System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting physical data including records of past disasters; means for extracting character information from the collected physical data; analyzing means using generative artificial intelligence for analyzing the extracted character information; means for storing the analyzed information in a database; and information providing means for providing the stored information to a user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Records and legends of past disasters are often preserved as physical stone monuments or documents, but there is a lack of efficient ways to collect, analyze, and utilize this information in modern disaster prevention measures. This means that past wisdom and lessons are not fully utilized, and disaster prevention awareness in the community is not improved. There is also a need for a means to issue appropriate warnings in real time when a disaster occurs and to quickly notify local residents and visitors. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing a system that collects physical data, including records of past disasters, extracts text information from the data, and analyzes it using generative AI. Specifically, the system includes a means for collecting physical data, including records of past disasters, a means for extracting text information from the collected physical data, an analysis means using generative AI to analyze the extracted text information, a means for storing the analyzed information in a database, and an information provision means for providing the stored information to users. The system also includes a means for collecting data with location information and performing risk assessments and issuing warnings based on the analysis results, enabling rapid response in the event of a disaster. Furthermore, the system provides a query processing means for users to search for specific regions or past disaster information, and a means for retrieving information corresponding to the query from a database and generating an appropriate response, thereby improving disaster prevention awareness and safety in the region.

[0006] "Physical data" refers to information such as records of past disasters and legends left behind in stone monuments, documents, or other forms.

[0007] "Textual information" refers to textual data extracted from physical data.

[0008] "Generative AI" refers to a system that uses artificial intelligence technologies such as machine learning and neural networks to analyze text data and recognize patterns.

[0009] A "database" refers to an information management system that organizes and stores analyzed information so that it can be easily searched and used later.

[0010] "Information provision means" refers to web apps, mobile apps, notification systems, etc. that provide information stored in the database to users.

[0011] "Risk assessment" refers to the process of assessing disaster risk in a particular area using real-time data and past disaster records.

[0012] "Warning" refers to a message or alert generated based on a risk assessment to notify of the possibility of a disaster occurring.

[0013] "Query processing means" refers to a system that receives a search request from a user, retrieves corresponding information from a database, and generates a response.

[0014] "Analysis method" refers to the process of analyzing collected text information using generative AI to extract important patterns and lessons.

[0015] "Location Information" means latitude and longitude data that indicates the location where collected physical data is found. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0024] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0037] This invention is a system that analyzes past disaster records and legends and provides them as information for modern disaster prevention measures. This system collects physical data and uses a generative AI to analyze it as text information, stores that information in a database, and provides it to users. The program's processing is explained in detail below.

[0038] Data collection

[0039] The user visits the site and takes photos of past disaster records, such as stone monuments and documents. The device attaches location information to the captured images and uploads this data to the server. In addition, the user can manually enter supplementary information and detailed explanations into the device.

[0040] Character Recognition and Analysis

[0041] The server uses OCR technology to extract text information from the received image data. The text data extracted by OCR is then analyzed in detail by the generative AI. This analysis allows important lessons to be extracted about past disaster patterns and legends.

[0042] Database Management

[0043] The server structures and stores the analyzed information in a database, which is updated each time new data is added and managed to optimize the information.

[0044] Information provision

[0045] Users can search for information about specific regions or disasters through web or mobile apps. The device sends the user's query to the server, which then searches for relevant information from a database, organizes it, and returns it to the device. This allows users to receive past disaster records and forecast information in real time.

[0046] Real-time risk assessment and alerting

[0047] The server periodically obtains and analyzes real-time information, such as the latest weather and earthquake data. It compares this information with past disaster records and generates an alert if it determines there is a high risk. This alert is then sent to the device, prompting the user to take appropriate action.

[0048] Specific examples

[0049] Here's a specific example: A user visits a mountain village in an earthquake-prone area and discovers an old stone monument mentioned by locals. The user takes a photo of the monument and uploads it to a server. The image is processed using OCR, and the generating AI discovers that "two large earthquakes have occurred in this area in the past, causing many buildings to collapse." The analysis results are stored in a database, and when the user searches for "earthquake records" in the app, information on past earthquakes is provided, along with appropriate evacuation plans and information on local shelters.

[0050] If the server determines that heavy rain is continuing in an area, it will compare the data with records of past large-scale floods and recognize that the risk is increasing.The server will then issue a flood warning and notify registered users' devices that "there is an increasing risk of large-scale flooding in this area. Please evacuate to nearby high ground."

[0051] This system will utilize past lessons learned for modern disaster prevention and provide appropriate information to local residents and visitors, thereby raising disaster prevention awareness and enabling rapid response.

[0052] The processing flow will be explained below.

[0053] Step 1:

[0054] Users discover stone monuments or disaster records on-site and take pictures using their smartphones or dedicated devices, which then attach location information (GPS data) to the captured image data.

[0055] Step 2:

[0056] The device uploads the captured image and its location information to the server, and the user manually enters additional information and descriptions into the device, which are also sent to the server.

[0057] Step 3:

[0058] The server receives the uploaded image data and uses OCR (Optical Character Recognition) technology to extract text information from the received image data.

[0059] Step 4:

[0060] The server inputs the text data extracted by OCR into a generative AI model for detailed analysis, which extracts important lessons about past disaster patterns and legends.

[0061] Step 5:

[0062] The server structures the parsed information and stores it in a database, which is updated with the newly added data.

[0063] Step 6:

[0064] A user searches for information about a specific area or disaster through a web or mobile app, and the device sends the query to the server.

[0065] Step 7:

[0066] The server searches the database based on the received query to retrieve relevant records of past disasters and legends, then organizes the retrieved information and generates a response.

[0067] Step 8:

[0068] The terminal receives the response from the server and displays it on the user interface, allowing the user to receive past disaster records and appropriate prevention information in real time.

[0069] Step 9:

[0070] The server periodically collects and analyzes real-time weather and earthquake data, and compares the analysis results with records of past disasters to assess whether a particular area is at increased risk.

[0071] Step 10:

[0072] If the server determines that the risk is high, it generates an alert, which is then sent to the user's terminal.

[0073] Step 11:

[0074] The terminal displays the received warning message on the user interface and prompts the user to take appropriate action.

[0075] This step will enable efficient analysis of past disaster records and contribute to current disaster prevention measures. Users and devices will receive useful information in real time, enabling safe and prompt responses.

[0076] Example 1

[0077] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0078] Records of past disasters and legends provide valuable information for local disaster risk assessments and disaster prevention measures, but this information is easily lost and should ideally be collected, analyzed, and utilized in current disaster prevention. An efficient system for real-time disaster risk assessment and rapid warning issuance is also needed. Therefore, an integrated system is needed that collects and analyzes past disaster records and combines them with the latest data to assess risk and issue warnings in real time.

[0079] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0080] In this invention, the server includes means for collecting past disaster records photographed on-site, means for adding location information to the collected past disaster records, means for transmitting the data with the added location information to the server, means for extracting text information from the transmitted data, means for analyzing the extracted text information using artificial intelligence, means for saving the generated analysis results such as disaster patterns and lessons learned in a database, means for providing the saved information to users, means for comparing past disaster records with the latest weather data to assess risk, and means for issuing an alert if the risk is high. This enables the provision of disaster prevention information based on past disaster records, real-time risk assessment, and rapid alert issuance.

[0081] "Records of past disasters photographed on-site" refers to images and videos of information related to past disasters, such as old stone monuments, documents, and local folklore, taken directly on-site.

[0082] "Means for adding location information" refers to technology that uses location information systems such as GPS to add latitude and longitude data of the location where a photograph was taken to an image or video.

[0083] "Server" refers to a computer system that centrally manages, analyzes, stores, and provides data.

[0084] "Means for extracting text information" refers to the use of OCR (optical character recognition) technology to read text from images or videos and extract it as digital text.

[0085] "Means of analysis using generative artificial intelligence" refers to technology that uses a generative AI model (such as GPT) to analyze extracted text information and derive disaster patterns and lessons learned.

[0086] A "database" refers to an information system for efficiently storing, searching, and managing structured data.

[0087] "Means of storage" refers to the technology that stores the analyzed information in a database so that it can be searched and used later.

[0088] "Means of providing to users" refers to technology that provides analyzed information to users through interfaces such as web apps and mobile apps.

[0089] "The latest weather data" refers to real-time weather information and earthquake data provided by institutions such as the Japan Meteorological Agency and the Earthquake Research Institute.

[0090] "Means for conducting risk assessment" refers to technology that compares past disaster records with the latest meteorological data to conduct current risk assessments.

[0091] "Means for issuing alerts" refers to technology that uses communication APIs such as Twilio to issue alerts to users when specific risks increase.

[0092] This invention is a system that analyzes past disaster records and legends and provides them as information for modern disaster prevention measures. This system collects physical data, uses generative AI to analyze it as text information, stores the information in a database, and provides it to users.

[0093] In the data collection module, users go to the site and take photos of past disaster records, such as stone monuments and documents, using a smartphone or tablet. At this time, the user manually enters supplementary information and detailed descriptions into the device. The device then uses GPS to add location information to this data and uploads it to the server.

[0094] In the image processing module, the server extracts text from the received image data using OCR technology (e.g., Amazon Textract). The text extracted through OCR technology is then analyzed in detail using generative AI (e.g., OpenAI GPT model). This analysis extracts important lessons about past disaster patterns and legends.

[0095] In the database management module, the server structures and stores the analyzed information in a database (e.g., MySQL). This database is updated each time new data is added and is managed to optimize the information.

[0096] In the information provision module, users can search for information about specific regions or disasters through web or mobile apps. The device sends the user's query to the server, which then searches for relevant information from a database, organizes it, and returns it to the device. This allows users to receive past disaster records and forecast information in real time.

[0097] In the real-time risk assessment module, the server periodically obtains and analyzes real-time information, such as the latest weather and earthquake data provided by the Japan Meteorological Agency and the Earthquake Research Institute. If the server compares this information with past disaster records and determines that the risk is high, it generates an alert using a communication API such as Twilio. This alert is then sent to the device, prompting the user to take appropriate action.

[0098] As a specific example, consider the case where a user visits a mountain village in an earthquake-prone area and discovers an old stone monument mentioned by locals. The user takes a picture of the monument with their smartphone and uploads it to the server along with supplementary information. This data is processed using OCR, and the generative AI analyzes it to determine that "two large earthquakes have occurred in this area in the past, causing many buildings to collapse." The analysis results are stored in a database, and when the user searches for "earthquake records" through the app, the information is immediately provided.

[0099] If the server determines that heavy rain is continuing, it compares real-time weather data with past disaster records and notifies users of the increasing risk.The server then uses Twilio to send an alert to the user's device, informing them that "there is an increasing risk of major flooding in this area. Please evacuate to nearby high ground."

[0100] Examples of prompts used to analyze generative AI models include the following:

[0101] "Analyze the following text data to extract patterns and important lessons from past disasters: '[Text data]'"

[0102] This system will enable the provision of disaster prevention information based on past disaster records, real-time risk assessment, and rapid warning issuance, providing appropriate disaster prevention information to local residents and visitors.

[0103] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0104] Step 1: Data collection

[0105] Users use their smartphones or tablets to take photos of local stone monuments, documents, and other records of past disasters.

[0106] Input: Disaster record image, supplementary information (e.g. details of the disaster, year, etc.)

[0107] Specific operation: After taking a disaster record, the user inputs supplementary information through the application and obtains the location information of the shooting location, making the data collected by the user specific and including location information.

[0108] Step 2: Send data

[0109] The device transmits the collected image data, supplementary information, and location information to the server.

[0110] Input: Disaster record image data, location information, supplementary information

[0111] Output: Image data, location information, and supplementary information of the uploaded disaster records are saved on the server.

[0112] Specific operation: The device sends the captured image, the input supplementary information, and the acquired location information in JSON format to the server, where the data is temporarily stored.

[0113] Step 3: Image processing (OCR)

[0114] The server uses OCR technology (e.g., Amazon Textract) to extract text information from the received image data.

[0115] Input: Uploaded image data

[0116] Output: Extracted character information (text data)

[0117] Specific operation: The server inputs image data into the OCR engine and extracts character information as text data. At this time, preprocessing such as adjusting image resolution and removing noise is performed.

[0118] Step 4: Analysis by generative AI

[0119] The server analyzes the extracted text information using generative AI (e.g., OpenAI GPT) to extract disaster patterns and lessons learned.

[0120] Input: Character information extracted by OCR

[0121] Output: Disaster patterns and lessons learned analyzed by generative AI

[0122] Specific operation: The server inputs the prompt and extracted text information into the generative AI model and obtains the analysis results. For example, the prompt could be, "Analyze the following text data and extract past disaster patterns and important lessons: '[Text data]'."

[0123] Step 5: Saving to the Database

[0124] The server structures and stores the parsed information in a database (e.g., MySQL).

[0125] Input: Disaster patterns and lessons learned analyzed by generative AI

[0126] Output: Analysis results stored in a database

[0127] Specific operation: The server classifies the analysis results by region, disaster, and year and month, and when storing them in a database, adds an index to optimize the search algorithm.

[0128] Step 6: Information search function

[0129] Users use web and mobile apps to search for information about specific regions and disasters.

[0130] The terminal sends a search query to the server, which retrieves relevant information from a database and provides it to the user.

[0131] Input: User's search query (area name, type of disaster, etc.)

[0132] Output: Search results (past disaster records, appropriate evacuation plans, etc.)

[0133] Specific operation: When a user's search query is sent from the terminal to the server, the server searches the database and returns relevant information to the terminal for display to the user.

[0134] Step 7: Real-time risk assessment

[0135] The server regularly obtains and analyzes the latest weather and earthquake data provided by the Japan Meteorological Agency and the Earthquake Research Institute.

[0136] Input: Latest weather data, earthquake data

[0137] Output: Real-time risk assessment results

[0138] Specific operation: The server periodically obtains weather and earthquake data from external APIs, compares it with past disaster records, and performs risk assessment.

[0139] Step 8: Send an alert

[0140] If the server determines that the risk is high, it generates an alert and sends it to the user's device using a communication API such as Twilio.

[0141] Input: Risk assessment results

[0142] Output: Alert notification to user terminal

[0143] Specific operation: The server generates a warning message based on the risk assessment result and notifies the user's device using the Twilio API. For example, it sends a message saying, "There is an increasing risk of major flooding in this area. Please evacuate to nearby high ground."

[0144] (Application example 1)

[0145] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0146] In recent years, the frequency of natural disasters has increased, making it increasingly important to apply lessons learned from past disaster records and legends to modern times. However, information about past disasters is often preserved in a physical, unwritten form, making it difficult to effectively utilize this information in modern disaster prevention measures. Furthermore, real-time disaster risk assessment and warning issuance are insufficient, which can delay prompt evacuation and disaster prevention actions. To solve this problem, it is necessary to collect and analyze past disaster records as digital data and provide them to users, as well as to build a warning system that utilizes real-time information.

[0147] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0148] In this invention, the server includes means for collecting physical data including records of past disasters, means for extracting text information from the collected physical data, means for analyzing the extracted text information using generative artificial intelligence, means for saving the analyzed information in a database, means for providing the saved information to users, and means for acquiring and analyzing meteorological and earthquake data in real time and issuing warnings. This makes it possible to effectively utilize past disaster records in modern disaster prevention measures, evaluate disaster risks in real time, and issue prompt warnings and appropriate action instructions.

[0149] "Physical data" refers to tangible information, including records of past disasters such as stone monuments and documents.

[0150] "Text information" refers to information expressed as text that is extracted from physical data.

[0151] "Generative artificial intelligence" is a system that uses machine learning and natural language processing techniques to analyze extracted text information.

[0152] A "database" is an electronic collection of information in which analyzed information is structured and stored.

[0153] "Information provision means" refers to a means for providing stored information to users in an appropriate form.

[0154] "Weather data" refers to data such as temperature, precipitation, and wind speed based on meteorological observations.

[0155] "Earthquake Data" means observed data relating to the occurrence of earthquakes.

[0156] "Warning issuing means" refers to a means for notifying users of emergency warnings based on analyzed weather data and earthquake data.

[0157] "Location information" means geographic coordinate information that indicates where physical data was collected.

[0158] "Disaster prevention information" refers to information on measures to reduce disaster risk based on past disaster records.

[0159] A "smartphone" is a mobile device that combines the functions of a mobile phone and a computer.

[0160] A "head-mounted display" is a device worn on the head that displays images.

[0161] "Disaster risk assessment" is the process of assessing current and future disaster risks based on past disaster records and real-time data.

[0162] The system of this invention analyzes past disaster records and provides them as information for modern disaster prevention measures. It is particularly focused on providing information in environments using smartphones and head-mounted displays.

[0163] Data collection

[0164] Users visit the disaster site and take photos of stone monuments, documents, and other records of past disasters using their smartphone's camera. When taking a photo, location information is automatically added using the GPS function. The collected data is uploaded to a server via the Internet. Users can also manually enter supplementary information and detailed explanations in text format.

[0165] Extraction and analysis of text information

[0166] The server extracts text from the uploaded image data using OCR (optical character recognition) technology. This could be done using open-source software such as Tesseract OCR. The extracted text data is then analyzed using a generative AI model (e.g., GPT-4). This analysis extracts important lessons from past disaster patterns and legends, and stores them in a structured database.

[0167] Database Management

[0168] The server stores the analyzed information in a database that is dynamically updated based on the data being added, ensuring consistency and optimization of the information, and effectively matching past and new data to help assess disaster risk.

[0169] Information provision

[0170] When a user searches for information about a specific region or disaster using a web app or smartphone app, the device sends a query to the server. The server searches the database for relevant information and responds to the query. The user can then receive evacuation plans and disaster prevention advice in real time based on past disaster records.

[0171] Real-time risk assessment and alerting

[0172] The server periodically obtains real-time information such as weather and earthquake data. The analyzed data is compared with past disaster records, and if a high risk is determined, a real-time warning is issued. A notification is immediately sent to the user's device, and instructions for appropriate action are displayed. Weather and earthquake data is generally obtained from public institutions such as the Japan Meteorological Agency and the Earthquake Research Institute.

[0173] Specific examples

[0174] As a specific example, suppose a user visits a mountain village in an earthquake-prone area. There, they discover an old stone monument that locals have mentioned, and take and upload a photo of it with their smartphone. The server processes the image using OCR technology and obtains the analysis result: "Two large earthquakes have occurred in this area in the past, causing many buildings to collapse." This result is stored in a database, and when a user searches for "earthquake records" in the app, past earthquake information is displayed. In addition, if heavy rain continues in the area, the server compares the data with past records of large-scale floods, recognizes the increased risk, and sends a message to the user's device saying, "There is an increasing risk of large-scale flooding in this area. Please evacuate to nearby high ground."

[0175] Prompt Sentence Examples

[0176] "We are analyzing records of past disasters and legends to provide disaster prevention information. We are considering a system that will read the characters on the following stone monument using OCR, analyze disaster patterns and lessons learned, register the results in a database, and provide this to users. Please provide us with the analysis results for the characters extracted from the following stone monument."

[0177] In this way, the system of the present invention provides information useful for modern disaster prevention measures based on knowledge gained from past disaster records, and enables risk assessment and warning issuance in real time.

[0178] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0179] Step 1:

[0180] Users go to the disaster site and take photos of disaster records such as stone monuments and documents using their smartphone camera. When taking a photo, location information is automatically added using the smartphone's GPS function. The input is the captured image and GPS location information, which are then uploaded from the device to the server.

[0181] Step 2:

[0182] The server converts the received image data into text using OCR technology. Specifically, it uses Tesseract OCR software to extract text from the image. The input is the uploaded image, and the output is the extracted text data.

[0183] Step 3:

[0184] The server analyzes the extracted text data using a generative AI model. This analysis extracts important lessons about past disaster patterns and legends. The generative AI model used is GPT-4, with the input being the text data and the output being the analyzed lesson data.

[0185] Step 4:

[0186] The server stores the analyzed information in a database. The database structures and stores the analysis results, ensuring consistency and optimization of the information. The input is the analyzed lessons learned data, and the output is an updated database.

[0187] Step 5:

[0188] When a user searches for information about a specific region or disaster using a web app or smartphone app, the device sends a query to the server. The server searches the database for relevant information and returns the results to the device. The input is the user's query, and the output is disaster information corresponding to the query.

[0189] Step 6:

[0190] The server periodically obtains real-time information such as weather and earthquake data. It obtains and analyzes data from public institutions such as the Japan Meteorological Agency and the Earthquake Research Institute. The input is real-time weather and earthquake data, and the output is the risk assessment results.

[0191] Step 7:

[0192] The server compares the analyzed data in real time with past disaster records and generates an alert if it determines that the risk is high. The alert is sent to the device and prompts the user to take appropriate action. The input is the risk assessment result, and the output is an alert notification.

[0193] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0194] This invention improves the quality of information provision by combining a system that analyzes past disaster records and legends and provides modern disaster prevention information with an emotion engine that recognizes the user's emotions. This system collects physical data, uses generative AI to analyze it as text information, stores that information in a database, and provides appropriate information according to the user's emotional state. The program's processing is explained in detail below.

