System

Abstract

A system is provided.SOLUTION: A system comprising: means for allowing a user to upload address information and a site photo; means for allowing a server to acquire information from a public database required to evaluate a risk of a corresponding address; means for allowing the server to analyze a disaster prevention risk using a generation AI based on the address information, the site photo, and the public database information; and means for allowing the server to generate a disaster prevention risk report.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] Traditionally, public data such as hazard maps provided by local governments have been the main source of information for disaster prevention measures, but there has been a problem in that specific risk assessments tailored to the characteristics of individual homes and sites have not been sufficiently conducted. While it is possible to understand the risks in a specific area in general, it is difficult to specifically assess the detailed risks of individual buildings and surrounding environments, making it difficult for users to plan appropriate disaster prevention measures themselves. In addition, many people find it time-consuming to analyze and understand public data, preventing them from taking appropriate measures. [Means for solving the problem]

[0005] The present invention solves the above problem by providing a system that allows users to upload their address information and site photos, and then uses generative AI based on this data to specifically and in detail analyze disaster prevention risks.

[0006] a means for users to upload address information and site photos;

[0007] a means for the server to obtain information from public databases necessary for risk assessment of the address;

[0008] A means for the server to analyze disaster prevention risks using generated AI based on address information, site photos, and public database information;

[0009] A means for the server to generate a disaster prevention risk report from the analysis results;

[0010] A system including a means for the server to transmit the generated disaster prevention risk report to the user's terminal makes it possible to provide individual and detailed disaster prevention risk information to the user.

[0011] In addition, by including analysis of the building's earthquake resistance and surrounding conditions using generative AI, it is possible to present more accurate risk assessments and specific disaster prevention measures.

[0012] A "user" is an individual or entity that utilizes the system to provide address information and site photographs.

[0013] "Address information" is data for identifying the location of a specified place, and indicates the specific location of a region or building.

[0014] "Site photos" are image data of a specified site provided by a user, and visually record the state of the building and surrounding environment.

[0015] "Terminal" means an electronic device that allows a user to input and send information, including a smartphone, tablet, or PC.

[0016] The "server" is a remote computer system that receives information from users, obtains public data, performs analysis using generative AI, and generates the final disaster prevention risk report.

[0017] "Public databases" are databases on disaster risks provided by local governments and government agencies, and include hazard maps and weather information.

[0018] "Generative AI" is an artificial intelligence technology that evaluates and analyzes specific risks based on multiple input data.

[0019] "Disaster prevention risk" refers to the danger and possibility caused by natural disasters.

[0020] A "disaster risk report" is a document created based on the results of the generative AI's analysis, which includes a disaster risk assessment and recommended measures for a specific address. [Brief explanation of the drawings]

[0021] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7]FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram 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

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

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

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

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

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

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

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

[0029] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0042] The present invention provides a system for evaluating disaster prevention risks in detail using address information and site photos provided by a user, as well as public databases, and providing the results to the user. This system is specifically implemented as follows.

[0043] Obtaining user information

[0044] User

[0045] First, a user accesses the system and uploads photos of their address and the site from their terminal. For example, a user enters an address in Nishi-Shinjuku, Shinjuku-ku, Tokyo, and takes and uploads multiple photos showing the exterior of the house and the surrounding area.

[0046] Uploading data

[0047] Terminal

[0048] The device sends the address information and photo entered by the user to the server. For security reasons, it is recommended to use encrypted communication such as SSL / TLS.

[0049] Obtaining information from public databases

[0050] server

[0051] The server retrieves necessary information from relevant public databases based on the received address information, such as earthquake risk information for the specified address via a disaster prevention API.

[0052] Risk data for floods, storm surges, etc. will also be obtained, including hazard maps and meteorological data provided by national and local governments.

[0053] Analysis and synthesis with generative AI

[0054] server

[0055] The server preprocesses the address information and site photos sent by the user and converts them into a data format that is easy for the AI ​​model to handle.

[0056] The AI ​​model uses information obtained from public databases and pre-processed photo data for analysis. The generative AI analyzes the building's earthquake resistance and the status of surrounding drainage facilities to identify and assess risks.

[0057] For example, the generating AI analyzes that the address provided by the server is in an earthquake-prone area and that there are rivers nearby that are prone to flooding, and then performs a risk assessment based on that.

[0058] Generate disaster risk reports

[0059] server

[0060] The server then creates a disaster risk report based on the analysis results of the AI. The report includes risk assessments for earthquakes, floods, storm surges, etc., along with specific countermeasures for each risk. For example, the report may include recommendations such as "Seismic reinforcement work on buildings is recommended" or "Evacuation routes must be checked."

[0061] Report distribution

[0062] server

[0063] The server sends the generated disaster risk report to the user's device in a format that can be easily viewed by the user, such as PDF or HTML.

[0064] Viewing the report

[0065] User

[0066] Users can check the disaster risk report received on their device and understand the specific risks and recommended measures for their home and surrounding area. For example, based on the contents of the report, users can consult with a specialist company and request earthquake-resistance reinforcement work.

[0067] Specific examples

[0068] For example, suppose a user uploads "Nishi-Shinjuku, Shinjuku-ku, Tokyo" as their address information and images of the exterior of their house and surrounding area as site photos. Based on that address, the server obtains earthquake risk information through the API of the National Research Institute for Earth Science and Disaster Prevention, and also collects flood risk data using the API of the Geospatial Information Authority of Japan. Furthermore, if the generation AI analyzes the photo data and determines that the building has poor earthquake resistance, the server will evaluate it as "high earthquake risk" or "low flood risk," and generate a disaster prevention risk report with specific countermeasures such as "seismic reinforcement work is recommended" and "evacuation routes need to be confirmed." Based on this report, users can take specific disaster prevention measures.

[0069] This invention allows users to understand the specific disaster prevention risks at home or on-site in detail and take appropriate disaster prevention measures. By utilizing generative AI, it is possible to integrate public data and individual on-site data to provide highly accurate risk assessments, making it possible to plan countermeasures more quickly and accurately than conventional methods.

[0070] The processing flow will be explained below.

[0071] Step 1:

[0072] User

[0073] The user logs in to the system, enters address information and site photos, and uploads them. For example, they enter the address of "Nishi-Shinjuku, Shinjuku-ku, Tokyo," and select photos of the exterior of the house and its surroundings.

[0074] Step 2:

[0075] Terminal

[0076] The device organizes the entered address information and photo data and sends them to the server. The address information is sent in text format, and the photo data is sent in image file format.

[0077] Step 3:

[0078] server

[0079] Based on the address information received by the server, the API of the relevant public database is called to obtain the necessary information. For example, earthquake risk data is obtained from the API of the National Research Institute for Earth Science and Disaster Prevention, and flood risk data is obtained from the API of the Geospatial Information Authority of Japan.

