means" is a technical means that takes into account the user's emotional data and generates and provides a safe and optimal evacuation route in real time.

[0895] The system for realizing this application example mainly consists of the following elements.

[0896] Data collection

[0897] The server collects text, audio, image, and video data. These data are transmitted in real time from users' smartphones, head-mounted displays, and other communication devices. The data is mainly collected from user reports.

[0898] Data analysis

[0899] The server analyzes the collected data to identify the location of the disaster and the extent of the damage. This analysis uses techniques such as image analysis, audio analysis, and text analysis. Specific software used includes image analysis tools (e.g., OpenCV), audio analysis tools (e.g., LibROSA), and text analysis tools (e.g., NLTK).

[0900] Emotion Recognition Engine

[0901] The server uses an emotion recognition engine that analyzes voice and text data to identify the user's emotional state and evaluate emotions such as fear and anxiety. The analysis results are used to generate evacuation routes.

[0902] Robot Dispatch

[0903] The server dispatches the robot to the identified disaster site to conduct on-site investigations and rescue victims. The robot is equipped with a camera and sensors, and transmits data collected on-site to the server in real time, enabling a detailed understanding of the situation on-site.

[0904] Evacuation route generation

[0905] The server generates optimal evacuation routes in real time and provides them to disaster victims. The generated evacuation routes are notified to users via their smartphone apps or head-mounted displays. Emotion data from the emotion recognition engine is also taken into account, providing users with optimal and reassuring evacuation instructions.

[0906] Specific examples

[0907] For example, if a fire breaks out in a factory, workers can report the situation using their smartphones or head-mounted displays. They can report, for example, "There's a fire. I want to escape quickly," and send image data to the server. The system collects and analyzes this data. If the emotion recognition engine determines that a worker is feeling strong fear, the server uses that information to generate the optimal evacuation route and alerts the worker to evacuate calmly.

[0908] Prompt Sentence Examples

[0909] User input: "There's a fire and I want to get out quickly."

[0910] System: "You seem scared and anxious. Calmly direct the evacuation route."

[0911] Hardware and software used

[0912] Smartphone / head-mounted display: Used for data collection and evacuation route display

[0913] Server: Responsible for data analysis and evacuation route generation

[0914] Robots: Used for disaster site surveys and rescue operations

[0915] Analysis tools:

[0916] Image analysis tool: OpenCV

[0917] Audio analysis tool: LibROSA

[0918] Text analysis tool: NLTK

[0919] Emotion Recognition Engine: An AI engine that analyzes the user's emotional state

[0920] In this way, the system enables rapid and appropriate disaster response and provides safe evacuation routes that take into account the psychological state of users.

[0921] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0922] Step 1:

[0923] Users can use their smartphones or head-mounted displays to report disasters and emergencies by voice or text. For example, they can report, "There's a fire. I want to escape quickly." At this time, they can also upload images and videos as needed.

[0924] Input: User-generated voice, text, image, and video data

[0925] Output: Report data sent to the server

[0926] Step 2:

[0927] The device transmits the voice, text, image, and video data collected from the user to the server in real time, where the data is packaged according to a specific format.

[0928] Input: Reported data collected from users

[0929] Output: Packaged data sent to the server

[0930] Step 3:

[0931] The server analyzes the received data to identify the location of the disaster and the extent of the damage. It uses a text analysis tool (e.g., NLTK) to convert the speech into text and analyzes the content of the text. It uses an image analysis tool (e.g., OpenCV) to analyze the image data and confirm the specific state of the disaster.

[0932] Input: Data sent from the terminal

[0933] Output: Identification of disaster location and damage status

[0934] Step 4:

[0935] The server uses an emotion recognition engine to identify the user's emotional state based on the analyzed data. Voice and text data are input into the emotion recognition engine, which calculates an emotion score such as fear or anxiety.

[0936] Input: Parsed audio and text data

[0937] Output: User sentiment score

[0938] Step 5:

[0939] The server issues instructions to dispatch robots to identified disaster sites. The robots are equipped with cameras and sensors to conduct on-site surveys and rescue victims. Data collected on-site is sent to the server in real time.

[0940] Input: Identification of disaster location and damage status

[0941] Output: Robot dispatch instructions and on-site investigation data

[0942] Step 6:

[0943] The server re-analyzes the on-site data sent from the robot and identifies the location of the victims. Based on this information, a safe and optimal evacuation route is generated. The user's emotion score is also taken into consideration, and appropriate evacuation instructions are given. The evacuation route is calculated using the NetworkX library, etc.

[0944] Input: Field survey data and emotion scores from the robot

[0945] Output: Optimal evacuation route and evacuation guidance information

[0946] Step 7:

[0947] The server notifies the user of the generated optimal evacuation route via a smartphone app or head-mounted display, displaying a message according to the user's emotional state.

[0948] Input: Optimal evacuation route and evacuation guidance information

[0949] Output: Evacuation route notification and evacuation instruction message to the user

[0950] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0951] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0952] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0953] [Third embodiment]

[0954] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0955] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0956] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0957] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0958] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0959] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0960] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0961] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0962] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0963] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0964] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0965] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0966] This invention is a system that uses multimodal AI and robots for disaster prevention and rescue. This system collects and analyzes text, audio, images, and video to support rapid information gathering and rescue operations in the event of a disaster. It also identifies victims and ensures their safety by providing optimal evacuation routes.

[0967] System overview and main components

[0968] The entire system is mainly composed of a server, a terminal, and a user interface. The specific operation of each component is explained below.

[0969] Server side

[0970] 1. Data Collection Module

[0971] The server collects text, audio, image, and video data. The sources of data include reports from users and automatic transmissions from devices. This allows for the acquisition of a wide range of data in real time.

[0972] 2. Data Analysis Module

[0973] The collected data is analyzed on a server. This analysis identifies the type and scale of the disaster, the extent of the damage, etc. For example, image analysis can be used to pinpoint the location of collapsed buildings, and audio analysis can be used to determine the situation from the voices of victims.

[0974] 3. Rescue operation support module

[0975] Based on the analysis results, the server issues instructions to the rescue robots, including a specific action plan for dispatching them to the disaster site, as well as detailed instructions for investigating the site and rescuing victims.

[0976] 4. Evacuation route optimization module

[0977] The server uses the information collected in real time to calculate the optimal evacuation route, taking into account the current situation at the disaster site in order to select the safest and fastest route for the victims.

[0978] Terminal side

[0979] 1. Data Entry Module

[0980] The device sends text, voice, image, and video data from the user to the server in real time, allowing the server to quickly grasp the situation of the disaster based on this data.

[0981] 2. Robot Control Module

[0982] This module controls the rescue robot by receiving instructions from the server. It moves the robot to the designated location, conducts an on-site investigation, and sends the acquired data back to the server.

[0983] User side

[0984] 1. Disaster Information Provision Interface

[0985] Users can provide necessary information in the event of a disaster using a smartphone or a dedicated app. Voice commands and image posting are possible through this interface.

[0986] 2. Evacuation route generation interface

[0987] This is an interface that notifies the user of the evacuation route generated by the server, allowing the user to confirm the optimal evacuation route and evacuate according to the instructions.

[0988] Specific Example Embodiments

[0989] For example, suppose a large earthquake occurs and many buildings collapse in a certain city area.

[0990] 1. User Reports

[0991] A user uses a smartphone app to report by voice, "An earthquake has occurred and a building has collapsed." In addition, the user takes a photo of the collapsed building within the app and sends it to the server.

[0992] 2. Data Collection

[0993] Text, voice, and image data sent from the terminal are sent to the server in real time.

[0994] 3. Data Analysis

[0995] The server analyzes the data, identifies the location of the collapsed building from the image data, and confirms the condition of the victims from the audio data.

[0996] 4. Dispatch of rescue robots

[0997] Based on the analysis results, the server issues instructions to rescue robots and dispatches them to the collapsed site. After arriving, the robots use cameras and sensors to conduct on-site surveys and send the data back to the server.

[0998] 5. Identifying victims and providing evacuation routes

[0999] The server reanalyzes the data received from the robot to identify the location of the victims, calculates a safe evacuation route, and notifies the user's smartphone app.

[1000] In this way, the system of the present invention realizes rapid and efficient disaster response and rescue operations, significantly improving the safety of disaster victims and saving their lives.

[1001] The processing flow will be explained below.

[1002] Step 1:

[1003] Users can report the occurrence of a disaster using a smartphone app. For example, they can report by voice, "An earthquake has occurred and a building has collapsed," and take and send a photo of the collapsed building with their smartphone.

[1004] Step 2:

[1005] The device collects text, voice, and image data provided by the user and transmits it to the server in real time, allowing disaster conditions to be immediately communicated to the server.

[1006] Step 3:

[1007] The server receives the data sent from the device and begins analysis using the data analysis module. Text analysis identifies the type and scale of the disaster, image analysis identifies the location of collapsed buildings, and voice analysis determines the situation from the voices of the victims.

[1008] Step 4:

[1009] Based on the results of the data analysis, the server identifies disaster locations with the highest urgency and issues instructions to rescue robots, such as sending GPS information of identified collapsed areas to the robots.

[1010] Step 5:

[1011] The terminal receives instructions from the server and dispatches the rescue robot to the site. The robot control module moves the robot to the specified location.

[1012] Step 6:

[1013] The rescue robot arrives at the designated disaster site and uses its on-board cameras and sensors to conduct on-site surveys, sending the survey data to a server in real time.

[1014] Step 7:

[1015] The server re-analyzes the on-site survey data sent from the robot to determine the location and condition of the victims, which will then be used to determine the priority of rescue efforts.

[1016] Step 8:

[1017] Based on the analysis results, the server creates an optimal rescue plan through the rescue operation support module and sends instructions to the rescue team, including the location information of the victims and instructions on the necessary rescue equipment.

[1018] Step 9:

[1019] The server generates optimal evacuation routes based on real-time data. The evacuation route optimization module selects the safest and fastest route for disaster victims.

[1020] Step 10:

[1021] The device notifies the user of the evacuation route information sent from the server, and the smartphone app displays evacuation instructions to the user, and the voice assistant provides route guidance.

[1022] Step 11:

[1023] Users follow the instructions on the smartphone app and evacuate to a safe location using the evacuation route provided. By acting quickly based on the instructions, safety is ensured.

[1024] Step 12:

[1025] The server monitors all rescue and evacuation operations in real time and updates instructions based on new information as needed, ensuring that responses are always based on the most up-to-date information.

[1026] Example 1

[1027] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1028] When a disaster occurs, rapid information gathering and situation assessment are required, but in many cases, rescue efforts for victims are delayed due to a lack of necessary data or the inability to provide appropriate evacuation routes. Furthermore, ineffective provision of information by victims or the use of robots can lead to the spread of damage. The objective of this invention is to solve these problems.

[1029] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1030] In this invention, the server includes means for collecting text, audio, image, and video data, means for analyzing the collected data and identifying the location of the disaster and the extent of the damage, means for dispatching a robot to the identified disaster location to conduct an on-site investigation and rescue victims, means for generating optimal evacuation routes in real time and providing them to the victims, means for generating an action plan for the robot based on the analysis results and sending instructions, and means for collecting information and providing evacuation routes via the user's smart device. This makes it possible to quickly and efficiently grasp the disaster situation and realize appropriate rescue operations and evacuation support.

[1031] "Text, audio, image, and video data" refers to digital data collected from users and devices that includes information on the situation and damage caused by a disaster.

[1032] "Collection methods" are the mechanisms and infrastructure for obtaining text, audio, image, and video data reported by users or automatically transmitted from devices.

[1033] "Means of analysis" refers to algorithms and software that process collected data and identify the type, scale, and damage caused by a disaster.

[1034] The "disaster occurrence location" refers to the location where the disaster actually occurred, and is an area identified based on the analyzed data.

[1035] "Damage situation" refers to the scope and extent of physical or human damage caused by a disaster, and is assessed based on collected and analyzed data.

[1036] A "robot" is an autonomous or remotely operated mechanical device that is dispatched to a designated disaster site to conduct on-site investigations and rescue victims.

[1037] "Field survey" refers to the act of a robot using cameras and sensors at the disaster site to confirm the extent of the damage and collect data.

