system

Abstract

We provide the system. [Solution] Means for acquiring an image and transmitting the said image to a data server, The data server includes an analysis means for analyzing the image and estimating the disaster situation, A generation means for transcribing the aforementioned disaster situation into text and outputting it in natural language, A plan generation means that automatically generates an evacuation plan based on the generated natural language information, A transmission and display means for transmitting and displaying the aforementioned evacuation plan to a user device, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In areas where natural disasters occur frequently, it is required that residents quickly grasp the situation during disasters and take appropriate evacuation actions. However, in many cases, it is difficult for residents to accurately recognize their own situation and quickly formulate an effective evacuation plan when a disaster occurs. This problem is particularly prominent for ordinary residents with limited knowledge and experience of disasters. The present invention aims to solve this problem by providing a system that enables the provision of quick and accurate evacuation information during disasters.

Means for Solving the Problems

[0005] This invention provides a system in which a user sends images they have taken to a data server, which then analyzes the images to estimate the disaster situation. The analyzed disaster situation is further transcribed into natural language, and an evacuation plan is automatically created based on the generated information. The evacuation plan includes the nearest evacuation shelter and safe evacuation routes, and this information is transmitted to and displayed on the user's device. This allows the user to obtain information to act quickly and accurately in the event of a disaster.

[0006] "Means for acquiring an image and transmitting the said image to a data server" refers to a function that allows a user to capture image data such as photographs or videos with an electronic device and transmit that data to a server via a network.

[0007] "Analysis means" refers to technical functions that process acquired images on a data server and estimate specific situations or states based on the information obtained therefrom.

[0008] "Generative means" refers to technology that has the ability to convert analyzed data into natural language and generate information in a form that humans can understand.

[0009] A "plan generation tool" is a function that automatically formulates action plans and strategies based on generated information, according to specific conditions.

[0010] A "transmission and display means" is a technical mechanism that transfers information generated from a data server to a user's device and presents the information to the user visually or in other ways. [Brief explanation of the drawing]

[0011] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3]This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0012] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0013] First, let's explain the terminology used in the following explanation.

[0014] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0015] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0016] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0017] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F manages 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), or Bluetooth (registered trademark), etc.

[0018] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0019] [First Embodiment]

[0020] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0021] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0022] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0023] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0024] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0025] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0026] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0027] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0029] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0030] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0031] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0032] This invention is a system that provides rapid and accurate evacuation information during disasters. Specifically, it is a mechanism that analyzes actual disaster situations photographed by the user and automatically generates and provides evacuation plans based on that analysis.

[0033] Users take pictures of disaster areas using their devices. These images are sent to a data server via the network. The data server uses image analysis technology to estimate the current state of the disaster based on the received images. This analysis uses deep learning models and image recognition algorithms to determine the possibility of river flooding and landslides based on visual features.

[0034] The analysis results are converted into user-friendly text using natural language processing technology. For example, information such as "The current rate of water level rise is at a dangerous level" or "Evacuation is necessary within a certain time" is generated.

[0035] The server then uses the generated text to formulate an optimal evacuation plan. This plan can take the user's location into account and include information about the nearest evacuation shelter and precautions to take during evacuation. For example, it may provide specific instructions such as, "The nearest evacuation shelter is XX Park, 1 kilometer away," or "Due to the possibility of ground subsidence caused by the earthquake, an evacuation route along the outside of the building is recommended."

[0036] Finally, the server sends these evacuation plans to the user's terminal, which then displays the information. Users can visually confirm safe evacuation routes and shelters through their terminal screen. This system makes it possible to support the rapid and appropriate evacuation of residents during disasters.

[0037] The following describes the processing flow.

[0038] Step 1:

[0039] Users capture images of the disaster site and surrounding area using devices such as smartphones.

[0040] Step 2:

[0041] Users upload the acquired images to a data server via a dedicated application or web interface over the network.

[0042] Step 3:

[0043] The server applies an image analysis algorithm to the received image data to estimate the extent of the disaster. This analysis is performed using a deep learning model to evaluate water level and the likelihood of landslides.

[0044] Step 4:

[0045] The server uses a natural language processing engine to generate text describing the disaster situation in order to convert the analysis results into natural language.

[0046] Step 5:

[0047] Based on the generated disaster situation description, the server develops an optimal evacuation plan, taking into account the user's current location. The plan includes the locations of evacuation shelters and recommended evacuation routes.

[0048] Step 6:

[0049] The server sends the completed evacuation plan to the user's terminal.

[0050] Step 7:

[0051] The terminal displays the received evacuation plan on its screen, providing the user with visualized evacuation information. The user then refers to this information and begins to evacuate safely.

[0052] (Example 1)

[0053] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0054] In modern society, providing residents with timely and appropriate evacuation information during natural disasters is crucial. However, traditional manual information gathering and analysis methods have been time-consuming, leading to delays in responses in urgent situations. Furthermore, technologies for automatically generating appropriate evacuation plans tailored to the nature of the disaster and providing information customized to each user have not yet been sufficiently established.

[0055] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0056] In this invention, the server includes means for receiving and analyzing images, means for generating a disaster state in natural language, and means for creating and transmitting an evacuation plan. This enables the rapid and accurate provision of information and personalized evacuation route guidance during a disaster.

[0057] "Means of acquiring images" refers to a function that uses a terminal with a camera function to capture visual information of the disaster area and generate image data from that image.

[0058] An "information processing device" is a device that has computing resources and algorithms for receiving and analyzing transmitted image data.

[0059] "Analysis means" refers to the process of interpreting and estimating the nature of a disaster from received image data using deep learning and image recognition technologies.

[0060] "Generation means" refers to a function that uses natural language processing technology based on analysis results to output information as text in a format that is easy for the user to understand.

[0061] A "plan generation method" is a process that automatically formulates an optimal evacuation plan by creating information on evacuation routes and safe shelters based on generated natural language information.

[0062] The "transmission and display means" refers to a function that transmits the formulated evacuation plan to the user's terminal via communication and displays it in a visually verifiable format.

[0063] "Integrated functionality" refers to a technology used in image analysis that integrates and processes data and media information in different formats.

[0064] "User location information" refers to the user's current geographical coordinates, obtained using the GPS function or other positioning technologies included with the device.

[0065] This invention is a system that provides rapid and accurate evacuation information during disasters. Specifically, it begins with a user taking images of the disaster area using a terminal. In this process, a smartphone or tablet with a camera function is used as hardware, and the image data is transmitted to an information processing device, i.e., a server, via network communication.

[0066] The server processes the received images using deep learning frameworks (e.g., TENSORFLOW® and PyTorch) and uses image analysis technology to infer the current state of the disaster. For example, it uses an analysis model to determine the possibility of river flooding or landslides. After this analysis, the server uses natural language processing technology to convert the analysis results into text. The software used here is a generative AI model (e.g., OpenAI®'s GPT series), which generates specific information such as "The current rate of water level rise is at a dangerous level" or "Evacuation is necessary within a certain time."

[0067] Next, the server formulates an optimal evacuation plan based on the generated natural language information. Here, it uses the user's location data to provide the user with the most suitable evacuation route and shelter information. At this stage, the evacuation information is formalized as specific instructions. For example, it may include guidance such as, "The nearest shelter is a park 1 kilometer away," or "Due to the possibility of ground subsidence caused by the earthquake, an evacuation route along the outside of the building is recommended."

[0068] Finally, the formulated evacuation information is transmitted from the server to the terminal, which then notifies the user and displays the information on the screen. This allows the user to receive information on safe evacuation routes and shelters in real time, enabling them to take swift evacuation action.

[0069] As a concrete example, suppose a user takes a picture of a rising river level due to heavy rain and sends the image to a server. This system assesses the danger of the water level and generates and provides to the user an instruction such as, "Evacuation is necessary due to the rapid rise in water level. Please evacuate to the nearest school." An example of a prompt message to the generating AI model would be, "Generate an evacuation order to inform the user of the danger of rising water levels due to heavy rain. Currently, the river is overflowing, and water levels in the surrounding area are rising rapidly."

[0070] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0071] Step 1:

[0072] Users take pictures of the disaster area using the camera function of their smartphone or tablet. These images are converted into digital data such as JPEG format on the device and sent to the server via network communication. The input is the image data captured by the camera, and the output is the image file received by the server.

[0073] Step 2:

[0074] The server analyzes the received image data. Data processing begins with pre-processing, which includes adjusting the resolution and reducing noise. Then, using a deep learning framework (such as TensorFlow or PyTorch), a pre-trained model is used to extract features from the image and estimate the nature of the disaster. The input is image data, and the output is the analysis result indicating the disaster situation.

[0075] Step 3:

[0076] The server converts the acquired analysis results into natural language. Specifically, it utilizes a generative AI model (such as OpenAI's GPT series) to generate text in a user-friendly format based on the analyzed numerical data and feature extraction results. The input is analysis results indicating the disaster situation, and the output is natural language text including specific evacuation instructions.

[0077] Step 4:

[0078] The server develops an evacuation plan based on the generated natural language information. This process takes into account the user's current location (GPS data). It searches for the nearest safe evacuation shelter and compiles emergency precautions along with route information. The input is natural language information and the user's location information, and the output is the evacuation plan proposed to the user.

[0079] Step 5:

[0080] The server transmits the formulated evacuation plan to the terminal, and the terminal displays the received information. Specifically, it uses the terminal's notification function to send emergency notifications to the user and also displays evacuation routes visually in conjunction with a map application. The input is the formulated evacuation plan, and the output is the evacuation information displayed on the user's terminal.

[0081] (Application Example 1)

[0082] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0083] Providing timely and accurate evacuation information during a disaster is a crucial factor in determining the success or failure of an evacuation. However, many current systems struggle to provide evacuation plans that adequately reflect the rapidly changing disaster situation in real time, which can result in the safety of residents being threatened. Furthermore, the difficulty in visually grasping complex information makes it difficult for users to make decisions that enable them to take appropriate action.

[0084] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0085] In this invention, the server includes means for acquiring an image and transmitting the image to a data processing device; analysis means for analyzing the image and estimating the disaster state; generation means for outputting the disaster state in natural language format; plan generation means for automatically generating an evacuation action plan based on the generated natural language information; transmission and display means for transmitting and displaying the evacuation action plan to an information terminal; and display means for displaying the evacuation action plan using a smartphone. This makes it possible for users to visually confirm an appropriate evacuation plan linked to disaster information that is updated in real time on their smartphones.

[0086] "Means for acquiring an image and transmitting the image to a data processing device" refers to a function for taking a photograph of the disaster situation using a terminal used by the user and transmitting the captured image to a data processing device via a network.

[0087] "Analysis means for analyzing the aforementioned images and estimating the disaster state" refers to a function for estimating the type of disaster and the extent of its impact based on the received images, using machine learning algorithms or the like.

[0088] "Generating means for outputting the disaster state in natural language format" refers to a function for converting the estimated disaster state into natural language text that is easy for humans to understand and outputting it.

[0089] "Plan generation means for automatically generating an evacuation action plan based on the generated natural language information" refers to a function for automatically formulating an evacuation action plan, including appropriate evacuation routes and evacuation locations, based on disaster information.

[0090] The "transmission and display means for transmitting and displaying the evacuation action plan on an information terminal" refers to a function for transmitting the generated evacuation action plan to an information terminal held by the user and displaying it on the screen of that terminal.

[0091] "Display means for displaying the evacuation action plan using a smartphone" refers to a function that visually provides the user with the generated evacuation plan using the smartphone screen, thereby facilitating appropriate actions according to the situation.

[0092] This invention is a system for providing appropriate evacuation information and evacuation action plans during disasters using smartphones. The main components are a server, a terminal, and the user. Each component is described in detail below.

[0093] The server utilizes advanced analytical techniques, such as deep learning models and complex modal functions, to receive disaster images sent by users and estimate the disaster state. The server outputs these analysis results in natural language format, which is then used to formulate evacuation action plans. In this process, machine learning frameworks such as TensorFlow and PyTorch are used to generate information quickly and accurately.

[0094] The terminal, primarily a smartphone, is responsible for displaying evacuation plans to the user. Based on the received information, the user can take appropriate evacuation actions in real time. The application on the terminal provides the display function, and is designed to allow the user to intuitively understand the information.

[0095] Users activate the entire system by taking photos of the disaster situation and sending those images to the server via their smartphones. This generates an evacuation plan that accurately reflects the situation on site.

[0096] As a concrete example, consider a scenario where a user takes a photo of a flooded city with their smartphone and sends it to the user. The server then analyzes the situation and outputs a recommended action, such as "There is a risk of rising water levels, please evacuate immediately," which is then sent to the user's device. This process allows the user to make a quick and appropriate decision.