[0080] Step 4:

[0081] server

[0082] The server stores the public database information it has acquired in an internal database and prepares it for analysis. It also organizes and stores various risk data in association with address information.

[0083] Step 5:

[0084] server

[0085] The server preprocesses the uploaded photos and converts them into a format that can be analyzed by the generative AI, for example, adjusting the resolution of the photos and extracting key building features (such as earthquake resistance and drainage facilities).

[0086] Step 6:

[0087] server

[0088] The server provides address information, public database information, and preprocessed photo data to the generation AI, which then analyzes this input data and assesses disaster risk.

[0089] Step 7:

[0090] server

[0091] Based on the analysis results of the generation AI, the server generates a disaster prevention risk report, which includes earthquake risk, flood risk, and storm surge risk, along with recommended countermeasures.

[0092] Step 8:

[0093] server

[0094] The server sends the generated disaster risk report to the user's device. The report is provided in a format that users can easily view, such as PDF or HTML.

[0095] Step 9:

[0096] User

[0097] Users can receive and view disaster risk reports on their devices. Based on the reports, they can take specific disaster prevention measures. For example, they can consider earthquake-resistance reinforcement work or check evacuation routes.

[0098] Example 1

[0099] 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."

[0100] In disaster risk assessment, there is a need for a method that can efficiently and accurately integrate user-provided on-site information with public data to quickly and specifically assess individual risks. However, current systems only refer to public databases and are unable to properly utilize user-provided on-site information. Furthermore, manual data analysis is required, making it difficult to perform rapid risk assessment.

[0101] 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.

[0102] In this invention, the server includes means for a user to upload address information and site photos, means for a terminal to send the address information and photos entered by the user to the server, means for the server to acquire information from a public database necessary for risk assessment of the address, means for the server to analyze disaster prevention risk using a generative AI model based on the address information, site photos, and public database information, means for the server to generate a disaster prevention risk report from the analysis results, and means for the server to send the generated disaster prevention risk report to the user's terminal. This enables highly accurate disaster prevention risk assessment that integrates user-provided site information and public data.

[0103] "User" refers to any person or entity that utilizes the System to provide their address information and site photos.

[0104] "Address Information" means data indicating a geographic location provided by a user for the purpose of conducting a disaster risk assessment.

[0105] "Site photos" refer to image data provided by users that show the exterior of a building and its surroundings.

[0106] "Terminal" refers to an electronic device, such as a computer, smartphone, or tablet, that a user uses to access the system and enter and transmit data.

[0107] "Server" refers to a computer system that receives, processes, and analyzes data sent by users.

[0108] "Public database" refers to a database managed by government agencies and public institutions that provides disaster prevention information on earthquakes, floods, storm surges, etc.

[0109] "Generative AI model" refers to an artificial intelligence system that uses machine learning techniques to analyze and integrate data to assess disaster risk.

[0110] "Disaster prevention risk" refers to the possibility of disasters occurring in a particular area, such as earthquakes, floods, and storm surges, and their impacts.

[0111] A "disaster prevention risk report" refers to a report on disaster prevention risk assessments of areas and buildings and specific countermeasures, created based on the analysis results of a generative AI model.

[0112] This system uses address information and site photos provided by users, as well as public databases, to evaluate disaster prevention risks in detail and provide the results to users. This system operates in cooperation with each stakeholder (user, terminal, server).

[0113] First, users access the system's web interface, enter their address information, and then take photos of the exterior of their home and surroundings using a smartphone or digital camera and upload them to the system, providing the data the system needs for analysis.

[0114] Next, the device sends the address information and photo data entered by the user to the server using encrypted communication such as SSL / TLS, ensuring the safety of the user's personal information. Communication is performed using a POST request between the web browser and the backend server.

[0115] The server retrieves the necessary information from relevant public databases based on the received address information. For example, it uses the API of the National Research Institute for Earth Science and Disaster Resilience to obtain earthquake risk information for the specified address, and the API of the Geospatial Information Authority of Japan to collect flood risk data. This data is saved in a structured format such as JSON and used for subsequent analysis.

[0116] The server then uses a generative AI model to analyze disaster risk. It preprocesses the address information and site photos uploaded by the user and converts them into an easy-to-analyze format, such as a data frame. During preprocessing, image recognition technology (e.g., OpenCV or deep learning models) is used to analyze the building's earthquake resistance and the status of surrounding drainage facilities. The generative AI model then combines the results of this analysis with information obtained from public databases to perform a comprehensive risk assessment.

[0117] Based on the analysis results of the AI ​​model, the server generates a disaster risk report. This report is created in PDF or HTML format and includes specific risk assessments and countermeasures. For example, it may include information such as "earthquake risk is high," "flood risk is low," "seismic reinforcement work is recommended," and "evacuation routes need to be checked."

[0118] The completed disaster risk report is sent from the server to the user's device. The report may be sent via email or a download link may be provided. The user receives the report and reviews the detailed disaster risk assessment and recommended measures.

[0119] An example of a prompt is:

[0120] "Based on the address information provided by the user ('Nishi-Shinjuku, Shinjuku-ku, Tokyo') and site photos, please use public databases to assess disaster prevention risks. Assessment items include earthquake risk, flood risk, and storm surge risk. Please also include specific measures to address each risk."

[0121] In this way, it is possible to utilize a generative AI model based on information provided by users and public data to quickly and accurately assess disaster risk and provide detailed reports.

[0122] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0123] Step 1:

[0124] User

[0125] Users access the system's web interface, enter address information, and take photos of the site (e.g., the exterior of the house and surrounding area) using a smartphone or digital camera and upload them to the system.

[0126] Input: Address information, site photo

[0127] Output: Data stored on the user's device

[0128] Step 2:

[0129] Terminal

[0130] The device sends the address information and photo data entered by the user to the server using encrypted communication such as SSL / TLS, ensuring that the user's personal information is securely protected. Communication uses a POST request between the web browser and the backend server.

[0131] Input: User-uploaded address information and photo

[0132] Output: Data sent to the server (address information, site photos)

[0133] Step 3:

[0134] server

[0135] The server retrieves the necessary information from relevant public databases based on the received address information. The server uses the API of the National Research Institute for Earth Science and Disaster Resilience to obtain earthquake risk information for the specified address, and also collects flood risk data using the API of the Geospatial Information Authority of Japan. These data are saved in JSON format.

[0136] Input: Address information

[0137] Output: Public data (earthquake risk information, flood risk data)

[0138] Step 4:

[0139] server

[0140] The server preprocesses the address information and site photos sent by the user and converts them into a data format that is easy for the generative AI model to handle. Preprocessing uses image recognition technology (e.g., OpenCV or deep learning models) to analyze the building's earthquake resistance and the status of surrounding drainage facilities. This converts the image data into a format that can be analyzed.