[0195] Data collection

[0196] Users discover records of past disasters, such as stone monuments or documents, on-site and take pictures with their smartphones or dedicated devices. The devices attach location information (GPS data) to the images and upload this data to a server. In addition, users can manually enter supplementary information and detailed descriptions into the device, which are also sent to the server.

[0197] Character Recognition and Analysis

[0198] The server uses OCR technology to extract text information from the received image data. The text data extracted by OCR is then analyzed in detail by the generative AI. This analysis allows important lessons to be extracted regarding past disaster patterns and legends.

[0199] Database Management

[0200] The analyzed information is structured and stored in a database by the server, which is updated with newly added data and managed to optimize the information.

[0201] Emotion engine and information provision

[0202] A user searches for information about a specific region or disaster through a web or mobile app. The device sends the query to the server. At the same time, the device uses a built-in emotion engine to analyze the user's emotional state (e.g., stress, relief, alertness, etc.). The emotion engine's analysis results are sent to the server along with the query.

[0203] The server searches a database based on the received query to retrieve relevant records of past disasters and legends. Based on the analysis results of the emotion engine, the server automatically adjusts the content and display method of the information provided. For example, if the user is in a state of high stress, it may provide information in an easy-to-understand and concise manner, or add support information on relaxation techniques and mental health. The device then displays the adjusted information on the user interface. This allows the user to receive past disaster records and appropriate prevention information in real time according to their emotional state.

[0204] Real-time risk assessment and alerting

[0205] The server periodically obtains and analyzes real-time information, such as the latest weather and earthquake data. It compares the analysis results with past disaster records to assess whether a particular area is at increased risk. If the server determines that the risk is high, it generates an alert, which is sent to the user's device. The device then displays the received alert message on its user interface, prompting the user to take appropriate action.

[0206] Specific examples

[0207] To give a specific example, a user visits a mountain village in an earthquake-prone area and discovers an old stone monument mentioned by locals. The user takes a picture of the monument with their smartphone and uploads the image to the server. The image is processed using OCR, and the generating AI discovers that "two large earthquakes have occurred in this area in the past, causing many buildings to collapse." The analysis results are stored in a database.

[0208] When a user searches for "earthquake records" in the app, the device uses its built-in emotion engine to analyze the user's current emotional state. For example, if the user is in a high stress state, the server will provide concise and easy-to-understand information based on the analysis results, and will also add relaxation techniques and mental health support information. The device will display this information on the user interface.

[0209] If the server determines that heavy rain is continuing in an area, it compares the data with past records of large-scale floods and recognizes that the risk is increasing. The server then issues a flood warning and notifies registered users' devices, saying, "There is an increasing risk of large-scale flooding in this area. Please evacuate to nearby high ground." The devices also display additional mental health support information based on the analysis results of the emotion engine.

[0210] This system will enable us to apply past lessons to modern disaster prevention and provide appropriate information to local residents and visitors. In addition, by providing disaster prevention information that takes into account the user's emotional state, we will be able to provide more effective and user-friendly responses.

[0211] The processing flow will be explained below.

[0212] Step 1:

[0213] Users discover stone monuments or disaster records on-site and take pictures using their smartphones or dedicated devices. The devices then attach location information (GPS data) to the captured image data and upload it to the server.

[0214] Step 2:

[0215] At the same time as uploading the image data, the terminal also sends supplementary information and detailed descriptions manually entered by the user to the server.

[0216] Step 3:

[0217] The server uses OCR (Optical Character Recognition) technology to extract character information from the received image data, generating text data from the image.

[0218] Step 4:

[0219] The server inputs the extracted text data into a generative AI model for detailed analysis, which extracts important lessons about past disaster patterns and legends.

[0220] Step 5:

[0221] The server structures the parsed information and stores it in a database, which is updated with newly added data and managed to optimize the information.

[0222] Step 6:

[0223] A user searches for information about a specific area or disaster through a web or mobile app, and the device sends the query to the server.

[0224] Step 7:

[0225] Simultaneously with the search query, the device uses a built-in emotion engine to analyze the user's emotional state, for example by detecting facial expressions and tone of voice through the camera and microphone.

[0226] Step 8:

[0227] The server searches the database based on the received query to retrieve relevant records of past disasters and legends, while also receiving the analysis results of the emotion engine.

[0228] Step 9:

[0229] The server automatically adjusts the content and display of information based on the analysis results of the emotion engine. For example, if the user is under high stress, the server will provide concise and easy-to-understand information and add relaxation techniques and mental health support information.

[0230] Step 10:

[0231] The terminal receives the adjusted information from the server and displays it on the user interface, allowing users to receive past disaster records and appropriate prevention information in real time according to their emotional state.

[0232] Step 11:

[0233] The server periodically retrieves and analyzes real-time information, such as the latest weather and earthquake data, and compares the analysis results with records of past disasters to assess whether a particular area is at increased risk.

[0234] Step 12:

[0235] If the server determines that the risk is high, it generates an alert, which is then sent to the user's terminal.

[0236] Step 13:

[0237] The device displays the received warning message on the user interface and prompts the user to take appropriate action. The emotion engine can also provide additional relaxation and mental health support content.

[0238] In this way, lessons learned from the past can be applied to modern disaster prevention, enabling more effective responses by providing information that responds to the user's emotions.

[0239] Example 2

[0240] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0241] Disaster prevention is important in modern times, but lessons learned from past disaster records and legends are not fully utilized. There is also a need to provide appropriate information according to the emotional state of users. Furthermore, there is a lack of systems for real-time risk assessment and warning issuance.

[0242] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0243] In this invention, the server includes means for collecting physical data including records of past disasters, means for extracting text information from the collected physical data, means for analyzing the extracted text information using generative artificial intelligence, means for saving the analyzed information in a database, means for providing the saved information to users, means for analyzing the emotional state of the user and adjusting the information provided, and means for conducting risk assessments and issuing warnings in real time. This makes it possible to provide appropriate disaster prevention information based on past disaster records, customize the information to suit the emotional state of the user, and further to conduct risk assessments and issue warnings in real time.

[0244] "Physical data" refers to tangible information such as stone monuments and documents collected on-site.

[0245] "Textual information" refers to textual data extracted from physical data.

[0246] "Generative AI" refers to artificial intelligence technology that analyzes data using natural language processing and machine learning algorithms.

[0247] A "database" refers to an electronic storage system that stores analyzed information in a structured manner.

[0248] "Information provision means" refers to systems and devices that appropriately display and convey stored information to users.

[0249] "Emotion analysis means" refers to techniques or devices for assessing a user's emotional state and tailoring information provision accordingly.

[0250] "Risk assessment" refers to the process of analyzing real-time situational data to determine the risk level of a particular situation.

[0251] "Alert generation means" refers to a system or device that generates a warning message and notifies the user when a risk increases.

[0252] "Location Information" means geographic information that indicates where data is collected.

[0253] "Disaster prevention information" refers to preventive measures and relief information provided based on past disaster records and analysis results.

[0254] This invention improves the quality of information provision by combining a system that analyzes past disaster records and legends and provides modern disaster prevention information with an emotion engine that recognizes the user's emotions. This system collects physical data, uses generative AI to analyze it as text information, stores that information in a database, and provides appropriate information according to the user's emotional state.

[0255] Hardware and Software

[0256] Users collect physical data using smartphones or dedicated devices. These devices are equipped with cameras, GPS, and sentiment analysis engines. The server runs on a cloud platform (e.g., AWS or Google Cloud) with high-performance computing capabilities and analyzes the data using OCR technology or generative AI models (e.g., Google Cloud Vision API or OpenAI GPT-4). A relational database (e.g., MySQL) is used as the database.

[0257] Data collection and upload

[0258] Users discover records of past disasters, such as stone monuments or documents, on-site and take pictures with their smartphones or dedicated devices. The devices then attach location information (GPS data) to the images and upload this data to a server. Users can also manually enter supplementary information and detailed descriptions into the device, and this data is also sent to the server.

[0259] Character Recognition and Analysis

[0260] The server uses OCR technology to extract text information from the received image data. The text data extracted by OCR is then analyzed in detail by the generative AI. This analysis extracts important lessons about past disaster patterns and legends, which are then structured and stored in a database.

[0261] Information provision and sentiment analysis

[0262] A user searches for information about a specific region or disaster through a web app or mobile app. The device sends the query to a server. At the same time, the device uses its built-in emotion engine to analyze the user's emotional state and sends the result along with the query to the server. The server searches a database based on the received query and retrieves relevant information. Based on the emotion engine's analysis results, the content and display method of the information provided are automatically adjusted. For example, if the user is under high stress, the device will provide information in an easy-to-understand and concise format, and also add support information on relaxation techniques and mental health. The device then displays the adjusted information on the user interface.

[0263] Real-time risk assessment and alerting

[0264] The server periodically obtains and analyzes real-time information, such as the latest weather and earthquake data. The analysis results are compared with past disaster records to assess whether a particular area is at increased risk. If the server determines that the risk is high, it generates an alert, which is sent to the user's device. The device then displays the received alert message on its user interface, prompting the user to take appropriate action.

[0265] Specific examples

[0266] To give a specific example, a user visits a mountain village in an earthquake-prone area and discovers an old stone monument mentioned by locals. The user takes a picture of the monument with their smartphone and uploads the image to the server. The image is processed using OCR, and the generating AI discovers that "two large earthquakes have occurred in this area in the past, causing many buildings to collapse." The analysis results are stored in a database.

[0267] When a user searches for "earthquake records" in the app, the device uses its built-in emotion engine to analyze the user's current emotional state. For example, if the user is in a high stress state, the server will provide concise and easy-to-understand information based on the analysis results, and will also add relaxation techniques and mental health support information. The device will display this information on the user interface.

[0268] Example prompt sentence:

[0269] "I would like to know about earthquake records. I've been feeling very stressed lately. Please also provide information on how to relax."

[0270] If the server determines that heavy rain is continuing in an area, it compares the data with past records of large-scale floods and recognizes that the risk is increasing. The server then issues a flood warning and notifies registered users' devices, saying, "There is an increasing risk of large-scale flooding in this area. Please evacuate to nearby high ground." The devices also display additional mental health support information based on the analysis results of the emotion engine.

[0271] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0272] Step 1: Data collection

[0273] Input: The user discovers records of past disasters, such as stone monuments or documents, on-site and takes pictures using a smartphone or dedicated device.

[0274] Specific operation: The user launches the camera app on their smartphone and takes a photo of a stone monument or document. The device then attaches location information (GPS data) to the image.

[0275] Output: Location information is added to the captured image data.

[0276] Step 2: Upload data

[0277] Input: Image data with location information.

[0278] Specific operation: The device uses the network to upload the collected image data and location information to the server.

[0279] Output: Image data with location information received by the server.

[0280] Step 3: Character Recognition (OCR Processing)

[0281] Input: Image data received by the server.

[0282] Specific operation: The server uses OCR technology to extract text information from image data, using an OCR library (e.g., Google Cloud Vision API).

[0283] Output: The extracted character data.

[0284] Step 4: Data analysis

[0285] Input: Extracted character data.

[0286] Specific operation: The server uses a generative AI model (e.g., OpenAI GPT-4) to analyze text data and extract patterns of past disasters and important lessons.

[0287] Output: Data on lessons and patterns analyzed.

[0288] Step 5: Save to database

[0289] Input: Data about lessons and patterns analyzed.

[0290] Specific operation: The server executes SQL queries to store the analysis results in a relational database (e.g., MySQL).

[0291] Output: Analysis results stored in a database.

[0292] Step 6: Information retrieval and sentiment analysis

[0293] Input: Search queries entered by users through web and mobile apps.

[0294] Specific operation: The device sends a query to the server. At the same time, the device uses its built-in emotion engine to analyze the user's emotional state and sends the results to the server.

[0295] Output: The search query and sentiment analysis results sent to the server.

[0296] Step 7: Database search and information reconciliation

[0297] Input: The search query and sentiment analysis results sent to the server.

[0298] What it does: The server executes SQL queries to retrieve relevant information from the database, and then tailors the content and presentation of that information based on the results of sentiment analysis.

[0299] Output: The adjusted information.

[0300] Step 8: Provide information

[0301] Input: Reconciled information.

[0302] Specific operation: The device uses a UI library (e.g., React Native) to display the adjusted information in the user interface.

[0303] Output: Disaster prevention information and mental health support information displayed to the user.

[0304] Step 9: Real-time risk assessment

[0305] Input: Latest weather and earthquake data.

[0306] Specific operation: The server periodically calls an external API (e.g., the Japan Meteorological Agency API) to obtain data and applies a risk assessment algorithm.

[0307] Output: Risk assessment results.

[0308] Step 10: Send an alert

[0309] Input: Risk assessment results.

[0310] Specific operation: If the server determines that the risk is high, it generates a notification message and sends it to the user's device using a push notification service (e.g., Firebase Cloud Messaging).

[0311] Output: The alert message displayed on the user's terminal.

[0312] (Application example 2)

[0313] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0314] In recent years, the frequency and scale of natural disasters have increased, and conventional disaster prevention information systems face the challenge of providing appropriate information based on the individual situation and emotional state of each user. Furthermore, users often have difficulty understanding complex disaster prevention information, which can lead to confusion during emergencies. Therefore, there is a need for a system that can improve the accuracy of disaster information analysis and flexibly adjust the information delivery method based on the user's emotional state.

[0315] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting physical data including records of past disasters, means for extracting text information from the collected physical data, analysis means using a generative AI model for analyzing the extracted text information, means for saving the analyzed information in a database, information provision means for providing the saved information to users, means equipped with an emotion engine for analyzing the emotional state of the user, and means for adjusting the information provision method based on the emotional state of the user. This makes it possible to provide disaster prevention information that is linked to the emotional state of the user, is easy to understand, and meets the needs of each individual user.

[0316] "Physical data" refers to information that actually exists and is stored in a visible form, such as stone monuments or documents that record past disasters.

[0317] "Textual information" is readable textual data extracted from physical data.

[0318] A "generative AI model" is an algorithm that uses artificial intelligence technology to perform advanced analysis of textual information and derive patterns and lessons learned from past disasters.

[0319] "Analysis means" refers to technology for analyzing collected text information in detail using a generative AI model.

[0320] A "database" is an information management system for structuring and storing analyzed textual information and disaster prevention information.

[0321] "Information provision means" refers to technology for providing information stored in a database in a format that is easy for users to understand.

[0322] The "emotion engine" is a technology that analyzes the user's emotional state and determines their state of stress, relief, vigilance, etc.

[0323] "Location information" is information used to identify the location where physical data was collected, using GPS data or the like.

[0324] "Disaster prevention information" refers to information on disaster prevention measures provided based on past disaster records and analysis results.

[0325] "Adjustment means" refers to technology that allows for flexible changes to the content and display method of disaster prevention information provided to users based on the emotion engine.

[0326] The present invention is a system that analyzes past disaster records and legends and provides them as modern disaster prevention countermeasure information, and aims to improve the quality of information provision based on the emotional state of the user. Specific embodiments of the present invention will be described.

[0327] Data collection

[0328] Using a smartphone equipped with a disaster prevention management app, users can take pictures of stone monuments, documents, and other records of past disasters they find in the field. The smartphone then attaches location information (GPS data) to the captured image and uploads this data to a server. In addition, users can manually enter supplementary information and detailed descriptions into their smartphone, which are also sent to the server.

[0329] Character Recognition and Analysis

[0330] The server uses OCR technology to extract textual information from the received image data. The textual information extracted through this OCR process is then analyzed in detail using a generative AI model. This analysis allows for the extraction of important lessons about past disaster patterns and legends.

[0331] Database Management

[0332] The analyzed information is structured and stored in a database by the server, which is constantly updated with new data and managed to optimize the information.

[0333] Emotion engine and information provision

[0334] When a user searches for information about a specific region or disaster through the disaster prevention management app, the smartphone uses its built-in emotion engine to analyze the user's emotional state (stress, relief, alertness, etc.). The emotion engine's analysis results are sent to the server along with the query. The server searches a database based on the received query and retrieves relevant records of past disasters and legends. Based on the emotion engine's analysis results, the content and display method of the information provided are automatically adjusted. For example, if the user is in a state of high stress, the information provided will be simple and easy to understand, and support information on relaxation techniques and mental health will also be added. The smartphone then displays the adjusted information on the user interface.

[0335] Real-time risk assessment and alerting

[0336] The server periodically obtains and analyzes real-time information, such as the latest weather and earthquake data. It compares the analysis results with past disaster records to assess whether a particular area is at increased risk. If the server determines that the risk is high, it generates an alert, which is sent to the user's smartphone. The smartphone then displays the received alert message on its user interface, prompting the user to take appropriate action.

[0337] Specific examples

[0338] Here's a specific example: A user visits a mountain village in an earthquake-prone area and discovers an old stone monument mentioned by locals. The user takes a picture of the monument with their smartphone and uploads it to the server. The image is processed using OCR, and the generating AI analyzes the information: "Two large earthquakes have occurred in this area in the past, causing many buildings to collapse." The analysis results are stored in a database.

[0339] When a user searches for "earthquake records" in the app, the smartphone uses its built-in emotion engine to analyze the user's current emotional state. For example, if the user is in a state of high stress, the server provides concise and easy-to-understand information based on the analysis results, and also adds relaxation techniques and mental health support information. The smartphone displays this information on the user interface. If heavy rain continues in an area, the server compares it with past records of large-scale floods and recognizes that the risk is increasing. The server issues a flood warning, notifying registered users' smartphones that "there is an increasing risk of large-scale flooding in this area. Please evacuate to nearby high ground." The smartphone also displays additional mental health support information based on the analysis results of the emotion engine.

[0340] Example of a data collection prompt:

[0341] "Upload an image of the stone monument taken with your smartphone, attach GPS data to the image, and send it to the server."

[0342] Example prompt for generative AI analysis:

[0343] "Analyze the disaster record information below, extract important information, and write it down in a format that will be useful for disaster prevention measures: {text}"

[0344] This allows disaster prevention information to be provided based on the user's emotional state, enabling real-time, user-friendly responses.

[0345] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0346] Step 1:

[0347] The user uses a smartphone equipped with a disaster prevention management app to take an image of a stone monument or document containing disaster records. The smartphone then attaches location information (GPS data) to the image and uploads this data to a server. The input here is the image containing the disaster record and the GPS data, and the output is the image and data including location information sent to the server. Specific operations in this step include taking an image using the smartphone's camera and GPS module, obtaining location information, and uploading the data.

[0348] Step 2:

[0349] The server uses OCR technology to extract text information from the uploaded image data. The input for this step is the image data uploaded by the user, and the output is the text information obtained by OCR processing. Specific operations include image analysis and text information extraction using OCR software on the server.

[0350] Step 3:

[0351] The server then uses a generative AI model to perform detailed analysis of the text information extracted by OCR. The input for this step is the text information obtained by OCR, and the output is information on past disaster patterns and lessons learned analyzed by the generative AI model. At this stage, the generative AI model performs text analysis on the server and extracts important information about past disasters.

[0352] Step 4:

[0353] The server structures and stores the analyzed information in a database. The input for this step is the textual information analyzed by the generative AI model, and the output is structured data stored in the database. Specific operations include storing and managing data using a database management system on the server.

[0354] Step 5:

[0355] A user searches for information about a specific area or disaster through a disaster prevention management app. The input to this step is a search query by the user, and the output is a search request sent to the server. Here, the search operation is performed by the smartphone application.

[0356] Step 6:

[0357] The smartphone uses its built-in emotion engine to analyze the user's emotional state. The input of this step is data for estimating the user's emotion, such as the user's current facial expression and voice, and the output is the determined emotional state information. Specific operations include capturing and analyzing emotion data using the smartphone's camera and microphone.

[0358] Step 7:

[0359] The server searches the database based on the received search query and the analysis results of the emotion engine to retrieve related disaster records and legend information. The input for this step is the user's search query and emotional state information, and the output is disaster information adjusted according to the emotional state. Specific operations include database search, information retrieval, and adjustment by the server.

[0360] Step 8:

[0361] The smartphone displays the adjusted information on the user interface. The input of this step is the adjusted disaster information sent from the server, and the output is the disaster prevention information displayed to the user. Specific operations include displaying the information on the smartphone display and updating the user interface.

[0362] Step 9:

[0363] The server periodically acquires the latest weather and earthquake data and performs real-time risk assessment. The input for this step is weather and earthquake data, and the output is the risk assessment result. Specific operations include acquiring and analyzing real-time data on the server.

[0364] Step 10:

[0365] If the server determines that the risk is high, it generates an alert and sends the alert message to the user's smartphone. The input of this step is the risk assessment result, and the output is the alert message sent to the user. Specific operations include sending the alert message from the server to the smartphone and the associated notification process.

[0366] Through the above steps, it becomes possible to provide disaster prevention information that is linked to the user's emotional state, is easy to understand, and meets the needs of each individual user.