[0097] Example prompt: "Clearly outline the steps to identify the type and situation of a disaster from the image and provide the user with the most suitable evacuation route and shelter in real time."

[0098] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0099] Step 1:

[0100] Users photograph the disaster situation with their smartphone cameras. These images serve as input. Data transmission via the network then takes place to send these images from the smartphone to the server.

[0101] Step 2:

[0102] The server uses a machine learning model to analyze the received images as input. Specifically, it performs image recognition using TensorFlow or PyTorch to estimate the type and scale of the disaster. The analysis results output the state of the disaster.

[0103] Step 3:

[0104] The server generates the disaster status obtained through analysis in natural language format. Here, a generative AI model is used to convert the estimation results into sentences such as "There is a risk of flooding, so immediate evacuation is necessary." This generated natural language sentence becomes the output.

[0105] Step 4:

[0106] The server uses this generated natural language text, along with the user's location information, to formulate an appropriate evacuation plan. During this process, information including specific instructions such as evacuation destinations and routes is output.

[0107] Step 5:

[0108] The server transmits the formulated evacuation plan to the terminal. The user's smartphone receives this information and treats it as input.

[0109] Step 6:

[0110] The device displays the received evacuation plan on its screen. The user can visually confirm evacuation routes and locations through their smartphone's display. In this step, the user takes specific evacuation actions based on the displayed information.

[0111] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0112] This invention is a system for providing users with rapid and accurate evacuation information during disasters, and in particular, it aims to deliver information more appropriately by taking into account the user's emotional state. The terminal receives images taken by the user at the disaster site and uploads these images to the server.

[0113] The server analyzes the received images to estimate the disaster situation. For example, it determines the severity of flooding and the likelihood of landslides. This analysis result is then converted into user-friendly text using natural language processing, where an emotion engine comes into play. The emotion engine recognizes the user's emotional state from their voice or text input and adjusts the tone of the text accordingly. For example, if it is determined that the user is feeling anxious, the explanatory text is adjusted to provide reassurance.

[0114] Furthermore, this system optimizes evacuation plans based on emotional states. The server considers the user's current location and emotional state to generate a plan that includes safe evacuation routes and information on nearby shelters. If the user is experiencing strong feelings of fear, the plan will include simpler, easier-to-understand instructions and provide additional information to enhance their sense of security.

[0115] Ultimately, the server sends this information to the user's terminal, which displays the plan. The user can then refer to this plan and take safe and efficient evacuation actions. This system, by taking emotions into consideration, makes it possible to provide a more user-friendly evacuation experience.

[0116] The following describes the processing flow.

[0117] Step 1:

[0118] Users capture images of the disaster site and surrounding area using devices such as smartphones.

[0119] Step 2:

[0120] Users upload acquired images to a server via a dedicated application. During this process, they can supplement their emotions and circumstances by using voice or text input as needed.

[0121] Step 3:

[0122] The server analyzes the received image data to estimate the disaster situation. This analysis uses image recognition algorithms to evaluate water levels and sediment conditions.

[0123] Step 4:

[0124] The server analyzes voice and text input from the user and uses an emotion engine to recognize the user's emotions. Examples of emotional states include anxiety, fear, and tension.

[0125] Step 5:

[0126] The server translates the analyzed disaster situation into natural language and adjusts the tone of the text based on the user's emotional state. For example, information is provided in a gentle, reassuring tone to users who are feeling anxious.

[0127] Step 6:

[0128] The server generates an optimal evacuation plan for the user based on the disaster situation and emotional state. This plan includes detailed information, such as the nearest evacuation shelter and safe evacuation routes, taking the user's location into consideration.

[0129] Step 7:

[0130] The server sends the evacuation plan to the user's terminal.

[0131] Step 8:

[0132] The terminal displays the received evacuation plan on its screen, providing the user with visual information. The user can then refer to this information and begin evacuating safely.

[0133] (Example 2)

[0134] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0135] During disasters, providing users with timely and accurate evacuation information is crucial. However, uniform information dissemination makes it difficult to encourage appropriate responses tailored to users' emotional states and circumstances. Therefore, it is necessary to provide information that takes into account the mental state of individual users to support safer and more secure evacuation actions.

[0136] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0137] In this invention, the server includes means for acquiring an image and transmitting the image to an information processing device; processing means for analyzing the image in the information processing device and estimating the disaster state; generation means for transcribing the disaster state into text and outputting it as natural language; emotion analysis means for analyzing the user's emotional state based on the transcribed natural language information and adjusting the tone of the output text; plan generation means for automatically generating an evacuation plan based on the generated natural language information and emotion information; and transmission / display means for transmitting and displaying the evacuation plan to a communication terminal. This makes it possible to provide evacuation information tailored to the user's emotional state.

[0138] "Means" refer to the specific methods or processes employed to achieve a particular objective.

[0139] An "information processing device" is a general term for hardware and software used to receive, analyze, transform, and transmit data.

[0140] "Disaster situation" refers to events caused by natural disasters and the resulting damage.

[0141] "Generation methods" refer to processes and technologies for generating text and content based on data.

[0142] "Emotional analysis means" refers to a technology that estimates a user's mental state from their input data and analyzes their emotions.

[0143] "Plan generation means" refers to methods and techniques for formulating and creating optimal action plans and instructions based on data.

[0144] "Transmission and display means" refers to the process of providing generated information to the user via a communication device and visualizing it on a display device.

[0145] The embodiments for carrying out this invention are shown below.

[0146] In this system, users take images at disaster sites using cameras such as smartphones or tablets. The device receives these images and transfers them to a server via Wi-Fi or mobile data communication. The server functions as an "information processing device" and uses cloud storage services to securely store the received images.

[0147] The server then analyzes the image using a "processing method" based on a deep learning model. This analysis utilizes machine learning frameworks such as TensorFlow to estimate the disaster state from elements in the image. For example, to determine the severity of a flood, the AI ​​model analyzes the water level and surrounding environment in the image.

[0148] The analysis results are then transcribed into text using natural language processing techniques. A natural language API is used as the "generation method" to convert the machine-understood information into meaningful text. In addition, an emotion engine is utilized as the "emotion analysis method" to grasp the user's emotional state from voice commands and text input.

[0149] The server creates an evacuation plan based on the user's emotional state information. This "plan generation method" incorporates optimized evacuation routes and shelter information using a map API. The evacuation plan is designed to provide a sense of security by adjusting the tone of the information in case the user is feeling fearful.

[0150] The generated evacuation plan and information reflecting emotions are sent from the server to the communication terminal. The terminal receives the information and supports the user by displaying it on the screen. For example, if a user takes a picture of a flood and the analysis results indicate that "the flood is severe," the route to the nearest safe evacuation center is shown, and a message to alleviate anxiety is added.

[0151] An example of a prompt would be, "Generate an evacuation message that provides reassurance to the user in response to their emotions during a disaster." This prompt allows the AI ​​model to generate appropriate instructions that are sensitive to the user's feelings.

[0152] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0153] Step 1:

[0154] Users take images at disaster sites using their smartphones or tablets. The input is image data from the device's camera sensor, and the output is an image file temporarily stored in local storage. This operation is completed when the user operates the device and presses the capture button on the camera application.

[0155] Step 2:

[0156] The device uploads captured images to the server via Wi-Fi or mobile data communication. The input is an image file in local storage, and the output is the transfer of image data to the server's cloud storage. This process involves issuing POST requests based on the HTTP protocol to send the data.

[0157] Step 3:

[0158] The server saves the received image data to a storage system for information analysis. The input is image data from the terminal, and the output is an image file securely stored in cloud storage. This saving operation utilizes a storage API, making the image data manageable within the system.

[0159] Step 4:

[0160] The server analyzes images using a "deep learning analysis module." The input is a saved image file, and the output is data on the disaster state estimated from the image. This process utilizes deep learning frameworks such as TensorFlow to execute the model's prediction algorithm to identify environmental changes.

[0161] Step 5:

[0162] The server passes the data obtained from image analysis to a "natural language generation module" for text conversion. The input is disaster status data, and the output is natural language text to notify the user. This process involves using a natural language processing API to convert the analysis results into an understandable format.

[0163] Step 6:

[0164] Upon receiving user voice or text input, the server activates its "emotion analysis engine" to analyze the user's emotional state. The input is user voice or text data, and the output is evaluation data indicating the user's emotions. The server uses speech recognition technology to identify the emotions.

[0165] Step 7:

[0166] The server generates an evacuation plan based on analyzed emotional data. The input is emotional state and location information, and the output is an evacuation plan tailored to the user's needs. A map API is used for optimization, calculating the optimal evacuation route in real time.

[0167] Step 8:

[0168] The server sends the generated evacuation plan to the terminal, which then displays it. The input is the plan data, and the output is a visual evacuation instruction on the user interface. The terminal then uses its own application to plot routes and shelter information on a map.

[0169] (Application Example 2)

[0170] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0171] During disasters, obtaining appropriate information to enable people to evacuate quickly and safely is extremely important. However, current systems fail to adequately consider users' emotions and psychological states when providing information, which can hinder evacuation. In particular, under the stress of a disaster, it becomes difficult to fully understand and act based on normal information alone, so there is a need for information that takes users' emotional states into account.

[0172] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0173] In this invention, the server includes means for acquiring an image and transmitting the image to a data server; analysis means for analyzing the image on the data server and estimating the disaster situation; and emotion adjustment means for analyzing the user's emotional state and adjusting the tone of the generated natural language information. This enables the rapid and accurate provision of information that takes the user's emotional state into consideration.

[0174] "Means for acquiring images" refers to a method or device for collecting images taken by users at a disaster site.

[0175] "Means of sending to a data server" refers to a method or function for transferring acquired image information to a central data processing device.

[0176] "Analysis means" refers to a method or technique for processing image data on a server to estimate the situation and impact of a disaster.

[0177] "Generation means" refers to a method or technology for converting analyzed disaster information into natural language and outputting it in a format that is easy for users to understand.

[0178] "Emotional adjustment techniques" refer to methods or techniques for analyzing a user's psychological state and adjusting the tone and wording of information based on the results.

[0179] "Plan generation means" refers to a method or function for automatically creating an evacuation plan based on analyzed information.

[0180] "Transmission and display means" refers to a method or device for transmitting and visually displaying an evacuation plan to a user's terminal.

[0181] The system for realizing this application operates through data communication between a smartphone and a server. Users acquire images at disaster sites using their smartphones and send these images to the server. The server is built on AWS (registered trademark) and analyzes the disaster situation using image analysis software such as OpenCV.

[0182] Once the analysis is complete, the server uses a generative AI model, such as GPT-3®, to translate the analysis results into natural language text. During this process, it uses an emotion analysis engine, such as IBM Watson®'s Tone Analyzer, to determine the user's emotional state and adjust the tone of the information accordingly. This enables the provision of information that is sensitive to the user's mental state.

[0183] Furthermore, the server creates an optimal evacuation plan based on the generated natural language information and the user's current location. The plan includes safe and rapid route information from the original location to the evacuation shelter, which is then sent to the user's smartphone for display.

[0184] As a concrete example, in the event of flooding due to heavy rain, even if the user is in a state of anxiety, a message such as, "Don't worry. You can follow this route to reach a safe evacuation center," will be provided.

[0185] An example of a prompt message might be, "If the user is feeling anxious, generate a more reassuring evacuation instruction." This allows the system to provide appropriate information and evacuation plans based on the user's emotions, supporting effective evacuation during disasters.

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

[0187] Step 1:

[0188] A user uses their smartphone to capture images of the disaster site. Images are taken using the device's camera function, and the captured image data is sent to the server. Input: Captured image. Output: Image data transferred to the server.

[0189] Step 2:

[0190] The server analyzes the received image data using OpenCV. It determines the type and severity of the disaster and detects changes in the environment. Input: Image data transferred to the server. Output: Analyzed disaster information.

[0191] Step 3:

[0192] The server uses a generative AI model (e.g., GPT-3) to generate a natural language description based on the analysis results. Input: Analyzed disaster information. Output: Generated natural language description.

[0193] Step 4:

[0194] The server uses IBM Watson's Tone Analyzer to analyze the user's emotional state and adjust the tone of the generated description according to the user's emotions. Input: Generated natural language description and user emotion data. Output: Tone-adjusted natural language description.

[0195] Step 5:

[0196] The server retrieves the user's current location information and generates a safe evacuation plan based on disaster information and emotionally tuned descriptions. Input: User's location information and emotionally tuned natural language descriptions. Output: Generated evacuation plan.