[0141] Input: Address information, site photo

[0142] Output: Preprocessed data (data frames, analyzable image data)

[0143] Step 5:

[0144] server

[0145] The server inputs pre-processed data and information obtained from public databases into a generative AI model to perform a comprehensive disaster risk assessment. The AI ​​model integrates this information to assess earthquake risk, flood risk, storm surge risk, etc.

[0146] Input: Preprocessed data, public data

[0147] Output: Risk assessment results (assessment of earthquake risk, flood risk, and storm surge risk)

[0148] Step 6:

[0149] server

[0150] The server generates a disaster prevention risk report based on the analysis results of the generation AI. This report is created in PDF or HTML format using a template engine (e.g., Jinja2) and includes a risk assessment and specific countermeasures.

[0151] Input: Risk assessment results

[0152] Output: Disaster risk report (PDF, HTML format)

[0153] Step 7:

[0154] server

[0155] The server sends the generated disaster risk report to the user's device, which may be sent via email or a download link may be provided.

[0156] Input: Disaster Risk Report

[0157] Output: Report sent to user (email, download link)

[0158] Step 8:

[0159] User

[0160] Users can open the disaster risk report they receive on their device and check the specific risks and recommended measures for their home and surrounding area. Based on the contents of the report, they can take specific measures, such as consulting with a specialist company to request earthquake-resistant reinforcement work.

[0161] Input: Report sent to user

[0162] Output: User action (countermeasure implementation)

[0163] (Application example 1)

[0164] 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."

[0165] In modern disaster prevention measures, it is important to thoroughly assess the specific environmental risks of individual homes and facilities and take appropriate measures. However, conventional methods make it difficult for users to grasp the detailed risks themselves, making it difficult to quickly develop appropriate disaster prevention measures. In addition, there is a lack of easy ways to obtain and analyze reliable information on risk assessments of natural disasters such as earthquakes and floods.

[0166] 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.

[0167] In this invention, the server includes: a means for a user to upload address information and site photos; a means for the server to acquire information from public databases necessary for risk assessment of the address; a means for the server to analyze disaster prevention risks using a generation AI based on the address information, site photos, and public database information; a means for the server to generate a disaster prevention risk report from the analysis results; a means for the server to send the generated disaster prevention risk report to the user's terminal; and a means for a smartphone application to notify the user of the disaster prevention risk report and present the risk assessment results and recommended measures. This allows the user to easily obtain detailed risk assessment results and quickly take appropriate disaster prevention measures.

[0168] "User" refers to an individual or company that uses the disaster prevention risk assessment system.

[0169] "Address information" is data on the address or location that a user inputs to indicate a specific location such as a home or facility.

[0170] "Site photos" are image data uploaded by users of the building and its surroundings that are the subject of risk assessment.

[0171] "Server" means a computer system that receives information from users and retrieves and analyzes data in conjunction with public databases.

[0172] "Public databases" are collections of highly reliable information related to disaster risk provided by government agencies and local governments.

[0173] "Generative AI" is an artificial intelligence model that automatically analyzes disaster prevention risks based on address information provided by users, site photos, and data from public databases.

[0174] "Disaster prevention risks" are dangers related to natural disasters such as earthquakes, floods, and storm surges.

[0175] A "disaster prevention risk report" is a document that summarizes individual risk assessments and countermeasures, created based on the results of analysis by the generating AI.

[0176] "User's device" refers to an electronic device such as a smartphone or computer that a user uses to receive and view disaster prevention risk reports.

[0177] A "smartphone application" is software that users install on their smartphones to access the disaster prevention risk assessment system.

[0178] "Notification" is a function in which the smartphone application informs the user of disaster risk assessment results and countermeasures.

[0179] The "risk assessment results" are detailed information on disaster prevention risks analyzed by the generating AI.

[0180] "Recommended measures" are proposals for specific disaster prevention measures that users should take based on the risk assessment results.

[0181] The present invention provides a system for evaluating disaster prevention risks in detail using address information and site photos provided by a user, as well as public databases, and providing the results to the user. This system is specifically implemented as follows.

[0182] 1. Obtaining user information

[0183] First, users access the system through a smartphone application and upload their address and photos of the site from their device. For example, a user enters an address such as "Nishi-Shinjuku, Shinjuku-ku, Tokyo," takes and uploads multiple photos showing the exterior of the house and the surrounding area. The application transmits the data using encryption protocols such as SSL / TLS.

[0184] 2. Uploading data

[0185] The device sends the address information and site photos entered by the user to the server, which then aggregates data related to the user's address and surrounding environment at the center.

[0186] 3. Acquisition of information from public databases

[0187] The server retrieves the necessary information from public disaster prevention databases based on the received address information. For example, earthquake risk information for the specified address is retrieved through a disaster prevention API, as well as data on flood risk and storm surge risk. This includes hazard maps and meteorological data provided by national and local governments.

[0188] 4. Analysis and integration with generative AI

[0189] The server preprocesses the address information and site photos sent by the user and converts them into a data format that the AI ​​model can easily handle. The generative AI model uses this data and information obtained from public databases to analyze disaster prevention risks. For example, the generative AI analyzes that the address provided by the server is in an earthquake-prone area and is near a river that is prone to flooding, and performs a risk assessment based on that information.

[0190] 5. Generation and distribution of disaster risk reports

[0191] The server creates a disaster risk report based on the analysis results of the generation AI. The report includes risk assessments for earthquakes, floods, and storm surges, as well as specific countermeasures for each risk. For example, it may include recommendations such as "Seismic reinforcement work on buildings is recommended" or "Evacuation routes must be checked." The report is provided in a format that users can easily view, such as PDF or HTML, and is notified to the user via a smartphone application.

[0192] 6. Viewing the report

[0193] Users can check the disaster risk report on their smartphone application to understand the specific risks and recommended measures for their home and surrounding area. For example, users can consult with a specialist based on the contents of the report and request earthquake-resistance reinforcement work.

[0194] Specific examples

[0195] For example, if a user uploads "Nishi-Shinjuku, Shinjuku-ku, Tokyo" as their address and images of the exterior of their home and surrounding area as site photos, the server will obtain earthquake risk information through a disaster prevention-related API based on that address, and also collect flood risk data using the Geospatial Information Authority of Japan's API. Furthermore, if the generation AI analyzes the photo data and determines that the building has poor earthquake resistance, the server will assess it as having a "high earthquake risk" or "low flood risk," and generate a disaster prevention risk report with specific countermeasures, such as "seismic reinforcement work is recommended" or "evacuation routes must be confirmed." Based on this report, users can take specific disaster prevention measures.