[1038] "Victim rescue" refers to the act of using robots or other means to safely evacuate people caught in disasters.

[1039] "Generating optimal evacuation routes in real time" is the process of calculating the quickest and safest route for disaster victims based on the latest data.

[1040] "Means to provide" refers to the communications infrastructure and interfaces for notifying disaster victims of the calculated evacuation routes and sending instructions.

[1041] The "means for generating a robot's action plan based on the analysis results and transmitting instructions" is a mechanism for creating a specific operation plan for the rescue robot based on data analysis and communicating those instructions to the robot.

[1042] "Means for collecting information and providing evacuation routes through users' smart devices" refers to a system for receiving data from users using portable electronic devices such as smartphones and tablets, and sending evacuation instructions and route guidance.

[1043] This invention is a system that uses multimodal AI and robots for disaster response and rescue, which collects and analyzes text, audio, image, and video data to support rapid information gathering and rescue operations. It also identifies victims and ensures their safety by providing optimal evacuation routes.

[1044] System configuration

[1045] The system is mainly composed of a server, a terminal, and a user interface. The operation and role of each component are explained below.

[1046] Server-side behavior

[1047] The server includes the following modules:

[1048] 1. Data Collection Module

[1049] The server receives voice, text, image, and video data reported by users in real time using a REST API. Users provide data through a smartphone app.

[1050] 2. Data Analysis Module

[1051] The server uses machine learning models such as TensorFlow to analyze image data and identify the location of collapsed buildings, and also uses a voice recognition system to analyze user reports and determine the status of victims.

[1052] 3. Rescue operation support module

[1053] Based on the results of the data analysis, the server generates an action plan for the rescue robot and sends instructions to the robot via Wi-Fi or LTE networks, including how to investigate the disaster site and how to rescue victims.

[1054] 4. Evacuation route optimization module

[1055] The server uses the Google Maps API and a proprietary route optimization algorithm to calculate the optimal evacuation route based on the latest disaster information, and the calculated route is notified to the user via a smartphone app.

[1056] Operation on the terminal side

[1057] The terminal includes the following modules:

[1058] 1. Data Entry Module

[1059] The device (smartphone or tablet) transmits text, voice, image, and video data provided by the user to the server in real time. This process uses a camera app and a voice recording app.

[1060] 2. Robot Control Module

[1061] The terminal receives instructions from the server and controls the rescue robot. The robot moves to the designated location, conducts an on-site investigation, and transmits data obtained from sensors and cameras back to the server.

[1062] User behavior

[1063] Users participate in the system through the following interfaces:

[1064] 1. Disaster Information Provision Interface

[1065] Users use a smartphone app to provide information in the event of a disaster by taking photos of the collapsed area or reporting the damage situation via voice.

[1066] 2. Evacuation route generation interface

[1067] The user receives the evacuation route generated by the server on their smartphone app and evacuates by following the displayed instructions, allowing the user to quickly confirm the optimal evacuation route.

[1068] Specific Example Embodiments

[1069] For example, the scenario is as follows when a large earthquake occurs in a city area and many buildings collapse.

[1070] 1. User Reports

[1071] A user uses a smartphone app to report by voice that "an earthquake has occurred and a building has collapsed," and sends a photo of the collapsed building to the server.

[1072] 2. Data Collection

[1073] The server receives text, voice, and image data sent by the user in real time.

[1074] 3. Data Analysis

[1075] The server analyzes image data to identify the location of collapsed buildings and analyzes audio data to understand the situation of victims.

[1076] 4. Dispatch of rescue robots

[1077] Based on the analysis results, the server issues specific instructions to the rescue robot and dispatches it to the collapsed site. The robot uses cameras and sensors to conduct on-site surveys and transmits the data to the server.

[1078] 5. Identifying victims and providing evacuation routes

[1079] The server reanalyzes the data obtained from the robot, locates the location of the victims, calculates safe evacuation routes, and notifies the user's smartphone app.

[1080] Example of input prompt for generative AI model

[1081] Prompt statement:

[1082] "We have a disaster response system in which users, terminals, and servers work together. Please explain in detail how this system enables quick and efficient disaster response."

[1083] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1084] Step 1:

[1085] The server receives reports from users and automatic transmissions from devices. Specifically, users provide disaster information in the form of text, audio, images, and videos through a smartphone app. This data is sent to the server and stored in the data collection module. The input is disaster information data from users, and the output is the collected, unanalyzed data.

[1086] Step 2:

[1087] The server analyzes the collected data. Specifically, it uses machine learning models such as TensorFlow to analyze image data and identify the location of collapsed buildings. It also uses voice recognition software to convert voice data into text and determine the status of victims. The input is the collected unanalyzed data, and the output is the analysis results (location of collapsed buildings, status of victims).

[1088] Step 3:

[1089] The server generates a behavior plan for the rescue robot based on the analysis results. Specifically, it uses a behavior plan generation algorithm to create an action plan to instruct the robot, including detailed steps and routes for the robot to take. The input is the analysis results, and the output is the robot's behavior plan.

[1090] Step 4:

[1091] The server sends the generated action plan to the rescue robot. Specifically, it sends instructions to the robot's control unit via Wi-Fi or LTE network. This causes the robot to move to the specified location and begin on-site investigation and rescue operations. The input is the robot's action plan, and the output is the instructions for the robot to initiate its actions.

[1092] Step 5:

[1093] The terminal then transmits the on-site data collected by the robot back to the server. Specifically, the data acquired by the robot using cameras and sensors is transmitted to the server via Wi-Fi or LTE networks. The input is the on-site data collected by the robot, and the output is the on-site data transmitted to the server.

[1094] Step 6:

[1095] The server re-analyzes the on-site data received from the robot. Specifically, as with the initial analysis, it uses machine learning models to identify the locations of victims and to confirm the on-site situation in detail. The input is the on-site data sent from the robot, and the output is the detailed analysis results.

[1096] Step 7:

[1097] The server generates the optimal evacuation route based on the detailed analysis results. Specifically, it uses the Google Maps API and a unique route optimization algorithm to calculate the optimal evacuation route based on the latest information. The input is the detailed analysis results, and the output is evacuation route information.

[1098] Step 8:

[1099] The server notifies the generated evacuation route to the user's smartphone app. Specifically, it uses the app's notification function to provide the user with the evacuation route in real time. The input is evacuation route information, and the output is the evacuation route notified to the user.

[1100] (Application example 1)

[1101] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1102] In conventional disaster response and rescue systems, it took time to gather information and rescue victims, which resulted in delays in providing appropriate evacuation routes. Furthermore, there was a lack of a comprehensive system that was integrated across different devices and applications, making it difficult for users to efficiently provide information and evacuate quickly.

[1103] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1104] In this invention, the server includes means for collecting text, audio, image, and video data, means for analyzing the collected data and identifying the location of a disaster and the extent of damage, means for dispatching a robot to the identified disaster location to conduct an on-site investigation and rescue victims, means for generating optimal evacuation routes in real time and providing them to victims, and means for operating as an application installed on a smartphone, smart glasses, a head-mounted display, or a robot. This allows for rapid and accurate information collection in the event of a disaster, smooth rescue operations on site, and immediate evacuation routes to be provided to users.

[1105] "Text" refers to written information expressed in a language.

[1106] "Speech" refers to the human voice and other acoustic information, including, in particular, linguistic information.

[1107] "Image" refers to still visual data, such as photographs or graphics.

[1108] "Video" refers to visual data made up of a series of frames, such as movies and animations.

[1109] A "collection means" is a method or device that collects information and captures it for use within the system.

[1110] An "analyzing means" is a method or device for analyzing collected data and extracting useful information.

[1111] "Means for identification" refers to a method or device for clarifying a specific location or situation based on the analysis results.

[1112] A "robot" is an automated machine, a device that is programmed to perform specific tasks.

[1113] A "dispatch means" is a method or means for sending a robot to a specific location.

[1114] "Field survey" refers to survey activities carried out to confirm the actual situation at the disaster site.

[1115] "Rescue" is the act or activity of helping people in difficult situations.

[1116] An "evacuation route" is a route to a safe place in the event of a disaster.

[1117] A "means for producing" is a method or device for producing a particular result or data.

[1118] The "means for providing" refers to a method or device for transmitting the generated information or data to the user.

[1119] A "system" is a set of devices or software in which multiple elements work together.

[1120] A "smartphone" is a portable electronic device that can run many applications in addition to the functions of a mobile phone.

[1121] "Smart glasses" are a wearable eyeglass-type device that has the function of displaying information.

[1122] A "head-mounted display" is a display device that is worn on the head.

[1123] An "installed application" is software that is pre-configured to run on a particular device.

[1124] This invention is a system that uses multimodal AI and robots for disaster prevention and rescue. Specifically, this invention collects text, audio, image, and video data and analyzes them to support rapid information gathering and rescue operations. It also ensures the safety of victims by identifying them and providing optimal evacuation routes.

[1125] This system operates in cooperation with the server, terminals, and users. The operation of each component is explained below.

[1126] Server side

[1127] The server consists of the following modules:

[1128] 1. Data Collection Module

[1129] The server collects text, voice, image, and video data sent from users and devices in real time using a communication module and a database management system.

[1130] 2. Data Analysis Module

[1131] The collected data is analyzed by an AI model (for example, a model trained with TensorFlow or PyTorch) to identify the type, scale, and extent of damage caused by the disaster.

[1132] 3. Rescue operation support module

[1133] Based on the analysis results, specific action plans and detailed instructions are given to the rescue robots using robot control software and communication protocols.

[1134] 4. Evacuation route generation module

[1135] The server calculates the optimal evacuation route based on the information collected in real time and provides it to the user. This function is realized using location calculation tools such as the geopy package.

[1136] Terminal side

[1137] The device consists of the following modules:

[1138] 1. Data Entry Module

[1139] The device transmits voice, text, image, and video data from the user to a server in real time through an application installed on a smartphone, smart glasses, head-mounted display, or robot.

[1140] 2. Robot Control Module

[1141] The system receives instructions from the server and controls the rescue robot. The robot is equipped with cameras and sensors, conducts on-site surveys, and sends the data to the server.

[1142] User side

[1143] The user interacts with the system through the following interfaces:

[1144] 1. Disaster Information Provision Interface

[1145] Users can report the damage situation using their smartphones or a dedicated app, and can use voice commands and post images.

[1146] 2. Evacuation route generation interface

[1147] The server notifies the user of the generated evacuation route, and the user evacuates by following the evacuation route based on this information.

[1148] Specific examples

[1149] For example, consider a case where a large earthquake occurs and many buildings collapse in a certain city. A user uses a smartphone app to report by voice that "an earthquake has occurred" and uploads photos and videos of the collapsed buildings. This data is sent to a server.

[1150] The server analyzes the received data and identifies the extent of the damage and the location of the victims. Based on the results of this analysis, rescue robots are dispatched to conduct on-site investigations. The data collected by the robots is also sent to the server for further analysis.

[1151] The calculated evacuation route is sent to the user's smartphone app, and the user follows the route to a safe location.

[1152] Example prompt sentence:

[1153] "An earthquake has occurred. A building is collapsing. Many victims have been killed. Please analyze the situation based on audio, images, and video. Please suggest appropriate rescue actions. Text: An earthquake has occurred. Images: Photos of collapsed buildings. Video: Video of the collapsed area. Audio: Screams of victims."

[1154] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1155] Step 1:

[1156] Users report the disaster situation through a smartphone app. They report "an earthquake has occurred" using voice commands or text input, and also upload photos and videos of collapsed buildings. This data is collected by the data collection module of the present invention and sent to the server in real time.

[1157] Input: Voice commands, text, images, video data

[1158] Output: Disaster report data sent to the server

[1159] Step 2:

[1160] The server centrally manages the received voice, text, image, and video data in a data collection module, then passes it to a data analysis module, which uses software to convert the voice data into text and uses the image and video data to identify the extent of the damage and victims.

[1161] Input: Audio, text, image, video data

[1162] Output: Analyzed text, damage situation data, victim location data

[1163] What it does: The server uses voice recognition software to convert speech to text and image analysis software to identify the details of the damage.