[0197] Step 6:

[0198] The generated evacuation plan is sent to the user's terminal and displayed. The user then takes the optimal evacuation action according to this plan. Input: Generated evacuation plan. Output: Displayed on the user's terminal.

[0199] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0200] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0201] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0202] [Second Embodiment]

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

[0204] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0205] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0206] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0207] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0208] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0209] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0210] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0211] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0212] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0213] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0214] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0215] This invention is a system that provides rapid and accurate evacuation information during disasters. Specifically, it is a mechanism that analyzes actual disaster situations photographed by the user and automatically generates and provides evacuation plans based on that analysis.

[0216] Users take pictures of disaster areas using their devices. These images are sent to a data server via the network. The data server uses image analysis technology to estimate the current state of the disaster based on the received images. This analysis uses deep learning models and image recognition algorithms to determine the possibility of river flooding and landslides based on visual features.

[0217] The analysis results are converted into user-friendly text using natural language processing technology. For example, information such as "The current rate of water level rise is at a dangerous level" or "Evacuation is necessary within a certain time" is generated.

[0218] The server then uses the generated text to formulate an optimal evacuation plan. This plan can take the user's location into account and include information about the nearest evacuation shelter and precautions to take during evacuation. For example, it may provide specific instructions such as, "The nearest evacuation shelter is XX Park, 1 kilometer away," or "Due to the possibility of ground subsidence caused by the earthquake, an evacuation route along the outside of the building is recommended."

[0219] Finally, the server sends these evacuation plans to the user's terminal, which then displays the information. Users can visually confirm safe evacuation routes and shelters through their terminal screen. This system makes it possible to support the rapid and appropriate evacuation of residents during disasters.

[0220] The following describes the processing flow.

[0221] Step 1:

[0222] Users capture images of the disaster site and surrounding area using devices such as smartphones.

[0223] Step 2:

[0224] Users upload the acquired images to a data server via a dedicated application or web interface over the network.

[0225] Step 3:

[0226] The server applies an image analysis algorithm to the received image data to estimate the extent of the disaster. This analysis is performed using a deep learning model to evaluate water level and the likelihood of landslides.

[0227] Step 4:

[0228] The server uses a natural language processing engine to generate text describing the disaster situation in order to convert the analysis results into natural language.

[0229] Step 5:

[0230] Based on the generated disaster situation description, the server develops an optimal evacuation plan, taking into account the user's current location. The plan includes the locations of evacuation shelters and recommended evacuation routes.

[0231] Step 6:

[0232] The server sends the completed evacuation plan to the user's terminal.

[0233] Step 7:

[0234] The terminal displays the received evacuation plan on its screen, providing the user with visualized evacuation information. The user then refers to this information and begins to evacuate safely.

[0235] (Example 1)

[0236] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0237] In modern society, providing residents with timely and appropriate evacuation information during natural disasters is crucial. However, traditional manual information gathering and analysis methods have been time-consuming, leading to delays in responses in urgent situations. Furthermore, technologies for automatically generating appropriate evacuation plans tailored to the nature of the disaster and providing information customized to each user have not yet been sufficiently established.

[0238] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0239] In this invention, the server includes means for receiving and analyzing images, means for generating a disaster state in natural language, and means for creating and transmitting an evacuation plan. This enables the rapid and accurate provision of information and personalized evacuation route guidance during a disaster.

[0240] "Means of acquiring images" refers to a function that uses a terminal with a camera function to capture visual information of the disaster area and generate image data from that image.

[0241] An "information processing device" is a device that has computing resources and algorithms for receiving and analyzing transmitted image data.

[0242] "Analysis means" refers to the process of interpreting and estimating the nature of a disaster from received image data using deep learning and image recognition technologies.

[0243] "Generation means" refers to a function that uses natural language processing technology based on analysis results to output information as text in a format that is easy for the user to understand.

[0244] A "plan generation method" is a process that automatically formulates an optimal evacuation plan by creating information on evacuation routes and safe shelters based on generated natural language information.

[0245] The "transmission and display means" refers to a function that transmits the formulated evacuation plan to the user's terminal via communication and displays it in a visually verifiable format.

[0246] "Integrated functionality" refers to a technology used in image analysis that integrates and processes data and media information in different formats.

[0247] "User location information" refers to the user's current geographical coordinates, obtained using the GPS function or other positioning technologies included with the device.

[0248] This invention is a system that provides rapid and accurate evacuation information during disasters. Specifically, it begins with a user taking images of the disaster area using a terminal. In this process, a smartphone or tablet with a camera function is used as hardware, and the image data is transmitted to an information processing device, i.e., a server, via network communication.

[0249] The server processes the received images using deep learning frameworks (e.g., TensorFlow and PyTorch) and uses image analysis techniques to infer the current state of the disaster. For example, it uses an analysis model to determine the possibility of river flooding or landslides. After this analysis, the server uses natural language processing techniques to convert the analysis results into text. The software used here is a generative AI model (e.g., OpenAI's GPT series), which generates specific information such as "The current rate of water level rise is at a dangerous level" or "Evacuation is necessary within a certain time."

[0250] Next, the server formulates an optimal evacuation plan based on the generated natural language information. Here, it uses the user's location data to provide the user with the most suitable evacuation route and shelter information. At this stage, the evacuation information is formalized as specific instructions. For example, it may include guidance such as, "The nearest shelter is a park 1 kilometer away," or "Due to the possibility of ground subsidence caused by the earthquake, an evacuation route along the outside of the building is recommended."

[0251] Finally, the formulated evacuation information is transmitted from the server to the terminal, which then notifies the user and displays the information on the screen. This allows the user to receive information on safe evacuation routes and shelters in real time, enabling them to take swift evacuation action.

[0252] As a concrete example, suppose a user takes a picture of a rising river level due to heavy rain and sends the image to a server. This system assesses the danger of the water level and generates and provides to the user an instruction such as, "Evacuation is necessary due to the rapid rise in water level. Please evacuate to the nearest school." An example of a prompt message to the generating AI model would be, "Generate an evacuation order to inform the user of the danger of rising water levels due to heavy rain. Currently, the river is overflowing, and water levels in the surrounding area are rising rapidly."

[0253] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0254] Step 1:

[0255] Users take pictures of the disaster area using the camera function of their smartphone or tablet. These images are converted into digital data such as JPEG format on the device and sent to the server via network communication. The input is the image data captured by the camera, and the output is the image file received by the server.

[0256] Step 2:

[0257] The server analyzes the received image data. Data processing begins with pre-processing, which includes adjusting the resolution and reducing noise. Then, using a deep learning framework (such as TensorFlow or PyTorch), a pre-trained model is used to extract features from the image and estimate the nature of the disaster. The input is image data, and the output is the analysis result indicating the disaster situation.

[0258] Step 3:

[0259] The server converts the acquired analysis results into natural language. Specifically, it utilizes a generative AI model (such as OpenAI's GPT series) to generate text in a user-friendly format based on the analyzed numerical data and feature extraction results. The input is analysis results indicating the disaster situation, and the output is natural language text including specific evacuation instructions.

[0260] Step 4:

[0261] The server develops an evacuation plan based on the generated natural language information. This process takes into account the user's current location (GPS data). It searches for the nearest safe evacuation shelter and compiles emergency precautions along with route information. The input is natural language information and the user's location information, and the output is the evacuation plan proposed to the user.

[0262] Step 5:

[0263] The server transmits the formulated evacuation plan to the terminal, and the terminal displays the received information. Specifically, it uses the terminal's notification function to send emergency notifications to the user and also displays evacuation routes visually in conjunction with a map application. The input is the formulated evacuation plan, and the output is the evacuation information displayed on the user's terminal.

[0264] (Application Example 1)

[0265] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0266] Providing timely and accurate evacuation information during a disaster is a crucial factor in determining the success or failure of an evacuation. However, many current systems struggle to provide evacuation plans that adequately reflect the rapidly changing disaster situation in real time, which can result in the safety of residents being threatened. Furthermore, the difficulty in visually grasping complex information makes it difficult for users to make decisions that enable them to take appropriate action.

[0267] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0268] In this invention, the server includes means for acquiring an image and transmitting the image to a data processing device; analysis means for analyzing the image and estimating the disaster state; generation means for outputting the disaster state in natural language format; plan generation means for automatically generating an evacuation action plan based on the generated natural language information; transmission and display means for transmitting and displaying the evacuation action plan to an information terminal; and display means for displaying the evacuation action plan using a smartphone. This makes it possible for users to visually confirm an appropriate evacuation plan linked to disaster information that is updated in real time on their smartphones.

[0269] "Means for acquiring an image and transmitting the image to a data processing device" refers to a function for taking a photograph of the disaster situation using a terminal used by the user and transmitting the captured image to a data processing device via a network.

[0270] "Analysis means for analyzing the aforementioned images and estimating the disaster state" refers to a function for estimating the type of disaster and the extent of its impact based on the received images, using machine learning algorithms or the like.

[0271] "Generating means for outputting the disaster state in natural language format" refers to a function for converting the estimated disaster state into natural language text that is easy for humans to understand and outputting it.

[0272] "Plan generation means for automatically generating an evacuation action plan based on the generated natural language information" refers to a function for automatically formulating an evacuation action plan, including appropriate evacuation routes and evacuation locations, based on disaster information.

[0273] The "transmission and display means for transmitting and displaying the evacuation action plan on an information terminal" refers to a function for transmitting the generated evacuation action plan to an information terminal held by the user and displaying it on the screen of that terminal.

[0274] "Display means for displaying the evacuation action plan using a smartphone" refers to a function that visually provides the user with the generated evacuation plan using the smartphone screen, thereby facilitating appropriate actions according to the situation.

[0275] This invention is a system for providing appropriate evacuation information and evacuation action plans during disasters using smartphones. The main components are a server, a terminal, and the user. Each component is described in detail below.

[0276] The server utilizes advanced analytical techniques, such as deep learning models and complex modal functions, to receive disaster images sent by users and estimate the disaster state. The server outputs these analysis results in natural language format, which is then used to formulate evacuation action plans. In this process, machine learning frameworks such as TensorFlow and PyTorch are used to generate information quickly and accurately.

[0277] The terminal, primarily a smartphone, is responsible for displaying evacuation plans to the user. Based on the received information, the user can take appropriate evacuation actions in real time. The application on the terminal provides the display function, and is designed to allow the user to intuitively understand the information.

[0278] Users activate the entire system by taking photos of the disaster situation and sending those images to the server via their smartphones. This generates an evacuation plan that accurately reflects the situation on site.

[0279] As a concrete example, consider a scenario where a user takes a photo of a flooded city with their smartphone and sends it to the user. The server then analyzes the situation and outputs a recommended action, such as "There is a risk of rising water levels, please evacuate immediately," which is then sent to the user's device. This process allows the user to make a quick and appropriate decision.

[0280] Example of a prompt sentence: "Please specify the procedure for identifying the type and situation of a disaster from an image and providing the optimal evacuation route and evacuation shelter to the user in real time."

[0281] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0282] Step 1:

[0283] The user takes a picture of the disaster situation with the camera of the smartphone. At this time, the image taken by the user serves as the input. In order to transmit this image from the smartphone to the server, data transmission via the network is performed.

[0284] Step 2:

[0285] The server uses the received image as input and performs analysis using a machine learning model. Specifically, image recognition is performed using TensorFlow or PyTorch to estimate the type and scale of the disaster. As an analysis result, the state of the disaster is output.

[0286] Step 3:

[0287] The server generates the disaster state obtained by the analysis in the form of natural language. Here, a generative AI model is utilized to convert the estimation result into a sentence such as "There is a risk of flooding, so immediate evacuation is necessary". This generated natural language sentence serves as the output.

[0288] Step 4:

[0289] Based on this generated natural language sentence, the server formulates an appropriate evacuation action plan while referring to the user's location information. In this process, information including specific instructions such as the evacuation destination and evacuation route is output.

[0290] Step 5:

[0291] The server transmits the formulated evacuation plan to the terminal. The user's smartphone receives this information and treats it as input.

[0292] Step 6:

[0293] The device displays the received evacuation plan on its screen. The user can visually confirm evacuation routes and locations through their smartphone's display. In this step, the user takes specific evacuation actions based on the displayed information.

[0294] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0295] This invention is a system for providing users with rapid and accurate evacuation information during disasters, and in particular, it aims to deliver information more appropriately by taking into account the user's emotional state. The terminal receives images taken by the user at the disaster site and uploads these images to the server.