[0196] Prompt Sentence Examples

[0197] Please conduct a detailed disaster risk assessment based on the address and photo information below. In your results, please include specific risks and countermeasures.

[0198] Address: Nishi-Shinjuku, Shinjuku-ku, Tokyo

[0199] Photo information: Base64 encoded image data

[0200] Please assess earthquake risks, flood risks, storm surge risks, etc., and include proposals for countermeasures for each.

[0201] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0202] Step 1:

[0203] User uploads address information and site photos.

[0204] How it works: A user launches the smartphone application and accesses the system. The user enters the address of their home or facility, takes photos of the site (exterior and surrounding area images), and uploads them.

[0205] Input: User-entered address information and site photos taken.

[0206] Output: Encrypted address information and scene photo data.

[0207] Step 2:

[0208] The terminal transmits the address information and photo acquired from the user to the server.

[0209] How it works: The device securely transmits address information and site photo data to the server using encryption protocols such as SSL / TLS.

[0210] Input: Encrypted address information and scene photo data.

[0211] Output: Address information and site photo data received by the server.

[0212] Step 3:

[0213] The server retrieves the information required for risk assessment from public databases.

[0214] Operation: Based on the received address information, the server retrieves the necessary data from public disaster prevention databases (e.g., earthquake risk information API, hazard maps, etc.).

[0215] Input: Address information.

[0216] Output: Risk-related data obtained from public databases.

[0217] Step 4:

[0218] The server analyzes disaster prevention risks using generated AI based on address information, site photos, and public database information.

[0219] How it works: As a preprocessing step, the server converts on-site photos into a data format suitable for the AI ​​model. The generative AI model analyzes address information, risk data from public databases, and on-site photos to assess specific disaster prevention risks, such as earthquake risk, flood risk, and storm surge risk.

[0220] Input: Address information, official data, pre-processed site photos.

[0221] Output: Disaster risk assessment results.

[0222] Step 5:

[0223] The server generates a disaster risk report and sends it to the user's terminal.

[0224] How it works: Based on the analysis results of the generation AI, the server creates a disaster risk report. The report includes a risk assessment and specific countermeasures (e.g., recommended seismic reinforcement work, confirmation of evacuation routes). The server generates this report in PDF or HTML format and sends it to the user's device.

[0225] Input: Disaster risk assessment results.

[0226] Output: Disaster risk report.

[0227] Step 6:

[0228] The smartphone application notifies users of disaster risk reports and presents risk assessment results and recommended countermeasures.

[0229] How it works: The smartphone application notifies the user when a report arrives. When the user opens the report, the application displays specific risk assessment results and recommended measures. The user can then take specific disaster prevention measures based on this information.

[0230] Input: Disaster Risk Report.

[0231] Output: Risk assessment results and recommended measures communicated to the user.

[0232] 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.

[0233] The present invention is a system that uses address information and site photos provided by the user, as well as public databases, to perform a detailed disaster risk assessment and provide the results to the user. One feature of the present invention is that it incorporates an emotion engine that recognizes the user's emotions. This system is specifically implemented as follows.

[0234] Obtaining user information

[0235] User

[0236] First, users log in to the system and upload photos of their address and the site from their terminal. For example, they enter the address of "Nishi-Shinjuku, Shinjuku-ku, Tokyo," take and upload multiple photos showing the exterior of the house and the surrounding area.

[0237] Uploading data

[0238] Terminal

[0239] The device organizes the entered address information and photo data and sends them to the server. The address information is sent in text format, and the photo data is sent in image file format.

[0240] Obtaining information from public databases

[0241] server

[0242] Based on the address information received by the server, the API of the relevant public database is called to obtain the necessary information. For example, earthquake risk data is obtained from the API of the National Research Institute for Earth Science and Disaster Prevention, and flood risk data is obtained from the API of the Geospatial Information Authority of Japan.

[0243] Risk data for floods, storm surges, etc. will also be obtained, including hazard maps and meteorological data provided by national and local governments.

[0244] Analysis and synthesis with generative AI

[0245] server

[0246] The server preprocesses the address information and site photos sent by the user and converts them into a format that the AI ​​model can analyze, for example, adjusting the resolution of the photos and extracting key building features (such as earthquake resistance and drainage facilities).

[0247] The AI ​​model uses information obtained from public databases and pre-processed photo data for analysis. The generative AI analyzes the building's earthquake resistance and the status of surrounding drainage facilities to identify and assess risks.

[0248] For example, the generating AI analyzes that the address provided by the server is in an earthquake-prone area and that there are rivers nearby that are prone to flooding, and then performs a risk assessment based on that.

[0249] Recognizing user emotions with an emotion engine

[0250] server

[0251] The server uses an emotion engine to recognize the user's emotional state based on the photos uploaded by the user and the voice data provided by the user. The emotion engine reads facial expressions from the photos and analyzes tone and vocabulary from the voice data.

[0252] Generate and adjust disaster risk reports

[0253] server

[0254] The server then creates a disaster risk report based on the analysis results of the AI. The report includes risk assessments for earthquakes, floods, storm surges, etc., along with specific countermeasures for each risk. For example, the report may include recommendations such as "Seismic reinforcement work on buildings is recommended" or "Evacuation routes must be checked."

[0255] The emotion engine recognizes the user's emotional state and adjusts the content and tone of the report based on that. For example, if the user is feeling anxious, the report will be more friendly and emphasize specific disaster prevention measures.

[0256] Report distribution

[0257] server

[0258] The server sends the generated disaster risk report to the user's device. The report is provided in a format that users can easily view, such as PDF or HTML.

[0259] Viewing the report

[0260] User

[0261] Users can receive and view disaster risk reports on their devices. Based on the reports, they can take specific disaster prevention measures. For example, they can consult with a specialist to request earthquake-resistance reinforcement work or create an evacuation plan.

[0262] Specific examples

[0263] For example, suppose a user uploads "Nishi-Shinjuku, Shinjuku-ku, Tokyo" as their address and images of the house's exterior and surrounding area as site photos. Based on that address, the server obtains earthquake risk information through the API of the National Research Institute for Earth Science and Disaster Prevention, and also collects flood risk data using the API of the Geospatial Information Authority of Japan. Furthermore, if the generation AI analyzes the photo data and determines that the building has poor earthquake resistance, the server will assess it as having a "high earthquake risk" or "low flood risk," and generate a disaster prevention risk report with specific countermeasures, such as "seismic reinforcement work is recommended" or "evacuation routes should be confirmed." If the emotion engine detects the user's anxiety, it will adjust the tone of the report accordingly. Based on this report, the user can take specific disaster prevention measures.