[1164] Step 3:

[1165] The server identifies the location of the disaster and the extent of the damage based on the analyzed data, and issues instructions to the rescue robot via the rescue operation support module. The rescue robot is dispatched to the designated location, re-surveys the local situation using sensors and cameras, and sends additional data to the server.

[1166] Input: Analysis results (disaster location, damage situation)

[1167] Output: Instructions for rescue robots

[1168] Specific operation: The server calculates the location where the rescue robot should head based on GPS data, sends the instructions to the robot, and has it carry out the instructions.

[1169] Step 4:

[1170] The server then analyzes the newly collected data again using the data analysis module, and generates an evacuation route optimized for the location of the disaster victims. The evacuation route generation module uses location calculation tools such as geopy to calculate the safest evacuation route.

[1171] Input: Local data sent from the rescue robot

[1172] Output: Optimized evacuation route data

[1173] Specific operation: The server uses the geographic information system to recalculate evacuation routes based on the newly received local data.

[1174] Step 5:

[1175] The server then sends the calculated evacuation route data to the user's smartphone app. The user can then check the optimal evacuation route through the app and follow the displayed instructions to evacuate. The app continues to update the evacuation route information in real time.

[1176] Input: Optimized evacuation route data

[1177] Output: Evacuation route information sent to the user's smartphone app

[1178] Specific operation: The server sends the calculated evacuation route to the user's smartphone and displays it on the app screen.

[1179] Example prompt sentence:

[1180] "An earthquake has occurred. A building is collapsing. Many victims have been killed. Please analyze the situation based on audio, images, and video. Please suggest appropriate rescue actions. Text: An earthquake has occurred. Images: Photos of collapsed buildings. Video: Video of the collapsed area. Audio: Screams of victims."

[1181] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1182] This invention is a system that improves the quality of rescue operations by combining a system that uses multimodal AI and robots for disaster prevention and rescue operations with an emotion engine that recognizes user emotions. This system not only supports rapid information gathering and rescue operations when a disaster occurs by collecting and analyzing text, audio, images, and videos, but also uses the emotion engine to analyze user emotions and take optimal responses based on those analysis results.

[1183] System overview and main components

[1184] The entire system is composed of a server, a terminal, a user interface, and an emotion engine. The specific operation of each component is explained below.

[1185] Server side

[1186] 1. Data Collection Module

[1187] The server collects text, audio, image, and video data. The data sources include user reports and automatic transmissions from devices. It also works with an emotion engine to collect data based on user emotions.

[1188] 2. Data Analysis Module

[1189] The collected data is analyzed on a server. This analysis identifies the type and scale of the disaster, the extent of the damage, etc. For example, image analysis can be used to pinpoint the location of collapsed buildings, and audio analysis can be used to determine the situation from the voices of victims.

[1190] 3. Rescue operation support module

[1191] Based on the analysis results, the server issues instructions to the rescue robots, including a specific action plan for dispatching them to the disaster site, detailed instructions for investigating the site and rescuing victims, and also takes into account the emotion data analyzed by the emotion engine.

[1192] 4. Evacuation route optimization module

[1193] The server uses the information collected in real time to calculate the optimal evacuation route, taking into account the current situation at the disaster site and the user's emotional state in order to select the safest and fastest route for the victims.

[1194] Terminal side

[1195] 1. Data Entry Module

[1196] The device sends text, voice, image, and video data from the user to the server in real time, and the server quickly grasps the disaster situation based on this data.

[1197] 2. Robot Control Module

[1198] This module controls the rescue robot by receiving instructions from the server. It moves the robot to the designated location, conducts an on-site investigation, and sends the acquired data back to the server.

[1199] User side

[1200] 1. Disaster Information Provision Interface

[1201] Users can provide necessary information in the event of a disaster using a smartphone or a dedicated app. Voice commands and images can be posted through this interface. The emotion engine also analyzes emotions from user speech and input text.

[1202] 2. Evacuation route generation interface

[1203] This is an interface that notifies the user of the evacuation route generated by the server, allowing the user to confirm the optimal evacuation route and evacuate according to the instructions.

[1204] Emotion Engine

[1205] 1. Sentiment Analysis Module

[1206] The emotion engine analyzes the voice and text data to identify the user's emotions, such as whether they are feeling anxious or scared, and notifies the server of the appropriate response.

[1207] 2. Emotion Data Linkage Module

[1208] It works in conjunction with a server and sends emotion-based data to other modules, allowing emotion data to be reflected in rescue operations and the optimization of evacuation routes.

[1209] Specific Example Embodiments

[1210] For example, suppose a large earthquake occurs and many buildings collapse in a certain city area.

[1211] 1. User Reports

[1212] A user uses a smartphone app to report by voice, "An earthquake has occurred and a building has collapsed." In addition, the user takes a photo of the collapsed building within the app and sends it to the server. The emotion engine analyzes emotions such as anxiety and fear from the user's voice.

[1213] 2. Data Collection

[1214] Text, voice, and image data sent from the device are sent to the server in real time, and emotional data is also collected.

[1215] 3. Data Analysis

[1216] The server analyzes the data, pinpoints the location of collapsed buildings from image data, and checks the status of victims from voice data. It also takes into account emotional data to understand the emotional state of the victims.

[1217] 4. Dispatch of rescue robots

[1218] The server issues instructions to rescue robots based on the analysis results and dispatches them to the collapsed site. After the robots arrive, they use cameras and sensors to conduct on-site surveys and send the data to the server. Based on the emotional data, the robots' behavior is also considered.

[1219] 5. Identifying victims and providing evacuation routes

[1220] The server reanalyzes the data received from the robot to identify the location of the victim. It then calculates a safe evacuation route and notifies the user's smartphone app. The evacuation route guidance is adjusted based on the emotion data.

[1221] In this way, the system of the present invention realizes rapid and efficient disaster response and rescue operations. By combining it with an emotion engine, it becomes possible to provide support that takes into consideration the psychological state of the victims, significantly improving the safety of victims and the rescue of their lives.

[1222] The processing flow will be explained below.

[1223] Step 1:

[1224] Users report the occurrence of a disaster using a smartphone app. For example, they report by voice, "An earthquake occurred and a building collapsed," and take and send a photo of the collapsed building with their smartphone. The emotion engine analyzes emotions such as anxiety and fear from the user's voice.

[1225] Step 2:

[1226] The device collects text, voice, and image data provided by the user and transmits them to the server in real time, along with analyzed emotional data.

[1227] Step 3:

[1228] The server receives the data sent from the device and begins analysis using the data analysis module. Text analysis identifies the type and scale of the disaster, image analysis identifies the location of collapsed buildings, and voice analysis determines the situation from the voices of the victims.

[1229] Step 4:

[1230] The server identifies disaster locations with high urgency based on the data analysis results and emotion data, and issues instructions to rescue robots. For example, it sends the robot a specific action plan based on the GPS information of the identified collapsed area and the user's emotional state.

[1231] Step 5:

[1232] The terminal receives instructions from the server and dispatches the rescue robot to the site. The robot control module moves the robot to the specified location.

[1233] Step 6:

[1234] The rescue robot arrives at the designated disaster site and uses its on-board cameras and sensors to conduct on-site surveys, sending the survey data to a server in real time.

[1235] Step 7:

[1236] The server reanalyzes the on-site survey data sent from the robot to identify the location and condition of the victims, and also takes into account the emotional data to understand the psychological state of the victims.

[1237] Step 8:

[1238] Based on the analysis results and emotional data, the server creates an optimal rescue plan through the rescue operation support module and sends instructions to the rescue team, including the location information of the victims and instructions on the necessary rescue equipment. Based on the emotional data, the rescue team is also instructed to take psychological considerations into account.

[1239] Step 9:

[1240] The server generates optimal evacuation routes based on real-time data. The evacuation route optimization module selects the safest and quickest route for disaster victims. It also takes into account emotional data and provides appropriate explanations for evacuation routes.

[1241] Step 10:

[1242] The device notifies the user of the evacuation route information sent from the server. The smartphone app displays evacuation instructions to the user, and the voice assistant guides the user along the evacuation route. The voice assistant provides guidance in a calm voice that adapts to the user's emotional state.

[1243] Step 11:

[1244] Users follow the instructions on the smartphone app and evacuate to a safe location using the evacuation route provided. By acting quickly and calmly based on the instructions, safety is ensured.

[1245] Step 12:

[1246] The server monitors all rescue operations and evacuation situations in real time and updates instructions as new information becomes available, ensuring that responses are always based on the latest information. It also references emotion data and provides enhanced support to users as needed.

[1247] Example 2

[1248] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1249] Current disaster response systems are capable of rapidly collecting and analyzing disaster information, but there are limitations to improving the quality of rescue operations by taking into account the emotional and psychological states of victims. A system that can quickly respond to the anxiety and fear of victims is needed. Furthermore, a system that comprehensively considers current disaster information and the psychological states of victims is also needed to provide optimal evacuation routes in real time.

[1250] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1251] In this invention, the server includes means for collecting text, voice, image, and video data, means for analyzing the collected data and identifying the location of the disaster and the extent of the damage, means for analyzing emotions from the user's voice and text and reflecting the data, means for dispatching a robot to the identified disaster location to conduct an on-site investigation and rescue of victims, and means for generating optimal evacuation routes in real time and providing them to the victims, thereby enabling rapid and efficient disaster response and rescue operations that take into account the emotional state of the victims.

[1252] "Text data" refers to data that includes text information such as sentences and words.

[1253] "Audio data" refers to data in which an audio signal is recorded in digital format.

[1254] "Image data" refers to still image information recorded in digital format.

[1255] "Video data" refers to data that records dynamic video in digital format.

[1256] "Sentiment analysis" refers to the process of identifying a user's emotional state from speech or text.

[1257] "Robot" refers to a mechanical device that can perform designated tasks automatically.

[1258] "Camera" means a device that records still or moving images.

[1259] "Sensor" refers to a device for collecting information about the physical environment.

[1260] An "evacuation route" refers to the geographical route that disaster victims can take to evacuate safely.

[1261] "Server" refers to a computer system for collecting, analyzing, and storing data.

[1262] "User" refers to a person who utilizes the system to provide information and receive instructions.

[1263] "Collection means" refers to the device or method used to obtain data.

[1264] "Analysis means" refers to devices and methods for processing collected data to extract useful information.

[1265] "Dispatch means" refers to a method or device for sending a robot or other device to a specific destination.

[1266] "Real-time" refers to time characteristics in which processing and response occur almost instantaneously.

[1267] This invention is a system for disaster prevention and rescue, and in particular improves the quality of rescue operations by combining an emotion engine that recognizes the user's emotions. The entire system consists of a server, a terminal, a user interface, and an emotion engine.

[1268] server

[1269] The server plays a central role in collecting and analyzing various data. Specifically, it uses the following hardware and software:

[1270] Data Collection Module

[1271] The server collects text, audio, image, and video data reported by users or automatically sent from devices using natural language processing and speech recognition technologies, such as the Google Cloud Speech-to-Text API.

[1272] Data Analysis Module

[1273] The server analyzes the collected data, using Google Cloud Natural Language API for natural language processing (NLP) of text data, Convolutional Neural Network (CNN) technology for image analysis, and the YOLO (You Only Look Once) object recognition algorithm, to identify the type, scale, and damage of the disaster.

[1274] Rescue operation support module

[1275] Based on the analysis results, the server sends specific instructions to the rescue robot, such as instructing it to search for collapsed buildings in the city and formulating a rescue plan for victims. The robot is then dispatched to a designated location to investigate the situation and rescue victims.

[1276] Evacuation route optimization module

[1277] The server uses the Dijkstra algorithm to calculate the optimal evacuation route based on the information and emotion data collected in real time, providing an evacuation route that takes into account the user's psychological state.

[1278] Terminal

[1279] The terminal is responsible for exchanging data between the user and the server. Specifically, a smartphone or a dedicated app is used.

[1280] Data Entry Module

[1281] Users use a smartphone app to input text, voice, image, and video data, which is then sent in real time to a server, where Google Cloud Speech-to-Text is used to convert the voice data into text.