[0296] The server analyzes the received images to estimate the disaster situation. For example, it determines the severity of flooding and the likelihood of landslides. This analysis result is then converted into user-friendly text using natural language processing, where an emotion engine comes into play. The emotion engine recognizes the user's emotional state from their voice or text input and adjusts the tone of the text accordingly. For example, if it is determined that the user is feeling anxious, the explanatory text is adjusted to provide reassurance.

[0297] Furthermore, this system optimizes evacuation plans based on emotional states. The server considers the user's current location and emotional state to generate a plan that includes safe evacuation routes and information on nearby shelters. If the user is experiencing strong feelings of fear, the plan will include simpler, easier-to-understand instructions and provide additional information to enhance their sense of security.

[0298] Finally, the server sends this information to the user's terminal, and the terminal displays the plan. The user can refer to this and take evacuation actions safely and efficiently. With this system, by considering emotions, it becomes possible to provide an evacuation experience that is easier for the user to execute.

[0299] The processing flow will be described below.

[0300] Step 1:

[0301] The user takes pictures of the disaster site and surrounding situations with a terminal such as a smartphone to obtain images.

[0302] Step 2:

[0303] The user uploads the obtained images to the server through a dedicated application. At this time, if necessary, the user's emotions and situations can be supplemented by voice input or text input.

[0304] Step 3:

[0305] The server analyzes the received image data and estimates the disaster situation. For this analysis, an image recognition algorithm is used to evaluate the water level height and sediment state.

[0306] Step 4:

[0307] The server analyzes the voice and text input from the user and recognizes the user's emotions using an emotion engine. Examples of emotional states include anxiety, fear, and tension.

[0308] Step 5:

[0309] The server converts the analyzed disaster situation into natural language and adjusts the tone of the text based on the user's emotional state. For example, for a user feeling anxious, information is provided in a gentle tone that gives a sense of security.

[0310] Step 6:

[0311] The server generates an optimal evacuation plan for the user based on the disaster situation and emotional state. This plan includes detailed information, such as the nearest evacuation shelter and safe evacuation routes, taking the user's location into consideration.

[0312] Step 7:

[0313] The server sends the evacuation plan to the user's terminal.

[0314] Step 8:

[0315] The terminal displays the received evacuation plan on its screen, providing the user with visual information. The user can then refer to this information and begin evacuating safely.

[0316] (Example 2)

[0317] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0318] During disasters, providing users with timely and accurate evacuation information is crucial. However, uniform information dissemination makes it difficult to encourage appropriate responses tailored to users' emotional states and circumstances. Therefore, it is necessary to provide information that takes into account the mental state of individual users to support safer and more secure evacuation actions.

[0319] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0320] In this invention, the server includes means for acquiring an image and transmitting the image to an information processing device; processing means for analyzing the image in the information processing device and estimating the disaster state; generation means for transcribing the disaster state into text and outputting it as natural language; emotion analysis means for analyzing the user's emotional state based on the transcribed natural language information and adjusting the tone of the output text; plan generation means for automatically generating an evacuation plan based on the generated natural language information and emotion information; and transmission / display means for transmitting and displaying the evacuation plan to a communication terminal. This makes it possible to provide evacuation information tailored to the user's emotional state.

[0321] "Means" refer to the specific methods or processes employed to achieve a particular objective.

[0322] An "information processing device" is a general term for hardware and software used to receive, analyze, transform, and transmit data.

[0323] "Disaster situation" refers to events caused by natural disasters and the resulting damage.

[0324] "Generation methods" refer to processes and technologies for generating text and content based on data.

[0325] "Emotional analysis means" refers to a technology that estimates a user's mental state from their input data and analyzes their emotions.

[0326] "Plan generation means" refers to methods and techniques for formulating and creating optimal action plans and instructions based on data.

[0327] "Transmission and display means" refers to the process of providing generated information to the user via a communication device and visualizing it on a display device.

[0328] The embodiments for carrying out this invention are shown below.

[0329] In this system, users take images at disaster sites using cameras such as smartphones or tablets. The device receives these images and transfers them to a server via Wi-Fi or mobile data communication. The server functions as an "information processing device" and uses cloud storage services to securely store the received images.

[0330] The server then analyzes the image using a "processing method" based on a deep learning model. This analysis utilizes machine learning frameworks such as TensorFlow to estimate the disaster state from elements in the image. For example, to determine the severity of a flood, the AI ​​model analyzes the water level and surrounding environment in the image.

[0331] The analysis results are then transcribed into text using natural language processing techniques. A natural language API is used as the "generation method" to convert the machine-understood information into meaningful text. In addition, an emotion engine is utilized as the "emotion analysis method" to grasp the user's emotional state from voice commands and text input.

[0332] The server creates an evacuation plan based on the user's emotional state information. This "plan generation method" incorporates optimized evacuation routes and shelter information using a map API. The evacuation plan is designed to provide a sense of security by adjusting the tone of the information in case the user is feeling fearful.

[0333] The generated evacuation plan and information reflecting emotions are sent from the server to the communication terminal. The terminal receives the information and supports the user by displaying it on the screen. For example, if a user takes a picture of a flood and the analysis results indicate that "the flood is severe," the route to the nearest safe evacuation center is shown, and a message to alleviate anxiety is added.

[0334] An example of a prompt would be, "Generate an evacuation message that provides reassurance to the user in response to their emotions during a disaster." This prompt allows the AI ​​model to generate appropriate instructions that are sensitive to the user's feelings.

[0335] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0336] Step 1:

[0337] Users take images at disaster sites using their smartphones or tablets. The input is image data from the device's camera sensor, and the output is an image file temporarily stored in local storage. This operation is completed when the user operates the device and presses the capture button on the camera application.

[0338] Step 2:

[0339] The device uploads captured images to the server via Wi-Fi or mobile data communication. The input is an image file in local storage, and the output is the transfer of image data to the server's cloud storage. This process involves issuing POST requests based on the HTTP protocol to send the data.

[0340] Step 3:

[0341] The server saves the received image data to a storage system for information analysis. The input is image data from the terminal, and the output is an image file securely stored in cloud storage. This saving operation utilizes a storage API, making the image data manageable within the system.

[0342] Step 4:

[0343] The server analyzes images using a "deep learning analysis module." The input is a saved image file, and the output is data on the disaster state estimated from the image. This process utilizes deep learning frameworks such as TensorFlow to execute the model's prediction algorithm to identify environmental changes.

[0344] Step 5:

[0345] The server passes the data obtained from image analysis to a "natural language generation module" for text conversion. The input is disaster status data, and the output is natural language text to notify the user. This process involves using a natural language processing API to convert the analysis results into an understandable format.

[0346] Step 6:

[0347] Upon receiving user voice or text input, the server activates its "emotion analysis engine" to analyze the user's emotional state. The input is user voice or text data, and the output is evaluation data indicating the user's emotions. The server uses speech recognition technology to identify the emotions.

[0348] Step 7:

[0349] The server generates an evacuation plan based on analyzed emotional data. The input is emotional state and location information, and the output is an evacuation plan tailored to the user's needs. A map API is used for optimization, calculating the optimal evacuation route in real time.

[0350] Step 8:

[0351] The server sends the generated evacuation plan to the terminal, which then displays it. The input is the plan data, and the output is a visual evacuation instruction on the user interface. The terminal then uses its own application to plot routes and shelter information on a map.

[0352] (Application Example 2)

[0353] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0354] During disasters, obtaining appropriate information to enable people to evacuate quickly and safely is extremely important. However, current systems fail to adequately consider users' emotions and psychological states when providing information, which can hinder evacuation. In particular, under the stress of a disaster, it becomes difficult to fully understand and act based on normal information alone, so there is a need for information that takes users' emotional states into account.

[0355] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0356] In this invention, the server includes means for acquiring an image and transmitting the image to a data server; analysis means for analyzing the image on the data server and estimating the disaster situation; and emotion adjustment means for analyzing the user's emotional state and adjusting the tone of the generated natural language information. This enables the rapid and accurate provision of information that takes the user's emotional state into consideration.

[0357] "Means for acquiring images" refers to a method or device for collecting images taken by users at a disaster site.

[0358] "Means of sending to a data server" refers to a method or function for transferring acquired image information to a central data processing device.

[0359] "Analysis means" refers to a method or technique for processing image data on a server to estimate the situation and impact of a disaster.

[0360] "Generation means" refers to a method or technology for converting analyzed disaster information into natural language and outputting it in a format that is easy for users to understand.

[0361] "Emotional adjustment techniques" refer to methods or techniques for analyzing a user's psychological state and adjusting the tone and wording of information based on the results.

[0362] "Plan generation means" refers to a method or function for automatically creating an evacuation plan based on analyzed information.

[0363] "Transmission and display means" refers to a method or device for transmitting and visually displaying an evacuation plan to a user's terminal.

[0364] The system used to implement this application operates through data communication between a smartphone and a server. Users acquire images at disaster sites using their smartphones and send these images to the server. The server, built on AWS, analyzes the disaster situation using image analysis software such as OpenCV.

[0365] Once the analysis is complete, the server uses a generative AI model, such as GPT-3, to translate the analysis results into natural language text. During this process, it uses a sentiment analysis engine, such as IBM Watson's Tone Analyzer, to determine the user's emotional state and adjust the tone of the information accordingly. This enables the provision of information that is sensitive to the user's mental state.

[0366] Furthermore, the server creates an optimal evacuation plan based on the generated natural language information and the user's current location. The plan includes safe and rapid route information from the original location to the evacuation shelter, which is then sent to the user's smartphone for display.

[0367] As a concrete example, in the event of flooding due to heavy rain, even if the user is in a state of anxiety, a message such as, "Don't worry. You can follow this route to reach a safe evacuation center," will be provided.

[0368] An example of a prompt message might be, "If the user is feeling anxious, generate a more reassuring evacuation instruction." This allows the system to provide appropriate information and evacuation plans based on the user's emotions, supporting effective evacuation during disasters.

[0369] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0370] Step 1:

[0371] A user uses their smartphone to capture images of the disaster site. Images are taken using the device's camera function, and the captured image data is sent to the server. Input: Captured image. Output: Image data transferred to the server.

[0372] Step 2:

[0373] The server analyzes the received image data using OpenCV. It determines the type and severity of the disaster and detects changes in the environment. Input: Image data transferred to the server. Output: Analyzed disaster information.

[0374] Step 3:

[0375] The server uses a generative AI model (e.g., GPT-3) to generate a natural language description based on the analysis results. Input: Analyzed disaster information. Output: Generated natural language description.

[0376] Step 4:

[0377] The server uses IBM Watson's Tone Analyzer to analyze the user's emotional state and adjust the tone of the generated description according to the user's emotions. Input: Generated natural language description and user emotion data. Output: Tone-adjusted natural language description.

[0378] Step 5:

[0379] The server retrieves the user's current location information and generates a safe evacuation plan based on disaster information and emotionally tuned descriptions. Input: User's location information and emotionally tuned natural language descriptions. Output: Generated evacuation plan.

[0380] Step 6:

[0381] The generated evacuation plan is sent to the user's terminal and displayed. The user then takes the optimal evacuation action according to this plan. Input: Generated evacuation plan. Output: Displayed on the user's terminal.

[0382] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0383] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0384] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0385] [Third Embodiment]

[0386] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0387] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0388] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0389] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0390] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0391] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0392] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0393] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0394] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0395] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0396] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0397] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0398] This invention is a system that provides rapid and accurate evacuation information during disasters. Specifically, it is a mechanism that analyzes actual disaster situations photographed by the user and automatically generates and provides evacuation plans based on that analysis.

[0399] Users take pictures of disaster areas using their devices. These images are sent to a data server via the network. The data server uses image analysis technology to estimate the current state of the disaster based on the received images. This analysis uses deep learning models and image recognition algorithms to determine the possibility of river flooding and landslides based on visual features.

[0400] The analysis results are converted into user-friendly text using natural language processing technology. For example, information such as "The current rate of water level rise is at a dangerous level" or "Evacuation is necessary within a certain time" is generated.

[0401] The server then uses the generated text to formulate an optimal evacuation plan. This plan can take the user's location into account and include information about the nearest evacuation shelter and precautions to take during evacuation. For example, it may provide specific instructions such as, "The nearest evacuation shelter is XX Park, 1 kilometer away," or "Due to the possibility of ground subsidence caused by the earthquake, an evacuation route along the outside of the building is recommended."

[0402] Finally, the server sends these evacuation plans to the user's terminal, which then displays the information. Users can visually confirm safe evacuation routes and shelters through their terminal screen. This system makes it possible to support the rapid and appropriate evacuation of residents during disasters.

[0403] The following describes the processing flow.

[0404] Step 1:

[0405] Users capture images of the disaster site and surrounding area using devices such as smartphones.