[0367] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0368] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0369] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0370] [Second embodiment]

[0371] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0372] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0373] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0374] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0375] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0376] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0377] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0378] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0379] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0380] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0381] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0382] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0383] This invention is a system that analyzes past disaster records and legends and provides them as information for modern disaster prevention measures. This system collects physical data and uses a generative AI to analyze it as text information, stores that information in a database, and provides it to users. The program's processing is explained in detail below.

[0384] Data collection

[0385] The user visits the site and takes photos of past disaster records, such as stone monuments and documents. The device attaches location information to the captured images and uploads this data to the server. In addition, the user can manually enter supplementary information and detailed explanations into the device.

[0386] Character Recognition and Analysis

[0387] The server uses OCR technology to extract text information from the received image data. The text data extracted by OCR is then analyzed in detail by the generative AI. This analysis allows important lessons to be extracted about past disaster patterns and legends.

[0388] Database Management

[0389] The server structures and stores the analyzed information in a database, which is updated each time new data is added and managed to optimize the information.

[0390] Information provision

[0391] Users can search for information about specific regions or disasters through web or mobile apps. The device sends the user's query to the server, which then searches for relevant information from a database, organizes it, and returns it to the device. This allows users to receive past disaster records and forecast information in real time.

[0392] Real-time risk assessment and alerting

[0393] The server periodically obtains and analyzes real-time information, such as the latest weather and earthquake data. It compares this information with past disaster records and generates an alert if it determines there is a high risk. This alert is then sent to the device, prompting the user to take appropriate action.

[0394] Specific examples

[0395] Here's a specific example: A user visits a mountain village in an earthquake-prone area and discovers an old stone monument mentioned by locals. The user takes a photo of the monument and uploads it to a server. The image is processed using OCR, and the generating AI discovers that "two large earthquakes have occurred in this area in the past, causing many buildings to collapse." The analysis results are stored in a database, and when the user searches for "earthquake records" in the app, information on past earthquakes is provided, along with appropriate evacuation plans and information on local shelters.

[0396] If the server determines that heavy rain is continuing in an area, it will compare the data with records of past large-scale floods and recognize that the risk is increasing.The server will then issue a flood warning and notify registered users' devices that "there is an increasing risk of large-scale flooding in this area. Please evacuate to nearby high ground."

[0397] This system will utilize past lessons learned for modern disaster prevention and provide appropriate information to local residents and visitors, thereby raising disaster prevention awareness and enabling rapid response.

[0398] The processing flow will be explained below.

[0399] Step 1:

[0400] Users discover stone monuments or disaster records on-site and take pictures using their smartphones or dedicated devices, which then attach location information (GPS data) to the captured image data.

[0401] Step 2:

[0402] The device uploads the captured image and its location information to the server, and the user manually enters additional information and descriptions into the device, which are also sent to the server.

[0403] Step 3:

[0404] The server receives the uploaded image data and uses OCR (Optical Character Recognition) technology to extract text information from the received image data.

[0405] Step 4:

[0406] The server inputs the text data extracted by OCR into a generative AI model for detailed analysis, which extracts important lessons about past disaster patterns and legends.

[0407] Step 5:

[0408] The server structures the parsed information and stores it in a database, which is updated with the newly added data.

[0409] Step 6:

[0410] A user searches for information about a specific area or disaster through a web or mobile app, and the device sends the query to the server.

[0411] Step 7:

[0412] The server searches the database based on the received query to retrieve relevant records of past disasters and legends, then organizes the retrieved information and generates a response.

[0413] Step 8:

[0414] The terminal receives the response from the server and displays it on the user interface, allowing the user to receive past disaster records and appropriate prevention information in real time.

[0415] Step 9:

[0416] The server periodically collects and analyzes real-time weather and earthquake data, and compares the analysis results with records of past disasters to assess whether a particular area is at increased risk.

[0417] Step 10:

[0418] If the server determines that the risk is high, it generates an alert, which is then sent to the user's terminal.

[0419] Step 11:

[0420] The terminal displays the received warning message on the user interface and prompts the user to take appropriate action.

[0421] This step will enable efficient analysis of past disaster records and contribute to current disaster prevention measures. Users and devices will receive useful information in real time, enabling safe and prompt responses.

[0422] Example 1

[0423] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0424] Records of past disasters and legends provide valuable information for local disaster risk assessments and disaster prevention measures, but this information is easily lost and should ideally be collected, analyzed, and utilized in current disaster prevention. An efficient system for real-time disaster risk assessment and rapid warning issuance is also needed. Therefore, an integrated system is needed that collects and analyzes past disaster records and combines them with the latest data to assess risk and issue warnings in real time.

[0425] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0426] In this invention, the server includes means for collecting past disaster records photographed on-site, means for adding location information to the collected past disaster records, means for transmitting the data with the added location information to the server, means for extracting text information from the transmitted data, means for analyzing the extracted text information using artificial intelligence, means for saving the generated analysis results such as disaster patterns and lessons learned in a database, means for providing the saved information to users, means for comparing past disaster records with the latest weather data to assess risk, and means for issuing an alert if the risk is high. This enables the provision of disaster prevention information based on past disaster records, real-time risk assessment, and rapid alert issuance.

[0427] "Records of past disasters photographed on-site" refers to images and videos of information related to past disasters, such as old stone monuments, documents, and local folklore, taken directly on-site.

[0428] "Means for adding location information" refers to technology that uses location information systems such as GPS to add latitude and longitude data of the location where a photograph was taken to an image or video.

[0429] "Server" refers to a computer system that centrally manages, analyzes, stores, and provides data.

[0430] "Means for extracting text information" refers to the use of OCR (optical character recognition) technology to read text from images or videos and extract it as digital text.

[0431] "Means of analysis using generative artificial intelligence" refers to technology that uses a generative AI model (such as GPT) to analyze extracted text information and derive disaster patterns and lessons learned.

[0432] A "database" refers to an information system for efficiently storing, searching, and managing structured data.

[0433] "Means of storage" refers to the technology that stores the analyzed information in a database so that it can be searched and used later.

[0434] "Means of providing to users" refers to technology that provides analyzed information to users through interfaces such as web apps and mobile apps.

[0435] "The latest weather data" refers to real-time weather information and earthquake data provided by institutions such as the Japan Meteorological Agency and the Earthquake Research Institute.

[0436] "Means for conducting risk assessment" refers to technology that compares past disaster records with the latest meteorological data to conduct current risk assessments.

[0437] "Means for issuing alerts" refers to technology that uses communication APIs such as Twilio to issue alerts to users when specific risks increase.

[0438] This invention is a system that analyzes past disaster records and legends and provides them as information for modern disaster prevention measures. This system collects physical data, uses generative AI to analyze it as text information, stores the information in a database, and provides it to users.

[0439] In the data collection module, users go to the site and take photos of past disaster records, such as stone monuments and documents, using a smartphone or tablet. At this time, the user manually enters supplementary information and detailed descriptions into the device. The device then uses GPS to add location information to this data and uploads it to the server.

[0440] In the image processing module, the server extracts text from the received image data using OCR technology (e.g., Amazon Textract). The text extracted through OCR technology is then analyzed in detail using generative AI (e.g., OpenAI GPT model). This analysis extracts important lessons about past disaster patterns and legends.

[0441] In the database management module, the server structures and stores the analyzed information in a database (e.g., MySQL). This database is updated each time new data is added and is managed to optimize the information.

[0442] In the information provision module, users can search for information about specific regions or disasters through web or mobile apps. The device sends the user's query to the server, which then searches for relevant information from a database, organizes it, and returns it to the device. This allows users to receive past disaster records and forecast information in real time.

[0443] In the real-time risk assessment module, the server periodically obtains and analyzes real-time information, such as the latest weather and earthquake data provided by the Japan Meteorological Agency and the Earthquake Research Institute. If the server compares this information with past disaster records and determines that the risk is high, it generates an alert using a communication API such as Twilio. This alert is then sent to the device, prompting the user to take appropriate action.

[0444] As a specific example, consider the case where a user visits a mountain village in an earthquake-prone area and discovers an old stone monument mentioned by locals. The user takes a picture of the monument with their smartphone and uploads it to the server along with supplementary information. This data is processed using OCR, and the generative AI analyzes it to determine that "two large earthquakes have occurred in this area in the past, causing many buildings to collapse." The analysis results are stored in a database, and when the user searches for "earthquake records" through the app, the information is immediately provided.

[0445] If the server determines that heavy rain is continuing, it compares real-time weather data with past disaster records and notifies users of the increasing risk.The server then uses Twilio to send an alert to the user's device, informing them that "there is an increasing risk of major flooding in this area. Please evacuate to nearby high ground."

[0446] Examples of prompts used to analyze generative AI models include the following:

[0447] "Analyze the following text data to extract patterns and important lessons from past disasters: '[Text data]'"

[0448] This system will enable the provision of disaster prevention information based on past disaster records, real-time risk assessment, and rapid warning issuance, providing appropriate disaster prevention information to local residents and visitors.

[0449] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0450] Step 1: Data collection

[0451] Users use their smartphones or tablets to take photos of local stone monuments, documents, and other records of past disasters.

[0452] Input: Disaster record image, supplementary information (e.g. details of the disaster, year, etc.)

[0453] Specific operation: After taking a disaster record, the user inputs supplementary information through the application and obtains the location information of the shooting location, making the data collected by the user specific and including location information.

[0454] Step 2: Send data

[0455] The device transmits the collected image data, supplementary information, and location information to the server.

[0456] Input: Disaster record image data, location information, supplementary information

[0457] Output: Image data, location information, and supplementary information of the uploaded disaster records are saved on the server.

[0458] Specific operation: The device sends the captured image, the input supplementary information, and the acquired location information in JSON format to the server, where the data is temporarily stored.

[0459] Step 3: Image processing (OCR)

[0460] The server uses OCR technology (e.g., Amazon Textract) to extract text information from the received image data.

[0461] Input: Uploaded image data

[0462] Output: Extracted character information (text data)

[0463] Specific operation: The server inputs image data into the OCR engine and extracts character information as text data. At this time, preprocessing such as adjusting image resolution and removing noise is performed.

[0464] Step 4: Analysis by generative AI

[0465] The server analyzes the extracted text information using generative AI (e.g., OpenAI GPT) to extract disaster patterns and lessons learned.

[0466] Input: Character information extracted by OCR

[0467] Output: Disaster patterns and lessons learned analyzed by generative AI

[0468] Specific operation: The server inputs the prompt and extracted text information into the generative AI model and obtains the analysis results. For example, the prompt could be, "Analyze the following text data and extract past disaster patterns and important lessons: '[Text data]'."

[0469] Step 5: Saving to the Database

[0470] The server structures and stores the parsed information in a database (e.g., MySQL).

[0471] Input: Disaster patterns and lessons learned analyzed by generative AI

[0472] Output: Analysis results stored in a database

[0473] Specific operation: The server classifies the analysis results by region, disaster, and year and month, and when storing them in a database, adds an index to optimize the search algorithm.

[0474] Step 6: Information search function

[0475] Users use web and mobile apps to search for information about specific regions and disasters.

[0476] The terminal sends a search query to the server, which retrieves relevant information from a database and provides it to the user.

[0477] Input: User's search query (area name, type of disaster, etc.)

[0478] Output: Search results (past disaster records, appropriate evacuation plans, etc.)

[0479] Specific operation: When a user's search query is sent from the terminal to the server, the server searches the database and returns relevant information to the terminal for display to the user.

[0480] Step 7: Real-time risk assessment

[0481] The server regularly obtains and analyzes the latest weather and earthquake data provided by the Japan Meteorological Agency and the Earthquake Research Institute.

[0482] Input: Latest weather data, earthquake data

[0483] Output: Real-time risk assessment results

[0484] Specific operation: The server periodically obtains weather and earthquake data from external APIs, compares it with past disaster records, and performs risk assessment.

[0485] Step 8: Send an alert

[0486] If the server determines that the risk is high, it generates an alert and sends it to the user's device using a communication API such as Twilio.

[0487] Input: Risk assessment results

[0488] Output: Alert notification to user terminal

[0489] Specific operation: The server generates a warning message based on the risk assessment result and notifies the user's device using the Twilio API. For example, it sends a message saying, "There is an increasing risk of major flooding in this area. Please evacuate to nearby high ground."

[0490] (Application example 1)

[0491] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0492] In recent years, the frequency of natural disasters has increased, making it increasingly important to apply lessons learned from past disaster records and legends to modern times. However, information about past disasters is often preserved in a physical, unwritten form, making it difficult to effectively utilize this information in modern disaster prevention measures. Furthermore, real-time disaster risk assessment and warning issuance are insufficient, which can delay prompt evacuation and disaster prevention actions. To solve this problem, it is necessary to collect and analyze past disaster records as digital data and provide them to users, as well as to build a warning system that utilizes real-time information.

[0493] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0494] In this invention, the server includes means for collecting physical data including records of past disasters, means for extracting text information from the collected physical data, means for analyzing the extracted text information using generative artificial intelligence, means for saving the analyzed information in a database, means for providing the saved information to users, and means for acquiring and analyzing meteorological and earthquake data in real time and issuing warnings. This makes it possible to effectively utilize past disaster records in modern disaster prevention measures, evaluate disaster risks in real time, and issue prompt warnings and appropriate action instructions.

[0495] "Physical data" refers to tangible information, including records of past disasters such as stone monuments and documents.

[0496] "Text information" refers to information expressed as text that is extracted from physical data.

[0497] "Generative artificial intelligence" is a system that uses machine learning and natural language processing techniques to analyze extracted text information.

[0498] A "database" is an electronic collection of information in which analyzed information is structured and stored.

[0499] "Information provision means" refers to a means for providing stored information to users in an appropriate form.

[0500] "Weather data" refers to data such as temperature, precipitation, and wind speed based on meteorological observations.

[0501] "Earthquake Data" means observed data relating to the occurrence of earthquakes.

[0502] "Warning issuing means" refers to a means for notifying users of emergency warnings based on analyzed weather data and earthquake data.

[0503] "Location information" means geographic coordinate information that indicates where physical data was collected.

[0504] "Disaster prevention information" refers to information on measures to reduce disaster risk based on past disaster records.

[0505] A "smartphone" is a mobile device that combines the functions of a mobile phone and a computer.

[0506] A "head-mounted display" is a device worn on the head that displays images.

[0507] "Disaster risk assessment" is the process of assessing current and future disaster risks based on past disaster records and real-time data.

[0508] The system of this invention analyzes past disaster records and provides them as information for modern disaster prevention measures. It is particularly focused on providing information in environments using smartphones and head-mounted displays.

[0509] Data collection

[0510] Users visit the disaster site and take photos of stone monuments, documents, and other records of past disasters using their smartphone's camera. When taking a photo, location information is automatically added using the GPS function. The collected data is uploaded to a server via the Internet. Users can also manually enter supplementary information and detailed explanations in text format.

[0511] Extraction and analysis of text information

[0512] The server extracts text from the uploaded image data using OCR (optical character recognition) technology. This could be done using open-source software such as Tesseract OCR. The extracted text data is then analyzed using a generative AI model (e.g., GPT-4). This analysis extracts important lessons from past disaster patterns and legends, and stores them in a structured database.

[0513] Database Management

[0514] The server stores the analyzed information in a database that is dynamically updated based on the data being added, ensuring consistency and optimization of the information, and effectively matching past and new data to help assess disaster risk.

[0515] Information provision

[0516] When a user searches for information about a specific region or disaster using a web app or smartphone app, the device sends a query to the server. The server searches the database for relevant information and responds to the query. The user can then receive evacuation plans and disaster prevention advice in real time based on past disaster records.

[0517] Real-time risk assessment and alerting

[0518] The server periodically obtains real-time information such as weather and earthquake data. The analyzed data is compared with past disaster records, and if a high risk is determined, a real-time warning is issued. A notification is immediately sent to the user's device, and instructions for appropriate action are displayed. Weather and earthquake data is generally obtained from public institutions such as the Japan Meteorological Agency and the Earthquake Research Institute.

[0519] Specific examples

[0520] As a specific example, suppose a user visits a mountain village in an earthquake-prone area. There, they discover an old stone monument that locals have mentioned, and take and upload a photo of it with their smartphone. The server processes the image using OCR technology and obtains the analysis result: "Two large earthquakes have occurred in this area in the past, causing many buildings to collapse." This result is stored in a database, and when a user searches for "earthquake records" in the app, past earthquake information is displayed. In addition, if heavy rain continues in the area, the server compares the data with past records of large-scale floods, recognizes the increased risk, and sends a message to the user's device saying, "There is an increasing risk of large-scale flooding in this area. Please evacuate to nearby high ground."

[0521] Prompt Sentence Examples

[0522] "We are analyzing records of past disasters and legends to provide disaster prevention information. We are considering a system that will read the characters on the following stone monument using OCR, analyze disaster patterns and lessons learned, register the results in a database, and provide this to users. Please provide us with the analysis results for the characters extracted from the following stone monument."

[0523] In this way, the system of the present invention provides information useful for modern disaster prevention measures based on knowledge gained from past disaster records, and enables risk assessment and warning issuance in real time.

[0524] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0525] Step 1:

[0526] Users go to the disaster site and take photos of disaster records such as stone monuments and documents using their smartphone camera. When taking a photo, location information is automatically added using the smartphone's GPS function. The input is the captured image and GPS location information, which are then uploaded from the device to the server.

[0527] Step 2:

[0528] The server converts the received image data into text using OCR technology. Specifically, it uses Tesseract OCR software to extract text from the image. The input is the uploaded image, and the output is the extracted text data.

[0529] Step 3:

[0530] The server analyzes the extracted text data using a generative AI model. This analysis extracts important lessons about past disaster patterns and legends. The generative AI model used is GPT-4, with the input being the text data and the output being the analyzed lesson data.

[0531] Step 4:

[0532] The server stores the analyzed information in a database. The database structures and stores the analysis results, ensuring consistency and optimization of the information. The input is the analyzed lessons learned data, and the output is an updated database.

[0533] Step 5:

[0534] When a user searches for information about a specific region or disaster using a web app or smartphone app, the device sends a query to the server. The server searches the database for relevant information and returns the results to the device. The input is the user's query, and the output is disaster information corresponding to the query.

[0535] Step 6:

[0536] The server periodically obtains real-time information such as weather and earthquake data. It obtains and analyzes data from public institutions such as the Japan Meteorological Agency and the Earthquake Research Institute. The input is real-time weather and earthquake data, and the output is the risk assessment results.

[0537] Step 7:

[0538] The server compares the analyzed data in real time with past disaster records and generates an alert if it determines that the risk is high. The alert is sent to the device and prompts the user to take appropriate action. The input is the risk assessment result, and the output is an alert notification.

[0539] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0540] This invention improves the quality of information provision by combining a system that analyzes past disaster records and legends and provides modern disaster prevention information with an emotion engine that recognizes the user's emotions. This system collects physical data, uses generative AI to analyze it as text information, stores that information in a database, and provides appropriate information according to the user's emotional state. The program's processing is explained in detail below.

[0541] Data collection

[0542] Users discover records of past disasters, such as stone monuments or documents, on-site and take pictures with their smartphones or dedicated devices. The devices attach location information (GPS data) to the images and upload this data to a server. In addition, users can manually enter supplementary information and detailed descriptions into the device, which are also sent to the server.

[0543] Character Recognition and Analysis

[0544] The server uses OCR technology to extract text information from the received image data. The text data extracted by OCR is then analyzed in detail by the generative AI. This analysis allows important lessons to be extracted regarding past disaster patterns and legends.

[0545] Database Management

[0546] The analyzed information is structured and stored in a database by the server, which is updated with newly added data and managed to optimize the information.

[0547] Emotion engine and information provision

[0548] A user searches for information about a specific region or disaster through a web or mobile app. The device sends the query to the server. At the same time, the device uses a built-in emotion engine to analyze the user's emotional state (e.g., stress, relief, alertness, etc.). The emotion engine's analysis results are sent to the server along with the query.

[0549] The server searches a database based on the received query to retrieve relevant records of past disasters and legends. Based on the analysis results of the emotion engine, the server automatically adjusts the content and display method of the information provided. For example, if the user is in a state of high stress, it may provide information in an easy-to-understand and concise manner, or add support information on relaxation techniques and mental health. The device then displays the adjusted information on the user interface. This allows the user to receive past disaster records and appropriate prevention information in real time according to their emotional state.

[0550] Real-time risk assessment and alerting

[0551] The server periodically obtains and analyzes real-time information, such as the latest weather and earthquake data. It compares the analysis results with past disaster records to assess whether a particular area is at increased risk. If the server determines that the risk is high, it generates an alert, which is sent to the user's device. The device then displays the received alert message on its user interface, prompting the user to take appropriate action.

[0552] Specific examples

[0553] To give a specific example, a user visits a mountain village in an earthquake-prone area and discovers an old stone monument mentioned by locals. The user takes a picture of the monument with their smartphone and uploads the image to the server. The image is processed using OCR, and the generating AI discovers that "two large earthquakes have occurred in this area in the past, causing many buildings to collapse." The analysis results are stored in a database.