[0264] This invention allows users to understand the specific disaster prevention risks at home or on-site in detail and take appropriate disaster prevention measures. By utilizing generative AI, it is possible to integrate public data and individual on-site data to provide highly accurate risk assessments, enabling faster and more accurate countermeasure planning than conventional methods. Furthermore, by utilizing an emotion engine, it is possible to respond flexibly by taking into account the user's emotional state, thereby reducing the user's psychological burden.

[0265] The processing flow will be explained below.

[0266] Step 1:

[0267] User

[0268] The user logs into the system, enters address information and site photos, and uploads them. For example, they enter an address in Nishi-Shinjuku, Shinjuku-ku, Tokyo, and select photos of the exterior of the house and its surroundings. If the user chooses, they can also record and upload a voice message.

[0269] Step 2:

[0270] Terminal

[0271] The terminal organizes the entered address information, photo data, and voice message, and sends them to the server. The address information is sent in text format, the photo data in image file format, and the voice message in voice file format.

[0272] Step 3:

[0273] server

[0274] Based on the address information received by the server, the API of the relevant public database is called to obtain the necessary information. For example, earthquake risk data is obtained from the API of the National Research Institute for Earth Science and Disaster Prevention, and flood risk data is obtained from the API of the Geospatial Information Authority of Japan. Data on storm surge risk is also obtained in the same way.

[0275] Step 4:

[0276] server

[0277] The server stores the public database information it has acquired in an internal database and prepares it for analysis. It also organizes and stores various risk data in association with address information.

[0278] Step 5:

[0279] server

[0280] The server preprocesses the uploaded photos and converts them into a format that can be analyzed by the generative AI, for example, adjusting the resolution of the photos and extracting key building features (such as earthquake resistance and drainage facilities).

[0281] Step 6:

[0282] server

[0283] The server provides address information, public database information, and preprocessed photo data to the generation AI, which then analyzes this input data and assesses disaster risk. For example, it assesses earthquake risk, flood risk, and storm surge risk, and then performs a risk assessment for each.

[0284] Step 7:

[0285] server

[0286] The server provides the uploaded voice messages and photo data to the emotion engine, which analyzes the user's emotions from this data and evaluates their emotional state, such as anxiety, relief, or excitement.

[0287] Step 8:

[0288] server

[0289] A disaster prevention risk report is generated based on the analysis results of the generation AI and the emotional state evaluation of the emotion engine. The report includes earthquake risk, flood risk, and storm surge risk, along with specific countermeasures. The tone and presentation of the report are adjusted according to the user's emotional state. For example, if the user is feeling anxious, the report will be adjusted to include specific and detailed countermeasures in a friendly tone.

[0290] Step 9:

[0291] server

[0292] The server sends the generated disaster risk report to the user's device. The report is provided in a format that users can easily view, such as PDF or HTML.

[0293] Step 10:

[0294] User

[0295] Users can receive and view disaster risk reports on their devices. Based on the reports, they can take specific disaster prevention measures. For example, they can consult with a specialist to request earthquake-resistance reinforcement work or create an evacuation plan. In addition, the emotion engine adjusts the tone of the information, reducing stress while receiving it.

[0296] Example 2

[0297] 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."

[0298] Conventional disaster risk assessment systems lacked sufficient functionality to integrate public databases and individual on-site data to perform risk assessments, making it difficult to provide accurate risk assessments and appropriate countermeasures to individual users. Furthermore, there was no way to communicate risk information that took into account the user's psychological state, which could cause unnecessary anxiety to users. This placed a heavy psychological burden on users when taking disaster prevention measures, making it difficult to respond quickly and accurately.

[0299] 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.

[0300] In this invention, the server includes: means for a user to upload address information and site photos; means for the server to acquire information from public databases necessary for risk assessment of the address; means for the server to analyze disaster prevention risks using a generation AI based on the address information, site photos, and public database information; means for the server to evaluate the analysis results using the generation AI and generate a disaster prevention risk report; emotion recognition means for the server to adjust the disaster prevention risk report based on the user's emotional state; and means for the server to send the generated disaster prevention risk report to the user's terminal. This allows the user to receive a detailed risk assessment that integrates public databases and individual site data, and enables the user to take appropriate disaster prevention measures while reducing psychological burden through the emotion recognition function.

[0301] "User" refers to an individual or organization that utilizes this system to provide address information and site photos and undergo a disaster risk assessment.

[0302] "Address information" is text data that indicates the location of a specific building or piece of land, and is information required to retrieve related information from public databases.

[0303] "Site photos" are photographic data provided by users that visually show the exterior of a building and its surrounding environment.

[0304] The "server" is the central computing device of this system, which receives data, analyzes and evaluates it, and generates reports.

[0305] A "public database" is a database containing disaster prevention-related information provided by national agencies or local governments, and the necessary information can be obtained through API.

[0306] "Generative AI" refers to a type of artificial intelligence model that analyzes user-provided data and information obtained from public databases to assess disaster risk.

[0307] "Disaster prevention risk" refers to the potential danger of natural disasters such as earthquakes, floods, and storm surges, and evaluates the impact on buildings and the surrounding environment.

[0308] A "disaster prevention risk report" is a document created by the server based on the analysis results of the AI, and includes an assessment of disaster prevention risks and specific countermeasures.

[0309] "Emotion recognition means" refers to devices or software that analyze and recognize a user's emotional state, and has the ability to read facial expressions from photographs and analyze voice tone and vocabulary from audio data.

[0310] "Terminal" means an electronic device that allows a user to input and upload address information and site photos and communicate with the server.

[0311] "Preprocessing" is the process of converting user-provided site photos and other data into an analyzable format, which is used to improve the accuracy of the analysis.

[0312] The present invention is a system that uses address information and site photos provided by the user, as well as public databases, to perform a detailed assessment of disaster prevention risks and provide the results to the user. A feature of the present invention is that it recognizes the user's emotions and reflects them in the presentation of the assessment results. Specific embodiments for implementing the present invention are described below.

[0313] This system mainly uses the following hardware and software:

[0314] User devices (smartphones, tablets, PCs, etc.)

[0315] server

[0316] Generative AI models for image analysis

[0317] Emotion Recognition Engine

[0318] User operations

[0319] First, a user logs in to the system, enters their address and photos of the site on their terminal, and uploads them. For example, a user enters the address "Nishi-Shinjuku, Shinjuku-ku, Tokyo," takes multiple photos showing the exterior of the house and the surrounding area, and uploads them to the system. At this time, the address information is entered in text format, and the photo data is entered in image file format.

[0320] Sending data

[0321] The device organizes the entered address information and photo data and sends them to the server. Specifically, the address data is stored in the "address text field," and the photo data is saved in the "photo folder" before being transferred to the server.