[0406] Step 2:

[0407] Users upload the acquired images to a data server via a dedicated application or web interface over the network.

[0408] Step 3:

[0409] The server applies an image analysis algorithm to the received image data to estimate the extent of the disaster. This analysis is performed using a deep learning model to evaluate water level and the likelihood of landslides.

[0410] Step 4:

[0411] The server uses a natural language processing engine to generate text describing the disaster situation in order to convert the analysis results into natural language.

[0412] Step 5:

[0413] Based on the generated disaster situation description, the server develops an optimal evacuation plan, taking into account the user's current location. The plan includes the locations of evacuation shelters and recommended evacuation routes.

[0414] Step 6:

[0415] The server sends the completed evacuation plan to the user's terminal.

[0416] Step 7:

[0417] The terminal displays the received evacuation plan on its screen, providing the user with visualized evacuation information. The user then refers to this information and begins to evacuate safely.

[0418] (Example 1)

[0419] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0420] In modern society, providing residents with timely and appropriate evacuation information during natural disasters is crucial. However, traditional manual information gathering and analysis methods have been time-consuming, leading to delays in responses in urgent situations. Furthermore, technologies for automatically generating appropriate evacuation plans tailored to the nature of the disaster and providing information customized to each user have not yet been sufficiently established.

[0421] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0422] In this invention, the server includes means for receiving and analyzing images, means for generating a disaster state in natural language, and means for creating and transmitting an evacuation plan. This enables the rapid and accurate provision of information and personalized evacuation route guidance during a disaster.

[0423] "Means of acquiring images" refers to a function that uses a terminal with a camera function to capture visual information of the disaster area and generate image data from that image.

[0424] An "information processing device" is a device that has computing resources and algorithms for receiving and analyzing transmitted image data.

[0425] "Analysis means" refers to the process of interpreting and estimating the nature of a disaster from received image data using deep learning and image recognition technologies.

[0426] "Generation means" refers to a function that uses natural language processing technology based on analysis results to output information as text in a format that is easy for the user to understand.

[0427] A "plan generation method" is a process that automatically formulates an optimal evacuation plan by creating information on evacuation routes and safe shelters based on generated natural language information.

[0428] The "transmission and display means" refers to a function that transmits the formulated evacuation plan to the user's terminal via communication and displays it in a visually verifiable format.

[0429] "Integrated functionality" refers to a technology used in image analysis that integrates and processes data and media information in different formats.

[0430] "User location information" refers to the user's current geographical coordinates, obtained using the GPS function or other positioning technologies included with the device.

[0431] This invention is a system that provides rapid and accurate evacuation information during disasters. Specifically, it begins with a user taking images of the disaster area using a terminal. In this process, a smartphone or tablet with a camera function is used as hardware, and the image data is transmitted to an information processing device, i.e., a server, via network communication.

[0432] The server processes the received images using deep learning frameworks (e.g., TensorFlow and PyTorch) and uses image analysis techniques to infer the current state of the disaster. For example, it uses an analysis model to determine the possibility of river flooding or landslides. After this analysis, the server uses natural language processing techniques to convert the analysis results into text. The software used here is a generative AI model (e.g., OpenAI's GPT series), which generates specific information such as "The current rate of water level rise is at a dangerous level" or "Evacuation is necessary within a certain time."

[0433] Next, the server formulates an optimal evacuation plan based on the generated natural language information. Here, it uses the user's location data to provide the user with the most suitable evacuation route and shelter information. At this stage, the evacuation information is formalized as specific instructions. For example, it may include guidance such as, "The nearest shelter is a park 1 kilometer away," or "Due to the possibility of ground subsidence caused by the earthquake, an evacuation route along the outside of the building is recommended."

[0434] Finally, the formulated evacuation information is transmitted from the server to the terminal, which then notifies the user and displays the information on the screen. This allows the user to receive information on safe evacuation routes and shelters in real time, enabling them to take swift evacuation action.

[0435] As a concrete example, suppose a user takes a picture of a rising river level due to heavy rain and sends the image to a server. This system assesses the danger of the water level and generates and provides to the user an instruction such as, "Evacuation is necessary due to the rapid rise in water level. Please evacuate to the nearest school." An example of a prompt message to the generating AI model would be, "Generate an evacuation order to inform the user of the danger of rising water levels due to heavy rain. Currently, the river is overflowing, and water levels in the surrounding area are rising rapidly."

[0436] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0437] Step 1:

[0438] Users take pictures of the disaster area using the camera function of their smartphone or tablet. These images are converted into digital data such as JPEG format on the device and sent to the server via network communication. The input is the image data captured by the camera, and the output is the image file received by the server.

[0439] Step 2:

[0440] The server analyzes the received image data. Data processing begins with pre-processing, which includes adjusting the resolution and reducing noise. Then, using a deep learning framework (such as TensorFlow or PyTorch), a pre-trained model is used to extract features from the image and estimate the nature of the disaster. The input is image data, and the output is the analysis result indicating the disaster situation.

[0441] Step 3:

[0442] The server converts the acquired analysis results into natural language. Specifically, it utilizes a generative AI model (such as OpenAI's GPT series) to generate text in a user-friendly format based on the analyzed numerical data and feature extraction results. The input is analysis results indicating the disaster situation, and the output is natural language text including specific evacuation instructions.

[0443] Step 4:

[0444] The server develops an evacuation plan based on the generated natural language information. This process takes into account the user's current location (GPS data). It searches for the nearest safe evacuation shelter and compiles emergency precautions along with route information. The input is natural language information and the user's location information, and the output is the evacuation plan proposed to the user.

[0445] Step 5:

[0446] The server transmits the formulated evacuation plan to the terminal, and the terminal displays the received information. Specifically, it uses the terminal's notification function to send emergency notifications to the user and also displays evacuation routes visually in conjunction with a map application. The input is the formulated evacuation plan, and the output is the evacuation information displayed on the user's terminal.

[0447] (Application Example 1)

[0448] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0449] Providing timely and accurate evacuation information during a disaster is a crucial factor in determining the success or failure of an evacuation. However, many current systems struggle to provide evacuation plans that adequately reflect the rapidly changing disaster situation in real time, which can result in the safety of residents being threatened. Furthermore, the difficulty in visually grasping complex information makes it difficult for users to make decisions that enable them to take appropriate action.

[0450] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0451] In this invention, the server includes means for acquiring an image and transmitting the image to a data processing device; analysis means for analyzing the image and estimating the disaster state; generation means for outputting the disaster state in natural language format; plan generation means for automatically generating an evacuation action plan based on the generated natural language information; transmission and display means for transmitting and displaying the evacuation action plan to an information terminal; and display means for displaying the evacuation action plan using a smartphone. This makes it possible for users to visually confirm an appropriate evacuation plan linked to disaster information that is updated in real time on their smartphones.

[0452] "Means for acquiring an image and transmitting the image to a data processing device" refers to a function for taking a photograph of the disaster situation using a terminal used by the user and transmitting the captured image to a data processing device via a network.

[0453] "Analysis means for analyzing the aforementioned images and estimating the disaster state" refers to a function for estimating the type of disaster and the extent of its impact based on the received images, using machine learning algorithms or the like.

[0454] "Generating means for outputting the disaster state in natural language format" refers to a function for converting the estimated disaster state into natural language text that is easy for humans to understand and outputting it.

[0455] "Plan generation means for automatically generating an evacuation action plan based on the generated natural language information" refers to a function for automatically formulating an evacuation action plan, including appropriate evacuation routes and evacuation locations, based on disaster information.

[0456] The "transmission and display means for transmitting and displaying the evacuation action plan on an information terminal" refers to a function for transmitting the generated evacuation action plan to an information terminal held by the user and displaying it on the screen of that terminal.

[0457] "Display means for displaying the evacuation action plan using a smartphone" refers to a function that visually provides the user with the generated evacuation plan using the smartphone screen, thereby facilitating appropriate actions according to the situation.

[0458] This invention is a system for providing appropriate evacuation information and evacuation action plans during disasters using smartphones. The main components are a server, a terminal, and the user. Each component is described in detail below.

[0459] The server utilizes advanced analytical techniques, such as deep learning models and complex modal functions, to receive disaster images sent by users and estimate the disaster state. The server outputs these analysis results in natural language format, which is then used to formulate evacuation action plans. In this process, machine learning frameworks such as TensorFlow and PyTorch are used to generate information quickly and accurately.

[0460] The terminal, primarily a smartphone, is responsible for displaying evacuation plans to the user. Based on the received information, the user can take appropriate evacuation actions in real time. The application on the terminal provides the display function, and is designed to allow the user to intuitively understand the information.

[0461] Users activate the entire system by taking photos of the disaster situation and sending those images to the server via their smartphones. This generates an evacuation plan that accurately reflects the situation on site.

[0462] As a concrete example, consider a scenario where a user takes a photo of a flooded city with their smartphone and sends it to the user. The server then analyzes the situation and outputs a recommended action, such as "There is a risk of rising water levels, please evacuate immediately," which is then sent to the user's device. This process allows the user to make a quick and appropriate decision.

[0463] Example prompt: "Clearly outline the steps to identify the type and situation of a disaster from the image and provide the user with the most suitable evacuation route and shelter in real time."

[0464] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0465] Step 1:

[0466] Users photograph the disaster situation with their smartphone cameras. These images serve as input. Data transmission via the network then takes place to send these images from the smartphone to the server.

[0467] Step 2:

[0468] The server uses a machine learning model to analyze the received images as input. Specifically, it performs image recognition using TensorFlow or PyTorch to estimate the type and scale of the disaster. The analysis results output the state of the disaster.

[0469] Step 3:

[0470] The server generates the disaster status obtained through analysis in natural language format. Here, a generative AI model is used to convert the estimation results into sentences such as "There is a risk of flooding, so immediate evacuation is necessary." This generated natural language sentence becomes the output.

[0471] Step 4:

[0472] The server uses this generated natural language text, along with the user's location information, to formulate an appropriate evacuation plan. During this process, information including specific instructions such as evacuation destinations and routes is output.

[0473] Step 5:

[0474] The server transmits the formulated evacuation plan to the terminal. The user's smartphone receives this information and treats it as input.

[0475] Step 6:

[0476] The device displays the received evacuation plan on its screen. The user can visually confirm evacuation routes and locations through their smartphone's display. In this step, the user takes specific evacuation actions based on the displayed information.

[0477] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0478] This invention is a system for providing users with rapid and accurate evacuation information during disasters, and in particular, it aims to deliver information more appropriately by taking into account the user's emotional state. The terminal receives images taken by the user at the disaster site and uploads these images to the server.

[0479] The server analyzes the received images to estimate the disaster situation. For example, it determines the severity of flooding and the likelihood of landslides. This analysis result is then converted into user-friendly text using natural language processing, where an emotion engine comes into play. The emotion engine recognizes the user's emotional state from their voice or text input and adjusts the tone of the text accordingly. For example, if it is determined that the user is feeling anxious, the explanatory text is adjusted to provide reassurance.

[0480] Furthermore, this system optimizes evacuation plans based on emotional states. The server considers the user's current location and emotional state to generate a plan that includes safe evacuation routes and information on nearby shelters. If the user is experiencing strong feelings of fear, the plan will include simpler, easier-to-understand instructions and provide additional information to enhance their sense of security.

[0481] Ultimately, the server sends this information to the user's terminal, which displays the plan. The user can then refer to this plan and take safe and efficient evacuation actions. This system, by taking emotions into consideration, makes it possible to provide a more user-friendly evacuation experience.

[0482] The following describes the processing flow.

[0483] Step 1:

[0484] Users capture images of the disaster site and surrounding area using devices such as smartphones.

[0485] Step 2:

[0486] Users upload acquired images to a server via a dedicated application. During this process, they can supplement their emotions and circumstances by using voice or text input as needed.

[0487] Step 3:

[0488] The server analyzes the received image data to estimate the disaster situation. This analysis uses image recognition algorithms to evaluate water levels and sediment conditions.

[0489] Step 4:

[0490] The server analyzes voice and text input from the user and uses an emotion engine to recognize the user's emotions. Examples of emotional states include anxiety, fear, and tension.

[0491] Step 5:

[0492] The server translates the analyzed disaster situation into natural language and adjusts the tone of the text based on the user's emotional state. For example, information is provided in a gentle, reassuring tone to users who are feeling anxious.

[0493] Step 6:

[0494] The server generates an optimal evacuation plan for the user based on the disaster situation and emotional state. This plan includes detailed information, such as the nearest evacuation shelter and safe evacuation routes, taking the user's location into consideration.