[0554] When a user searches for "earthquake records" in the app, the device uses its built-in emotion engine to analyze the user's current emotional state. For example, if the user is in a high stress state, the server will provide concise and easy-to-understand information based on the analysis results, and will also add relaxation techniques and mental health support information. The device will display this information on the user interface.

[0555] If the server determines that heavy rain is continuing in an area, it compares the data with past records of large-scale floods and recognizes that the risk is increasing. The server then issues a flood warning and notifies registered users' devices, saying, "There is an increasing risk of large-scale flooding in this area. Please evacuate to nearby high ground." The devices also display additional mental health support information based on the analysis results of the emotion engine.

[0556] This system will enable us to apply past lessons to modern disaster prevention and provide appropriate information to local residents and visitors. In addition, by providing disaster prevention information that takes into account the user's emotional state, we will be able to provide more effective and user-friendly responses.

[0557] The processing flow will be explained below.

[0558] Step 1:

[0559] Users discover stone monuments or disaster records on-site and take pictures using their smartphones or dedicated devices. The devices then attach location information (GPS data) to the captured image data and upload it to the server.

[0560] Step 2:

[0561] At the same time as uploading the image data, the terminal also sends supplementary information and detailed descriptions manually entered by the user to the server.

[0562] Step 3:

[0563] The server uses OCR (Optical Character Recognition) technology to extract character information from the received image data, generating text data from the image.

[0564] Step 4:

[0565] The server inputs the extracted text data into a generative AI model for detailed analysis, which extracts important lessons about past disaster patterns and legends.

[0566] Step 5:

[0567] The server structures the parsed information and stores it in a database, which is updated with newly added data and managed to optimize the information.

[0568] Step 6:

[0569] A user searches for information about a specific area or disaster through a web or mobile app, and the device sends the query to the server.

[0570] Step 7:

[0571] Simultaneously with the search query, the device uses a built-in emotion engine to analyze the user's emotional state, for example by detecting facial expressions and tone of voice through the camera and microphone.

[0572] Step 8:

[0573] The server searches the database based on the received query to retrieve relevant records of past disasters and legends, while also receiving the analysis results of the emotion engine.

[0574] Step 9:

[0575] The server automatically adjusts the content and display of information based on the analysis results of the emotion engine. For example, if the user is under high stress, the server will provide concise and easy-to-understand information and add relaxation techniques and mental health support information.

[0576] Step 10:

[0577] The terminal receives the adjusted information from the server and displays it on the user interface, allowing users to receive past disaster records and appropriate prevention information in real time according to their emotional state.

[0578] Step 11:

[0579] The server periodically retrieves and analyzes real-time information, such as the latest weather and earthquake data, and compares the analysis results with records of past disasters to assess whether a particular area is at increased risk.

[0580] Step 12:

[0581] If the server determines that the risk is high, it generates an alert, which is then sent to the user's terminal.

[0582] Step 13:

[0583] The device displays the received warning message on the user interface and prompts the user to take appropriate action. The emotion engine can also provide additional relaxation and mental health support content.

[0584] In this way, lessons learned from the past can be applied to modern disaster prevention, enabling more effective responses by providing information that responds to the user's emotions.

[0585] Example 2

[0586] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0587] Disaster prevention is important in modern times, but lessons learned from past disaster records and legends are not fully utilized. There is also a need to provide appropriate information according to the emotional state of users. Furthermore, there is a lack of systems for real-time risk assessment and warning issuance.

[0588] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0589] In this invention, the server includes means for collecting physical data including records of past disasters, means for extracting text information from the collected physical data, means for analyzing the extracted text information using generative artificial intelligence, means for saving the analyzed information in a database, means for providing the saved information to users, means for analyzing the emotional state of the user and adjusting the information provided, and means for conducting risk assessments and issuing warnings in real time. This makes it possible to provide appropriate disaster prevention information based on past disaster records, customize the information to suit the emotional state of the user, and further to conduct risk assessments and issue warnings in real time.

[0590] "Physical data" refers to tangible information such as stone monuments and documents collected on-site.

[0591] "Textual information" refers to textual data extracted from physical data.

[0592] "Generative AI" refers to artificial intelligence technology that analyzes data using natural language processing and machine learning algorithms.

[0593] A "database" refers to an electronic storage system that stores analyzed information in a structured manner.

[0594] "Information provision means" refers to systems and devices that appropriately display and convey stored information to users.

[0595] "Emotion analysis means" refers to techniques or devices for assessing a user's emotional state and tailoring information provision accordingly.

[0596] "Risk assessment" refers to the process of analyzing real-time situational data to determine the risk level of a particular situation.

[0597] "Alert generation means" refers to a system or device that generates a warning message and notifies the user when a risk increases.

[0598] "Location Information" means geographic information that indicates where data is collected.

[0599] "Disaster prevention information" refers to preventive measures and relief information provided based on past disaster records and analysis results.

[0600] This invention improves the quality of information provision by combining a system that analyzes past disaster records and legends and provides modern disaster prevention information with an emotion engine that recognizes the user's emotions. This system collects physical data, uses generative AI to analyze it as text information, stores that information in a database, and provides appropriate information according to the user's emotional state.

[0601] Hardware and Software

[0602] Users collect physical data using smartphones or dedicated devices. These devices are equipped with cameras, GPS, and sentiment analysis engines. The server runs on a cloud platform (e.g., AWS or Google Cloud) with high-performance computing capabilities and analyzes the data using OCR technology or generative AI models (e.g., Google Cloud Vision API or OpenAI GPT-4). A relational database (e.g., MySQL) is used as the database.

[0603] Data collection and upload

[0604] Users discover records of past disasters, such as stone monuments or documents, on-site and take pictures with their smartphones or dedicated devices. The devices then attach location information (GPS data) to the images and upload this data to a server. Users can also manually enter supplementary information and detailed descriptions into the device, and this data is also sent to the server.

[0605] Character Recognition and Analysis

[0606] The server uses OCR technology to extract text information from the received image data. The text data extracted by OCR is then analyzed in detail by the generative AI. This analysis extracts important lessons about past disaster patterns and legends, which are then structured and stored in a database.

[0607] Information provision and sentiment analysis

[0608] A user searches for information about a specific region or disaster through a web app or mobile app. The device sends the query to a server. At the same time, the device uses its built-in emotion engine to analyze the user's emotional state and sends the result along with the query to the server. The server searches a database based on the received query and retrieves relevant information. Based on the emotion engine's analysis results, the content and display method of the information provided are automatically adjusted. For example, if the user is under high stress, the device will provide information in an easy-to-understand and concise format, and also add support information on relaxation techniques and mental health. The device then displays the adjusted information on the user interface.

[0609] Real-time risk assessment and alerting

[0610] The server periodically obtains and analyzes real-time information, such as the latest weather and earthquake data. The analysis results are compared with past disaster records to assess whether a particular area is at increased risk. If the server determines that the risk is high, it generates an alert, which is sent to the user's device. The device then displays the received alert message on its user interface, prompting the user to take appropriate action.

[0611] Specific examples

[0612] To give a specific example, a user visits a mountain village in an earthquake-prone area and discovers an old stone monument mentioned by locals. The user takes a picture of the monument with their smartphone and uploads the image to the server. The image is processed using OCR, and the generating AI discovers that "two large earthquakes have occurred in this area in the past, causing many buildings to collapse." The analysis results are stored in a database.

[0613] When a user searches for "earthquake records" in the app, the device uses its built-in emotion engine to analyze the user's current emotional state. For example, if the user is in a high stress state, the server will provide concise and easy-to-understand information based on the analysis results, and will also add relaxation techniques and mental health support information. The device will display this information on the user interface.

[0614] Example prompt sentence:

[0615] "I would like to know about earthquake records. I've been feeling very stressed lately. Please also provide information on how to relax."

[0616] If the server determines that heavy rain is continuing in an area, it compares the data with past records of large-scale floods and recognizes that the risk is increasing. The server then issues a flood warning and notifies registered users' devices, saying, "There is an increasing risk of large-scale flooding in this area. Please evacuate to nearby high ground." The devices also display additional mental health support information based on the analysis results of the emotion engine.

[0617] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0618] Step 1: Data collection

[0619] Input: The user discovers records of past disasters, such as stone monuments or documents, on-site and takes pictures using a smartphone or dedicated device.

[0620] Specific operation: The user launches the camera app on their smartphone and takes a photo of a stone monument or document. The device then attaches location information (GPS data) to the image.

[0621] Output: Location information is added to the captured image data.

[0622] Step 2: Upload data

[0623] Input: Image data with location information.

[0624] Specific operation: The device uses the network to upload the collected image data and location information to the server.

[0625] Output: Image data with location information received by the server.

[0626] Step 3: Character Recognition (OCR Processing)

[0627] Input: Image data received by the server.

[0628] Specific operation: The server uses OCR technology to extract text information from image data, using an OCR library (e.g., Google Cloud Vision API).

[0629] Output: The extracted character data.

[0630] Step 4: Data analysis

[0631] Input: Extracted character data.

[0632] Specific operation: The server uses a generative AI model (e.g., OpenAI GPT-4) to analyze text data and extract patterns of past disasters and important lessons.

[0633] Output: Data on lessons and patterns analyzed.

[0634] Step 5: Save to database

[0635] Input: Data about lessons and patterns analyzed.

[0636] Specific operation: The server executes SQL queries to store the analysis results in a relational database (e.g., MySQL).

[0637] Output: Analysis results stored in a database.

[0638] Step 6: Information retrieval and sentiment analysis

[0639] Input: Search queries entered by users through web and mobile apps.

[0640] Specific operation: The device sends a query to the server. At the same time, the device uses its built-in emotion engine to analyze the user's emotional state and sends the results to the server.

[0641] Output: The search query and sentiment analysis results sent to the server.

[0642] Step 7: Database search and information reconciliation

[0643] Input: The search query and sentiment analysis results sent to the server.

[0644] What it does: The server executes SQL queries to retrieve relevant information from the database, and then tailors the content and presentation of that information based on the results of sentiment analysis.

[0645] Output: The adjusted information.

[0646] Step 8: Provide information

[0647] Input: Reconciled information.

[0648] Specific operation: The device uses a UI library (e.g., React Native) to display the adjusted information in the user interface.

[0649] Output: Disaster prevention information and mental health support information displayed to the user.

[0650] Step 9: Real-time risk assessment

[0651] Input: Latest weather and earthquake data.

[0652] Specific operation: The server periodically calls an external API (e.g., the Japan Meteorological Agency API) to obtain data and applies a risk assessment algorithm.

[0653] Output: Risk assessment results.

[0654] Step 10: Send an alert

[0655] Input: Risk assessment results.

[0656] Specific operation: If the server determines that the risk is high, it generates a notification message and sends it to the user's device using a push notification service (e.g., Firebase Cloud Messaging).

[0657] Output: The alert message displayed on the user's terminal.

[0658] (Application example 2)

[0659] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0660] In recent years, the frequency and scale of natural disasters have increased, and conventional disaster prevention information systems face the challenge of providing appropriate information based on the individual situation and emotional state of each user. Furthermore, users often have difficulty understanding complex disaster prevention information, which can lead to confusion during emergencies. Therefore, there is a need for a system that can improve the accuracy of disaster information analysis and flexibly adjust the information delivery method based on the user's emotional state.

[0661] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting physical data including records of past disasters, means for extracting text information from the collected physical data, analysis means using a generative AI model for analyzing the extracted text information, means for saving the analyzed information in a database, information provision means for providing the saved information to users, means equipped with an emotion engine for analyzing the emotional state of the user, and means for adjusting the information provision method based on the emotional state of the user. This makes it possible to provide disaster prevention information that is linked to the emotional state of the user, is easy to understand, and meets the needs of each individual user.

[0662] "Physical data" refers to information that actually exists and is stored in a visible form, such as stone monuments or documents that record past disasters.

[0663] "Textual information" is readable textual data extracted from physical data.

[0664] A "generative AI model" is an algorithm that uses artificial intelligence technology to perform advanced analysis of textual information and derive patterns and lessons learned from past disasters.

[0665] "Analysis means" refers to technology for analyzing collected text information in detail using a generative AI model.

[0666] A "database" is an information management system for structuring and storing analyzed textual information and disaster prevention information.

[0667] "Information provision means" refers to technology for providing information stored in a database in a format that is easy for users to understand.

[0668] The "emotion engine" is a technology that analyzes the user's emotional state and determines their state of stress, relief, vigilance, etc.

[0669] "Location information" is information used to identify the location where physical data was collected, using GPS data or the like.

[0670] "Disaster prevention information" refers to information on disaster prevention measures provided based on past disaster records and analysis results.

[0671] "Adjustment means" refers to technology that allows for flexible changes to the content and display method of disaster prevention information provided to users based on the emotion engine.

[0672] The present invention is a system that analyzes past disaster records and legends and provides them as modern disaster prevention countermeasure information, and aims to improve the quality of information provision based on the emotional state of the user. Specific embodiments of the present invention will be described.

[0673] Data collection

[0674] Using a smartphone equipped with a disaster prevention management app, users can take pictures of stone monuments, documents, and other records of past disasters they find in the field. The smartphone then attaches location information (GPS data) to the captured image and uploads this data to a server. In addition, users can manually enter supplementary information and detailed descriptions into their smartphone, which are also sent to the server.

[0675] Character Recognition and Analysis

[0676] The server uses OCR technology to extract textual information from the received image data. The textual information extracted through this OCR process is then analyzed in detail using a generative AI model. This analysis allows for the extraction of important lessons about past disaster patterns and legends.

[0677] Database Management

[0678] The analyzed information is structured and stored in a database by the server, which is constantly updated with new data and managed to optimize the information.

[0679] Emotion engine and information provision

[0680] When a user searches for information about a specific region or disaster through the disaster prevention management app, the smartphone uses its built-in emotion engine to analyze the user's emotional state (stress, relief, alertness, etc.). The emotion engine's analysis results are sent to the server along with the query. The server searches a database based on the received query and retrieves relevant records of past disasters and legends. Based on the emotion engine's analysis results, the content and display method of the information provided are automatically adjusted. For example, if the user is in a state of high stress, the information provided will be simple and easy to understand, and support information on relaxation techniques and mental health will also be added. The smartphone then displays the adjusted information on the user interface.

[0681] Real-time risk assessment and alerting

[0682] The server periodically obtains and analyzes real-time information, such as the latest weather and earthquake data. It compares the analysis results with past disaster records to assess whether a particular area is at increased risk. If the server determines that the risk is high, it generates an alert, which is sent to the user's smartphone. The smartphone then displays the received alert message on its user interface, prompting the user to take appropriate action.

[0683] Specific examples

[0684] Here's a specific example: A user visits a mountain village in an earthquake-prone area and discovers an old stone monument mentioned by locals. The user takes a picture of the monument with their smartphone and uploads it to the server. The image is processed using OCR, and the generating AI analyzes the information: "Two large earthquakes have occurred in this area in the past, causing many buildings to collapse." The analysis results are stored in a database.

[0685] When a user searches for "earthquake records" in the app, the smartphone uses its built-in emotion engine to analyze the user's current emotional state. For example, if the user is in a state of high stress, the server provides concise and easy-to-understand information based on the analysis results, and also adds relaxation techniques and mental health support information. The smartphone displays this information on the user interface. If heavy rain continues in an area, the server compares it with past records of large-scale floods and recognizes that the risk is increasing. The server issues a flood warning, notifying registered users' smartphones that "there is an increasing risk of large-scale flooding in this area. Please evacuate to nearby high ground." The smartphone also displays additional mental health support information based on the analysis results of the emotion engine.

[0686] Example of a data collection prompt:

[0687] "Upload an image of the stone monument taken with your smartphone, attach GPS data to the image, and send it to the server."

[0688] Example prompt for generative AI analysis:

[0689] "Analyze the disaster record information below, extract important information, and write it down in a format that will be useful for disaster prevention measures: {text}"

[0690] This allows disaster prevention information to be provided based on the user's emotional state, enabling real-time, user-friendly responses.

[0691] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0692] Step 1:

[0693] The user uses a smartphone equipped with a disaster prevention management app to take an image of a stone monument or document containing disaster records. The smartphone then attaches location information (GPS data) to the image and uploads this data to a server. The input here is the image containing the disaster record and the GPS data, and the output is the image and data including location information sent to the server. Specific operations in this step include taking an image using the smartphone's camera and GPS module, obtaining location information, and uploading the data.

[0694] Step 2:

[0695] The server uses OCR technology to extract text information from the uploaded image data. The input for this step is the image data uploaded by the user, and the output is the text information obtained by OCR processing. Specific operations include image analysis and text information extraction using OCR software on the server.

[0696] Step 3:

[0697] The server then uses a generative AI model to perform detailed analysis of the text information extracted by OCR. The input for this step is the text information obtained by OCR, and the output is information on past disaster patterns and lessons learned analyzed by the generative AI model. At this stage, the generative AI model performs text analysis on the server and extracts important information about past disasters.

[0698] Step 4:

[0699] The server structures and stores the analyzed information in a database. The input for this step is the textual information analyzed by the generative AI model, and the output is structured data stored in the database. Specific operations include storing and managing data using a database management system on the server.

[0700] Step 5:

[0701] A user searches for information about a specific area or disaster through a disaster prevention management app. The input to this step is a search query by the user, and the output is a search request sent to the server. Here, the search operation is performed by the smartphone application.

[0702] Step 6:

[0703] The smartphone uses its built-in emotion engine to analyze the user's emotional state. The input of this step is data for estimating the user's emotion, such as the user's current facial expression and voice, and the output is the determined emotional state information. Specific operations include capturing and analyzing emotion data using the smartphone's camera and microphone.

[0704] Step 7:

[0705] The server searches the database based on the received search query and the analysis results of the emotion engine to retrieve related disaster records and legend information. The input for this step is the user's search query and emotional state information, and the output is disaster information adjusted according to the emotional state. Specific operations include database search, information retrieval, and adjustment by the server.

[0706] Step 8:

[0707] The smartphone displays the adjusted information on the user interface. The input of this step is the adjusted disaster information sent from the server, and the output is the disaster prevention information displayed to the user. Specific operations include displaying the information on the smartphone display and updating the user interface.

[0708] Step 9:

[0709] The server periodically acquires the latest weather and earthquake data and performs real-time risk assessment. The input for this step is weather and earthquake data, and the output is the risk assessment result. Specific operations include acquiring and analyzing real-time data on the server.

[0710] Step 10:

[0711] If the server determines that the risk is high, it generates an alert and sends the alert message to the user's smartphone. The input of this step is the risk assessment result, and the output is the alert message sent to the user. Specific operations include sending the alert message from the server to the smartphone and the associated notification process.

[0712] Through the above steps, it becomes possible to provide disaster prevention information that is linked to the user's emotional state, is easy to understand, and meets the needs of each individual user.

[0713] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0714] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0715] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0716] [Third embodiment]

[0717] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0718] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0719] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0720] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0721] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0722] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0723] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0724] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0725] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0726] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0727] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0728] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0729] This invention is a system that analyzes past disaster records and legends and provides them as information for modern disaster prevention measures. This system collects physical data and uses a generative AI to analyze it as text information, stores that information in a database, and provides it to users. The program's processing is explained in detail below.

[0730] Data collection

[0731] The user visits the site and takes photos of past disaster records, such as stone monuments and documents. The device attaches location information to the captured images and uploads this data to the server. In addition, the user can manually enter supplementary information and detailed explanations into the device.

[0732] Character Recognition and Analysis

[0733] The server uses OCR technology to extract text information from the received image data. The text data extracted by OCR is then analyzed in detail by the generative AI. This analysis allows important lessons to be extracted about past disaster patterns and legends.

[0734] Database Management

[0735] The server structures and stores the analyzed information in a database, which is updated each time new data is added and managed to optimize the information.

[0736] Information provision

[0737] Users can search for information about specific regions or disasters through web or mobile apps. The device sends the user's query to the server, which then searches for relevant information from a database, organizes it, and returns it to the device. This allows users to receive past disaster records and forecast information in real time.

[0738] Real-time risk assessment and alerting

[0739] The server periodically obtains and analyzes real-time information, such as the latest weather and earthquake data. It compares this information with past disaster records and generates an alert if it determines there is a high risk. This alert is then sent to the device, prompting the user to take appropriate action.

[0740] Specific examples

[0741] Here's a specific example: A user visits a mountain village in an earthquake-prone area and discovers an old stone monument mentioned by locals. The user takes a photo of the monument and uploads it to a server. The image is processed using OCR, and the generating AI discovers that "two large earthquakes have occurred in this area in the past, causing many buildings to collapse." The analysis results are stored in a database, and when the user searches for "earthquake records" in the app, information on past earthquakes is provided, along with appropriate evacuation plans and information on local shelters.