[0322] Obtaining information from public databases

[0323] Based on the received address information, the server calls the API of public databases to obtain the necessary disaster prevention information. For example, earthquake risk data is obtained from the API of the National Research Institute for Earth Science and Disaster Prevention, and flood risk data is obtained using the API of the Geospatial Information Authority of Japan. In addition, other risk data such as high tides is also obtained in the same way.

[0324] Data preprocessing and analysis using generative AI models

[0325] The server preprocesses the address information and site photos sent by the user and converts them into a format that the AI ​​model can analyze. The resolution of the photo data is standardized, and key features such as the building's earthquake resistance and drainage facilities are extracted using image analysis technology. The generative AI model identifies and evaluates disaster prevention risks based on the preprocessed data and acquired public data. For example, it makes risk assessments such as "the building has poor earthquake resistance" or "there is a river nearby that is prone to flooding."

[0326] Understanding the user's emotional state through emotion recognition

[0327] The server inputs the photos uploaded by the user and the voice data provided into an emotion engine to recognize the user's emotional state. By reading facial expressions from the photos and analyzing the tone of voice and vocabulary from the voice data, it determines whether the user is feeling "anxiety" or "relief."

[0328] Generate and adjust disaster risk reports

[0329] The server creates a disaster risk report based on the analysis results of the generation AI and the user's emotional state. The report includes an assessment of each risk (e.g., earthquake, flood, storm surge) and specific countermeasures. For example, it may include, "Due to the high earthquake risk, seismic reinforcement work on buildings is recommended," or "Due to the low flood risk, no special countermeasures are necessary." If the user feels anxious, the report's language is softer and uses reassuring language. For example, it may include phrases such as, "There's no need to worry, but just to be safe, check your evacuation routes."

[0330] Report distribution

[0331] The server sends the generated disaster risk report to the user's device. The report is provided in a format that the user can easily view, such as PDF or HTML. For example, it can be sent as an email attachment or a link that the user can download after logging in.

[0332] View reports and take action

[0333] Users can receive disaster risk reports on their devices and review the details. They can open the PDF file to read the risk assessment and recommended measures. Based on the report, they can hire a specialist to carry out earthquake-resistance reinforcement work or create an evacuation plan with their family.

[0334] For example, if a user uploads an address in "Nishi-Shinjuku, Shinjuku-ku, Tokyo" and photos of the exterior and surrounding area of ​​the house, the server will retrieve earthquake risk information and flood risk data from a public database based on that address. If the server analyzes the photo data and determines that the building is not earthquake-resistant, it will report the results as "high earthquake risk" or "low flood risk," along with specific measures such as "recommended earthquake reinforcement work" and "need to check evacuation routes." If the emotion engine detects the user's anxiety, it will use expressions that alleviate that anxiety. Based on this report, the user can take specific disaster prevention measures.

[0335] This system allows users to gain a detailed understanding of disaster prevention risks in their living environment and take appropriate measures. By using generative AI and emotion recognition functions, it is possible to provide quick and accurate risk assessments and psychologically considerate advice.

[0336] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0337] Step 1:

[0338] User

[0339] A user logs in to the system, enters address information and site photos from a terminal, and uploads them. The input data is address information (e.g., "Nishi-Shinjuku, Shinjuku-ku, Tokyo") and multiple site photos. This allows the system to obtain the initial data it needs.

[0340] Step 2:

[0341] Terminal

[0342] The terminal organizes the entered address information and photo data and sends them to the server. The address information is saved in text format, and the photo data is saved in image file format. The server converts this data into a format that can be received and sends it. The output data is the address information in text format and the photo data in image file format, which are sent to the server.

[0343] Step 3:

[0344] server

[0345] Based on the address information received by the server, the API of a public database is called to obtain the necessary disaster prevention information. The input data is address information, and risk data obtained through the API (e.g., earthquake risk data, flood risk data) is output. Specifically, risk information is obtained from the APIs of the National Research Institute for Earth Science and Disaster Prevention and the Geospatial Information Authority of Japan.

[0346] Step 4:

[0347] server

[0348] The server preprocesses the address information and site photos sent by the user and converts them into a format that can be analyzed by the generative AI model. Specific preprocessing operations include standardizing the resolution of the photo data and extracting key features (e.g., earthquake resistance, drainage facilities). The input data is the photo data, and the output data is preprocessed data in an analyzable format.

[0349] Step 5:

[0350] server

[0351] The generative AI model identifies and assesses disaster prevention risks based on preprocessed data and information obtained from public databases. The input data is preprocessed photo data and acquired risk data, and the output data is the risk assessment results. The generative AI model analyzes the earthquake resistance and flood risk of buildings, and identifies specific disaster prevention risks.

[0352] Step 6:

[0353] server

[0354] The server inputs photos uploaded by the user and voice data provided by the user into the emotion engine to recognize the user's emotional state. The input data is photo data and voice data, and the output data is the emotion recognition results. The emotion engine analyzes facial expressions and tone of voice to identify the user's emotion (e.g., anxiety, relief).

[0355] Step 7:

[0356] server

[0357] The server generates a disaster risk report based on the AI's analysis results and emotion recognition results, and adjusts it based on the user's emotional state. The input data are the risk assessment results and emotion recognition results, and the output data is an adjusted disaster risk report. Specific measures (e.g., recommending earthquake-resistant reinforcement work, checking evacuation routes) are included, and the report is created in a format that matches the user's psychological state.

[0358] Step 8:

[0359] server

[0360] The server sends the generated disaster risk report to the user's device. The input data is the disaster risk report, and the output data is the report sent to the user's device. The report is provided in PDF or HTML format.

[0361] Step 9:

[0362] User

[0363] The user receives the disaster prevention risk report on their device and checks the details. The input data is the received disaster prevention risk report, and the output data is the disaster prevention risk information and countermeasures that the user understands. The user takes specific disaster prevention measures based on the report (e.g., requesting earthquake-resistance reinforcement work by a specialist company, drawing up an evacuation plan).

[0364] (Application example 2)

[0365] 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."

[0366] Conventional disaster risk assessment systems are limited to risk assessments using user address information and public data, and lack the ability to analyze on-site photos or take into account the user's emotions. Furthermore, when creating disaster risk reports, adjustments are not made to reflect the user's emotional state, resulting in insufficient feedback to the user. Furthermore, simply displaying risks does not provide specific advice on what measures the user should take, making the systems ineffective.

[0367] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0368] In this invention, the server includes a means for uploading a user's address information and site photos, a means for acquiring information necessary for risk assessment from a public database, a means for recognizing the user's emotional state using an emotion engine, and a means for generating a disaster risk report and adjusting the content and tone based on the analysis results and the user's emotional state. This enables detailed risk assessment and countermeasure suggestions tailored to the user's specific emotional state. It also enables the provision of more specific and feasible disaster prevention measures while reducing the user's anxiety.