[0495] Step 7:

[0496] The server sends the evacuation plan to the user's terminal.

[0497] Step 8:

[0498] The terminal displays the received evacuation plan on its screen, providing the user with visual information. The user can then refer to this information and begin evacuating safely.

[0499] (Example 2)

[0500] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0501] During disasters, providing users with timely and accurate evacuation information is crucial. However, uniform information dissemination makes it difficult to encourage appropriate responses tailored to users' emotional states and circumstances. Therefore, it is necessary to provide information that takes into account the mental state of individual users to support safer and more secure evacuation actions.

[0502] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0503] In this invention, the server includes means for acquiring an image and transmitting the image to an information processing device; processing means for analyzing the image in the information processing device and estimating the disaster state; generation means for transcribing the disaster state into text and outputting it as natural language; emotion analysis means for analyzing the user's emotional state based on the transcribed natural language information and adjusting the tone of the output text; plan generation means for automatically generating an evacuation plan based on the generated natural language information and emotion information; and transmission / display means for transmitting and displaying the evacuation plan to a communication terminal. This makes it possible to provide evacuation information tailored to the user's emotional state.

[0504] "Means" refer to the specific methods or processes employed to achieve a particular objective.

[0505] An "information processing device" is a general term for hardware and software used to receive, analyze, transform, and transmit data.

[0506] "Disaster situation" refers to events caused by natural disasters and the resulting damage.

[0507] "Generation methods" refer to processes and technologies for generating text and content based on data.

[0508] "Emotional analysis means" refers to a technology that estimates a user's mental state from their input data and analyzes their emotions.

[0509] "Plan generation means" refers to methods and techniques for formulating and creating optimal action plans and instructions based on data.

[0510] "Transmission and display means" refers to the process of providing generated information to the user via a communication device and visualizing it on a display device.

[0511] The embodiments for carrying out this invention are shown below.

[0512] In this system, users take images at disaster sites using cameras such as smartphones or tablets. The device receives these images and transfers them to a server via Wi-Fi or mobile data communication. The server functions as an "information processing device" and uses cloud storage services to securely store the received images.

[0513] The server then analyzes the image using a "processing method" based on a deep learning model. This analysis utilizes machine learning frameworks such as TensorFlow to estimate the disaster state from elements in the image. For example, to determine the severity of a flood, the AI ​​model analyzes the water level and surrounding environment in the image.

[0514] The analysis results are then transcribed into text using natural language processing techniques. A natural language API is used as the "generation method" to convert the machine-understood information into meaningful text. In addition, an emotion engine is utilized as the "emotion analysis method" to grasp the user's emotional state from voice commands and text input.

[0515] The server creates an evacuation plan based on the user's emotional state information. This "plan generation method" incorporates optimized evacuation routes and shelter information using a map API. The evacuation plan is designed to provide a sense of security by adjusting the tone of the information in case the user is feeling fearful.

[0516] The generated evacuation plan and information reflecting emotions are sent from the server to the communication terminal. The terminal receives the information and supports the user by displaying it on the screen. For example, if a user takes a picture of a flood and the analysis results indicate that "the flood is severe," the route to the nearest safe evacuation center is shown, and a message to alleviate anxiety is added.

[0517] An example of a prompt would be, "Generate an evacuation message that provides reassurance to the user in response to their emotions during a disaster." This prompt allows the AI ​​model to generate appropriate instructions that are sensitive to the user's feelings.

[0518] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0519] Step 1:

[0520] Users take images at disaster sites using their smartphones or tablets. The input is image data from the device's camera sensor, and the output is an image file temporarily stored in local storage. This operation is completed when the user operates the device and presses the capture button on the camera application.

[0521] Step 2:

[0522] The device uploads captured images to the server via Wi-Fi or mobile data communication. The input is an image file in local storage, and the output is the transfer of image data to the server's cloud storage. This process involves issuing POST requests based on the HTTP protocol to send the data.

[0523] Step 3:

[0524] The server saves the received image data to a storage system for information analysis. The input is image data from the terminal, and the output is an image file securely stored in cloud storage. This saving operation utilizes a storage API, making the image data manageable within the system.

[0525] Step 4:

[0526] The server analyzes images using a "deep learning analysis module." The input is a saved image file, and the output is data on the disaster state estimated from the image. This process utilizes deep learning frameworks such as TensorFlow to execute the model's prediction algorithm to identify environmental changes.

[0527] Step 5:

[0528] The server passes the data obtained from image analysis to a "natural language generation module" for text conversion. The input is disaster status data, and the output is natural language text to notify the user. This process involves using a natural language processing API to convert the analysis results into an understandable format.

[0529] Step 6:

[0530] Upon receiving user voice or text input, the server activates its "emotion analysis engine" to analyze the user's emotional state. The input is user voice or text data, and the output is evaluation data indicating the user's emotions. The server uses speech recognition technology to identify the emotions.

[0531] Step 7:

[0532] The server generates an evacuation plan based on analyzed emotional data. The input is emotional state and location information, and the output is an evacuation plan tailored to the user's needs. A map API is used for optimization, calculating the optimal evacuation route in real time.

[0533] Step 8:

[0534] The server sends the generated evacuation plan to the terminal, which then displays it. The input is the plan data, and the output is a visual evacuation instruction on the user interface. The terminal then uses its own application to plot routes and shelter information on a map.

[0535] (Application Example 2)

[0536] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0537] During disasters, obtaining appropriate information to enable people to evacuate quickly and safely is extremely important. However, current systems fail to adequately consider users' emotions and psychological states when providing information, which can hinder evacuation. In particular, under the stress of a disaster, it becomes difficult to fully understand and act based on normal information alone, so there is a need for information that takes users' emotional states into account.

[0538] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0539] In this invention, the server includes means for acquiring an image and transmitting the image to a data server; analysis means for analyzing the image on the data server and estimating the disaster situation; and emotion adjustment means for analyzing the user's emotional state and adjusting the tone of the generated natural language information. This enables the rapid and accurate provision of information that takes the user's emotional state into consideration.

[0540] "Means for acquiring images" refers to a method or device for collecting images taken by users at a disaster site.

[0541] "Means of sending to a data server" refers to a method or function for transferring acquired image information to a central data processing device.

[0542] "Analysis means" refers to a method or technique for processing image data on a server to estimate the situation and impact of a disaster.

[0543] "Generation means" refers to a method or technology for converting analyzed disaster information into natural language and outputting it in a format that is easy for users to understand.

[0544] "Emotional adjustment techniques" refer to methods or techniques for analyzing a user's psychological state and adjusting the tone and wording of information based on the results.

[0545] "Plan generation means" refers to a method or function for automatically creating an evacuation plan based on analyzed information.

[0546] "Transmission and display means" refers to a method or device for transmitting and visually displaying an evacuation plan to a user's terminal.

[0547] The system used to implement this application operates through data communication between a smartphone and a server. Users acquire images at disaster sites using their smartphones and send these images to the server. The server, built on AWS, analyzes the disaster situation using image analysis software such as OpenCV.

[0548] Once the analysis is complete, the server uses a generative AI model, such as GPT-3, to translate the analysis results into natural language text. During this process, it uses a sentiment analysis engine, such as IBM Watson's Tone Analyzer, to determine the user's emotional state and adjust the tone of the information accordingly. This enables the provision of information that is sensitive to the user's mental state.

[0549] Furthermore, the server creates an optimal evacuation plan based on the generated natural language information and the user's current location. The plan includes safe and rapid route information from the original location to the evacuation shelter, which is then sent to the user's smartphone for display.

[0550] As a concrete example, in the event of flooding due to heavy rain, even if the user is in a state of anxiety, a message such as, "Don't worry. You can follow this route to reach a safe evacuation center," will be provided.

[0551] An example of a prompt message might be, "If the user is feeling anxious, generate a more reassuring evacuation instruction." This allows the system to provide appropriate information and evacuation plans based on the user's emotions, supporting effective evacuation during disasters.

[0552] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0553] Step 1:

[0554] A user uses their smartphone to capture images of the disaster site. Images are taken using the device's camera function, and the captured image data is sent to the server. Input: Captured image. Output: Image data transferred to the server.

[0555] Step 2:

[0556] The server analyzes the received image data using OpenCV. It determines the type and severity of the disaster and detects changes in the environment. Input: Image data transferred to the server. Output: Analyzed disaster information.

[0557] Step 3:

[0558] The server uses a generative AI model (e.g., GPT-3) to generate a natural language description based on the analysis results. Input: Analyzed disaster information. Output: Generated natural language description.

[0559] Step 4:

[0560] The server uses IBM Watson's Tone Analyzer to analyze the user's emotional state and adjust the tone of the generated description according to the user's emotions. Input: Generated natural language description and user emotion data. Output: Tone-adjusted natural language description.

[0561] Step 5:

[0562] The server retrieves the user's current location information and generates a safe evacuation plan based on disaster information and emotionally tuned descriptions. Input: User's location information and emotionally tuned natural language descriptions. Output: Generated evacuation plan.

[0563] Step 6:

[0564] The generated evacuation plan is sent to the user's terminal and displayed. The user then takes the optimal evacuation action according to this plan. Input: Generated evacuation plan. Output: Displayed on the user's terminal.

[0565] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0566] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0567] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0568] [Fourth Embodiment]

[0569] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0570] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0571] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0572] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0573] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0574] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0575] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0576] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0577] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0578] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0579] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0580] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0581] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0582] This invention is a system that provides rapid and accurate evacuation information during disasters. Specifically, it is a mechanism that analyzes actual disaster situations photographed by the user and automatically generates and provides evacuation plans based on that analysis.

[0583] Users take pictures of disaster areas using their devices. These images are sent to a data server via the network. The data server uses image analysis technology to estimate the current state of the disaster based on the received images. This analysis uses deep learning models and image recognition algorithms to determine the possibility of river flooding and landslides based on visual features.

[0584] The analysis results are converted into user-friendly text using natural language processing technology. For example, information such as "The current rate of water level rise is at a dangerous level" or "Evacuation is necessary within a certain time" is generated.

[0585] The server then uses the generated text to formulate an optimal evacuation plan. This plan can take the user's location into account and include information about the nearest evacuation shelter and precautions to take during evacuation. For example, it may provide specific instructions such as, "The nearest evacuation shelter is XX Park, 1 kilometer away," or "Due to the possibility of ground subsidence caused by the earthquake, an evacuation route along the outside of the building is recommended."

[0586] Finally, the server sends these evacuation plans to the user's terminal, which then displays the information. Users can visually confirm safe evacuation routes and shelters through their terminal screen. This system makes it possible to support the rapid and appropriate evacuation of residents during disasters.

[0587] The following describes the processing flow.

[0588] Step 1:

[0589] Users capture images of the disaster site and surrounding area using devices such as smartphones.

[0590] Step 2:

[0591] Users upload the acquired images to a data server via a dedicated application or web interface over the network.

[0592] Step 3:

[0593] The server applies an image analysis algorithm to the received image data to estimate the extent of the disaster. This analysis is performed using a deep learning model to evaluate water level and the likelihood of landslides.

[0594] Step 4:

[0595] The server uses a natural language processing engine to generate text describing the disaster situation in order to convert the analysis results into natural language.

[0596] Step 5:

[0597] Based on the generated disaster situation description, the server develops an optimal evacuation plan, taking into account the user's current location. The plan includes the locations of evacuation shelters and recommended evacuation routes.

[0598] Step 6:

[0599] The server sends the completed evacuation plan to the user's terminal.

[0600] Step 7:

[0601] The terminal displays the received evacuation plan on its screen, providing the user with visualized evacuation information. The user then refers to this information and begins to evacuate safely.

[0602] (Example 1)

[0603] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0604] In modern society, providing residents with timely and appropriate evacuation information during natural disasters is crucial. However, traditional manual information gathering and analysis methods have been time-consuming, leading to delays in responses in urgent situations. Furthermore, technologies for automatically generating appropriate evacuation plans tailored to the nature of the disaster and providing information customized to each user have not yet been sufficiently established.

[0605] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0606] In this invention, the server includes means for receiving and analyzing images, means for generating a disaster state in natural language, and means for creating and transmitting an evacuation plan. This enables the rapid and accurate provision of information and personalized evacuation route guidance during a disaster.

[0607] "Means of acquiring images" refers to a function that uses a terminal with a camera function to capture visual information of the disaster area and generate image data from that image.

[0608] An "information processing device" is a device that has computing resources and algorithms for receiving and analyzing transmitted image data.

[0609] "Analysis means" refers to the process of interpreting and estimating the nature of a disaster from received image data using deep learning and image recognition technologies.