[1282] Robot Control Module

[1283] This module controls the rescue robot by receiving instructions from the server. It is responsible for sending commands to move the robot to a specified location, conducting on-site investigations, and sending the acquired data back to the server.

[1284] User

[1285] Users are responsible for providing disaster information and receiving evacuation route instructions. Specifically, information is exchanged via smartphones and dedicated apps.

[1286] Disaster information provision interface

[1287] Users can provide necessary information in the event of a disaster using a smartphone or a dedicated app. This allows them to send voice commands and post images. The emotion engine also analyzes emotions from the user's speech and input text.

[1288] Evacuation route generation interface

[1289] This is an interface that notifies the user of the evacuation route generated by the server, allowing the user to confirm the optimal evacuation route and evacuate according to the instructions.

[1290] Emotion Engine

[1291] Sentiment Analysis Module

[1292] The emotion engine analyzes voice and text data to identify the user's emotions. This uses IBM Watson's Tone Analyzer technology, which determines emotions such as anxiety or fear, and notifies the server of the appropriate response.

[1293] Emotion data linking module

[1294] It works in conjunction with a server and sends emotion-based data to other modules, allowing emotion data to be reflected in rescue operations and the optimization of evacuation routes.

[1295] Specific Example Embodiments

[1296] For example, suppose a large earthquake occurs and many buildings collapse in a certain city area.

[1297] User Reports

[1298] A user uses a smartphone app to report by voice, "An earthquake has occurred and a building has collapsed." In addition, the user takes a photo of the collapsed building within the app and sends it to the server. The emotion engine analyzes emotions such as anxiety and fear from the user's voice.

[1299] Data collection

[1300] Text, voice, and image data sent from the device are sent to the server in real time, and emotional data is also collected.

[1301] Data analysis

[1302] The server analyzes the data, pinpoints the location of collapsed buildings from image data, and checks the status of victims from voice data. It also takes into account emotional data to understand the emotional state of the victims.

[1303] Dispatch of rescue robots

[1304] The server issues instructions to rescue robots based on the analysis results and dispatches them to the collapsed site. After the robots arrive, they use cameras and sensors to conduct on-site surveys and send the data to the server. Based on the emotional data, the robots' behavior is also considered.

[1305] Identifying victims and providing evacuation routes

[1306] The server reanalyzes the data received from the robot to identify the location of the victim, calculates a safe evacuation route, and notifies the user's smartphone app. The evacuation route guidance is adjusted based on the emotion data.

[1307] Prompt Sentence Examples

[1308] By inputting the following prompt sentence into the generative AI model, an explanation of evacuation route optimization using the emotion engine can be obtained.

[1309] "An earthquake occurred and a building collapsed. I'm very worried. Which evacuation route is safe?"

[1310] Based on this prompt, the system generates the optimal evacuation route and notifies the user.

[1311] In this way, the system of the present invention realizes rapid and efficient disaster response and rescue operations. By combining it with an emotion engine, it becomes possible to provide support that takes into consideration the psychological state of the victims, greatly improving the safety of victims and the ability to save their lives.

[1312] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1313] Step 1:

[1314] Data collection

[1315] Input: A user reports a disaster using a smartphone app. This report can include text, audio, images, and video. For example, a voice message saying "An earthquake has occurred and buildings have collapsed" and a photo of a collapsed building.

[1316] How it works: The device receives user input and converts voice data to text using the Google Cloud Speech-to-Text API. It also uploads image data to cloud storage and processes video data in the same way.

[1317] Output: Text, audio, image, and video data sent from the device to the server.

[1318] Step 2:

[1319] Data analysis

[1320] Input: Text, audio, image, and video data sent from your device to the server.

[1321] How it works: The server analyzes the text data using the Google Cloud Natural Language API to identify the type and scale of the disaster. Image data is analyzed using the YOLO algorithm to identify the state of building collapse, and video data is also analyzed. Audio data is again analyzed using natural language processing.

[1322] Output: Various analyzed data (type of disaster, scale, damage situation, collapsed location, etc.).

[1323] Step 3:

[1324] Emotion analysis

[1325] Input: Voice and text data from the user.

[1326] How it works: The server uses IBM Watson's Tone Analyzer to analyze the user's emotions, extracting emotions such as anxiety or fear from voice and determining similar emotions from text data.

[1327] Output: Analyzed emotion data (user's psychological state such as anxiety or fear).

[1328] Step 4:

[1329] Dispatch and control of rescue robots

[1330] Input: Data analysis results and sentiment analysis results.

[1331] Operation: The server issues instructions to the rescue robot based on the analysis results. Specifically, it instructs it to head to the collapsed area and conduct an on-site investigation using cameras and sensors. The robot collects data and sends it to the server.

[1332] Output: Field survey data (images, videos, sensor data, etc.).

[1333] Step 5:

[1334] Optimizing evacuation routes

[1335] Input: Field survey data and sentiment data collected in real time.

[1336] How it works: The server uses the Dijkstra algorithm to calculate the optimal evacuation route based on the latest collected data, taking into account the current state of the disaster and the user's psychological state.

[1337] Output: Optimal evacuation route.

[1338] Step 6:

[1339] Interface Notifications

[1340] Input: The calculated optimal evacuation route.

[1341] How it works: The server notifies the user's smartphone app of the optimal evacuation route. The user receives the information through the app and follows the evacuation route. The app also provides audio guidance and visual navigation.

[1342] Output: Information to assist the user in evacuation actions.

[1343] In this way, disaster response and rescue operations can be carried out quickly and efficiently through each step. By incorporating an emotion engine, evacuation instructions and rescue operations can be carried out taking into account the psychological state of the victims, further ensuring their safety.

[1344] (Application example 2)

[1345] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1346] In disasters and emergencies, rescue of victims and provision of evacuation routes must be prompt and accurate. However, the current system makes it difficult to respond while taking into account the psychological state of the victims, which may result in inappropriate instructions being given. In particular, in emergencies such as fires and chemical leaks in factories, it is necessary to quickly gather information and provide evacuation instructions that take into account the emotions of workers, so there is room for improvement in the current system.

[1347] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1348] In this invention, the server includes means for collecting text, audio, image, and video data, means for analyzing the collected data and identifying the disaster site and damage status, means for dispatching a robot to the identified disaster site to conduct an on-site investigation and rescue victims, an emotion recognition engine for analyzing the user's emotions and means for adjusting and providing evacuation routes taking the data into consideration, and means for generating optimal evacuation routes in real time and providing them to victims. This enables rapid and accurate disaster response and supports safe evacuation behavior while taking into consideration the psychological state of the victims.

[1349] "Text data" refers to textual information from users, including reports on disasters and emergencies.

[1350] "Voice data" refers to voice information from users, and is used to report or explain the situation in the event of a disaster or emergency.

[1351] "Image data" refers to photographs and image information sent by users, and is used to understand the situation on site and confirm damage.

[1352] "Video data" refers to video footage sent by users and is used to grasp the real-time situation at disaster sites.

[1353] "Data analysis means" refers to the technical means of analyzing collected text, audio, image, and video data to identify the location of the disaster and the extent of the damage.

[1354] "Robot dispatch means" refers to a technical means of dispatching a robot to a specified disaster site to conduct an on-site investigation and rescue victims.

[1355] An "emotion recognition engine" is a technological means of analyzing a user's voice and text data to identify and evaluate their emotional state.

[1356] An "evacuation route adjustment means" is a technical means that takes into account the user's emotional data and generates and provides a safe and optimal evacuation route in real time.

[1357] The system for realizing this application example mainly consists of the following elements.

[1358] Data collection

[1359] The server collects text, audio, image, and video data. These data are transmitted in real time from users' smartphones, head-mounted displays, and other communication devices. The data is mainly collected from user reports.

[1360] Data analysis

[1361] The server analyzes the collected data to identify the location of the disaster and the extent of the damage. This analysis uses techniques such as image analysis, audio analysis, and text analysis. Specific software used includes image analysis tools (e.g., OpenCV), audio analysis tools (e.g., LibROSA), and text analysis tools (e.g., NLTK).

[1362] Emotion Recognition Engine

[1363] The server uses an emotion recognition engine that analyzes voice and text data to identify the user's emotional state and evaluate emotions such as fear and anxiety. The analysis results are used to generate evacuation routes.

[1364] Robot Dispatch

[1365] The server dispatches the robot to the identified disaster site to conduct on-site investigations and rescue victims. The robot is equipped with a camera and sensors, and transmits data collected on-site to the server in real time, enabling a detailed understanding of the situation on-site.

[1366] Evacuation route generation

[1367] The server generates optimal evacuation routes in real time and provides them to disaster victims. The generated evacuation routes are notified to users via their smartphone apps or head-mounted displays. Emotion data from the emotion recognition engine is also taken into account, providing users with optimal and reassuring evacuation instructions.

[1368] Specific examples

[1369] For example, if a fire breaks out in a factory, workers can report the situation using their smartphones or head-mounted displays. They can report, for example, "There's a fire. I want to escape quickly," and send image data to the server. The system collects and analyzes this data. If the emotion recognition engine determines that a worker is feeling strong fear, the server uses that information to generate the optimal evacuation route and alerts the worker to evacuate calmly.

[1370] Prompt Sentence Examples

[1371] User input: "There's a fire and I want to get out quickly."

[1372] System: "You seem scared and anxious. Calmly direct the evacuation route."

[1373] Hardware and software used

[1374] Smartphone / head-mounted display: Used for data collection and evacuation route display

[1375] Server: Responsible for data analysis and evacuation route generation

[1376] Robots: Used for disaster site surveys and rescue operations

[1377] Analysis tools:

[1378] Image analysis tool: OpenCV

[1379] Audio analysis tool: LibROSA

[1380] Text analysis tool: NLTK

[1381] Emotion Recognition Engine: An AI engine that analyzes the user's emotional state

[1382] In this way, the system enables rapid and appropriate disaster response and provides safe evacuation routes that take into account the psychological state of users.

[1383] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1384] Step 1:

[1385] Users can use their smartphones or head-mounted displays to report disasters and emergencies by voice or text. For example, they can report, "There's a fire. I want to escape quickly." At this time, they can also upload images and videos as needed.

[1386] Input: User-generated voice, text, image, and video data

[1387] Output: Report data sent to the server

[1388] Step 2:

[1389] The device transmits the voice, text, image, and video data collected from the user to the server in real time, where the data is packaged according to a specific format.

[1390] Input: Reported data collected from users

[1391] Output: Packaged data sent to the server

[1392] Step 3:

[1393] The server analyzes the received data to identify the location of the disaster and the extent of the damage. It uses a text analysis tool (e.g., NLTK) to convert the speech into text and analyzes the content of the text. It uses an image analysis tool (e.g., OpenCV) to analyze the image data and confirm the specific state of the disaster.

[1394] Input: Data sent from the terminal

[1395] Output: Identification of disaster location and damage status

[1396] Step 4:

[1397] The server uses an emotion recognition engine to identify the user's emotional state based on the analyzed data. Voice and text data are input into the emotion recognition engine, which calculates an emotion score such as fear or anxiety.

[1398] Input: Parsed audio and text data

[1399] Output: User sentiment score

[1400] Step 5:

[1401] The server issues instructions to dispatch robots to identified disaster sites. The robots are equipped with cameras and sensors to conduct on-site surveys and rescue victims. Data collected on-site is sent to the server in real time.

[1402] Input: Identification of disaster location and damage status

[1403] Output: Robot dispatch instructions and on-site investigation data

[1404] Step 6:

[1405] The server re-analyzes the on-site data sent from the robot and identifies the location of the victims. Based on this information, a safe and optimal evacuation route is generated. The user's emotion score is also taken into consideration, and appropriate evacuation instructions are given. The evacuation route is calculated using the NetworkX library, etc.

[1406] Input: Field survey data and emotion scores from the robot

[1407] Output: Optimal evacuation route and evacuation guidance information

[1408] Step 7:

[1409] The server notifies the user of the generated optimal evacuation route via a smartphone app or head-mounted display, displaying a message according to the user's emotional state.