[0369] "User information" refers to address information and site photo data provided by the user.

[0370] "Public databases" are databases containing information on disaster prevention risks provided by local governments and national agencies.

[0371] "Generative AI" is a system that uses artificial intelligence technology to analyze disaster prevention risks.

[0372] The "Emotion Engine" is a system that analyzes a user's emotional state from their photo and voice data.

[0373] A "disaster prevention risk report" is a report provided to a user that includes analysis results and proposed countermeasures.

[0374] "Preprocessing of on-site photos" is the process of converting uploaded photos into a format that is easy to analyze.

[0375] "Earthquake risk" is a risk that evaluates whether the user's location is susceptible to the effects of earthquakes.

[0376] "Flood Risk" is a risk assessment of whether the user's location is susceptible to flooding.

[0377] "Storm surge risk" is a risk that evaluates whether the user's location is susceptible to the effects of a storm surge.

[0378] System configuration

[0379] This invention is a system that evaluates disaster prevention risks in detail using address information and site photos provided by the user, as well as data obtained from public databases, and provides the results to the user.Furthermore, it is characterized by combining an emotion engine to respond according to the user's emotional state.

[0380] Obtaining user information

[0381] First, a user logs into the system and uploads their address and photos of the location from their device. For example, a user enters the address "Nishi-Shinjuku, Shinjuku-ku, Tokyo," takes and uploads several photos showing the exterior of the house and the surrounding area. The device organizes the entered address information and photo data and sends them to the server. The address information is sent in text format, and the photo data is sent as an image file.

[0382] Obtaining information from public databases

[0383] Based on the address information received by the server, the API of the relevant public database is called to obtain the necessary information. For example, earthquake risk data is obtained from the API of a public institution, and flood risk data is obtained from the API of a local government. Risk data for floods, storm surges, etc. is also obtained in the same way. This includes hazard maps and weather data provided by national and local agencies.

[0384] Analysis and synthesis with generative AI

[0385] The server preprocesses the address information and site photos sent by the user and converts them into a format that the AI ​​model can analyze. For example, it adjusts the resolution of the photos and extracts the building's key features (earthquake resistance, drainage facilities, etc.). The generation AI performs analysis using information obtained from public databases and the preprocessed photo data. The AI ​​model analyzes the building's earthquake resistance and the surrounding drainage facilities, and identifies and assesses risks. For example, the generation AI analyzes that the address provided by the server is in an earthquake-prone area and there are rivers nearby that are prone to flooding, and performs a risk assessment based on that information.

[0386] Recognizing user emotions with an emotion engine

[0387] The server uses an emotion engine to recognize the user's emotional state based on the photos uploaded by the user and the voice data provided by the user. The emotion engine reads facial expressions from the photos and analyzes tone and vocabulary from the voice data.

[0388] Generate and adjust disaster risk reports

[0389] The server creates a disaster risk report based on the analysis results of the generation AI. The report includes risk assessments for earthquakes, floods, storm surges, etc., along with specific countermeasures for each risk. For example, "Seismic reinforcement work on buildings is recommended" or "Evacuation routes must be checked." The emotion engine adjusts the content and tone of the report based on the user's emotional state. For example, if the user is feeling anxious, the report's language will be more friendly and specific disaster prevention measures will be emphasized.

[0390] Report distribution

[0391] The server sends the generated disaster risk report to the user's device. The report is provided in a format that users can easily view, such as PDF or HTML. Based on this report, users can take specific disaster prevention measures. For example, they can consult with a specialist to request earthquake-resistance reinforcement work or create an evacuation plan.

[0392] Specific examples

[0393] For example, suppose a user uploads "Nishi-Shinjuku, Shinjuku-ku, Tokyo" as their address and images of the house's exterior and surrounding area as site photos. The server obtains earthquake risk information through a public institution's API based on the address, and also collects flood risk data using a local government's API. If the generation AI analyzes the photo data and determines that the building has poor earthquake resistance, the server will evaluate it as having a "high earthquake risk" or "low flood risk," and generate a disaster prevention risk report with specific countermeasures such as "seismic reinforcement work is recommended" and "evacuation routes must be confirmed." If the emotion engine detects the user's anxiety, it will adjust the tone of the report accordingly. The user can then take specific disaster prevention measures based on this report.

[0394] Prompt Sentence Examples

[0395] User: "I want to use a disaster risk assessment app. First, I need to upload my home address and a photo."

[0396] App: "Address and photo upload complete. Disaster risk analysis is currently underway."

[0397] App: "The results are in. The earthquake risk is high. We recommend earthquake-resistance reinforcement work. We also recommend checking evacuation routes."

[0398] User: "Okay, thank you. That puts my mind at ease."

[0399] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0400] Step 1:

[0401] The user uploads address information and site photos from the terminal.

[0402] Input: Address information (text format), site photo (image file format)

[0403] Output: Organized information (address information and photo data)

[0404] What happens: A user launches the app, logs in, enters address information, and takes or selects and uploads a site photo.

[0405] Step 2:

[0406] The terminal transmits the entered address information and photo data to the server.

[0407] Input: Organized address information and photo data

[0408] Output: Data sent to the server

[0409] Specific operation: The device transfers address information and photo data in text and image file format to the server and confirms receipt of the data.

[0410] Step 3:

[0411] Based on the address information received by the server, the API of a public database is called to obtain the necessary information.

[0412] Input: User's address information

[0413] Output: Risk data obtained from public databases (earthquake risk, flood risk, storm surge risk, etc.)

[0414] Specific operation: The server requests risk data based on address information from each public database (API of national agencies and local governments), and stores and organizes the obtained data.

[0415] Step 4:

[0416] The server preprocesses the received address information and site photos and provides input data for the generative AI model.

[0417] Input: User address information, risk data from public databases, scene photos

[0418] Output: Data in a format suitable for generative AI models

[0419] Specific operation: The server adjusts the resolution of the photo, extracts necessary features (such as the building's earthquake resistance and drainage facilities), and creates data to be input into the generative AI model.

[0420] Step 5:

[0421] Using a generative AI model, disaster prevention risks are analyzed based on the user's address information, site photos, and public database information.

[0422] Input: Data in a format suitable for generative AI models

[0423] Output: Detailed disaster risk assessment results (earthquake risk, flood risk, storm surge risk, etc.)

[0424] How it works: The generative AI model analyzes addresses in earthquake-prone areas and the presence of rivers prone to flooding, and performs risk assessments.

[0425] Step 6:

[0426] The server uses an emotion engine to recognize the user's emotional state.

[0427] Input: User-uploaded photos and audio data

[0428] Output: User's emotional state (anxious, relieved, etc.)

[0429] Specific operation: The server analyzes the user's facial expressions from photos and analyzes tone and vocabulary from audio data to recognize their emotional state.