[0742] If the server determines that heavy rain is continuing in an area, it will compare the data with records of past large-scale floods and recognize that the risk is increasing.The server will then issue a flood warning and notify registered users' devices that "there is an increasing risk of large-scale flooding in this area. Please evacuate to nearby high ground."

[0743] This system will utilize past lessons learned for modern disaster prevention and provide appropriate information to local residents and visitors, thereby raising disaster prevention awareness and enabling rapid response.

[0744] The processing flow will be explained below.

[0745] Step 1:

[0746] Users discover stone monuments or disaster records on-site and take pictures using their smartphones or dedicated devices, which then attach location information (GPS data) to the captured image data.

[0747] Step 2:

[0748] The device uploads the captured image and its location information to the server, and the user manually enters additional information and descriptions into the device, which are also sent to the server.

[0749] Step 3:

[0750] The server receives the uploaded image data and uses OCR (Optical Character Recognition) technology to extract text information from the received image data.

[0751] Step 4:

[0752] The server inputs the text data extracted by OCR into a generative AI model for detailed analysis, which extracts important lessons about past disaster patterns and legends.

[0753] Step 5:

[0754] The server structures the parsed information and stores it in a database, which is updated with the newly added data.

[0755] Step 6:

[0756] A user searches for information about a specific area or disaster through a web or mobile app, and the device sends the query to the server.

[0757] Step 7:

[0758] The server searches the database based on the received query to retrieve relevant records of past disasters and legends, then organizes the retrieved information and generates a response.

[0759] Step 8:

[0760] The terminal receives the response from the server and displays it on the user interface, allowing the user to receive past disaster records and appropriate prevention information in real time.

[0761] Step 9:

[0762] The server periodically collects and analyzes real-time weather and earthquake data, and compares the analysis results with records of past disasters to assess whether a particular area is at increased risk.

[0763] Step 10:

[0764] If the server determines that the risk is high, it generates an alert, which is then sent to the user's terminal.

[0765] Step 11:

[0766] The terminal displays the received warning message on the user interface and prompts the user to take appropriate action.

[0767] This step will enable efficient analysis of past disaster records and contribute to current disaster prevention measures. Users and devices will receive useful information in real time, enabling safe and prompt responses.

[0768] Example 1

[0769] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0770] Records of past disasters and legends provide valuable information for local disaster risk assessments and disaster prevention measures, but this information is easily lost and should ideally be collected, analyzed, and utilized in current disaster prevention. An efficient system for real-time disaster risk assessment and rapid warning issuance is also needed. Therefore, an integrated system is needed that collects and analyzes past disaster records and combines them with the latest data to assess risk and issue warnings in real time.

[0771] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0772] In this invention, the server includes means for collecting past disaster records photographed on-site, means for adding location information to the collected past disaster records, means for transmitting the data with the added location information to the server, means for extracting text information from the transmitted data, means for analyzing the extracted text information using artificial intelligence, means for saving the generated analysis results such as disaster patterns and lessons learned in a database, means for providing the saved information to users, means for comparing past disaster records with the latest weather data to assess risk, and means for issuing an alert if the risk is high. This enables the provision of disaster prevention information based on past disaster records, real-time risk assessment, and rapid alert issuance.

[0773] "Records of past disasters photographed on-site" refers to images and videos of information related to past disasters, such as old stone monuments, documents, and local folklore, taken directly on-site.

[0774] "Means for adding location information" refers to technology that uses location information systems such as GPS to add latitude and longitude data of the location where a photograph was taken to an image or video.

[0775] "Server" refers to a computer system that centrally manages, analyzes, stores, and provides data.

[0776] "Means for extracting text information" refers to the use of OCR (optical character recognition) technology to read text from images or videos and extract it as digital text.

[0777] "Means of analysis using generative artificial intelligence" refers to technology that uses a generative AI model (such as GPT) to analyze extracted text information and derive disaster patterns and lessons learned.

[0778] A "database" refers to an information system for efficiently storing, searching, and managing structured data.

[0779] "Means of storage" refers to the technology that stores the analyzed information in a database so that it can be searched and used later.

[0780] "Means of providing to users" refers to technology that provides analyzed information to users through interfaces such as web apps and mobile apps.

[0781] "The latest weather data" refers to real-time weather information and earthquake data provided by institutions such as the Japan Meteorological Agency and the Earthquake Research Institute.

[0782] "Means for conducting risk assessment" refers to technology that compares past disaster records with the latest meteorological data to conduct current risk assessments.

[0783] "Means for issuing alerts" refers to technology that uses communication APIs such as Twilio to issue alerts to users when specific risks increase.

[0784] This invention is a system that analyzes past disaster records and legends and provides them as information for modern disaster prevention measures. This system collects physical data, uses generative AI to analyze it as text information, stores the information in a database, and provides it to users.

[0785] In the data collection module, users go to the site and take photos of past disaster records, such as stone monuments and documents, using a smartphone or tablet. At this time, the user manually enters supplementary information and detailed descriptions into the device. The device then uses GPS to add location information to this data and uploads it to the server.

[0786] In the image processing module, the server extracts text from the received image data using OCR technology (e.g., Amazon Textract). The text extracted through OCR technology is then analyzed in detail using generative AI (e.g., OpenAI GPT model). This analysis extracts important lessons about past disaster patterns and legends.

[0787] In the database management module, the server structures and stores the analyzed information in a database (e.g., MySQL). This database is updated each time new data is added and is managed to optimize the information.

[0788] In the information provision module, users can search for information about specific regions or disasters through web or mobile apps. The device sends the user's query to the server, which then searches for relevant information from a database, organizes it, and returns it to the device. This allows users to receive past disaster records and forecast information in real time.

[0789] In the real-time risk assessment module, the server periodically obtains and analyzes real-time information, such as the latest weather and earthquake data provided by the Japan Meteorological Agency and the Earthquake Research Institute. If the server compares this information with past disaster records and determines that the risk is high, it generates an alert using a communication API such as Twilio. This alert is then sent to the device, prompting the user to take appropriate action.

[0790] As a specific example, consider the case where a user visits a mountain village in an earthquake-prone area and discovers an old stone monument mentioned by locals. The user takes a picture of the monument with their smartphone and uploads it to the server along with supplementary information. This data is processed using OCR, and the generative AI analyzes it to determine that "two large earthquakes have occurred in this area in the past, causing many buildings to collapse." The analysis results are stored in a database, and when the user searches for "earthquake records" through the app, the information is immediately provided.

[0791] If the server determines that heavy rain is continuing, it compares real-time weather data with past disaster records and notifies users of the increasing risk.The server then uses Twilio to send an alert to the user's device, informing them that "there is an increasing risk of major flooding in this area. Please evacuate to nearby high ground."

[0792] Examples of prompts used to analyze generative AI models include the following:

[0793] "Analyze the following text data to extract patterns and important lessons from past disasters: '[Text data]'"

[0794] This system will enable the provision of disaster prevention information based on past disaster records, real-time risk assessment, and rapid warning issuance, providing appropriate disaster prevention information to local residents and visitors.

[0795] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0796] Step 1: Data collection

[0797] Users use their smartphones or tablets to take photos of local stone monuments, documents, and other records of past disasters.

[0798] Input: Disaster record image, supplementary information (e.g. details of the disaster, year, etc.)

[0799] Specific operation: After taking a disaster record, the user inputs supplementary information through the application and obtains the location information of the shooting location, making the data collected by the user specific and including location information.

[0800] Step 2: Send data

[0801] The device transmits the collected image data, supplementary information, and location information to the server.

[0802] Input: Disaster record image data, location information, supplementary information

[0803] Output: Image data, location information, and supplementary information of the uploaded disaster records are saved on the server.

[0804] Specific operation: The device sends the captured image, the input supplementary information, and the acquired location information in JSON format to the server, where the data is temporarily stored.

[0805] Step 3: Image processing (OCR)

[0806] The server uses OCR technology (e.g., Amazon Textract) to extract text information from the received image data.

[0807] Input: Uploaded image data

[0808] Output: Extracted character information (text data)

[0809] Specific operation: The server inputs image data into the OCR engine and extracts character information as text data. At this time, preprocessing such as adjusting image resolution and removing noise is performed.

[0810] Step 4: Analysis by generative AI

[0811] The server analyzes the extracted text information using generative AI (e.g., OpenAI GPT) to extract disaster patterns and lessons learned.

[0812] Input: Character information extracted by OCR

[0813] Output: Disaster patterns and lessons learned analyzed by generative AI

[0814] Specific operation: The server inputs the prompt and extracted text information into the generative AI model and obtains the analysis results. For example, the prompt could be, "Analyze the following text data and extract past disaster patterns and important lessons: '[Text data]'."

[0815] Step 5: Saving to the Database

[0816] The server structures and stores the parsed information in a database (e.g., MySQL).

[0817] Input: Disaster patterns and lessons learned analyzed by generative AI

[0818] Output: Analysis results stored in a database

[0819] Specific operation: The server classifies the analysis results by region, disaster, and year and month, and when storing them in a database, adds an index to optimize the search algorithm.

[0820] Step 6: Information search function

[0821] Users use web and mobile apps to search for information about specific regions and disasters.

[0822] The terminal sends a search query to the server, which retrieves relevant information from a database and provides it to the user.

[0823] Input: User's search query (area name, type of disaster, etc.)

[0824] Output: Search results (past disaster records, appropriate evacuation plans, etc.)

[0825] Specific operation: When a user's search query is sent from the terminal to the server, the server searches the database and returns relevant information to the terminal for display to the user.

[0826] Step 7: Real-time risk assessment

[0827] The server regularly obtains and analyzes the latest weather and earthquake data provided by the Japan Meteorological Agency and the Earthquake Research Institute.

[0828] Input: Latest weather data, earthquake data

[0829] Output: Real-time risk assessment results

[0830] Specific operation: The server periodically obtains weather and earthquake data from external APIs, compares it with past disaster records, and performs risk assessment.

[0831] Step 8: Send an alert

[0832] If the server determines that the risk is high, it generates an alert and sends it to the user's device using a communication API such as Twilio.

[0833] Input: Risk assessment results

[0834] Output: Alert notification to user terminal

[0835] Specific operation: The server generates a warning message based on the risk assessment result and notifies the user's device using the Twilio API. For example, it sends a message saying, "There is an increasing risk of major flooding in this area. Please evacuate to nearby high ground."

[0836] (Application example 1)

[0837] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0838] In recent years, the frequency of natural disasters has increased, making it increasingly important to apply lessons learned from past disaster records and legends to modern times. However, information about past disasters is often preserved in a physical, unwritten form, making it difficult to effectively utilize this information in modern disaster prevention measures. Furthermore, real-time disaster risk assessment and warning issuance are insufficient, which can delay prompt evacuation and disaster prevention actions. To solve this problem, it is necessary to collect and analyze past disaster records as digital data and provide them to users, as well as to build a warning system that utilizes real-time information.

[0839] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0840] In this invention, the server includes means for collecting physical data including records of past disasters, means for extracting text information from the collected physical data, means for analyzing the extracted text information using generative artificial intelligence, means for saving the analyzed information in a database, means for providing the saved information to users, and means for acquiring and analyzing meteorological and earthquake data in real time and issuing warnings. This makes it possible to effectively utilize past disaster records in modern disaster prevention measures, evaluate disaster risks in real time, and issue prompt warnings and appropriate action instructions.

[0841] "Physical data" refers to tangible information, including records of past disasters such as stone monuments and documents.

[0842] "Text information" refers to information expressed as text that is extracted from physical data.

[0843] "Generative artificial intelligence" is a system that uses machine learning and natural language processing techniques to analyze extracted text information.

[0844] A "database" is an electronic collection of information in which analyzed information is structured and stored.

[0845] "Information provision means" refers to a means for providing stored information to users in an appropriate form.

[0846] "Weather data" refers to data such as temperature, precipitation, and wind speed based on meteorological observations.

[0847] "Earthquake Data" means observed data relating to the occurrence of earthquakes.

[0848] "Warning issuing means" refers to a means for notifying users of emergency warnings based on analyzed weather data and earthquake data.

[0849] "Location information" means geographic coordinate information that indicates where physical data was collected.

[0850] "Disaster prevention information" refers to information on measures to reduce disaster risk based on past disaster records.

[0851] A "smartphone" is a mobile device that combines the functions of a mobile phone and a computer.

[0852] A "head-mounted display" is a device worn on the head that displays images.

[0853] "Disaster risk assessment" is the process of assessing current and future disaster risks based on past disaster records and real-time data.

[0854] The system of this invention analyzes past disaster records and provides them as information for modern disaster prevention measures. It is particularly focused on providing information in environments using smartphones and head-mounted displays.

[0855] Data collection

[0856] Users visit the disaster site and take photos of stone monuments, documents, and other records of past disasters using their smartphone's camera. When taking a photo, location information is automatically added using the GPS function. The collected data is uploaded to a server via the Internet. Users can also manually enter supplementary information and detailed explanations in text format.

[0857] Extraction and analysis of text information

[0858] The server extracts text from the uploaded image data using OCR (optical character recognition) technology. This could be done using open-source software such as Tesseract OCR. The extracted text data is then analyzed using a generative AI model (e.g., GPT-4). This analysis extracts important lessons from past disaster patterns and legends, and stores them in a structured database.

[0859] Database Management

[0860] The server stores the analyzed information in a database that is dynamically updated based on the data being added, ensuring consistency and optimization of the information, and effectively matching past and new data to help assess disaster risk.

[0861] Information provision

[0862] When a user searches for information about a specific region or disaster using a web app or smartphone app, the device sends a query to the server. The server searches the database for relevant information and responds to the query. The user can then receive evacuation plans and disaster prevention advice in real time based on past disaster records.

[0863] Real-time risk assessment and alerting

[0864] The server periodically obtains real-time information such as weather and earthquake data. The analyzed data is compared with past disaster records, and if a high risk is determined, a real-time warning is issued. A notification is immediately sent to the user's device, and instructions for appropriate action are displayed. Weather and earthquake data is generally obtained from public institutions such as the Japan Meteorological Agency and the Earthquake Research Institute.

[0865] Specific examples

[0866] As a specific example, suppose a user visits a mountain village in an earthquake-prone area. There, they discover an old stone monument that locals have mentioned, and take and upload a photo of it with their smartphone. The server processes the image using OCR technology and obtains the analysis result: "Two large earthquakes have occurred in this area in the past, causing many buildings to collapse." This result is stored in a database, and when a user searches for "earthquake records" in the app, past earthquake information is displayed. In addition, if heavy rain continues in the area, the server compares the data with past records of large-scale floods, recognizes the increased risk, and sends a message to the user's device saying, "There is an increasing risk of large-scale flooding in this area. Please evacuate to nearby high ground."

[0867] Prompt Sentence Examples

[0868] "We are analyzing records of past disasters and legends to provide disaster prevention information. We are considering a system that will read the characters on the following stone monument using OCR, analyze disaster patterns and lessons learned, register the results in a database, and provide this to users. Please provide us with the analysis results for the characters extracted from the following stone monument."

[0869] In this way, the system of the present invention provides information useful for modern disaster prevention measures based on knowledge gained from past disaster records, and enables risk assessment and warning issuance in real time.

[0870] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0871] Step 1:

[0872] Users go to the disaster site and take photos of disaster records such as stone monuments and documents using their smartphone camera. When taking a photo, location information is automatically added using the smartphone's GPS function. The input is the captured image and GPS location information, which are then uploaded from the device to the server.

[0873] Step 2:

[0874] The server converts the received image data into text using OCR technology. Specifically, it uses Tesseract OCR software to extract text from the image. The input is the uploaded image, and the output is the extracted text data.

[0875] Step 3:

[0876] The server analyzes the extracted text data using a generative AI model. This analysis extracts important lessons about past disaster patterns and legends. The generative AI model used is GPT-4, with the input being the text data and the output being the analyzed lesson data.

[0877] Step 4:

[0878] The server stores the analyzed information in a database. The database structures and stores the analysis results, ensuring consistency and optimization of the information. The input is the analyzed lessons learned data, and the output is an updated database.

[0879] Step 5:

[0880] When a user searches for information about a specific region or disaster using a web app or smartphone app, the device sends a query to the server. The server searches the database for relevant information and returns the results to the device. The input is the user's query, and the output is disaster information corresponding to the query.

[0881] Step 6:

[0882] The server periodically obtains real-time information such as weather and earthquake data. It obtains and analyzes data from public institutions such as the Japan Meteorological Agency and the Earthquake Research Institute. The input is real-time weather and earthquake data, and the output is the risk assessment results.

[0883] Step 7:

[0884] The server compares the analyzed data in real time with past disaster records and generates an alert if it determines that the risk is high. The alert is sent to the device and prompts the user to take appropriate action. The input is the risk assessment result, and the output is an alert notification.

[0885] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0886] This invention improves the quality of information provision by combining a system that analyzes past disaster records and legends and provides modern disaster prevention information with an emotion engine that recognizes the user's emotions. This system collects physical data, uses generative AI to analyze it as text information, stores that information in a database, and provides appropriate information according to the user's emotional state. The program's processing is explained in detail below.

[0887] Data collection

[0888] Users discover records of past disasters, such as stone monuments or documents, on-site and take pictures with their smartphones or dedicated devices. The devices attach location information (GPS data) to the images and upload this data to a server. In addition, users can manually enter supplementary information and detailed descriptions into the device, which are also sent to the server.

[0889] Character Recognition and Analysis

[0890] The server uses OCR technology to extract text information from the received image data. The text data extracted by OCR is then analyzed in detail by the generative AI. This analysis allows important lessons to be extracted regarding past disaster patterns and legends.

[0891] Database Management

[0892] The analyzed information is structured and stored in a database by the server, which is updated with newly added data and managed to optimize the information.

[0893] Emotion engine and information provision

[0894] A user searches for information about a specific region or disaster through a web or mobile app. The device sends the query to the server. At the same time, the device uses a built-in emotion engine to analyze the user's emotional state (e.g., stress, relief, alertness, etc.). The emotion engine's analysis results are sent to the server along with the query.

[0895] The server searches a database based on the received query to retrieve relevant records of past disasters and legends. Based on the analysis results of the emotion engine, the server automatically adjusts the content and display method of the information provided. For example, if the user is in a state of high stress, it may provide information in an easy-to-understand and concise manner, or add support information on relaxation techniques and mental health. The device then displays the adjusted information on the user interface. This allows the user to receive past disaster records and appropriate prevention information in real time according to their emotional state.

[0896] Real-time risk assessment and alerting

[0897] The server periodically obtains and analyzes real-time information, such as the latest weather and earthquake data. It compares the analysis results with past disaster records to assess whether a particular area is at increased risk. If the server determines that the risk is high, it generates an alert, which is sent to the user's device. The device then displays the received alert message on its user interface, prompting the user to take appropriate action.

[0898] Specific examples

[0899] To give a specific example, a user visits a mountain village in an earthquake-prone area and discovers an old stone monument mentioned by locals. The user takes a picture of the monument with their smartphone and uploads the image to the server. The image is processed using OCR, and the generating AI discovers that "two large earthquakes have occurred in this area in the past, causing many buildings to collapse." The analysis results are stored in a database.

[0900] When a user searches for "earthquake records" in the app, the device uses its built-in emotion engine to analyze the user's current emotional state. For example, if the user is in a high stress state, the server will provide concise and easy-to-understand information based on the analysis results, and will also add relaxation techniques and mental health support information. The device will display this information on the user interface.

[0901] If the server determines that heavy rain is continuing in an area, it compares the data with past records of large-scale floods and recognizes that the risk is increasing. The server then issues a flood warning and notifies registered users' devices, saying, "There is an increasing risk of large-scale flooding in this area. Please evacuate to nearby high ground." The devices also display additional mental health support information based on the analysis results of the emotion engine.

[0902] This system will enable us to apply past lessons to modern disaster prevention and provide appropriate information to local residents and visitors. In addition, by providing disaster prevention information that takes into account the user's emotional state, we will be able to provide more effective and user-friendly responses.

[0903] The processing flow will be explained below.

[0904] Step 1:

[0905] Users discover stone monuments or disaster records on-site and take pictures using their smartphones or dedicated devices. The devices then attach location information (GPS data) to the captured image data and upload it to the server.

[0906] Step 2:

[0907] At the same time as uploading the image data, the terminal also sends supplementary information and detailed descriptions manually entered by the user to the server.

[0908] Step 3:

[0909] The server uses OCR (Optical Character Recognition) technology to extract character information from the received image data, generating text data from the image.

[0910] Step 4:

[0911] The server inputs the extracted text data into a generative AI model for detailed analysis, which extracts important lessons about past disaster patterns and legends.

[0912] Step 5:

[0913] The server structures the parsed information and stores it in a database, which is updated with newly added data and managed to optimize the information.

[0914] Step 6:

[0915] A user searches for information about a specific area or disaster through a web or mobile app, and the device sends the query to the server.

[0916] Step 7:

[0917] Simultaneously with the search query, the device uses a built-in emotion engine to analyze the user's emotional state, for example by detecting facial expressions and tone of voice through the camera and microphone.