[1410] Input: Optimal evacuation route and evacuation guidance information

[1411] Output: Evacuation route notification and evacuation instruction message to the user

[1412] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1413] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1414] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1415] [Fourth embodiment]

[1416] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1417] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1418] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1419] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1420] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1421] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1422] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1423] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1424] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1425] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1426] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1427] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1428] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1429] This invention is a system that uses multimodal AI and robots for disaster prevention and rescue. This system collects and analyzes text, audio, images, and video to support rapid information gathering and rescue operations in the event of a disaster. It also identifies victims and ensures their safety by providing optimal evacuation routes.

[1430] System overview and main components

[1431] The entire system is mainly composed of a server, a terminal, and a user interface. The specific operation of each component is explained below.

[1432] Server side

[1433] 1. Data Collection Module

[1434] The server collects text, audio, image, and video data. The sources of data include reports from users and automatic transmissions from devices. This allows for the acquisition of a wide range of data in real time.

[1435] 2. Data Analysis Module

[1436] The collected data is analyzed on a server. This analysis identifies the type and scale of the disaster, the extent of the damage, etc. For example, image analysis can be used to pinpoint the location of collapsed buildings, and audio analysis can be used to determine the situation from the voices of victims.

[1437] 3. Rescue operation support module

[1438] Based on the analysis results, the server issues instructions to the rescue robots, including a specific action plan for dispatching them to the disaster site, as well as detailed instructions for investigating the site and rescuing victims.

[1439] 4. Evacuation route optimization module

[1440] The server uses the information collected in real time to calculate the optimal evacuation route, taking into account the current situation at the disaster site in order to select the safest and fastest route for the victims.

[1441] Terminal side

[1442] 1. Data Entry Module

[1443] The device sends text, voice, image, and video data from the user to the server in real time, allowing the server to quickly grasp the situation of the disaster based on this data.

[1444] 2. Robot Control Module

[1445] This module controls the rescue robot by receiving instructions from the server. It moves the robot to the designated location, conducts an on-site investigation, and sends the acquired data back to the server.

[1446] User side

[1447] 1. Disaster Information Provision Interface

[1448] Users can provide necessary information in the event of a disaster using a smartphone or a dedicated app. Voice commands and image posting are possible through this interface.

[1449] 2. Evacuation route generation interface

[1450] This is an interface that notifies the user of the evacuation route generated by the server, allowing the user to confirm the optimal evacuation route and evacuate according to the instructions.

[1451] Specific Example Embodiments

[1452] For example, suppose a large earthquake occurs and many buildings collapse in a certain city area.

[1453] 1. User Reports

[1454] A user uses a smartphone app to report by voice, "An earthquake has occurred and a building has collapsed." In addition, the user takes a photo of the collapsed building within the app and sends it to the server.

[1455] 2. Data Collection

[1456] Text, voice, and image data sent from the terminal are sent to the server in real time.

[1457] 3. Data Analysis

[1458] The server analyzes the data, identifies the location of the collapsed building from the image data, and confirms the condition of the victims from the audio data.

[1459] 4. Dispatch of rescue robots

[1460] Based on the analysis results, the server issues instructions to rescue robots and dispatches them to the collapsed site. After arriving, the robots use cameras and sensors to conduct on-site surveys and send the data back to the server.

[1461] 5. Identifying victims and providing evacuation routes

[1462] The server reanalyzes the data received from the robot to identify the location of the victims, calculates a safe evacuation route, and notifies the user's smartphone app.

[1463] In this way, the system of the present invention realizes rapid and efficient disaster response and rescue operations, significantly improving the safety of disaster victims and saving their lives.

[1464] The processing flow will be explained below.

[1465] Step 1:

[1466] Users can report the occurrence of a disaster using a smartphone app. For example, they can report by voice, "An earthquake has occurred and a building has collapsed," and take and send a photo of the collapsed building with their smartphone.

[1467] Step 2:

[1468] The device collects text, voice, and image data provided by the user and transmits it to the server in real time, allowing disaster conditions to be immediately communicated to the server.

[1469] Step 3:

[1470] The server receives the data sent from the device and begins analysis using the data analysis module. Text analysis identifies the type and scale of the disaster, image analysis identifies the location of collapsed buildings, and voice analysis determines the situation from the voices of the victims.

[1471] Step 4:

[1472] Based on the results of the data analysis, the server identifies disaster locations with the highest urgency and issues instructions to rescue robots, such as sending GPS information of identified collapsed areas to the robots.

[1473] Step 5:

[1474] The terminal receives instructions from the server and dispatches the rescue robot to the site. The robot control module moves the robot to the specified location.

[1475] Step 6:

[1476] The rescue robot arrives at the designated disaster site and uses its on-board cameras and sensors to conduct on-site surveys, sending the survey data to a server in real time.

[1477] Step 7:

[1478] The server re-analyzes the on-site survey data sent from the robot to determine the location and condition of the victims, which will then be used to determine the priority of rescue efforts.

[1479] Step 8:

[1480] Based on the analysis results, the server creates an optimal rescue plan through the rescue operation support module and sends instructions to the rescue team, including the location information of the victims and instructions on the necessary rescue equipment.

[1481] Step 9:

[1482] The server generates optimal evacuation routes based on real-time data. The evacuation route optimization module selects the safest and fastest route for disaster victims.

[1483] Step 10:

[1484] The device notifies the user of the evacuation route information sent from the server, and the smartphone app displays evacuation instructions to the user, and the voice assistant provides route guidance.

[1485] Step 11:

[1486] Users follow the instructions on the smartphone app and evacuate to a safe location using the evacuation route provided. By acting quickly based on the instructions, safety is ensured.

[1487] Step 12:

[1488] The server monitors all rescue and evacuation operations in real time and updates instructions based on new information as needed, ensuring that responses are always based on the most up-to-date information.

[1489] Example 1

[1490] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1491] When a disaster occurs, rapid information gathering and situation assessment are required, but in many cases, rescue efforts for victims are delayed due to a lack of necessary data or the inability to provide appropriate evacuation routes. Furthermore, ineffective provision of information by victims or the use of robots can lead to the spread of damage. The objective of this invention is to solve these problems.

[1492] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1493] In this invention, the server includes means for collecting text, audio, image, and video data, means for analyzing the collected data and identifying the location of the disaster and the extent of the damage, means for dispatching a robot to the identified disaster location to conduct an on-site investigation and rescue victims, means for generating optimal evacuation routes in real time and providing them to the victims, means for generating an action plan for the robot based on the analysis results and sending instructions, and means for collecting information and providing evacuation routes via the user's smart device. This makes it possible to quickly and efficiently grasp the disaster situation and realize appropriate rescue operations and evacuation support.

[1494] "Text, audio, image, and video data" refers to digital data collected from users and devices that includes information on the situation and damage caused by a disaster.

[1495] "Collection methods" are the mechanisms and infrastructure for obtaining text, audio, image, and video data reported by users or automatically transmitted from devices.

[1496] "Means of analysis" refers to algorithms and software that process collected data and identify the type, scale, and damage caused by a disaster.

[1497] The "disaster occurrence location" refers to the location where the disaster actually occurred, and is an area identified based on the analyzed data.

[1498] "Damage situation" refers to the scope and extent of physical or human damage caused by a disaster, and is assessed based on collected and analyzed data.

[1499] A "robot" is an autonomous or remotely operated mechanical device that is dispatched to a designated disaster site to conduct on-site investigations and rescue victims.

[1500] "Field survey" refers to the act of a robot using cameras and sensors at the disaster site to confirm the extent of the damage and collect data.

[1501] "Victim rescue" refers to the act of using robots or other means to safely evacuate people caught in disasters.

[1502] "Generating optimal evacuation routes in real time" is the process of calculating the quickest and safest route for disaster victims based on the latest data.

[1503] "Means to provide" refers to the communications infrastructure and interfaces for notifying disaster victims of the calculated evacuation routes and sending instructions.

[1504] The "means for generating a robot's action plan based on the analysis results and transmitting instructions" is a mechanism for creating a specific operation plan for the rescue robot based on data analysis and communicating those instructions to the robot.

[1505] "Means for collecting information and providing evacuation routes through users' smart devices" refers to a system for receiving data from users using portable electronic devices such as smartphones and tablets, and sending evacuation instructions and route guidance.

[1506] This invention is a system that uses multimodal AI and robots for disaster response and rescue, which collects and analyzes text, audio, image, and video data to support rapid information gathering and rescue operations. It also identifies victims and ensures their safety by providing optimal evacuation routes.

[1507] System configuration

[1508] The system is mainly composed of a server, a terminal, and a user interface. The operation and role of each component are explained below.

[1509] Server-side behavior

[1510] The server includes the following modules:

[1511] 1. Data Collection Module

[1512] The server receives voice, text, image, and video data reported by users in real time using a REST API. Users provide data through a smartphone app.

[1513] 2. Data Analysis Module

[1514] The server uses machine learning models such as TensorFlow to analyze image data and identify the location of collapsed buildings, and also uses a voice recognition system to analyze user reports and determine the status of victims.

[1515] 3. Rescue operation support module

[1516] Based on the results of the data analysis, the server generates an action plan for the rescue robot and sends instructions to the robot via Wi-Fi or LTE networks, including how to investigate the disaster site and how to rescue victims.

[1517] 4. Evacuation route optimization module

[1518] The server uses the Google Maps API and a proprietary route optimization algorithm to calculate the optimal evacuation route based on the latest disaster information, and the calculated route is notified to the user via a smartphone app.

[1519] Operation on the terminal side

[1520] The terminal includes the following modules:

[1521] 1. Data Entry Module

[1522] The device (smartphone or tablet) transmits text, voice, image, and video data provided by the user to the server in real time. This process uses a camera app and a voice recording app.

[1523] 2. Robot Control Module

[1524] The terminal receives instructions from the server and controls the rescue robot. The robot moves to the designated location, conducts an on-site investigation, and transmits data obtained from sensors and cameras back to the server.

[1525] User behavior

[1526] Users participate in the system through the following interfaces:

[1527] 1. Disaster Information Provision Interface

[1528] Users use a smartphone app to provide information in the event of a disaster by taking photos of the collapsed area or reporting the damage situation via voice.

[1529] 2. Evacuation route generation interface

[1530] The user receives the evacuation route generated by the server on their smartphone app and evacuates by following the displayed instructions, allowing the user to quickly confirm the optimal evacuation route.

[1531] Specific Example Embodiments

[1532] For example, the scenario is as follows when a large earthquake occurs in a city area and many buildings collapse.

[1533] 1. User Reports

[1534] A user uses a smartphone app to report by voice that "an earthquake has occurred and a building has collapsed," and sends a photo of the collapsed building to the server.

[1535] 2. Data Collection

[1536] The server receives text, voice, and image data sent by the user in real time.

[1537] 3. Data Analysis

[1538] The server analyzes image data to identify the location of collapsed buildings and analyzes audio data to understand the situation of victims.

[1539] 4. Dispatch of rescue robots

[1540] Based on the analysis results, the server issues specific instructions to the rescue robot and dispatches it to the collapsed site. The robot uses cameras and sensors to conduct on-site surveys and transmits the data to the server.

[1541] 5. Identifying victims and providing evacuation routes

[1542] The server reanalyzes the data obtained from the robot, locates the location of the victims, calculates safe evacuation routes, and notifies the user's smartphone app.

[1543] Example of input prompt for generative AI model

[1544] Prompt statement:

[1545] "We have a disaster response system in which users, terminals, and servers work together. Please explain in detail how this system enables quick and efficient disaster response."

[1546] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1547] Step 1:

[1548] The server receives reports from users and automatic transmissions from devices. Specifically, users provide disaster information in the form of text, audio, images, and videos through a smartphone app. This data is sent to the server and stored in the data collection module. The input is disaster information data from users, and the output is the collected, unanalyzed data.

[1549] Step 2:

[1550] The server analyzes the collected data. Specifically, it uses machine learning models such as TensorFlow to analyze image data and identify the location of collapsed buildings. It also uses voice recognition software to convert voice data into text and determine the status of victims. The input is the collected unanalyzed data, and the output is the analysis results (location of collapsed buildings, status of victims).

[1551] Step 3:

[1552] The server generates a behavior plan for the rescue robot based on the analysis results. Specifically, it uses a behavior plan generation algorithm to create an action plan to instruct the robot, including detailed steps and routes for the robot to take. The input is the analysis results, and the output is the robot's behavior plan.