[0610] "Generation means" refers to a function that uses natural language processing technology based on analysis results to output information as text in a format that is easy for the user to understand.

[0611] A "plan generation method" is a process that automatically formulates an optimal evacuation plan by creating information on evacuation routes and safe shelters based on generated natural language information.

[0612] The "transmission and display means" refers to a function that transmits the formulated evacuation plan to the user's terminal via communication and displays it in a visually verifiable format.

[0613] "Integrated functionality" refers to a technology used in image analysis that integrates and processes data and media information in different formats.

[0614] "User location information" refers to the user's current geographical coordinates, obtained using the GPS function or other positioning technologies included with the device.

[0615] This invention is a system that provides rapid and accurate evacuation information during disasters. Specifically, it begins with a user taking images of the disaster area using a terminal. In this process, a smartphone or tablet with a camera function is used as hardware, and the image data is transmitted to an information processing device, i.e., a server, via network communication.

[0616] The server processes the received images using deep learning frameworks (e.g., TensorFlow and PyTorch) and uses image analysis techniques to infer the current state of the disaster. For example, it uses an analysis model to determine the possibility of river flooding or landslides. After this analysis, the server uses natural language processing techniques to convert the analysis results into text. The software used here is a generative AI model (e.g., OpenAI's GPT series), which generates specific information such as "The current rate of water level rise is at a dangerous level" or "Evacuation is necessary within a certain time."

[0617] Next, the server formulates an optimal evacuation plan based on the generated natural language information. Here, it uses the user's location data to provide the user with the most suitable evacuation route and shelter information. At this stage, the evacuation information is formalized as specific instructions. For example, it may include guidance such as, "The nearest shelter is a park 1 kilometer away," or "Due to the possibility of ground subsidence caused by the earthquake, an evacuation route along the outside of the building is recommended."

[0618] Finally, the formulated evacuation information is transmitted from the server to the terminal, which then notifies the user and displays the information on the screen. This allows the user to receive information on safe evacuation routes and shelters in real time, enabling them to take swift evacuation action.

[0619] As a concrete example, suppose a user takes a picture of a rising river level due to heavy rain and sends the image to a server. This system assesses the danger of the water level and generates and provides to the user an instruction such as, "Evacuation is necessary due to the rapid rise in water level. Please evacuate to the nearest school." An example of a prompt message to the generating AI model would be, "Generate an evacuation order to inform the user of the danger of rising water levels due to heavy rain. Currently, the river is overflowing, and water levels in the surrounding area are rising rapidly."

[0620] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0621] Step 1:

[0622] Users take pictures of the disaster area using the camera function of their smartphone or tablet. These images are converted into digital data such as JPEG format on the device and sent to the server via network communication. The input is the image data captured by the camera, and the output is the image file received by the server.

[0623] Step 2:

[0624] The server analyzes the received image data. Data processing begins with pre-processing, which includes adjusting the resolution and reducing noise. Then, using a deep learning framework (such as TensorFlow or PyTorch), a pre-trained model is used to extract features from the image and estimate the nature of the disaster. The input is image data, and the output is the analysis result indicating the disaster situation.

[0625] Step 3:

[0626] The server converts the acquired analysis results into natural language. Specifically, it utilizes a generative AI model (such as OpenAI's GPT series) to generate text in a user-friendly format based on the analyzed numerical data and feature extraction results. The input is analysis results indicating the disaster situation, and the output is natural language text including specific evacuation instructions.

[0627] Step 4:

[0628] The server develops an evacuation plan based on the generated natural language information. This process takes into account the user's current location (GPS data). It searches for the nearest safe evacuation shelter and compiles emergency precautions along with route information. The input is natural language information and the user's location information, and the output is the evacuation plan proposed to the user.

[0629] Step 5:

[0630] The server transmits the formulated evacuation plan to the terminal, and the terminal displays the received information. Specifically, it uses the terminal's notification function to send emergency notifications to the user and also displays evacuation routes visually in conjunction with a map application. The input is the formulated evacuation plan, and the output is the evacuation information displayed on the user's terminal.

[0631] (Application Example 1)

[0632] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0633] Providing timely and accurate evacuation information during a disaster is a crucial factor in determining the success or failure of an evacuation. However, many current systems struggle to provide evacuation plans that adequately reflect the rapidly changing disaster situation in real time, which can result in the safety of residents being threatened. Furthermore, the difficulty in visually grasping complex information makes it difficult for users to make decisions that enable them to take appropriate action.

[0634] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0635] In this invention, the server includes means for acquiring an image and transmitting the image to a data processing device; analysis means for analyzing the image and estimating the disaster state; generation means for outputting the disaster state in natural language format; plan generation means for automatically generating an evacuation action plan based on the generated natural language information; transmission and display means for transmitting and displaying the evacuation action plan to an information terminal; and display means for displaying the evacuation action plan using a smartphone. This makes it possible for users to visually confirm an appropriate evacuation plan linked to disaster information that is updated in real time on their smartphones.

[0636] "Means for acquiring an image and transmitting the image to a data processing device" refers to a function for taking a photograph of the disaster situation using a terminal used by the user and transmitting the captured image to a data processing device via a network.

[0637] "Analysis means for analyzing the aforementioned images and estimating the disaster state" refers to a function for estimating the type of disaster and the extent of its impact based on the received images, using machine learning algorithms or the like.

[0638] "Generating means for outputting the disaster state in natural language format" refers to a function for converting the estimated disaster state into natural language text that is easy for humans to understand and outputting it.

[0639] "Plan generation means for automatically generating an evacuation action plan based on the generated natural language information" refers to a function for automatically formulating an evacuation action plan, including appropriate evacuation routes and evacuation locations, based on disaster information.

[0640] The "transmission and display means for transmitting and displaying the evacuation action plan on an information terminal" refers to a function for transmitting the generated evacuation action plan to an information terminal held by the user and displaying it on the screen of that terminal.

[0641] "Display means for displaying the evacuation action plan using a smartphone" refers to a function that visually provides the user with the generated evacuation plan using the smartphone screen, thereby facilitating appropriate actions according to the situation.

[0642] This invention is a system for providing appropriate evacuation information and evacuation action plans during disasters using smartphones. The main components are a server, a terminal, and the user. Each component is described in detail below.

[0643] The server utilizes advanced analytical techniques, such as deep learning models and complex modal functions, to receive disaster images sent by users and estimate the disaster state. The server outputs these analysis results in natural language format, which is then used to formulate evacuation action plans. In this process, machine learning frameworks such as TensorFlow and PyTorch are used to generate information quickly and accurately.

[0644] The terminal, primarily a smartphone, is responsible for displaying evacuation plans to the user. Based on the received information, the user can take appropriate evacuation actions in real time. The application on the terminal provides the display function, and is designed to allow the user to intuitively understand the information.

[0645] Users activate the entire system by taking photos of the disaster situation and sending those images to the server via their smartphones. This generates an evacuation plan that accurately reflects the situation on site.

[0646] As a concrete example, consider a scenario where a user takes a photo of a flooded city with their smartphone and sends it to the user. The server then analyzes the situation and outputs a recommended action, such as "There is a risk of rising water levels, please evacuate immediately," which is then sent to the user's device. This process allows the user to make a quick and appropriate decision.

[0647] Example prompt: "Clearly outline the steps to identify the type and situation of a disaster from the image and provide the user with the most suitable evacuation route and shelter in real time."

[0648] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0649] Step 1:

[0650] Users photograph the disaster situation with their smartphone cameras. These images serve as input. Data transmission via the network then takes place to send these images from the smartphone to the server.

[0651] Step 2:

[0652] The server uses a machine learning model to analyze the received images as input. Specifically, it performs image recognition using TensorFlow or PyTorch to estimate the type and scale of the disaster. The analysis results output the state of the disaster.

[0653] Step 3:

[0654] The server generates the disaster status obtained through analysis in natural language format. Here, a generative AI model is used to convert the estimation results into sentences such as "There is a risk of flooding, so immediate evacuation is necessary." This generated natural language sentence becomes the output.

[0655] Step 4:

[0656] The server uses this generated natural language text, along with the user's location information, to formulate an appropriate evacuation plan. During this process, information including specific instructions such as evacuation destinations and routes is output.

[0657] Step 5:

[0658] The server transmits the formulated evacuation plan to the terminal. The user's smartphone receives this information and treats it as input.

[0659] Step 6:

[0660] The device displays the received evacuation plan on its screen. The user can visually confirm evacuation routes and locations through their smartphone's display. In this step, the user takes specific evacuation actions based on the displayed information.

[0661] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0662] This invention is a system for providing users with rapid and accurate evacuation information during disasters, and in particular, it aims to deliver information more appropriately by taking into account the user's emotional state. The terminal receives images taken by the user at the disaster site and uploads these images to the server.

[0663] The server analyzes the received images to estimate the disaster situation. For example, it determines the severity of flooding and the likelihood of landslides. This analysis result is then converted into user-friendly text using natural language processing, where an emotion engine comes into play. The emotion engine recognizes the user's emotional state from their voice or text input and adjusts the tone of the text accordingly. For example, if it is determined that the user is feeling anxious, the explanatory text is adjusted to provide reassurance.

[0664] Furthermore, this system optimizes evacuation plans based on emotional states. The server considers the user's current location and emotional state to generate a plan that includes safe evacuation routes and information on nearby shelters. If the user is experiencing strong feelings of fear, the plan will include simpler, easier-to-understand instructions and provide additional information to enhance their sense of security.

[0665] Ultimately, the server sends this information to the user's terminal, which displays the plan. The user can then refer to this plan and take safe and efficient evacuation actions. This system, by taking emotions into consideration, makes it possible to provide a more user-friendly evacuation experience.

[0666] The following describes the processing flow.

[0667] Step 1:

[0668] Users capture images of the disaster site and surrounding area using devices such as smartphones.

[0669] Step 2:

[0670] Users upload acquired images to a server via a dedicated application. During this process, they can supplement their emotions and circumstances by using voice or text input as needed.

[0671] Step 3:

[0672] The server analyzes the received image data to estimate the disaster situation. This analysis uses image recognition algorithms to evaluate water levels and sediment conditions.

[0673] Step 4:

[0674] The server analyzes voice and text input from the user and uses an emotion engine to recognize the user's emotions. Examples of emotional states include anxiety, fear, and tension.

[0675] Step 5:

[0676] The server translates the analyzed disaster situation into natural language and adjusts the tone of the text based on the user's emotional state. For example, information is provided in a gentle, reassuring tone to users who are feeling anxious.

[0677] Step 6:

[0678] The server generates an optimal evacuation plan for the user based on the disaster situation and emotional state. This plan includes detailed information, such as the nearest evacuation shelter and safe evacuation routes, taking the user's location into consideration.

[0679] Step 7:

[0680] The server sends the evacuation plan to the user's terminal.

[0681] Step 8:

[0682] The terminal displays the received evacuation plan on its screen, providing the user with visual information. The user can then refer to this information and begin evacuating safely.

[0683] (Example 2)

[0684] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0685] During disasters, providing users with timely and accurate evacuation information is crucial. However, uniform information dissemination makes it difficult to encourage appropriate responses tailored to users' emotional states and circumstances. Therefore, it is necessary to provide information that takes into account the mental state of individual users to support safer and more secure evacuation actions.

[0686] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0687] In this invention, the server includes means for acquiring an image and transmitting the image to an information processing device; processing means for analyzing the image in the information processing device and estimating the disaster state; generation means for transcribing the disaster state into text and outputting it as natural language; emotion analysis means for analyzing the user's emotional state based on the transcribed natural language information and adjusting the tone of the output text; plan generation means for automatically generating an evacuation plan based on the generated natural language information and emotion information; and transmission / display means for transmitting and displaying the evacuation plan to a communication terminal. This makes it possible to provide evacuation information tailored to the user's emotional state.

[0688] "Means" refer to the specific methods or processes employed to achieve a particular objective.

[0689] An "information processing device" is a general term for hardware and software used to receive, analyze, transform, and transmit data.

[0690] "Disaster situation" refers to events caused by natural disasters and the resulting damage.

[0691] "Generation methods" refer to processes and technologies for generating text and content based on data.

[0692] "Emotional analysis means" refers to a technology that estimates a user's mental state from their input data and analyzes their emotions.

[0693] "Plan generation means" refers to methods and techniques for formulating and creating optimal action plans and instructions based on data.

[0694] "Transmission and display means" refers to the process of providing generated information to the user via a communication device and visualizing it on a display device.

[0695] The embodiments for carrying out this invention are shown below.

[0696] In this system, users take images at disaster sites using cameras such as smartphones or tablets. The device receives these images and transfers them to a server via Wi-Fi or mobile data communication. The server functions as an "information processing device" and uses cloud storage services to securely store the received images.