[0918] Step 8:

[0919] The server searches the database based on the received query to retrieve relevant records of past disasters and legends, while also receiving the analysis results of the emotion engine.

[0920] Step 9:

[0921] The server automatically adjusts the content and display of information based on the analysis results of the emotion engine. For example, if the user is under high stress, the server will provide concise and easy-to-understand information and add relaxation techniques and mental health support information.

[0922] Step 10:

[0923] The terminal receives the adjusted information from the server and displays it on the user interface, allowing users to receive past disaster records and appropriate prevention information in real time according to their emotional state.

[0924] Step 11:

[0925] The server periodically retrieves and analyzes real-time information, such as the latest weather and earthquake data, and compares the analysis results with records of past disasters to assess whether a particular area is at increased risk.

[0926] Step 12:

[0927] If the server determines that the risk is high, it generates an alert, which is then sent to the user's terminal.

[0928] Step 13:

[0929] The device displays the received warning message on the user interface and prompts the user to take appropriate action. The emotion engine can also provide additional relaxation and mental health support content.

[0930] In this way, lessons learned from the past can be applied to modern disaster prevention, enabling more effective responses by providing information that responds to the user's emotions.

[0931] Example 2

[0932] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0933] Disaster prevention is important in modern times, but lessons learned from past disaster records and legends are not fully utilized. There is also a need to provide appropriate information according to the emotional state of users. Furthermore, there is a lack of systems for real-time risk assessment and warning issuance.

[0934] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0935] In this invention, the server includes means for collecting physical data including records of past disasters, means for extracting text information from the collected physical data, means for analyzing the extracted text information using generative artificial intelligence, means for saving the analyzed information in a database, means for providing the saved information to users, means for analyzing the emotional state of the user and adjusting the information provided, and means for conducting risk assessments and issuing warnings in real time. This makes it possible to provide appropriate disaster prevention information based on past disaster records, customize the information to suit the emotional state of the user, and further to conduct risk assessments and issue warnings in real time.

[0936] "Physical data" refers to tangible information such as stone monuments and documents collected on-site.

[0937] "Textual information" refers to textual data extracted from physical data.

[0938] "Generative AI" refers to artificial intelligence technology that analyzes data using natural language processing and machine learning algorithms.

[0939] A "database" refers to an electronic storage system that stores analyzed information in a structured manner.

[0940] "Information provision means" refers to systems and devices that appropriately display and convey stored information to users.

[0941] "Emotion analysis means" refers to techniques or devices for assessing a user's emotional state and tailoring information provision accordingly.

[0942] "Risk assessment" refers to the process of analyzing real-time situational data to determine the risk level of a particular situation.

[0943] "Alert generation means" refers to a system or device that generates a warning message and notifies the user when a risk increases.

[0944] "Location Information" means geographic information that indicates where data is collected.

[0945] "Disaster prevention information" refers to preventive measures and relief information provided based on past disaster records and analysis results.

[0946] This invention improves the quality of information provision by combining a system that analyzes past disaster records and legends and provides modern disaster prevention information with an emotion engine that recognizes the user's emotions. This system collects physical data, uses generative AI to analyze it as text information, stores that information in a database, and provides appropriate information according to the user's emotional state.

[0947] Hardware and Software

[0948] Users collect physical data using smartphones or dedicated devices. These devices are equipped with cameras, GPS, and sentiment analysis engines. The server runs on a cloud platform (e.g., AWS or Google Cloud) with high-performance computing capabilities and analyzes the data using OCR technology or generative AI models (e.g., Google Cloud Vision API or OpenAI GPT-4). A relational database (e.g., MySQL) is used as the database.

[0949] Data collection and upload

[0950] Users discover records of past disasters, such as stone monuments or documents, on-site and take pictures with their smartphones or dedicated devices. The devices then attach location information (GPS data) to the images and upload this data to a server. Users can also manually enter supplementary information and detailed descriptions into the device, and this data is also sent to the server.

[0951] Character Recognition and Analysis

[0952] The server uses OCR technology to extract text information from the received image data. The text data extracted by OCR is then analyzed in detail by the generative AI. This analysis extracts important lessons about past disaster patterns and legends, which are then structured and stored in a database.

[0953] Information provision and sentiment analysis

[0954] A user searches for information about a specific region or disaster through a web app or mobile app. The device sends the query to a server. At the same time, the device uses its built-in emotion engine to analyze the user's emotional state and sends the result along with the query to the server. The server searches a database based on the received query and retrieves relevant information. Based on the emotion engine's analysis results, the content and display method of the information provided are automatically adjusted. For example, if the user is under high stress, the device will provide information in an easy-to-understand and concise format, and also add support information on relaxation techniques and mental health. The device then displays the adjusted information on the user interface.

[0955] Real-time risk assessment and alerting

[0956] The server periodically obtains and analyzes real-time information, such as the latest weather and earthquake data. The analysis results are compared with past disaster records to assess whether a particular area is at increased risk. If the server determines that the risk is high, it generates an alert, which is sent to the user's device. The device then displays the received alert message on its user interface, prompting the user to take appropriate action.

[0957] Specific examples

[0958] To give a specific example, a user visits a mountain village in an earthquake-prone area and discovers an old stone monument mentioned by locals. The user takes a picture of the monument with their smartphone and uploads the image to the server. The image is processed using OCR, and the generating AI discovers that "two large earthquakes have occurred in this area in the past, causing many buildings to collapse." The analysis results are stored in a database.

[0959] When a user searches for "earthquake records" in the app, the device uses its built-in emotion engine to analyze the user's current emotional state. For example, if the user is in a high stress state, the server will provide concise and easy-to-understand information based on the analysis results, and will also add relaxation techniques and mental health support information. The device will display this information on the user interface.

[0960] Example prompt sentence:

[0961] "I would like to know about earthquake records. I've been feeling very stressed lately. Please also provide information on how to relax."

[0962] If the server determines that heavy rain is continuing in an area, it compares the data with past records of large-scale floods and recognizes that the risk is increasing. The server then issues a flood warning and notifies registered users' devices, saying, "There is an increasing risk of large-scale flooding in this area. Please evacuate to nearby high ground." The devices also display additional mental health support information based on the analysis results of the emotion engine.

[0963] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0964] Step 1: Data collection

[0965] Input: The user discovers records of past disasters, such as stone monuments or documents, on-site and takes pictures using a smartphone or dedicated device.

[0966] Specific operation: The user launches the camera app on their smartphone and takes a photo of a stone monument or document. The device then attaches location information (GPS data) to the image.

[0967] Output: Location information is added to the captured image data.

[0968] Step 2: Upload data

[0969] Input: Image data with location information.

[0970] Specific operation: The device uses the network to upload the collected image data and location information to the server.

[0971] Output: Image data with location information received by the server.

[0972] Step 3: Character Recognition (OCR Processing)

[0973] Input: Image data received by the server.

[0974] Specific operation: The server uses OCR technology to extract text information from image data, using an OCR library (e.g., Google Cloud Vision API).

[0975] Output: The extracted character data.

[0976] Step 4: Data analysis

[0977] Input: Extracted character data.

[0978] Specific operation: The server uses a generative AI model (e.g., OpenAI GPT-4) to analyze text data and extract patterns of past disasters and important lessons.

[0979] Output: Data on lessons and patterns analyzed.

[0980] Step 5: Save to database

[0981] Input: Data about lessons and patterns analyzed.

[0982] Specific operation: The server executes SQL queries to store the analysis results in a relational database (e.g., MySQL).

[0983] Output: Analysis results stored in a database.

[0984] Step 6: Information retrieval and sentiment analysis

[0985] Input: Search queries entered by users through web and mobile apps.

[0986] Specific operation: The device sends a query to the server. At the same time, the device uses its built-in emotion engine to analyze the user's emotional state and sends the results to the server.

[0987] Output: The search query and sentiment analysis results sent to the server.

[0988] Step 7: Database search and information reconciliation

[0989] Input: The search query and sentiment analysis results sent to the server.

[0990] What it does: The server executes SQL queries to retrieve relevant information from the database, and then tailors the content and presentation of that information based on the results of sentiment analysis.

[0991] Output: The adjusted information.

[0992] Step 8: Provide information

[0993] Input: Reconciled information.

[0994] Specific operation: The device uses a UI library (e.g., React Native) to display the adjusted information in the user interface.

[0995] Output: Disaster prevention information and mental health support information displayed to the user.

[0996] Step 9: Real-time risk assessment

[0997] Input: Latest weather and earthquake data.

[0998] Specific operation: The server periodically calls an external API (e.g., the Japan Meteorological Agency API) to obtain data and applies a risk assessment algorithm.

[0999] Output: Risk assessment results.

[1000] Step 10: Send an alert

[1001] Input: Risk assessment results.

[1002] Specific operation: If the server determines that the risk is high, it generates a notification message and sends it to the user's device using a push notification service (e.g., Firebase Cloud Messaging).

[1003] Output: The alert message displayed on the user's terminal.

[1004] (Application example 2)

[1005] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1006] In recent years, the frequency and scale of natural disasters have increased, and conventional disaster prevention information systems face the challenge of providing appropriate information based on the individual situation and emotional state of each user. Furthermore, users often have difficulty understanding complex disaster prevention information, which can lead to confusion during emergencies. Therefore, there is a need for a system that can improve the accuracy of disaster information analysis and flexibly adjust the information delivery method based on the user's emotional state.

[1007] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting physical data including records of past disasters, means for extracting text information from the collected physical data, analysis means using a generative AI model for analyzing the extracted text information, means for saving the analyzed information in a database, information provision means for providing the saved information to users, means equipped with an emotion engine for analyzing the emotional state of the user, and means for adjusting the information provision method based on the emotional state of the user. This makes it possible to provide disaster prevention information that is linked to the emotional state of the user, is easy to understand, and meets the needs of each individual user.

[1008] "Physical data" refers to information that actually exists and is stored in a visible form, such as stone monuments or documents that record past disasters.

[1009] "Textual information" is readable textual data extracted from physical data.

[1010] A "generative AI model" is an algorithm that uses artificial intelligence technology to perform advanced analysis of textual information and derive patterns and lessons learned from past disasters.

[1011] "Analysis means" refers to technology for analyzing collected text information in detail using a generative AI model.

[1012] A "database" is an information management system for structuring and storing analyzed textual information and disaster prevention information.

[1013] "Information provision means" refers to technology for providing information stored in a database in a format that is easy for users to understand.

[1014] The "emotion engine" is a technology that analyzes the user's emotional state and determines their state of stress, relief, vigilance, etc.

[1015] "Location information" is information used to identify the location where physical data was collected, using GPS data or the like.

[1016] "Disaster prevention information" refers to information on disaster prevention measures provided based on past disaster records and analysis results.

[1017] "Adjustment means" refers to technology that allows for flexible changes to the content and display method of disaster prevention information provided to users based on the emotion engine.

[1018] The present invention is a system that analyzes past disaster records and legends and provides them as modern disaster prevention countermeasure information, and aims to improve the quality of information provision based on the emotional state of the user. Specific embodiments of the present invention will be described.

[1019] Data collection

[1020] Using a smartphone equipped with a disaster prevention management app, users can take pictures of stone monuments, documents, and other records of past disasters they find in the field. The smartphone then attaches location information (GPS data) to the captured image and uploads this data to a server. In addition, users can manually enter supplementary information and detailed descriptions into their smartphone, which are also sent to the server.

[1021] Character Recognition and Analysis

[1022] The server uses OCR technology to extract textual information from the received image data. The textual information extracted through this OCR process is then analyzed in detail using a generative AI model. This analysis allows for the extraction of important lessons about past disaster patterns and legends.

[1023] Database Management

[1024] The analyzed information is structured and stored in a database by the server, which is constantly updated with new data and managed to optimize the information.

[1025] Emotion engine and information provision

[1026] When a user searches for information about a specific region or disaster through the disaster prevention management app, the smartphone uses its built-in emotion engine to analyze the user's emotional state (stress, relief, alertness, etc.). The emotion engine's analysis results are sent to the server along with the query. The server searches a database based on the received query and retrieves relevant records of past disasters and legends. Based on the emotion engine's analysis results, the content and display method of the information provided are automatically adjusted. For example, if the user is in a state of high stress, the information provided will be simple and easy to understand, and support information on relaxation techniques and mental health will also be added. The smartphone then displays the adjusted information on the user interface.

[1027] Real-time risk assessment and alerting

[1028] The server periodically obtains and analyzes real-time information, such as the latest weather and earthquake data. It compares the analysis results with past disaster records to assess whether a particular area is at increased risk. If the server determines that the risk is high, it generates an alert, which is sent to the user's smartphone. The smartphone then displays the received alert message on its user interface, prompting the user to take appropriate action.

[1029] Specific examples

[1030] Here's a specific example: A user visits a mountain village in an earthquake-prone area and discovers an old stone monument mentioned by locals. The user takes a picture of the monument with their smartphone and uploads it to the server. The image is processed using OCR, and the generating AI analyzes the information: "Two large earthquakes have occurred in this area in the past, causing many buildings to collapse." The analysis results are stored in a database.

[1031] When a user searches for "earthquake records" in the app, the smartphone uses its built-in emotion engine to analyze the user's current emotional state. For example, if the user is in a state of high stress, the server provides concise and easy-to-understand information based on the analysis results, and also adds relaxation techniques and mental health support information. The smartphone displays this information on the user interface. If heavy rain continues in an area, the server compares it with past records of large-scale floods and recognizes that the risk is increasing. The server issues a flood warning, notifying registered users' smartphones that "there is an increasing risk of large-scale flooding in this area. Please evacuate to nearby high ground." The smartphone also displays additional mental health support information based on the analysis results of the emotion engine.

[1032] Example of a data collection prompt:

[1033] "Upload an image of the stone monument taken with your smartphone, attach GPS data to the image, and send it to the server."

[1034] Example prompt for generative AI analysis:

[1035] "Analyze the disaster record information below, extract important information, and write it down in a format that will be useful for disaster prevention measures: {text}"

[1036] This allows disaster prevention information to be provided based on the user's emotional state, enabling real-time, user-friendly responses.

[1037] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1038] Step 1:

[1039] The user uses a smartphone equipped with a disaster prevention management app to take an image of a stone monument or document containing disaster records. The smartphone then attaches location information (GPS data) to the image and uploads this data to a server. The input here is the image containing the disaster record and the GPS data, and the output is the image and data including location information sent to the server. Specific operations in this step include taking an image using the smartphone's camera and GPS module, obtaining location information, and uploading the data.

[1040] Step 2:

[1041] The server uses OCR technology to extract text information from the uploaded image data. The input for this step is the image data uploaded by the user, and the output is the text information obtained by OCR processing. Specific operations include image analysis and text information extraction using OCR software on the server.

[1042] Step 3:

[1043] The server then uses a generative AI model to perform detailed analysis of the text information extracted by OCR. The input for this step is the text information obtained by OCR, and the output is information on past disaster patterns and lessons learned analyzed by the generative AI model. At this stage, the generative AI model performs text analysis on the server and extracts important information about past disasters.

[1044] Step 4:

[1045] The server structures and stores the analyzed information in a database. The input for this step is the textual information analyzed by the generative AI model, and the output is structured data stored in the database. Specific operations include storing and managing data using a database management system on the server.

[1046] Step 5:

[1047] A user searches for information about a specific area or disaster through a disaster prevention management app. The input to this step is a search query by the user, and the output is a search request sent to the server. Here, the search operation is performed by the smartphone application.

[1048] Step 6:

[1049] The smartphone uses its built-in emotion engine to analyze the user's emotional state. The input of this step is data for estimating the user's emotion, such as the user's current facial expression and voice, and the output is the determined emotional state information. Specific operations include capturing and analyzing emotion data using the smartphone's camera and microphone.

[1050] Step 7:

[1051] The server searches the database based on the received search query and the analysis results of the emotion engine to retrieve related disaster records and legend information. The input for this step is the user's search query and emotional state information, and the output is disaster information adjusted according to the emotional state. Specific operations include database search, information retrieval, and adjustment by the server.

[1052] Step 8:

[1053] The smartphone displays the adjusted information on the user interface. The input of this step is the adjusted disaster information sent from the server, and the output is the disaster prevention information displayed to the user. Specific operations include displaying the information on the smartphone display and updating the user interface.

[1054] Step 9:

[1055] The server periodically acquires the latest weather and earthquake data and performs real-time risk assessment. The input for this step is weather and earthquake data, and the output is the risk assessment result. Specific operations include acquiring and analyzing real-time data on the server.

[1056] Step 10:

[1057] If the server determines that the risk is high, it generates an alert and sends the alert message to the user's smartphone. The input of this step is the risk assessment result, and the output is the alert message sent to the user. Specific operations include sending the alert message from the server to the smartphone and the associated notification process.

[1058] Through the above steps, it becomes possible to provide disaster prevention information that is linked to the user's emotional state, is easy to understand, and meets the needs of each individual user.

[1059] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1060] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1061] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1062] [Fourth embodiment]

[1063] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1064] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1065] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1066] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1067] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1068] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1069] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1070] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1071] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1072] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1073] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1074] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1075] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1076] This invention is a system that analyzes past disaster records and legends and provides them as information for modern disaster prevention measures. This system collects physical data and uses a generative AI to analyze it as text information, stores that information in a database, and provides it to users. The program's processing is explained in detail below.

[1077] Data collection

[1078] The user visits the site and takes photos of past disaster records, such as stone monuments and documents. The device attaches location information to the captured images and uploads this data to the server. In addition, the user can manually enter supplementary information and detailed explanations into the device.

[1079] Character Recognition and Analysis

[1080] The server uses OCR technology to extract text information from the received image data. The text data extracted by OCR is then analyzed in detail by the generative AI. This analysis allows important lessons to be extracted about past disaster patterns and legends.

[1081] Database Management

[1082] The server structures and stores the analyzed information in a database, which is updated each time new data is added and managed to optimize the information.

[1083] Information provision

[1084] Users can search for information about specific regions or disasters through web or mobile apps. The device sends the user's query to the server, which then searches for relevant information from a database, organizes it, and returns it to the device. This allows users to receive past disaster records and forecast information in real time.

[1085] Real-time risk assessment and alerting

[1086] The server periodically obtains and analyzes real-time information, such as the latest weather and earthquake data. It compares this information with past disaster records and generates an alert if it determines there is a high risk. This alert is then sent to the device, prompting the user to take appropriate action.

[1087] Specific examples

[1088] Here's a specific example: A user visits a mountain village in an earthquake-prone area and discovers an old stone monument mentioned by locals. The user takes a photo of the monument and uploads it to a server. The image is processed using OCR, and the generating AI discovers that "two large earthquakes have occurred in this area in the past, causing many buildings to collapse." The analysis results are stored in a database, and when the user searches for "earthquake records" in the app, information on past earthquakes is provided, along with appropriate evacuation plans and information on local shelters.

[1089] If the server determines that heavy rain is continuing in an area, it will compare the data with records of past large-scale floods and recognize that the risk is increasing.The server will then issue a flood warning and notify registered users' devices that "there is an increasing risk of large-scale flooding in this area. Please evacuate to nearby high ground."

[1090] This system will utilize past lessons learned for modern disaster prevention and provide appropriate information to local residents and visitors, thereby raising disaster prevention awareness and enabling rapid response.

[1091] The processing flow will be explained below.

[1092] Step 1:

[1093] Users discover stone monuments or disaster records on-site and take pictures using their smartphones or dedicated devices, which then attach location information (GPS data) to the captured image data.

[1094] Step 2:

[1095] The device uploads the captured image and its location information to the server, and the user manually enters additional information and descriptions into the device, which are also sent to the server.

[1096] Step 3:

[1097] The server receives the uploaded image data and uses OCR (Optical Character Recognition) technology to extract text information from the received image data.

[1098] Step 4:

[1099] The server inputs the text data extracted by OCR into a generative AI model for detailed analysis, which extracts important lessons about past disaster patterns and legends.

[1100] Step 5:

[1101] The server structures the parsed information and stores it in a database, which is updated with the newly added data.

[1102] Step 6:

[1103] A user searches for information about a specific area or disaster through a web or mobile app, and the device sends the query to the server.

[1104] Step 7:

[1105] The server searches the database based on the received query to retrieve relevant records of past disasters and legends, then organizes the retrieved information and generates a response.

[1106] Step 8:

[1107] The terminal receives the response from the server and displays it on the user interface, allowing the user to receive past disaster records and appropriate prevention information in real time.

[1108] Step 9:

[1109] The server periodically collects and analyzes real-time weather and earthquake data, and compares the analysis results with records of past disasters to assess whether a particular area is at increased risk.

[1110] Step 10:

[1111] If the server determines that the risk is high, it generates an alert, which is then sent to the user's terminal.

[1112] Step 11:

[1113] The terminal displays the received warning message on the user interface and prompts the user to take appropriate action.

[1114] This step will enable efficient analysis of past disaster records and contribute to current disaster prevention measures. Users and devices will receive useful information in real time, enabling safe and prompt responses.