[1553] Step 4:

[1554] The server sends the generated action plan to the rescue robot. Specifically, it sends instructions to the robot's control unit via Wi-Fi or LTE network. This causes the robot to move to the specified location and begin on-site investigation and rescue operations. The input is the robot's action plan, and the output is the instructions for the robot to initiate its actions.

[1555] Step 5:

[1556] The terminal then transmits the on-site data collected by the robot back to the server. Specifically, the data acquired by the robot using cameras and sensors is transmitted to the server via Wi-Fi or LTE networks. The input is the on-site data collected by the robot, and the output is the on-site data transmitted to the server.

[1557] Step 6:

[1558] The server re-analyzes the on-site data received from the robot. Specifically, as with the initial analysis, it uses machine learning models to identify the locations of victims and to confirm the on-site situation in detail. The input is the on-site data sent from the robot, and the output is the detailed analysis results.

[1559] Step 7:

[1560] The server generates the optimal evacuation route based on the detailed analysis results. Specifically, it uses the Google Maps API and a unique route optimization algorithm to calculate the optimal evacuation route based on the latest information. The input is the detailed analysis results, and the output is evacuation route information.

[1561] Step 8:

[1562] The server notifies the generated evacuation route to the user's smartphone app. Specifically, it uses the app's notification function to provide the user with the evacuation route in real time. The input is evacuation route information, and the output is the evacuation route notified to the user.

[1563] (Application example 1)

[1564] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1565] In conventional disaster response and rescue systems, it took time to gather information and rescue victims, which resulted in delays in providing appropriate evacuation routes. Furthermore, there was a lack of a comprehensive system that was integrated across different devices and applications, making it difficult for users to efficiently provide information and evacuate quickly.

[1566] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1567] In this invention, the server includes means for collecting text, audio, image, and video data, means for analyzing the collected data and identifying the location of a disaster and the extent of damage, means for dispatching a robot to the identified disaster location to conduct an on-site investigation and rescue victims, means for generating optimal evacuation routes in real time and providing them to victims, and means for operating as an application installed on a smartphone, smart glasses, a head-mounted display, or a robot. This allows for rapid and accurate information collection in the event of a disaster, smooth rescue operations on site, and immediate evacuation routes to be provided to users.

[1568] "Text" refers to written information expressed in a language.

[1569] "Speech" refers to the human voice and other acoustic information, including, in particular, linguistic information.

[1570] "Image" refers to still visual data, such as photographs or graphics.

[1571] "Video" refers to visual data made up of a series of frames, such as movies and animations.

[1572] A "collection means" is a method or device that collects information and captures it for use within the system.

[1573] An "analyzing means" is a method or device for analyzing collected data and extracting useful information.

[1574] "Means for identification" refers to a method or device for clarifying a specific location or situation based on the analysis results.

[1575] A "robot" is an automated machine, a device that is programmed to perform specific tasks.

[1576] A "dispatch means" is a method or means for sending a robot to a specific location.

[1577] "Field survey" refers to survey activities carried out to confirm the actual situation at the disaster site.

[1578] "Rescue" is the act or activity of helping people in difficult situations.

[1579] An "evacuation route" is a route to a safe place in the event of a disaster.

[1580] A "means for producing" is a method or device for producing a particular result or data.

[1581] The "means for providing" refers to a method or device for transmitting the generated information or data to the user.

[1582] A "system" is a set of devices or software in which multiple elements work together.

[1583] A "smartphone" is a portable electronic device that can run many applications in addition to the functions of a mobile phone.

[1584] "Smart glasses" are a wearable eyeglass-type device that has the function of displaying information.

[1585] A "head-mounted display" is a display device that is worn on the head.

[1586] An "installed application" is software that is pre-configured to run on a particular device.

[1587] This invention is a system that uses multimodal AI and robots for disaster prevention and rescue. Specifically, this invention collects text, audio, image, and video data and analyzes them to support rapid information gathering and rescue operations. It also ensures the safety of victims by identifying them and providing optimal evacuation routes.

[1588] This system operates in cooperation with the server, terminals, and users. The operation of each component is explained below.

[1589] Server side

[1590] The server consists of the following modules:

[1591] 1. Data Collection Module

[1592] The server collects text, voice, image, and video data sent from users and devices in real time using a communication module and a database management system.

[1593] 2. Data Analysis Module

[1594] The collected data is analyzed by an AI model (for example, a model trained with TensorFlow or PyTorch) to identify the type, scale, and extent of damage caused by the disaster.

[1595] 3. Rescue operation support module

[1596] Based on the analysis results, specific action plans and detailed instructions are given to the rescue robots using robot control software and communication protocols.

[1597] 4. Evacuation route generation module

[1598] The server calculates the optimal evacuation route based on the information collected in real time and provides it to the user. This function is realized using location calculation tools such as the geopy package.

[1599] Terminal side

[1600] The device consists of the following modules:

[1601] 1. Data Entry Module

[1602] The device transmits voice, text, image, and video data from the user to a server in real time through an application installed on a smartphone, smart glasses, head-mounted display, or robot.

[1603] 2. Robot Control Module

[1604] The system receives instructions from the server and controls the rescue robot. The robot is equipped with cameras and sensors, conducts on-site surveys, and sends the data to the server.

[1605] User side

[1606] The user interacts with the system through the following interfaces:

[1607] 1. Disaster Information Provision Interface

[1608] Users can report the damage situation using their smartphones or a dedicated app, and can use voice commands and post images.

[1609] 2. Evacuation route generation interface

[1610] The server notifies the user of the generated evacuation route, and the user evacuates by following the evacuation route based on this information.

[1611] Specific examples

[1612] For example, consider a case where a large earthquake occurs and many buildings collapse in a certain city. A user uses a smartphone app to report by voice that "an earthquake has occurred" and uploads photos and videos of the collapsed buildings. This data is sent to a server.

[1613] The server analyzes the received data and identifies the extent of the damage and the location of the victims. Based on the results of this analysis, rescue robots are dispatched to conduct on-site investigations. The data collected by the robots is also sent to the server for further analysis.

[1614] The calculated evacuation route is sent to the user's smartphone app, and the user follows the route to a safe location.

[1615] Example prompt sentence:

[1616] "An earthquake has occurred. A building is collapsing. Many victims have been killed. Please analyze the situation based on audio, images, and video. Please suggest appropriate rescue actions. Text: An earthquake has occurred. Images: Photos of collapsed buildings. Video: Video of the collapsed area. Audio: Screams of victims."

[1617] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1618] Step 1:

[1619] Users report the disaster situation through a smartphone app. They report "an earthquake has occurred" using voice commands or text input, and also upload photos and videos of collapsed buildings. This data is collected by the data collection module of the present invention and sent to the server in real time.

[1620] Input: Voice commands, text, images, video data

[1621] Output: Disaster report data sent to the server

[1622] Step 2:

[1623] The server centrally manages the received voice, text, image, and video data in a data collection module, then passes it to a data analysis module, which uses software to convert the voice data into text and uses the image and video data to identify the extent of the damage and victims.

[1624] Input: Audio, text, image, video data

[1625] Output: Analyzed text, damage situation data, victim location data

[1626] What it does: The server uses voice recognition software to convert speech to text and image analysis software to identify the details of the damage.

[1627] Step 3:

[1628] The server identifies the location of the disaster and the extent of the damage based on the analyzed data, and issues instructions to the rescue robot via the rescue operation support module. The rescue robot is dispatched to the designated location, re-surveys the local situation using sensors and cameras, and sends additional data to the server.

[1629] Input: Analysis results (disaster location, damage situation)

[1630] Output: Instructions for rescue robots

[1631] Specific operation: The server calculates the location where the rescue robot should head based on GPS data, sends the instructions to the robot, and has it carry out the instructions.

[1632] Step 4:

[1633] The server then analyzes the newly collected data again using the data analysis module, and generates an evacuation route optimized for the location of the disaster victims. The evacuation route generation module uses location calculation tools such as geopy to calculate the safest evacuation route.

[1634] Input: Local data sent from the rescue robot

[1635] Output: Optimized evacuation route data

[1636] Specific operation: The server uses the geographic information system to recalculate evacuation routes based on the newly received local data.

[1637] Step 5:

[1638] The server then sends the calculated evacuation route data to the user's smartphone app. The user can then check the optimal evacuation route through the app and follow the displayed instructions to evacuate. The app continues to update the evacuation route information in real time.

[1639] Input: Optimized evacuation route data

[1640] Output: Evacuation route information sent to the user's smartphone app

[1641] Specific operation: The server sends the calculated evacuation route to the user's smartphone and displays it on the app screen.

[1642] Example prompt sentence:

[1643] "An earthquake has occurred. A building is collapsing. Many victims have been killed. Please analyze the situation based on audio, images, and video. Please suggest appropriate rescue actions. Text: An earthquake has occurred. Images: Photos of collapsed buildings. Video: Video of the collapsed area. Audio: Screams of victims."

[1644] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1645] This invention is a system that improves the quality of rescue operations by combining a system that uses multimodal AI and robots for disaster prevention and rescue operations with an emotion engine that recognizes user emotions. This system not only supports rapid information gathering and rescue operations when a disaster occurs by collecting and analyzing text, audio, images, and videos, but also uses the emotion engine to analyze user emotions and take optimal responses based on those analysis results.

[1646] System overview and main components

[1647] The entire system is composed of a server, a terminal, a user interface, and an emotion engine. The specific operation of each component is explained below.

[1648] Server side

[1649] 1. Data Collection Module

[1650] The server collects text, audio, image, and video data. The data sources include user reports and automatic transmissions from devices. It also works with an emotion engine to collect data based on user emotions.

[1651] 2. Data Analysis Module

[1652] The collected data is analyzed on a server. This analysis identifies the type and scale of the disaster, the extent of the damage, etc. For example, image analysis can be used to pinpoint the location of collapsed buildings, and audio analysis can be used to determine the situation from the voices of victims.

[1653] 3. Rescue operation support module

[1654] Based on the analysis results, the server issues instructions to the rescue robots, including a specific action plan for dispatching them to the disaster site, detailed instructions for investigating the site and rescuing victims, and also takes into account the emotion data analyzed by the emotion engine.

[1655] 4. Evacuation route optimization module

[1656] The server uses the information collected in real time to calculate the optimal evacuation route, taking into account the current situation at the disaster site and the user's emotional state in order to select the safest and fastest route for the victims.

[1657] Terminal side

[1658] 1. Data Entry Module

[1659] The device sends text, voice, image, and video data from the user to the server in real time, and the server quickly grasps the disaster situation based on this data.

[1660] 2. Robot Control Module

[1661] This module controls the rescue robot by receiving instructions from the server. It moves the robot to the designated location, conducts an on-site investigation, and sends the acquired data back to the server.

[1662] User side

[1663] 1. Disaster Information Provision Interface

[1664] Users can provide necessary information in the event of a disaster using a smartphone or a dedicated app. Voice commands and images can be posted through this interface. The emotion engine also analyzes emotions from user speech and input text.

[1665] 2. Evacuation route generation interface

[1666] This is an interface that notifies the user of the evacuation route generated by the server, allowing the user to confirm the optimal evacuation route and evacuate according to the instructions.

[1667] Emotion Engine

[1668] 1. Sentiment Analysis Module

[1669] The emotion engine analyzes the voice and text data to identify the user's emotions, such as whether they are feeling anxious or scared, and notifies the server of the appropriate response.

[1670] 2. Emotion Data Linkage Module

[1671] It works in conjunction with a server and sends emotion-based data to other modules, allowing emotion data to be reflected in rescue operations and the optimization of evacuation routes.

[1672] Specific Example Embodiments

[1673] For example, suppose a large earthquake occurs and many buildings collapse in a certain city area.

[1674] 1. User Reports

[1675] A user uses a smartphone app to report by voice, "An earthquake has occurred and a building has collapsed." In addition, the user takes a photo of the collapsed building within the app and sends it to the server. The emotion engine analyzes emotions such as anxiety and fear from the user's voice.