[0697] The server then analyzes the image using a "processing method" based on a deep learning model. This analysis utilizes machine learning frameworks such as TensorFlow to estimate the disaster state from elements in the image. For example, to determine the severity of a flood, the AI ​​model analyzes the water level and surrounding environment in the image.

[0698] The analysis results are then transcribed into text using natural language processing techniques. A natural language API is used as the "generation method" to convert the machine-understood information into meaningful text. In addition, an emotion engine is utilized as the "emotion analysis method" to grasp the user's emotional state from voice commands and text input.

[0699] The server creates an evacuation plan based on the user's emotional state information. This "plan generation method" incorporates optimized evacuation routes and shelter information using a map API. The evacuation plan is designed to provide a sense of security by adjusting the tone of the information in case the user is feeling fearful.

[0700] The generated evacuation plan and information reflecting emotions are sent from the server to the communication terminal. The terminal receives the information and supports the user by displaying it on the screen. For example, if a user takes a picture of a flood and the analysis results indicate that "the flood is severe," the route to the nearest safe evacuation center is shown, and a message to alleviate anxiety is added.

[0701] An example of a prompt would be, "Generate an evacuation message that provides reassurance to the user in response to their emotions during a disaster." This prompt allows the AI ​​model to generate appropriate instructions that are sensitive to the user's feelings.

[0702] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0703] Step 1:

[0704] Users take images at disaster sites using their smartphones or tablets. The input is image data from the device's camera sensor, and the output is an image file temporarily stored in local storage. This operation is completed when the user operates the device and presses the capture button on the camera application.

[0705] Step 2:

[0706] The device uploads captured images to the server via Wi-Fi or mobile data communication. The input is an image file in local storage, and the output is the transfer of image data to the server's cloud storage. This process involves issuing POST requests based on the HTTP protocol to send the data.

[0707] Step 3:

[0708] The server saves the received image data to a storage system for information analysis. The input is image data from the terminal, and the output is an image file securely stored in cloud storage. This saving operation utilizes a storage API, making the image data manageable within the system.

[0709] Step 4:

[0710] The server analyzes images using a "deep learning analysis module." The input is a saved image file, and the output is data on the disaster state estimated from the image. This process utilizes deep learning frameworks such as TensorFlow to execute the model's prediction algorithm to identify environmental changes.

[0711] Step 5:

[0712] The server passes the data obtained from image analysis to a "natural language generation module" for text conversion. The input is disaster status data, and the output is natural language text to notify the user. This process involves using a natural language processing API to convert the analysis results into an understandable format.

[0713] Step 6:

[0714] Upon receiving user voice or text input, the server activates its "emotion analysis engine" to analyze the user's emotional state. The input is user voice or text data, and the output is evaluation data indicating the user's emotions. The server uses speech recognition technology to identify the emotions.

[0715] Step 7:

[0716] The server generates an evacuation plan based on analyzed emotional data. The input is emotional state and location information, and the output is an evacuation plan tailored to the user's needs. A map API is used for optimization, calculating the optimal evacuation route in real time.

[0717] Step 8:

[0718] The server sends the generated evacuation plan to the terminal, which then displays it. The input is the plan data, and the output is a visual evacuation instruction on the user interface. The terminal then uses its own application to plot routes and shelter information on a map.

[0719] (Application Example 2)

[0720] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0721] During disasters, obtaining appropriate information to enable people to evacuate quickly and safely is extremely important. However, current systems fail to adequately consider users' emotions and psychological states when providing information, which can hinder evacuation. In particular, under the stress of a disaster, it becomes difficult to fully understand and act based on normal information alone, so there is a need for information that takes users' emotional states into account.

[0722] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0723] In this invention, the server includes means for acquiring an image and transmitting the image to a data server; analysis means for analyzing the image on the data server and estimating the disaster situation; and emotion adjustment means for analyzing the user's emotional state and adjusting the tone of the generated natural language information. This enables the rapid and accurate provision of information that takes the user's emotional state into consideration.

[0724] "Means for acquiring images" refers to a method or device for collecting images taken by users at a disaster site.

[0725] "Means of sending to a data server" refers to a method or function for transferring acquired image information to a central data processing device.

[0726] "Analysis means" refers to a method or technique for processing image data on a server to estimate the situation and impact of a disaster.

[0727] "Generation means" refers to a method or technology for converting analyzed disaster information into natural language and outputting it in a format that is easy for users to understand.

[0728] "Emotional adjustment techniques" refer to methods or techniques for analyzing a user's psychological state and adjusting the tone and wording of information based on the results.

[0729] "Plan generation means" refers to a method or function for automatically creating an evacuation plan based on analyzed information.

[0730] "Transmission and display means" refers to a method or device for transmitting and visually displaying an evacuation plan to a user's terminal.

[0731] The system used to implement this application operates through data communication between a smartphone and a server. Users acquire images at disaster sites using their smartphones and send these images to the server. The server, built on AWS, analyzes the disaster situation using image analysis software such as OpenCV.

[0732] Once the analysis is complete, the server uses a generative AI model, such as GPT-3, to translate the analysis results into natural language text. During this process, it uses a sentiment analysis engine, such as IBM Watson's Tone Analyzer, to determine the user's emotional state and adjust the tone of the information accordingly. This enables the provision of information that is sensitive to the user's mental state.

[0733] Furthermore, the server creates an optimal evacuation plan based on the generated natural language information and the user's current location. The plan includes safe and rapid route information from the original location to the evacuation shelter, which is then sent to the user's smartphone for display.

[0734] As a concrete example, in the event of flooding due to heavy rain, even if the user is in a state of anxiety, a message such as, "Don't worry. You can follow this route to reach a safe evacuation center," will be provided.

[0735] An example of a prompt message might be, "If the user is feeling anxious, generate a more reassuring evacuation instruction." This allows the system to provide appropriate information and evacuation plans based on the user's emotions, supporting effective evacuation during disasters.

[0736] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0737] Step 1:

[0738] A user uses their smartphone to capture images of the disaster site. Images are taken using the device's camera function, and the captured image data is sent to the server. Input: Captured image. Output: Image data transferred to the server.

[0739] Step 2:

[0740] The server analyzes the received image data using OpenCV. It determines the type and severity of the disaster and detects changes in the environment. Input: Image data transferred to the server. Output: Analyzed disaster information.

[0741] Step 3:

[0742] The server uses a generative AI model (e.g., GPT-3) to generate a natural language description based on the analysis results. Input: Analyzed disaster information. Output: Generated natural language description.

[0743] Step 4:

[0744] The server uses IBM Watson's Tone Analyzer to analyze the user's emotional state and adjust the tone of the generated description according to the user's emotions. Input: Generated natural language description and user emotion data. Output: Tone-adjusted natural language description.

[0745] Step 5:

[0746] The server retrieves the user's current location information and generates a safe evacuation plan based on disaster information and emotionally tuned descriptions. Input: User's location information and emotionally tuned natural language descriptions. Output: Generated evacuation plan.

[0747] Step 6:

[0748] The generated evacuation plan is sent to the user's terminal and displayed. The user then takes the optimal evacuation action according to this plan. Input: Generated evacuation plan. Output: Displayed on the user's terminal.

[0749] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0750] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0751] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0752] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0753] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0754] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0755] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0756] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0757] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0758] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0759] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0760] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0761] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0762] 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.

[0763] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0764] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0765] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0766] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0767] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0768] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0769] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0770] The following is further disclosed regarding the embodiments described above.

[0771] (Claim 1)

[0772] Means for acquiring an image and transmitting the said image to a data server,

[0773] The data server includes an analysis means for analyzing the image and estimating the disaster situation,

[0774] A generation means for transcribing the aforementioned disaster situation into text and outputting it in natural language,

[0775] A plan generation means that automatically generates an evacuation plan based on the generated natural language information,

[0776] A transmission and display means for transmitting and displaying the aforementioned evacuation plan to a user device,

[0777] A system that includes this.

[0778] (Claim 2)

[0779] The system according to claim 1, further comprising means for using multimodal functionality to analyze the aforementioned image.

[0780] (Claim 3)

[0781] The system according to claim 1, comprising means for generating information including the nearest evacuation shelter and a safe route, taking into account the user's location information in the generation of the evacuation plan.

[0782] "Example 1"

[0783] (Claim 1)

[0784] Means for acquiring an image and transmitting the image to an information processing device,

[0785] The aforementioned information processing device includes an analysis means for analyzing the image and estimating the disaster state,

[0786] A generation means for transcribing the aforementioned disaster situation into text and outputting it as natural language,

[0787] A plan generation means that automatically generates an evacuation plan based on the generated natural language information,

[0788] A transmission and display means for transmitting and displaying the aforementioned evacuation plan to a user terminal,

[0789] A system that includes this.

[0790] (Claim 2)

[0791] The system according to claim 1, further comprising means for using a composite function to analyze the aforementioned image.

[0792] (Claim 3)

[0793] The system according to claim 1, further comprising means for generating information including the nearest evacuation facility and a safe route, taking into account the user's location information in the evacuation plan generation.

[0794] "Application Example 1"

[0795] (Claim 1)

[0796] Means for acquiring an image and transmitting the image to a data processing device,

[0797] The data processing device includes an analysis means for analyzing the image and estimating the disaster state,

[0798] A generation means for outputting the aforementioned disaster state in natural language format,

[0799] A plan generation means that automatically generates an evacuation action plan based on the generated natural language information,

[0800] The aforementioned evacuation action plan is transmitted to and displayed on an information terminal by a transmission / display means,

[0801] A display means for displaying the evacuation action plan using a smartphone,

[0802] A system that includes this.

[0803] (Claim 2)

[0804] The system according to claim 1, further comprising means for using a composite modal function to analyze the aforementioned image.

[0805] (Claim 3)

[0806] The system according to claim 1, comprising means for generating information including the nearest evacuation facility and a safe route, taking into account the user's location information in the generation of the evacuation action plan.

[0807] "Example 2 of combining an emotion engine"

[0808] (Claim 1)

[0809] Means for acquiring an image and transmitting the image to an information processing device,

[0810] The aforementioned information processing device includes processing means for analyzing the image and estimating the disaster state,

[0811] A generation means for transcribing the aforementioned disaster situation into text and outputting it as natural language,

[0812] A sentiment analysis means analyzes the user's emotional state based on the transcribed natural language information and adjusts the tone of the output text.

[0813] A plan generation means that automatically generates an evacuation plan based on the generated natural language information and emotional information,

[0814] A transmission and display means for transmitting and displaying the aforementioned evacuation plan to a communication terminal,

[0815] A system that includes this.

[0816] (Claim 2)

[0817] The system according to claim 1, further comprising means for using a function that combines and utilizes multiple data formats in order to analyze the aforementioned image.

[0818] (Claim 3)

[0819] The system according to claim 1, comprising means for generating information including the nearest evacuation facility and a safe route, taking into account the user's location information and emotional state in the evacuation plan generation.

[0820] "Application example 2 when combining with an emotional engine"

[0821] (Claim 1)

[0822] Means for acquiring an image and transmitting the said image to a data server,

[0823] The data server includes an analysis means for analyzing the image and estimating the disaster situation,

[0824] A generation means for transcribing the aforementioned disaster situation into text and outputting it in natural language,

[0825] An emotion adjustment means that analyzes the user's emotional state and adjusts the tone of the generated natural language information,

[0826] A plan generation means that automatically generates an evacuation plan based on the generated natural language information,

[0827] A transmission and display means for transmitting and displaying the aforementioned evacuation plan to a user device,

[0828] A system that includes this.

[0829] (Claim 2)

[0830] The system according to claim 1, further comprising means for using multimodal functionality to analyze the aforementioned image.

[0831] (Claim 3)

[0832] The system according to claim 1, comprising means for generating information including the nearest evacuation shelter and a safe route, taking into account the user's location information and emotional state in the evacuation plan generation. [Explanation of Symbols]

[0833] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means for acquiring an image and transmitting the said image to a data server, The data server includes an analysis means for analyzing the image and estimating the disaster situation, A generation means for transcribing the aforementioned disaster situation into text and outputting it in natural language, A plan generation means that automatically generates an evacuation plan based on the generated natural language information, A transmission and display means for transmitting and displaying the aforementioned evacuation plan to a user device, A system that includes this.

2. The system according to claim 1, further comprising means for using multimodal functionality to analyze the aforementioned image.

3. The system according to claim 1, further comprising means for generating information including the nearest evacuation shelter and a safe route, taking into account the user's location information in the generation of the evacuation plan.

Images