[1115] Example 1

[1116] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1117] Records of past disasters and legends provide valuable information for local disaster risk assessments and disaster prevention measures, but this information is easily lost and should ideally be collected, analyzed, and utilized in current disaster prevention. An efficient system for real-time disaster risk assessment and rapid warning issuance is also needed. Therefore, an integrated system is needed that collects and analyzes past disaster records and combines them with the latest data to assess risk and issue warnings in real time.

[1118] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1119] In this invention, the server includes means for collecting past disaster records photographed on-site, means for adding location information to the collected past disaster records, means for transmitting the data with the added location information to the server, means for extracting text information from the transmitted data, means for analyzing the extracted text information using artificial intelligence, means for saving the generated analysis results such as disaster patterns and lessons learned in a database, means for providing the saved information to users, means for comparing past disaster records with the latest weather data to assess risk, and means for issuing an alert if the risk is high. This enables the provision of disaster prevention information based on past disaster records, real-time risk assessment, and rapid alert issuance.

[1120] "Records of past disasters photographed on-site" refers to images and videos of information related to past disasters, such as old stone monuments, documents, and local folklore, taken directly on-site.

[1121] "Means for adding location information" refers to technology that uses location information systems such as GPS to add latitude and longitude data of the location where a photograph was taken to an image or video.

[1122] "Server" refers to a computer system that centrally manages, analyzes, stores, and provides data.

[1123] "Means for extracting text information" refers to the use of OCR (optical character recognition) technology to read text from images or videos and extract it as digital text.

[1124] "Means of analysis using generative artificial intelligence" refers to technology that uses a generative AI model (such as GPT) to analyze extracted text information and derive disaster patterns and lessons learned.

[1125] A "database" refers to an information system for efficiently storing, searching, and managing structured data.

[1126] "Means of storage" refers to the technology that stores the analyzed information in a database so that it can be searched and used later.

[1127] "Means of providing to users" refers to technology that provides analyzed information to users through interfaces such as web apps and mobile apps.

[1128] "The latest weather data" refers to real-time weather information and earthquake data provided by institutions such as the Japan Meteorological Agency and the Earthquake Research Institute.

[1129] "Means for conducting risk assessment" refers to technology that compares past disaster records with the latest meteorological data to conduct current risk assessments.

[1130] "Means for issuing alerts" refers to technology that uses communication APIs such as Twilio to issue alerts to users when specific risks increase.

[1131] This invention is a system that analyzes past disaster records and legends and provides them as information for modern disaster prevention measures. This system collects physical data, uses generative AI to analyze it as text information, stores the information in a database, and provides it to users.

[1132] In the data collection module, users go to the site and take photos of past disaster records, such as stone monuments and documents, using a smartphone or tablet. At this time, the user manually enters supplementary information and detailed descriptions into the device. The device then uses GPS to add location information to this data and uploads it to the server.

[1133] In the image processing module, the server extracts text from the received image data using OCR technology (e.g., Amazon Textract). The text extracted through OCR technology is then analyzed in detail using generative AI (e.g., OpenAI GPT model). This analysis extracts important lessons about past disaster patterns and legends.

[1134] In the database management module, the server structures and stores the analyzed information in a database (e.g., MySQL). This database is updated each time new data is added and is managed to optimize the information.

[1135] In the information provision module, users can search for information about specific regions or disasters through web or mobile apps. The device sends the user's query to the server, which then searches for relevant information from a database, organizes it, and returns it to the device. This allows users to receive past disaster records and forecast information in real time.

[1136] In the real-time risk assessment module, the server periodically obtains and analyzes real-time information, such as the latest weather and earthquake data provided by the Japan Meteorological Agency and the Earthquake Research Institute. If the server compares this information with past disaster records and determines that the risk is high, it generates an alert using a communication API such as Twilio. This alert is then sent to the device, prompting the user to take appropriate action.

[1137] As a specific example, consider the case where a user visits a mountain village in an earthquake-prone area and discovers an old stone monument mentioned by locals. The user takes a picture of the monument with their smartphone and uploads it to the server along with supplementary information. This data is processed using OCR, and the generative AI analyzes it to determine that "two large earthquakes have occurred in this area in the past, causing many buildings to collapse." The analysis results are stored in a database, and when the user searches for "earthquake records" through the app, the information is immediately provided.

[1138] If the server determines that heavy rain is continuing, it compares real-time weather data with past disaster records and notifies users of the increasing risk.The server then uses Twilio to send an alert to the user's device, informing them that "there is an increasing risk of major flooding in this area. Please evacuate to nearby high ground."

[1139] Examples of prompts used to analyze generative AI models include the following:

[1140] "Analyze the following text data to extract patterns and important lessons from past disasters: '[Text data]'"

[1141] This system will enable the provision of disaster prevention information based on past disaster records, real-time risk assessment, and rapid warning issuance, providing appropriate disaster prevention information to local residents and visitors.

[1142] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1143] Step 1: Data collection

[1144] Users use their smartphones or tablets to take photos of local stone monuments, documents, and other records of past disasters.

[1145] Input: Disaster record image, supplementary information (e.g. details of the disaster, year, etc.)

[1146] Specific operation: After taking a disaster record, the user inputs supplementary information through the application and obtains the location information of the shooting location, making the data collected by the user specific and including location information.

[1147] Step 2: Send data

[1148] The device transmits the collected image data, supplementary information, and location information to the server.

[1149] Input: Disaster record image data, location information, supplementary information

[1150] Output: Image data, location information, and supplementary information of the uploaded disaster records are saved on the server.

[1151] Specific operation: The device sends the captured image, the input supplementary information, and the acquired location information in JSON format to the server, where the data is temporarily stored.

[1152] Step 3: Image processing (OCR)

[1153] The server uses OCR technology (e.g., Amazon Textract) to extract text information from the received image data.

[1154] Input: Uploaded image data

[1155] Output: Extracted character information (text data)

[1156] Specific operation: The server inputs image data into the OCR engine and extracts character information as text data. At this time, preprocessing such as adjusting image resolution and removing noise is performed.

[1157] Step 4: Analysis by generative AI

[1158] The server analyzes the extracted text information using generative AI (e.g., OpenAI GPT) to extract disaster patterns and lessons learned.

[1159] Input: Character information extracted by OCR

[1160] Output: Disaster patterns and lessons learned analyzed by generative AI

[1161] Specific operation: The server inputs the prompt and extracted text information into the generative AI model and obtains the analysis results. For example, the prompt could be, "Analyze the following text data and extract past disaster patterns and important lessons: '[Text data]'."

[1162] Step 5: Saving to the Database

[1163] The server structures and stores the parsed information in a database (e.g., MySQL).

[1164] Input: Disaster patterns and lessons learned analyzed by generative AI

[1165] Output: Analysis results stored in a database

[1166] Specific operation: The server classifies the analysis results by region, disaster, and year and month, and when storing them in a database, adds an index to optimize the search algorithm.

[1167] Step 6: Information search function

[1168] Users use web and mobile apps to search for information about specific regions and disasters.

[1169] The terminal sends a search query to the server, which retrieves relevant information from a database and provides it to the user.

[1170] Input: User's search query (area name, type of disaster, etc.)

[1171] Output: Search results (past disaster records, appropriate evacuation plans, etc.)

[1172] Specific operation: When a user's search query is sent from the terminal to the server, the server searches the database and returns relevant information to the terminal for display to the user.

[1173] Step 7: Real-time risk assessment

[1174] The server regularly obtains and analyzes the latest weather and earthquake data provided by the Japan Meteorological Agency and the Earthquake Research Institute.

[1175] Input: Latest weather data, earthquake data

[1176] Output: Real-time risk assessment results

[1177] Specific operation: The server periodically obtains weather and earthquake data from external APIs, compares it with past disaster records, and performs risk assessment.

[1178] Step 8: Send an alert

[1179] If the server determines that the risk is high, it generates an alert and sends it to the user's device using a communication API such as Twilio.

[1180] Input: Risk assessment results

[1181] Output: Alert notification to user terminal

[1182] Specific operation: The server generates a warning message based on the risk assessment result and notifies the user's device using the Twilio API. For example, it sends a message saying, "There is an increasing risk of major flooding in this area. Please evacuate to nearby high ground."

[1183] (Application example 1)

[1184] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1185] In recent years, the frequency of natural disasters has increased, making it increasingly important to apply lessons learned from past disaster records and legends to modern times. However, information about past disasters is often preserved in a physical, unwritten form, making it difficult to effectively utilize this information in modern disaster prevention measures. Furthermore, real-time disaster risk assessment and warning issuance are insufficient, which can delay prompt evacuation and disaster prevention actions. To solve this problem, it is necessary to collect and analyze past disaster records as digital data and provide them to users, as well as to build a warning system that utilizes real-time information.

[1186] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1187] In this invention, the server includes means for collecting physical data including records of past disasters, means for extracting text information from the collected physical data, means for analyzing the extracted text information using generative artificial intelligence, means for saving the analyzed information in a database, means for providing the saved information to users, and means for acquiring and analyzing meteorological and earthquake data in real time and issuing warnings. This makes it possible to effectively utilize past disaster records in modern disaster prevention measures, evaluate disaster risks in real time, and issue prompt warnings and appropriate action instructions.

[1188] "Physical data" refers to tangible information, including records of past disasters such as stone monuments and documents.

[1189] "Text information" refers to information expressed as text that is extracted from physical data.

[1190] "Generative artificial intelligence" is a system that uses machine learning and natural language processing techniques to analyze extracted text information.

[1191] A "database" is an electronic collection of information in which analyzed information is structured and stored.

[1192] "Information provision means" refers to a means for providing stored information to users in an appropriate form.

[1193] "Weather data" refers to data such as temperature, precipitation, and wind speed based on meteorological observations.

[1194] "Earthquake Data" means observed data relating to the occurrence of earthquakes.

[1195] "Warning issuing means" refers to a means for notifying users of emergency warnings based on analyzed weather data and earthquake data.

[1196] "Location information" means geographic coordinate information that indicates where physical data was collected.

[1197] "Disaster prevention information" refers to information on measures to reduce disaster risk based on past disaster records.

[1198] A "smartphone" is a mobile device that combines the functions of a mobile phone and a computer.

[1199] A "head-mounted display" is a device worn on the head that displays images.

[1200] "Disaster risk assessment" is the process of assessing current and future disaster risks based on past disaster records and real-time data.

[1201] The system of this invention analyzes past disaster records and provides them as information for modern disaster prevention measures. It is particularly focused on providing information in environments using smartphones and head-mounted displays.

[1202] Data collection

[1203] Users visit the disaster site and take photos of stone monuments, documents, and other records of past disasters using their smartphone's camera. When taking a photo, location information is automatically added using the GPS function. The collected data is uploaded to a server via the Internet. Users can also manually enter supplementary information and detailed explanations in text format.

[1204] Extraction and analysis of text information

[1205] The server extracts text from the uploaded image data using OCR (optical character recognition) technology. This could be done using open-source software such as Tesseract OCR. The extracted text data is then analyzed using a generative AI model (e.g., GPT-4). This analysis extracts important lessons from past disaster patterns and legends, and stores them in a structured database.

[1206] Database Management

[1207] The server stores the analyzed information in a database that is dynamically updated based on the data being added, ensuring consistency and optimization of the information, and effectively matching past and new data to help assess disaster risk.

[1208] Information provision

[1209] When a user searches for information about a specific region or disaster using a web app or smartphone app, the device sends a query to the server. The server searches the database for relevant information and responds to the query. The user can then receive evacuation plans and disaster prevention advice in real time based on past disaster records.

[1210] Real-time risk assessment and alerting

[1211] The server periodically obtains real-time information such as weather and earthquake data. The analyzed data is compared with past disaster records, and if a high risk is determined, a real-time warning is issued. A notification is immediately sent to the user's device, and instructions for appropriate action are displayed. Weather and earthquake data is generally obtained from public institutions such as the Japan Meteorological Agency and the Earthquake Research Institute.

[1212] Specific examples

[1213] As a specific example, suppose a user visits a mountain village in an earthquake-prone area. There, they discover an old stone monument that locals have mentioned, and take and upload a photo of it with their smartphone. The server processes the image using OCR technology and obtains the analysis result: "Two large earthquakes have occurred in this area in the past, causing many buildings to collapse." This result is stored in a database, and when a user searches for "earthquake records" in the app, past earthquake information is displayed. In addition, if heavy rain continues in the area, the server compares the data with past records of large-scale floods, recognizes the increased risk, and sends a message to the user's device saying, "There is an increasing risk of large-scale flooding in this area. Please evacuate to nearby high ground."

[1214] Prompt Sentence Examples

[1215] "We are analyzing records of past disasters and legends to provide disaster prevention information. We are considering a system that will read the characters on the following stone monument using OCR, analyze disaster patterns and lessons learned, register the results in a database, and provide this to users. Please provide us with the analysis results for the characters extracted from the following stone monument."

[1216] In this way, the system of the present invention provides information useful for modern disaster prevention measures based on knowledge gained from past disaster records, and enables risk assessment and warning issuance in real time.

[1217] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1218] Step 1:

[1219] Users go to the disaster site and take photos of disaster records such as stone monuments and documents using their smartphone camera. When taking a photo, location information is automatically added using the smartphone's GPS function. The input is the captured image and GPS location information, which are then uploaded from the device to the server.

[1220] Step 2:

[1221] The server converts the received image data into text using OCR technology. Specifically, it uses Tesseract OCR software to extract text from the image. The input is the uploaded image, and the output is the extracted text data.

[1222] Step 3:

[1223] The server analyzes the extracted text data using a generative AI model. This analysis extracts important lessons about past disaster patterns and legends. The generative AI model used is GPT-4, with the input being the text data and the output being the analyzed lesson data.

[1224] Step 4:

[1225] The server stores the analyzed information in a database. The database structures and stores the analysis results, ensuring consistency and optimization of the information. The input is the analyzed lessons learned data, and the output is an updated database.

[1226] Step 5:

[1227] When a user searches for information about a specific region or disaster using a web app or smartphone app, the device sends a query to the server. The server searches the database for relevant information and returns the results to the device. The input is the user's query, and the output is disaster information corresponding to the query.

[1228] Step 6:

[1229] The server periodically obtains real-time information such as weather and earthquake data. It obtains and analyzes data from public institutions such as the Japan Meteorological Agency and the Earthquake Research Institute. The input is real-time weather and earthquake data, and the output is the risk assessment results.

[1230] Step 7:

[1231] The server compares the analyzed data in real time with past disaster records and generates an alert if it determines that the risk is high. The alert is sent to the device and prompts the user to take appropriate action. The input is the risk assessment result, and the output is an alert notification.

[1232] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1233] This invention improves the quality of information provision by combining a system that analyzes past disaster records and legends and provides modern disaster prevention information with an emotion engine that recognizes the user's emotions. This system collects physical data, uses generative AI to analyze it as text information, stores that information in a database, and provides appropriate information according to the user's emotional state. The program's processing is explained in detail below.

[1234] Data collection

[1235] Users discover records of past disasters, such as stone monuments or documents, on-site and take pictures with their smartphones or dedicated devices. The devices attach location information (GPS data) to the images and upload this data to a server. In addition, users can manually enter supplementary information and detailed descriptions into the device, which are also sent to the server.

[1236] Character Recognition and Analysis

[1237] The server uses OCR technology to extract text information from the received image data. The text data extracted by OCR is then analyzed in detail by the generative AI. This analysis allows important lessons to be extracted regarding past disaster patterns and legends.

[1238] Database Management

[1239] The analyzed information is structured and stored in a database by the server, which is updated with newly added data and managed to optimize the information.

[1240] Emotion engine and information provision

[1241] A user searches for information about a specific region or disaster through a web or mobile app. The device sends the query to the server. At the same time, the device uses a built-in emotion engine to analyze the user's emotional state (e.g., stress, relief, alertness, etc.). The emotion engine's analysis results are sent to the server along with the query.

[1242] The server searches a database based on the received query to retrieve relevant records of past disasters and legends. Based on the analysis results of the emotion engine, the server automatically adjusts the content and display method of the information provided. For example, if the user is in a state of high stress, it may provide information in an easy-to-understand and concise manner, or add support information on relaxation techniques and mental health. The device then displays the adjusted information on the user interface. This allows the user to receive past disaster records and appropriate prevention information in real time according to their emotional state.

[1243] Real-time risk assessment and alerting

[1244] The server periodically obtains and analyzes real-time information, such as the latest weather and earthquake data. It compares the analysis results with past disaster records to assess whether a particular area is at increased risk. If the server determines that the risk is high, it generates an alert, which is sent to the user's device. The device then displays the received alert message on its user interface, prompting the user to take appropriate action.

[1245] Specific examples

[1246] To give a specific example, a user visits a mountain village in an earthquake-prone area and discovers an old stone monument mentioned by locals. The user takes a picture of the monument with their smartphone and uploads the image to the server. The image is processed using OCR, and the generating AI discovers that "two large earthquakes have occurred in this area in the past, causing many buildings to collapse." The analysis results are stored in a database.

[1247] When a user searches for "earthquake records" in the app, the device uses its built-in emotion engine to analyze the user's current emotional state. For example, if the user is in a high stress state, the server will provide concise and easy-to-understand information based on the analysis results, and will also add relaxation techniques and mental health support information. The device will display this information on the user interface.

[1248] If the server determines that heavy rain is continuing in an area, it compares the data with past records of large-scale floods and recognizes that the risk is increasing. The server then issues a flood warning and notifies registered users' devices, saying, "There is an increasing risk of large-scale flooding in this area. Please evacuate to nearby high ground." The devices also display additional mental health support information based on the analysis results of the emotion engine.

[1249] This system will enable us to apply past lessons to modern disaster prevention and provide appropriate information to local residents and visitors. In addition, by providing disaster prevention information that takes into account the user's emotional state, we will be able to provide more effective and user-friendly responses.

[1250] The processing flow will be explained below.

[1251] Step 1:

[1252] Users discover stone monuments or disaster records on-site and take pictures using their smartphones or dedicated devices. The devices then attach location information (GPS data) to the captured image data and upload it to the server.

[1253] Step 2:

[1254] At the same time as uploading the image data, the terminal also sends supplementary information and detailed descriptions manually entered by the user to the server.

[1255] Step 3:

[1256] The server uses OCR (Optical Character Recognition) technology to extract character information from the received image data, generating text data from the image.

[1257] Step 4:

[1258] The server inputs the extracted text data into a generative AI model for detailed analysis, which extracts important lessons about past disaster patterns and legends.

[1259] Step 5:

[1260] The server structures the parsed information and stores it in a database, which is updated with newly added data and managed to optimize the information.

[1261] Step 6:

[1262] A user searches for information about a specific area or disaster through a web or mobile app, and the device sends the query to the server.

[1263] Step 7:

[1264] Simultaneously with the search query, the device uses a built-in emotion engine to analyze the user's emotional state, for example by detecting facial expressions and tone of voice through the camera and microphone.

[1265] Step 8:

[1266] The server searches the database based on the received query to retrieve relevant records of past disasters and legends, while also receiving the analysis results of the emotion engine.

[1267] Step 9:

[1268] The server automatically adjusts the content and display of information based on the analysis results of the emotion engine. For example, if the user is under high stress, the server will provide concise and easy-to-understand information and add relaxation techniques and mental health support information.

[1269] Step 10:

[1270] The terminal receives the adjusted information from the server and displays it on the user interface, allowing users to receive past disaster records and appropriate prevention information in real time according to their emotional state.

[1271] Step 11:

[1272] The server periodically retrieves and analyzes real-time information, such as the latest weather and earthquake data, and compares the analysis results with records of past disasters to assess whether a particular area is at increased risk.

[1273] Step 12:

[1274] If the server determines that the risk is high, it generates an alert, which is then sent to the user's terminal.

[1275] Step 13:

[1276] The device displays the received warning message on the user interface and prompts the user to take appropriate action. The emotion engine can also provide additional relaxation and mental health support content.

[1277] In this way, lessons learned from the past can be applied to modern disaster prevention, enabling more effective responses by providing information that responds to the user's emotions.

[1278] Example 2

[1279] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1280] Disaster prevention is important in modern times, but lessons learned from past disaster records and legends are not fully utilized. There is also a need to provide appropriate information according to the emotional state of users. Furthermore, there is a lack of systems for real-time risk assessment and warning issuance.

[1281] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1282] In this invention, the server includes means for collecting physical data including records of past disasters, means for extracting text information from the collected physical data, means for analyzing the extracted text information using generative artificial intelligence, means for saving the analyzed information in a database, means for providing the saved information to users, means for analyzing the emotional state of the user and adjusting the information provided, and means for conducting risk assessments and issuing warnings in real time. This makes it possible to provide appropriate disaster prevention information based on past disaster records, customize the information to suit the emotional state of the user, and further to conduct risk assessments and issue warnings in real time.

[1283] "Physical data" refers to tangible information such as stone monuments and documents collected on-site.

[1284] "Textual information" refers to textual data extracted from physical data.