[1676] 2. Data Collection

[1677] Text, voice, and image data sent from the device are sent to the server in real time, and emotional data is also collected.

[1678] 3. Data Analysis

[1679] The server analyzes the data, pinpoints the location of collapsed buildings from image data, and checks the status of victims from voice data. It also takes into account emotional data to understand the emotional state of the victims.

[1680] 4. Dispatch of rescue robots

[1681] The server issues instructions to rescue robots based on the analysis results and dispatches them to the collapsed site. After the robots arrive, they use cameras and sensors to conduct on-site surveys and send the data to the server. Based on the emotional data, the robots' behavior is also considered.

[1682] 5. Identifying victims and providing evacuation routes

[1683] The server reanalyzes the data received from the robot to identify the location of the victim. It then calculates a safe evacuation route and notifies the user's smartphone app. The evacuation route guidance is adjusted based on the emotion data.

[1684] In this way, the system of the present invention realizes rapid and efficient disaster response and rescue operations. By combining it with an emotion engine, it becomes possible to provide support that takes into consideration the psychological state of the victims, significantly improving the safety of victims and the rescue of their lives.

[1685] The processing flow will be explained below.

[1686] Step 1:

[1687] Users report the occurrence of a disaster using a smartphone app. For example, they report by voice, "An earthquake occurred and a building collapsed," and take and send a photo of the collapsed building with their smartphone. The emotion engine analyzes emotions such as anxiety and fear from the user's voice.

[1688] Step 2:

[1689] The device collects text, voice, and image data provided by the user and transmits them to the server in real time, along with analyzed emotional data.

[1690] Step 3:

[1691] The server receives the data sent from the device and begins analysis using the data analysis module. Text analysis identifies the type and scale of the disaster, image analysis identifies the location of collapsed buildings, and voice analysis determines the situation from the voices of the victims.

[1692] Step 4:

[1693] The server identifies disaster locations with high urgency based on the data analysis results and emotion data, and issues instructions to rescue robots. For example, it sends the robot a specific action plan based on the GPS information of the identified collapsed area and the user's emotional state.

[1694] Step 5:

[1695] The terminal receives instructions from the server and dispatches the rescue robot to the site. The robot control module moves the robot to the specified location.

[1696] Step 6:

[1697] The rescue robot arrives at the designated disaster site and uses its on-board cameras and sensors to conduct on-site surveys, sending the survey data to a server in real time.

[1698] Step 7:

[1699] The server reanalyzes the on-site survey data sent from the robot to identify the location and condition of the victims, and also takes into account the emotional data to understand the psychological state of the victims.

[1700] Step 8:

[1701] Based on the analysis results and emotional data, the server creates an optimal rescue plan through the rescue operation support module and sends instructions to the rescue team, including the location information of the victims and instructions on the necessary rescue equipment. Based on the emotional data, the rescue team is also instructed to take psychological considerations into account.

[1702] Step 9:

[1703] The server generates optimal evacuation routes based on real-time data. The evacuation route optimization module selects the safest and quickest route for disaster victims. It also takes into account emotional data and provides appropriate explanations for evacuation routes.

[1704] Step 10:

[1705] The device notifies the user of the evacuation route information sent from the server. The smartphone app displays evacuation instructions to the user, and the voice assistant guides the user along the evacuation route. The voice assistant provides guidance in a calm voice that adapts to the user's emotional state.

[1706] Step 11:

[1707] Users follow the instructions on the smartphone app and evacuate to a safe location using the evacuation route provided. By acting quickly and calmly based on the instructions, safety is ensured.

[1708] Step 12:

[1709] The server monitors all rescue operations and evacuation situations in real time and updates instructions as new information becomes available, ensuring that responses are always based on the latest information. It also references emotion data and provides enhanced support to users as needed.

[1710] Example 2

[1711] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1712] Current disaster response systems are capable of rapidly collecting and analyzing disaster information, but there are limitations to improving the quality of rescue operations by taking into account the emotional and psychological states of victims. A system that can quickly respond to the anxiety and fear of victims is needed. Furthermore, a system that comprehensively considers current disaster information and the psychological states of victims is also needed to provide optimal evacuation routes in real time.

[1713] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1714] In this invention, the server includes means for collecting text, voice, image, and video data, means for analyzing the collected data and identifying the location of the disaster and the extent of the damage, means for analyzing emotions from the user's voice and text and reflecting the data, means for dispatching a robot to the identified disaster location to conduct an on-site investigation and rescue of victims, and means for generating optimal evacuation routes in real time and providing them to the victims, thereby enabling rapid and efficient disaster response and rescue operations that take into account the emotional state of the victims.

[1715] "Text data" refers to data that includes text information such as sentences and words.

[1716] "Audio data" refers to data in which an audio signal is recorded in digital format.

[1717] "Image data" refers to still image information recorded in digital format.

[1718] "Video data" refers to data that records dynamic video in digital format.

[1719] "Sentiment analysis" refers to the process of identifying a user's emotional state from speech or text.

[1720] "Robot" refers to a mechanical device that can perform designated tasks automatically.

[1721] "Camera" means a device that records still or moving images.

[1722] "Sensor" refers to a device for collecting information about the physical environment.

[1723] An "evacuation route" refers to the geographical route that disaster victims can take to evacuate safely.

[1724] "Server" refers to a computer system for collecting, analyzing, and storing data.

[1725] "User" refers to a person who utilizes the system to provide information and receive instructions.

[1726] "Collection means" refers to the device or method used to obtain data.

[1727] "Analysis means" refers to devices and methods for processing collected data to extract useful information.

[1728] "Dispatch means" refers to a method or device for sending a robot or other device to a specific destination.

[1729] "Real-time" refers to time characteristics in which processing and response occur almost instantaneously.

[1730] This invention is a system for disaster prevention and rescue, and in particular improves the quality of rescue operations by combining an emotion engine that recognizes the user's emotions. The entire system consists of a server, a terminal, a user interface, and an emotion engine.

[1731] server

[1732] The server plays a central role in collecting and analyzing various data. Specifically, it uses the following hardware and software:

[1733] Data Collection Module

[1734] The server collects text, audio, image, and video data reported by users or automatically sent from devices using natural language processing and speech recognition technologies, such as the Google Cloud Speech-to-Text API.

[1735] Data Analysis Module

[1736] The server analyzes the collected data, using Google Cloud Natural Language API for natural language processing (NLP) of text data, Convolutional Neural Network (CNN) technology for image analysis, and the YOLO (You Only Look Once) object recognition algorithm, to identify the type, scale, and damage of the disaster.

[1737] Rescue operation support module

[1738] Based on the analysis results, the server sends specific instructions to the rescue robot, such as instructing it to search for collapsed buildings in the city and formulating a rescue plan for victims. The robot is then dispatched to a designated location to investigate the situation and rescue victims.

[1739] Evacuation route optimization module

[1740] The server uses the Dijkstra algorithm to calculate the optimal evacuation route based on the information and emotion data collected in real time, providing an evacuation route that takes into account the user's psychological state.

[1741] Terminal

[1742] The terminal is responsible for exchanging data between the user and the server. Specifically, a smartphone or a dedicated app is used.

[1743] Data Entry Module

[1744] Users use a smartphone app to input text, voice, image, and video data, which is then sent in real time to a server, where Google Cloud Speech-to-Text is used to convert the voice data into text.

[1745] Robot Control Module

[1746] This module controls the rescue robot by receiving instructions from the server. It is responsible for sending commands to move the robot to a specified location, conducting on-site investigations, and sending the acquired data back to the server.

[1747] User

[1748] Users are responsible for providing disaster information and receiving evacuation route instructions. Specifically, information is exchanged via smartphones and dedicated apps.

[1749] Disaster information provision interface

[1750] Users can provide necessary information in the event of a disaster using a smartphone or a dedicated app. This allows them to send voice commands and post images. The emotion engine also analyzes emotions from the user's speech and input text.

[1751] Evacuation route generation interface

[1752] This is an interface that notifies the user of the evacuation route generated by the server, allowing the user to confirm the optimal evacuation route and evacuate according to the instructions.

[1753] Emotion Engine

[1754] Sentiment Analysis Module

[1755] The emotion engine analyzes voice and text data to identify the user's emotions. This uses IBM Watson's Tone Analyzer technology, which determines emotions such as anxiety or fear, and notifies the server of the appropriate response.

[1756] Emotion data linking module

[1757] It works in conjunction with a server and sends emotion-based data to other modules, allowing emotion data to be reflected in rescue operations and the optimization of evacuation routes.

[1758] Specific Example Embodiments

[1759] For example, suppose a large earthquake occurs and many buildings collapse in a certain city area.

[1760] User Reports

[1761] A user uses a smartphone app to report by voice, "An earthquake has occurred and a building has collapsed." In addition, the user takes a photo of the collapsed building within the app and sends it to the server. The emotion engine analyzes emotions such as anxiety and fear from the user's voice.

[1762] Data collection

[1763] Text, voice, and image data sent from the device are sent to the server in real time, and emotional data is also collected.

[1764] Data analysis

[1765] The server analyzes the data, pinpoints the location of collapsed buildings from image data, and checks the status of victims from voice data. It also takes into account emotional data to understand the emotional state of the victims.

[1766] Dispatch of rescue robots

[1767] The server issues instructions to rescue robots based on the analysis results and dispatches them to the collapsed site. After the robots arrive, they use cameras and sensors to conduct on-site surveys and send the data to the server. Based on the emotional data, the robots' behavior is also considered.

[1768] Identifying victims and providing evacuation routes

[1769] The server reanalyzes the data received from the robot to identify the location of the victim, calculates a safe evacuation route, and notifies the user's smartphone app. The evacuation route guidance is adjusted based on the emotion data.

[1770] Prompt Sentence Examples

[1771] By inputting the following prompt sentence into the generative AI model, an explanation of evacuation route optimization using the emotion engine can be obtained.

[1772] "An earthquake occurred and a building collapsed. I'm very worried. Which evacuation route is safe?"

[1773] Based on this prompt, the system generates the optimal evacuation route and notifies the user.

[1774] In this way, the system of the present invention realizes rapid and efficient disaster response and rescue operations. By combining it with an emotion engine, it becomes possible to provide support that takes into consideration the psychological state of the victims, greatly improving the safety of victims and the ability to save their lives.

[1775] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1776] Step 1:

[1777] Data collection

[1778] Input: A user reports a disaster using a smartphone app. This report can include text, audio, images, and video. For example, a voice message saying "An earthquake has occurred and buildings have collapsed" and a photo of a collapsed building.

[1779] How it works: The device receives user input and converts voice data to text using the Google Cloud Speech-to-Text API. It also uploads image data to cloud storage and processes video data in the same way.

[1780] Output: Text, audio, image, and video data sent from the device to the server.

[1781] Step 2:

[1782] Data analysis

[1783] Input: Text, audio, image, and video data sent from your device to the server.

[1784] How it works: The server analyzes the text data using the Google Cloud Natural Language API to identify the type and scale of the disaster. Image data is analyzed using the YOLO algorithm to identify the state of building collapse, and video data is also analyzed. Audio data is again analyzed using natural language processing.

[1785] Output: Various analyzed data (type of disaster, scale, damage situation, collapsed location, etc.).

[1786] Step 3:

[1787] Emotion analysis

[1788] Input: Voice and text data from the user.

[1789] How it works: The server uses IBM Watson's Tone Analyzer to analyze the user's emotions, extracting emotions such as anxiety or fear from voice and determining similar emotions from text data.

[1790] Output: Analyzed emotion data (user's psychological state such as anxiety or fear).

[1791] Step 4:

[1792] Dispatch and control of rescue robots

[1793] Input: Data analysis results and sentiment analysis results.

[1794] Operation: The server issues instructions to the rescue robot based on the analysis results. Specifically, it instructs it to head to the collapsed area and conduct an on-site investigation using cameras and sensors. The robot collects data and sends it to the server.

[1795] Output: Field survey data (images, videos, sensor data, etc.).

[1796] Step 5:

[1797] Optimizing evacuation routes

[1798] Input: Field survey data and sentiment data collected in real time.

[1799] How it works: The server uses the Dijkstra algorithm to calculate the optimal evacuation route based on the latest collected data, taking into account the current state of the disaster and the user's psychological state.

[1800] Output: Optimal evacuation route.

[1801] Step 6:

[1802] Interface Notifications

[1803] Input: The calculated optimal evacuation route.

[1804] How it works: The server notifies the user's smartphone app of the optimal evacuation route. The user receives the information through the app and follows the evacuation route. The app also provides audio guidance and visual navigation.

[1805] Output: Information to assist the user in evacuation actions.

[1806] In this way, disaster response and rescue operations can be carried out quickly and efficiently through each step. By incorporating an emotion engine, evacuation instructions and rescue operations can be carried out taking into account the psychological state of the victims, further ensuring their safety.

[1807] (Application example 2)

[1808] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1809] In disasters and emergencies, rescue of victims and provision of evacuation routes must be prompt and accurate. However, the current system makes it difficult to respond while taking into account the psychological state of the victims, which may result in inappropriate instructions being given. In particular, in emergencies such as fires and chemical leaks in factories, it is necessary to quickly gather information and provide evacuation instructions that take into account the emotions of workers, so there is room for improvement in the current system.

[1810] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1811] In this invention, the server includes means for collecting text, audio, image, and video data, means for analyzing the collected data and identifying the disaster site and damage status, means for dispatching a robot to the identified disaster site to conduct an on-site investigation and rescue victims, an emotion recognition engine for analyzing the user's emotions and means for adjusting and providing evacuation routes taking the data into consideration, and means for generating optimal evacuation routes in real time and providing them to victims. This enables rapid and accurate disaster response and supports safe evacuation behavior while taking into consideration the psychological state of the victims.

[1812] "Text data" refers to textual information from users, including reports on disasters and emergencies.

[1813] "Voice data" refers to voice information from users, and is used to report or explain the situation in the event of a disaster or emergency.

[1814] "Image data" refers to photographs and image information sent by users, and is used to understand the situation on site and confirm damage.

[1815] "Video data" refers to video footage sent by users and is used to grasp the real-time situation at disaster sites.

[1816] "Data analysis means" refers to the technical means of analyzing collected text, audio, image, and video data to identify the location of the disaster and the extent of the damage.

[1817] "Robot dispatch means" refers to a technical means of dispatching a robot to a specified disaster site to conduct an on-site investigation and rescue victims.

[1818] An "emotion recognition engine" is a technological means of analyzing a user's voice and text data to identify and evaluate their emotional state.

[1819] An "evacuation route adjustment means" is a technical means that takes into account the user's emotional data and generates and provides a safe and optimal evacuation route in real time.

[1820] The system for realizing this application example mainly consists of the following elements.

[1821] Data collection

[1822] The server collects text, audio, image, and video data. These data are transmitted in real time from users' smartphones, head-mounted displays, and other communication devices. The data is mainly collected from user reports.

[1823] Data analysis

[1824] The server analyzes the collected data to identify the location of the disaster and the extent of the damage. This analysis uses techniques such as image analysis, audio analysis, and text analysis. Specific software used includes image analysis tools (e.g., OpenCV), audio analysis tools (e.g., LibROSA), and text analysis tools (e.g., NLTK).

[1825] Emotion Recognition Engine

[1826] The server uses an emotion recognition engine that analyzes voice and text data to identify the user's emotional state and evaluate emotions such as fear and anxiety. The analysis results are used to generate evacuation routes.

[1827] Robot Dispatch

[1828] The server dispatches the robot to the identified disaster site to conduct on-site investigations and rescue victims. The robot is equipped with a camera and sensors, and transmits data collected on-site to the server in real time, enabling a detailed understanding of the situation on-site.

[1829] Evacuation route generation

[1830] The server generates optimal evacuation routes in real time and provides them to disaster victims. The generated evacuation routes are notified to users via their smartphone apps or head-mounted displays. Emotion data from the emotion recognition engine is also taken into account, providing users with optimal and reassuring evacuation instructions.

[1831] Specific examples

[1832] For example, if a fire breaks out in a factory, workers can report the situation using their smartphones or head-mounted displays. They can report, for example, "There's a fire. I want to escape quickly," and send image data to the server. The system collects and analyzes this data. If the emotion recognition engine determines that a worker is feeling strong fear, the server uses that information to generate the optimal evacuation route and alerts the worker to evacuate calmly.

[1833] Prompt Sentence Examples

[1834] User input: "There's a fire and I want to get out quickly."

[1835] System: "You seem scared and anxious. Calmly direct the evacuation route."

[1836] Hardware and software used

[1837] Smartphone / head-mounted display: Used for data collection and evacuation route display

[1838] Server: Responsible for data analysis and evacuation route generation

[1839] Robots: Used for disaster site surveys and rescue operations

[1840] Analysis tools:

[1841] Image analysis tool: OpenCV

[1842] Audio analysis tool: LibROSA

[1843] Text analysis tool: NLTK

[1844] Emotion Recognition Engine: An AI engine that analyzes the user's emotional state

[1845] In this way, the system enables rapid and appropriate disaster response and provides safe evacuation routes that take into account the psychological state of users.

[1846] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1847] Step 1:

[1848] Users can use their smartphones or head-mounted displays to report disasters and emergencies by voice or text. For example, they can report, "There's a fire. I want to escape quickly." At this time, they can also upload images and videos as needed.

[1849] Input: User-generated voice, text, image, and video data

[1850] Output: Report data sent to the server

[1851] Step 2:

[1852] The device transmits the voice, text, image, and video data collected from the user to the server in real time, where the data is packaged according to a specific format.

[1853] Input: Reported data collected from users

[1854] Output: Packaged data sent to the server

[1855] Step 3:

[1856] The server analyzes the received data to identify the location of the disaster and the extent of the damage. It uses a text analysis tool (e.g., NLTK) to convert the speech into text and analyzes the content of the text. It uses an image analysis tool (e.g., OpenCV) to analyze the image data and confirm the specific state of the disaster.

[1857] Input: Data sent from the terminal

[1858] Output: Identification of disaster location and damage status

[1859] Step 4:

[1860] The server uses an emotion recognition engine to identify the user's emotional state based on the analyzed data. Voice and text data are input into the emotion recognition engine, which calculates an emotion score such as fear or anxiety.

[1861] Input: Parsed audio and text data

[1862] Output: User sentiment score

[1863] Step 5:

[1864] The server issues instructions to dispatch robots to identified disaster sites. The robots are equipped with cameras and sensors to conduct on-site surveys and rescue victims. Data collected on-site is sent to the server in real time.

[1865] Input: Identification of disaster location and damage status

[1866] Output: Robot dispatch instructions and on-site investigation data

[1867] Step 6:

[1868] The server re-analyzes the on-site data sent from the robot and identifies the location of the victims. Based on this information, a safe and optimal evacuation route is generated. The user's emotion score is also taken into consideration, and appropriate evacuation instructions are given. The evacuation route is calculated using the NetworkX library, etc.

[1869] Input: Field survey data and emotion scores from the robot

[1870] Output: Optimal evacuation route and evacuation guidance information

[1871] Step 7:

[1872] The server notifies the user of the generated optimal evacuation route via a smartphone app or head-mounted display, displaying a message according to the user's emotional state.

[1873] Input: Optimal evacuation route and evacuation guidance information

[1874] Output: Evacuation route notification and evacuation instruction message to the user

[1875] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1876] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1877] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1878] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1879] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1880] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1881] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1882] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1883] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1884] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1885] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1886] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1887] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1888] 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.

[1889] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1890] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1891] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1892] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1893] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1894] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1895] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1896] The following is further disclosed regarding the above embodiment.

[1897] (Claim 1)

[1898] a means of collecting text, audio, image, and video data;

[1899] A means for analyzing the collected data and identifying the location of the disaster and the extent of the damage;

[1900] A means for dispatching a robot to the identified disaster site to conduct on-site investigation and rescue of victims;

[1901] and a means for generating optimal evacuation routes in real time and providing the routes to disaster victims.

[1902] (Claim 2)

[1903] 2. The system of claim 1, wherein the collection of text, audio, image, and video data includes reports from users and real-time transmissions from communication terminals.

[1904] (Claim 3)

[1905] 10. The system of claim 1, wherein the robot is equipped with a camera and sensors and transmits data collected in the field to a server for analysis.

[1906] "Example 1"

[1907] (Claim 1)

[1908] a means of collecting text, audio, image, and video data;

[1909] A means for analyzing the collected data and identifying the location of the disaster and the extent of the damage;

[1910] A means for dispatching a robot to the identified disaster site to conduct on-site investigation and rescue of victims;

[1911] A means to generate optimal evacuation routes in real time and provide them to disaster victims;

[1912] means for generating an action plan for the robot based on the analysis results and transmitting instructions;

[1913] A means for collecting information and providing evacuation routes through a user's smart device;

[1914] A system including:

[1915] (Claim 2)

[1916] 2. The system of claim 1, wherein the collection of text, audio, image, and video data includes reports from users and real-time transmissions from communication terminals.

[1917] (Claim 3)

[1918] 10. The system of claim 1, wherein the robot is equipped with a camera and sensors and transmits data collected in the field to a server for analysis.

[1919] "Application Example 1"

[1920] (Claim 1)

[1921] a means of collecting text, audio, image, and video data;

[1922] A means for analyzing the collected data and identifying the location of the disaster and the extent of the damage;

[1923] A means for dispatching a robot to the identified disaster site to conduct on-site investigation and rescue of victims;

[1924] A means to generate optimal evacuation routes in real time and provide them to disaster victims;

[1925] means operating as an application installed on a smartphone, smart glasses, a head-mounted display, or a robot;

[1926] A system including:

[1927] (Claim 2)

[1928] 2. The system of claim 1, wherein the collection of text, audio, image, and video data includes reports from users and real-time transmissions from communication terminals.

[1929] (Claim 3)

[1930] 10. The system of claim 1, wherein the robot is equipped with a camera and sensors and transmits data collected in the field to a server for analysis.

[1931] "Example 2: Combining Emotion Engines"

[1932] (Claim 1)

[1933] a means of collecting text, audio, image, and video data;

[1934] A means for analyzing the collected data and identifying the location of the disaster and the extent of the damage;

[1935] A means of analyzing emotions from user voice and text and reflecting that data;

[1936] A means for dispatching a robot to the identified disaster site to conduct on-site investigation and rescue of victims;

[1937] A means to generate optimal evacuation routes in real time and provide them to disaster victims;

[1938] A system including:

[1939] (Claim 2)

[1940] 2. The system of claim 1, wherein the collection of text, audio, image, and video data includes reports from users and real-time transmissions from communication terminals.

[1941] (Claim 3)

[1942] 10. The system of claim 1, wherein the robot is equipped with a camera and sensors and transmits data collected in the field to a server for analysis.

[1943] "Application example 2 when combining emotion engines"

[1944] (Claim 1)

[1945] a means of collecting text, audio, image, and video data;

[1946] A means for analyzing the collected data and identifying the location of the disaster and the extent of the damage;

[1947] A means for dispatching a robot to the identified disaster site to conduct on-site investigation and rescue of victims;

[1948] an emotion recognition engine that analyzes the emotions of users and a means for adjusting and providing evacuation routes in consideration of the data;

[1949] A means to generate optimal evacuation routes in real time and provide them to disaster victims;

[1950] A system including:

[1951] (Claim 2)

[1952] 2. The system of claim 1, wherein the collection of text, audio, image, and video data includes reports from users and real-time transmissions from communication terminals.

[1953] (Claim 3)

[1954] 10. The system of claim 1, wherein the robot is equipped with a camera and sensors and transmits data collected in the field to a server for analysis. [Explanation of symbols]

[1955] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means of collecting text, audio, image, and video data; A means for analyzing the collected data and identifying the location of the disaster and the extent of the damage; A means for dispatching a robot to the identified disaster site to conduct on-site investigation and rescue of victims; and a means for generating optimal evacuation routes in real time and providing the routes to disaster victims.

2. 2. The system of claim 1, wherein the collection of text, audio, image, and video data includes reports from users and real-time transmissions from communication terminals.

3. The system of claim 1 , wherein the robot is equipped with a camera and sensors and transmits data collected in the field to a server for analysis.

Images