[1285] "Generative AI" refers to artificial intelligence technology that analyzes data using natural language processing and machine learning algorithms.

[1286] A "database" refers to an electronic storage system that stores analyzed information in a structured manner.

[1287] "Information provision means" refers to systems and devices that appropriately display and convey stored information to users.

[1288] "Emotion analysis means" refers to techniques or devices for assessing a user's emotional state and tailoring information provision accordingly.

[1289] "Risk assessment" refers to the process of analyzing real-time situational data to determine the risk level of a particular situation.

[1290] "Alert generation means" refers to a system or device that generates a warning message and notifies the user when a risk increases.

[1291] "Location Information" means geographic information that indicates where data is collected.

[1292] "Disaster prevention information" refers to preventive measures and relief information provided based on past disaster records and analysis results.

[1293] This invention improves the quality of information provision by combining a system that analyzes past disaster records and legends and provides modern disaster prevention information with an emotion engine that recognizes the user's emotions. This system collects physical data, uses generative AI to analyze it as text information, stores that information in a database, and provides appropriate information according to the user's emotional state.

[1294] Hardware and Software

[1295] Users collect physical data using smartphones or dedicated devices. These devices are equipped with cameras, GPS, and sentiment analysis engines. The server runs on a cloud platform (e.g., AWS or Google Cloud) with high-performance computing capabilities and analyzes the data using OCR technology or generative AI models (e.g., Google Cloud Vision API or OpenAI GPT-4). A relational database (e.g., MySQL) is used as the database.

[1296] Data collection and upload

[1297] Users discover records of past disasters, such as stone monuments or documents, on-site and take pictures with their smartphones or dedicated devices. The devices then attach location information (GPS data) to the images and upload this data to a server. Users can also manually enter supplementary information and detailed descriptions into the device, and this data is also sent to the server.

[1298] Character Recognition and Analysis

[1299] The server uses OCR technology to extract text information from the received image data. The text data extracted by OCR is then analyzed in detail by the generative AI. This analysis extracts important lessons about past disaster patterns and legends, which are then structured and stored in a database.

[1300] Information provision and sentiment analysis

[1301] A user searches for information about a specific region or disaster through a web app or mobile app. The device sends the query to a server. At the same time, the device uses its built-in emotion engine to analyze the user's emotional state and sends the result along with the query to the server. The server searches a database based on the received query and retrieves relevant information. Based on the emotion engine's analysis results, the content and display method of the information provided are automatically adjusted. For example, if the user is under high stress, the device will provide information in an easy-to-understand and concise format, and also add support information on relaxation techniques and mental health. The device then displays the adjusted information on the user interface.

[1302] Real-time risk assessment and alerting

[1303] The server periodically obtains and analyzes real-time information, such as the latest weather and earthquake data. The analysis results are compared with past disaster records to assess whether a particular area is at increased risk. If the server determines that the risk is high, it generates an alert, which is sent to the user's device. The device then displays the received alert message on its user interface, prompting the user to take appropriate action.

[1304] Specific examples

[1305] To give a specific example, a user visits a mountain village in an earthquake-prone area and discovers an old stone monument mentioned by locals. The user takes a picture of the monument with their smartphone and uploads the image to the server. The image is processed using OCR, and the generating AI discovers that "two large earthquakes have occurred in this area in the past, causing many buildings to collapse." The analysis results are stored in a database.

[1306] When a user searches for "earthquake records" in the app, the device uses its built-in emotion engine to analyze the user's current emotional state. For example, if the user is in a high stress state, the server will provide concise and easy-to-understand information based on the analysis results, and will also add relaxation techniques and mental health support information. The device will display this information on the user interface.

[1307] Example prompt sentence:

[1308] "I would like to know about earthquake records. I've been feeling very stressed lately. Please also provide information on how to relax."

[1309] If the server determines that heavy rain is continuing in an area, it compares the data with past records of large-scale floods and recognizes that the risk is increasing. The server then issues a flood warning and notifies registered users' devices, saying, "There is an increasing risk of large-scale flooding in this area. Please evacuate to nearby high ground." The devices also display additional mental health support information based on the analysis results of the emotion engine.

[1310] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1311] Step 1: Data collection

[1312] Input: The user discovers records of past disasters, such as stone monuments or documents, on-site and takes pictures using a smartphone or dedicated device.

[1313] Specific operation: The user launches the camera app on their smartphone and takes a photo of a stone monument or document. The device then attaches location information (GPS data) to the image.

[1314] Output: Location information is added to the captured image data.

[1315] Step 2: Upload data

[1316] Input: Image data with location information.

[1317] Specific operation: The device uses the network to upload the collected image data and location information to the server.

[1318] Output: Image data with location information received by the server.

[1319] Step 3: Character Recognition (OCR Processing)

[1320] Input: Image data received by the server.

[1321] Specific operation: The server uses OCR technology to extract text information from image data, using an OCR library (e.g., Google Cloud Vision API).

[1322] Output: The extracted character data.

[1323] Step 4: Data analysis

[1324] Input: Extracted character data.

[1325] Specific operation: The server uses a generative AI model (e.g., OpenAI GPT-4) to analyze text data and extract patterns of past disasters and important lessons.

[1326] Output: Data on lessons and patterns analyzed.

[1327] Step 5: Save to database

[1328] Input: Data about lessons and patterns analyzed.

[1329] Specific operation: The server executes SQL queries to store the analysis results in a relational database (e.g., MySQL).

[1330] Output: Analysis results stored in a database.

[1331] Step 6: Information retrieval and sentiment analysis

[1332] Input: Search queries entered by users through web and mobile apps.

[1333] Specific operation: The device sends a query to the server. At the same time, the device uses its built-in emotion engine to analyze the user's emotional state and sends the results to the server.

[1334] Output: The search query and sentiment analysis results sent to the server.

[1335] Step 7: Database search and information reconciliation

[1336] Input: The search query and sentiment analysis results sent to the server.

[1337] What it does: The server executes SQL queries to retrieve relevant information from the database, and then tailors the content and presentation of that information based on the results of sentiment analysis.

[1338] Output: The adjusted information.

[1339] Step 8: Provide information

[1340] Input: Reconciled information.

[1341] Specific operation: The device uses a UI library (e.g., React Native) to display the adjusted information in the user interface.

[1342] Output: Disaster prevention information and mental health support information displayed to the user.

[1343] Step 9: Real-time risk assessment

[1344] Input: Latest weather and earthquake data.

[1345] Specific operation: The server periodically calls an external API (e.g., the Japan Meteorological Agency API) to obtain data and applies a risk assessment algorithm.

[1346] Output: Risk assessment results.

[1347] Step 10: Send an alert

[1348] Input: Risk assessment results.

[1349] Specific operation: If the server determines that the risk is high, it generates a notification message and sends it to the user's device using a push notification service (e.g., Firebase Cloud Messaging).

[1350] Output: The alert message displayed on the user's terminal.

[1351] (Application example 2)

[1352] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1353] In recent years, the frequency and scale of natural disasters have increased, and conventional disaster prevention information systems face the challenge of providing appropriate information based on the individual situation and emotional state of each user. Furthermore, users often have difficulty understanding complex disaster prevention information, which can lead to confusion during emergencies. Therefore, there is a need for a system that can improve the accuracy of disaster information analysis and flexibly adjust the information delivery method based on the user's emotional state.

[1354] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting physical data including records of past disasters, means for extracting text information from the collected physical data, analysis means using a generative AI model for analyzing the extracted text information, means for saving the analyzed information in a database, information provision means for providing the saved information to users, means equipped with an emotion engine for analyzing the emotional state of the user, and means for adjusting the information provision method based on the emotional state of the user. This makes it possible to provide disaster prevention information that is linked to the emotional state of the user, is easy to understand, and meets the needs of each individual user.

[1355] "Physical data" refers to information that actually exists and is stored in a visible form, such as stone monuments or documents that record past disasters.

[1356] "Textual information" is readable textual data extracted from physical data.

[1357] A "generative AI model" is an algorithm that uses artificial intelligence technology to perform advanced analysis of textual information and derive patterns and lessons learned from past disasters.

[1358] "Analysis means" refers to technology for analyzing collected text information in detail using a generative AI model.

[1359] A "database" is an information management system for structuring and storing analyzed textual information and disaster prevention information.

[1360] "Information provision means" refers to technology for providing information stored in a database in a format that is easy for users to understand.

[1361] The "emotion engine" is a technology that analyzes the user's emotional state and determines their state of stress, relief, vigilance, etc.

[1362] "Location information" is information used to identify the location where physical data was collected, using GPS data or the like.

[1363] "Disaster prevention information" refers to information on disaster prevention measures provided based on past disaster records and analysis results.

[1364] "Adjustment means" refers to technology that allows for flexible changes to the content and display method of disaster prevention information provided to users based on the emotion engine.

[1365] The present invention is a system that analyzes past disaster records and legends and provides them as modern disaster prevention countermeasure information, and aims to improve the quality of information provision based on the emotional state of the user. Specific embodiments of the present invention will be described.

[1366] Data collection

[1367] Using a smartphone equipped with a disaster prevention management app, users can take pictures of stone monuments, documents, and other records of past disasters they find in the field. The smartphone then attaches location information (GPS data) to the captured image and uploads this data to a server. In addition, users can manually enter supplementary information and detailed descriptions into their smartphone, which are also sent to the server.

[1368] Character Recognition and Analysis

[1369] The server uses OCR technology to extract textual information from the received image data. The textual information extracted through this OCR process is then analyzed in detail using a generative AI model. This analysis allows for the extraction of important lessons about past disaster patterns and legends.

[1370] Database Management

[1371] The analyzed information is structured and stored in a database by the server, which is constantly updated with new data and managed to optimize the information.

[1372] Emotion engine and information provision

[1373] When a user searches for information about a specific region or disaster through the disaster prevention management app, the smartphone uses its built-in emotion engine to analyze the user's emotional state (stress, relief, alertness, etc.). The emotion engine's analysis results are sent to the server along with the query. The server searches a database based on the received query and retrieves relevant records of past disasters and legends. Based on the emotion engine's analysis results, the content and display method of the information provided are automatically adjusted. For example, if the user is in a state of high stress, the information provided will be simple and easy to understand, and support information on relaxation techniques and mental health will also be added. The smartphone then displays the adjusted information on the user interface.

[1374] Real-time risk assessment and alerting

[1375] The server periodically obtains and analyzes real-time information, such as the latest weather and earthquake data. It compares the analysis results with past disaster records to assess whether a particular area is at increased risk. If the server determines that the risk is high, it generates an alert, which is sent to the user's smartphone. The smartphone then displays the received alert message on its user interface, prompting the user to take appropriate action.

[1376] Specific examples

[1377] Here's a specific example: A user visits a mountain village in an earthquake-prone area and discovers an old stone monument mentioned by locals. The user takes a picture of the monument with their smartphone and uploads it to the server. The image is processed using OCR, and the generating AI analyzes the information: "Two large earthquakes have occurred in this area in the past, causing many buildings to collapse." The analysis results are stored in a database.

[1378] When a user searches for "earthquake records" in the app, the smartphone uses its built-in emotion engine to analyze the user's current emotional state. For example, if the user is in a state of high stress, the server provides concise and easy-to-understand information based on the analysis results, and also adds relaxation techniques and mental health support information. The smartphone displays this information on the user interface. If heavy rain continues in an area, the server compares it with past records of large-scale floods and recognizes that the risk is increasing. The server issues a flood warning, notifying registered users' smartphones that "there is an increasing risk of large-scale flooding in this area. Please evacuate to nearby high ground." The smartphone also displays additional mental health support information based on the analysis results of the emotion engine.

[1379] Example of a data collection prompt:

[1380] "Upload an image of the stone monument taken with your smartphone, attach GPS data to the image, and send it to the server."

[1381] Example prompt for generative AI analysis:

[1382] "Analyze the disaster record information below, extract important information, and write it down in a format that will be useful for disaster prevention measures: {text}"

[1383] This allows disaster prevention information to be provided based on the user's emotional state, enabling real-time, user-friendly responses.

[1384] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1385] Step 1:

[1386] The user uses a smartphone equipped with a disaster prevention management app to take an image of a stone monument or document containing disaster records. The smartphone then attaches location information (GPS data) to the image and uploads this data to a server. The input here is the image containing the disaster record and the GPS data, and the output is the image and data including location information sent to the server. Specific operations in this step include taking an image using the smartphone's camera and GPS module, obtaining location information, and uploading the data.

[1387] Step 2:

[1388] The server uses OCR technology to extract text information from the uploaded image data. The input for this step is the image data uploaded by the user, and the output is the text information obtained by OCR processing. Specific operations include image analysis and text information extraction using OCR software on the server.

[1389] Step 3:

[1390] The server then uses a generative AI model to perform detailed analysis of the text information extracted by OCR. The input for this step is the text information obtained by OCR, and the output is information on past disaster patterns and lessons learned analyzed by the generative AI model. At this stage, the generative AI model performs text analysis on the server and extracts important information about past disasters.

[1391] Step 4:

[1392] The server structures and stores the analyzed information in a database. The input for this step is the textual information analyzed by the generative AI model, and the output is structured data stored in the database. Specific operations include storing and managing data using a database management system on the server.

[1393] Step 5:

[1394] A user searches for information about a specific area or disaster through a disaster prevention management app. The input to this step is a search query by the user, and the output is a search request sent to the server. Here, the search operation is performed by the smartphone application.

[1395] Step 6:

[1396] The smartphone uses its built-in emotion engine to analyze the user's emotional state. The input of this step is data for estimating the user's emotion, such as the user's current facial expression and voice, and the output is the determined emotional state information. Specific operations include capturing and analyzing emotion data using the smartphone's camera and microphone.

[1397] Step 7:

[1398] The server searches the database based on the received search query and the analysis results of the emotion engine to retrieve related disaster records and legend information. The input for this step is the user's search query and emotional state information, and the output is disaster information adjusted according to the emotional state. Specific operations include database search, information retrieval, and adjustment by the server.

[1399] Step 8:

[1400] The smartphone displays the adjusted information on the user interface. The input of this step is the adjusted disaster information sent from the server, and the output is the disaster prevention information displayed to the user. Specific operations include displaying the information on the smartphone display and updating the user interface.

[1401] Step 9:

[1402] The server periodically acquires the latest weather and earthquake data and performs real-time risk assessment. The input for this step is weather and earthquake data, and the output is the risk assessment result. Specific operations include acquiring and analyzing real-time data on the server.

[1403] Step 10:

[1404] If the server determines that the risk is high, it generates an alert and sends the alert message to the user's smartphone. The input of this step is the risk assessment result, and the output is the alert message sent to the user. Specific operations include sending the alert message from the server to the smartphone and the associated notification process.

[1405] Through the above steps, it becomes possible to provide disaster prevention information that is linked to the user's emotional state, is easy to understand, and meets the needs of each individual user.

[1406] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1407] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1408] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1409] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1410] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1411] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1412] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1413] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1414] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1415] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1416] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1417] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1418] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1419] 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.

[1420] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1421] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1422] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1423] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1424] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1425] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1426] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1427] The following is further disclosed regarding the above embodiment.

[1428] (Claim 1)

[1429] means of collecting physical data, including records of past disasters;

[1430] a means for extracting textual information from the collected physical data;

[1431] an analysis means using a generative artificial intelligence to analyze the extracted character information;

[1432] a means for storing the analyzed information in a database;

[1433] an information providing means for providing the stored information to a user;

[1434] A system including:

[1435] (Claim 2)

[1436] The system according to claim 1, which analyzes lessons from past disaster patterns and legends based on the extracted text information.

[1437] (Claim 3)

[1438] a means for adding location information to the data collected from the field;

[1439] 10. The system of claim 1, providing data including disaster preparedness information analyzed based on a generative artificial intelligence model.

[1440] (Claim 4)

[1441] A means of obtaining real-time external data and comparing it with past disaster records to conduct risk assessments;

[1442] means for generating an alert based on the risk assessment and notifying the alert to a user's terminal;

[1443] 10. The system of claim 1, comprising:

[1444] (Claim 5)

[1445] A query processing means for users to search for specific areas or past disaster information;

[1446] means for retrieving information from a database corresponding to a query and generating a response;

[1447] 10. The system of claim 1, comprising:

[1448] "Example 1"

[1449] (Claim 1)

[1450] A means of collecting photographed records of past disasters on-site;

[1451] A means for adding location information to the collected records of past disasters;

[1452] means for transmitting data to which location information has been added to a server;

[1453] means for extracting textual information from the transmitted data;

[1454] A means for analyzing the extracted character information using a generating artificial intelligence;

[1455] A means to store the analysis results, such as the disaster patterns and lessons learned, in a database;

[1456] a means for providing the stored information to the user;

[1457] A means of comparing past disaster records with the latest meteorological data to assess risk, and

[1458] a means of issuing warnings in cases of high risk;

[1459] A system including:

[1460] (Claim 2)

[1461] The system according to claim 1, which analyzes lessons from past disaster patterns and legends based on the extracted text information and provides the results of the analysis to the user.

[1462] (Claim 3)

[1463] The system of claim 1 analyzes the latest weather data collected in real time and past disaster records using artificial intelligence, and issues an alert to users when there is a high risk.

[1464] "Application Example 1"

[1465] (Claim 1)

[1466] means of collecting physical data, including records of past disasters;

[1467] a means for extracting textual information from the collected physical data;

[1468] an analysis means using a generative artificial intelligence to analyze the extracted character information;

[1469] a means for storing the analyzed information in a database;

[1470] an information providing means for providing the stored information to a user;

[1471] A means of acquiring meteorological and earthquake data in real time, analyzing it, and issuing warnings.

[1472] A system including:

[1473] (Claim 2)

[1474] The system according to claim 1, which analyzes lessons from past disaster patterns and legends based on the extracted text information.

[1475] (Claim 3)

[1476] a means for adding location information to the data collected from the field;

[1477] 10. The system of claim 1, providing data including disaster preparedness information analyzed based on a generative artificial intelligence model.

[1478] (Claim 4)

[1479] 2. The system according to claim 1, further comprising a means for evaluating disaster risk in a designated area based on the stored information and notifying registered users of appropriate disaster prevention information and evacuation instructions.

[1480] (Claim 5)

[1481] The system according to claim 1, further comprising means for enabling a user to obtain disaster information via a smartphone or a head-mounted display by the information providing means.

[1482] "Example 2: Combining Emotion Engines"

[1483] (Claim 1)

[1484] means of collecting physical data, including records of past disasters;

[1485] a means for extracting textual information from the collected physical data;

[1486] an analysis means using a generative artificial intelligence to analyze the extracted character information;

[1487] a means for storing the analyzed information in a database;

[1488] an information providing means for providing the stored information to a user;

[1489] emotion analysis means for analyzing the user's emotional state and adjusting the provision of information;

[1490] A means of conducting real-time risk assessments and issuing alerts;

[1491] A system including:

[1492] (Claim 2)

[1493] The system according to claim 1, which analyzes lessons from past disaster patterns and legends based on the extracted text information.

[1494] (Claim 3)

[1495] a means for adding location information to the data collected from the field;

[1496] 10. The system of claim 1, providing data including disaster preparedness information analyzed based on a generative artificial intelligence model.

[1497] "Application example 2 when combining emotion engines"

[1498] (Claim 1)

[1499] means of collecting physical data, including records of past disasters;

[1500] a means for extracting textual information from the collected physical data;

[1501] an analysis means using a generative AI model to analyze the extracted character information;

[1502] a means for storing the analyzed information in a database;

[1503] an information providing means for providing the stored information to a user;

[1504] A means equipped with an emotion engine that analyzes the user's emotional state;

[1505] means for adjusting the information presentation method based on the user's emotional state;

[1506] A system including:

[1507] (Claim 2)

[1508] The system according to claim 1 analyzes lessons learned from past disaster patterns and legends based on the extracted text information, and provides disaster prevention information adjusted based on the user's emotional state.

[1509] (Claim 3)

[1510] a means for adding location information to the data collected from the field;

[1511] The system according to claim 1, wherein the data including disaster prevention information analyzed based on the generative AI model is appropriately adjusted by an emotion engine and provided. [Explanation of symbols]

[1512] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means of collecting physical data, including records of past disasters; a means for extracting textual information from the collected physical data; an analysis means using a generative artificial intelligence to analyze the extracted character information; a means for storing the analyzed information in a database; an information providing means for providing the stored information to a user; A system including:

2. 2. The system according to claim 1, wherein the extracted character information is used to analyze lessons learned from past disaster patterns and legends.

3. a means for adding location information to the data collected from the field; The system of claim 1 , providing data including disaster preparedness information analyzed based on a generative artificial intelligence model.

4. A means of obtaining real-time external data and comparing it with past disaster records to conduct risk assessments; means for generating an alert based on the risk assessment and notifying the alert to a user's terminal; The system of claim 1 , comprising:

5. A query processing means for users to search for specific areas or past disaster information; means for retrieving information from a database corresponding to a query and generating a response; The system of claim 1 , comprising:

Images