[0430] Step 7:

[0431] The server generates a disaster risk report based on the analysis results of the generation AI and the user's emotional state, and adjusts the content and tone.

[0432] Input: Disaster risk assessment results, user's emotional state

[0433] Output: Adjusted disaster risk report

[0434] Specific actions: The server describes specific countermeasures for each risk based on the risk assessment results, and changes the content and tone of the report depending on the user's emotional state.

[0435] Step 8:

[0436] The server transmits the generated disaster risk report to the user's terminal.

[0437] Input: Adjusted Disaster Risk Report

[0438] Output: Report sent to the user's device

[0439] Specific operation: The server generates a risk report in PDF or HTML format and sends it to the user's device.

[0440] 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.

[0441] 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.

[0442] 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.

[0443] [Second embodiment]

[0444] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0445] 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.

[0446] 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).

[0447] 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.

[0448] 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.

[0449] 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).

[0450] 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.

[0451] 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.

[0452] 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.

[0453] 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.

[0454] 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.

[0455] 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."

[0456] The present invention provides a system for evaluating disaster prevention risks in detail using address information and site photos provided by a user, as well as public databases, and providing the results to the user. This system is specifically implemented as follows.

[0457] Obtaining user information

[0458] User

[0459] First, a user accesses the system and uploads photos of their address and the site from their terminal. For example, a user enters an address in Nishi-Shinjuku, Shinjuku-ku, Tokyo, and takes and uploads multiple photos showing the exterior of the house and the surrounding area.

[0460] Uploading data

[0461] Terminal

[0462] The device sends the address information and photo entered by the user to the server. For security reasons, it is recommended to use encrypted communication such as SSL / TLS.

[0463] Obtaining information from public databases

[0464] server

[0465] The server retrieves necessary information from relevant public databases based on the received address information, such as earthquake risk information for the specified address via a disaster prevention API.

[0466] Risk data for floods, storm surges, etc. will also be obtained, including hazard maps and meteorological data provided by national and local governments.

[0467] Analysis and synthesis with generative AI

[0468] server

[0469] The server preprocesses the address information and site photos sent by the user and converts them into a data format that is easy for the AI ​​model to handle.

[0470] The AI ​​model uses information obtained from public databases and pre-processed photo data for analysis. The generative AI analyzes the building's earthquake resistance and the status of surrounding drainage facilities to identify and assess risks.

[0471] For example, the generating AI analyzes that the address provided by the server is in an earthquake-prone area and that there are rivers nearby that are prone to flooding, and then performs a risk assessment based on that.

[0472] Generate disaster risk reports

[0473] server

[0474] The server then creates a disaster risk report based on the analysis results of the AI. The report includes risk assessments for earthquakes, floods, storm surges, etc., along with specific countermeasures for each risk. For example, the report may include recommendations such as "Seismic reinforcement work on buildings is recommended" or "Evacuation routes must be checked."

[0475] Report distribution

[0476] server

[0477] The server sends the generated disaster risk report to the user's device in a format that is easy for the user to view, such as PDF or HTML.

[0478] Viewing the report

[0479] User

[0480] Users can check the disaster risk report received on their device and understand the specific risks and recommended measures for their home and surrounding area. For example, based on the contents of the report, users can consult with a specialist company and request earthquake-resistance reinforcement work.

[0481] Specific examples

[0482] For example, suppose a user uploads "Nishi-Shinjuku, Shinjuku-ku, Tokyo" as their address information and images of the exterior of their house and surrounding area as site photos. Based on that address, the server obtains earthquake risk information through the API of the National Research Institute for Earth Science and Disaster Prevention, and also collects flood risk data using the API of the Geospatial Information Authority of Japan. Furthermore, if the generation AI analyzes the photo data and determines that the building has poor earthquake resistance, the server will evaluate it as "high earthquake risk" or "low flood risk," and generate a disaster prevention risk report with specific countermeasures such as "seismic reinforcement work is recommended" and "evacuation routes need to be confirmed." Based on this report, users can take specific disaster prevention measures.

[0483] This invention allows users to understand the specific disaster prevention risks at home or on-site in detail and take appropriate disaster prevention measures. By utilizing generative AI, it is possible to integrate public data and individual on-site data to provide highly accurate risk assessments, making it possible to plan countermeasures more quickly and accurately than conventional methods.

[0484] The processing flow will be explained below.

[0485] Step 1:

[0486] User

[0487] The user logs in to the system, enters address information and site photos, and uploads them. For example, they enter the address of "Nishi-Shinjuku, Shinjuku-ku, Tokyo," and select photos of the exterior of the house and its surroundings.

[0488] Step 2:

[0489] Terminal

[0490] The device organizes the entered address information and photo data and sends them to the server. The address information is sent in text format, and the photo data is sent in image file format.

[0491] Step 3:

[0492] server

[0493] Based on the address information received by the server, the API of the relevant public database is called to obtain the necessary information. For example, earthquake risk data is obtained from the API of the National Research Institute for Earth Science and Disaster Prevention, and flood risk data is obtained from the API of the Geospatial Information Authority of Japan.

[0494] Step 4:

[0495] server

[0496] The server stores the public database information it has acquired in an internal database and prepares it for analysis. It also organizes and stores various risk data in association with address information.

[0497] Step 5:

[0498] server

[0499] The server preprocesses the uploaded photos and converts them into a format that can be analyzed by the generative AI, for example, adjusting the resolution of the photos and extracting key building features (such as earthquake resistance and drainage facilities).

[0500] Step 6:

[0501] server

[0502] The server provides address information, public database information, and preprocessed photo data to the generation AI, which then analyzes this input data and assesses disaster risk.

[0503] Step 7:

[0504] server

[0505] Based on the analysis results of the generation AI, the server generates a disaster prevention risk report, which includes earthquake risk, flood risk, and storm surge risk, along with recommended countermeasures.

[0506] Step 8:

[0507] server

[0508] The server sends the generated disaster risk report to the user's device. The report is provided in a format that users can easily view, such as PDF or HTML.

[0509] Step 9:

[0510] User

[0511] Users can receive and view disaster risk reports on their devices. Based on the reports, they can take specific disaster prevention measures. For example, they can consider earthquake-resistance reinforcement work or check evacuation routes.

[0512] Example 1

[0513] 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."

[0514] In disaster risk assessment, there is a need for a method that can efficiently and accurately integrate user-provided on-site information with public data to quickly and specifically assess individual risks. However, current systems only refer to public databases and are unable to properly utilize user-provided on-site information. Furthermore, manual data analysis is required, making it difficult to perform rapid risk assessment.

[0515] 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.

[0516] In this invention, the server includes means for a user to upload address information and site photos, means for a terminal to send the address information and photos entered by the user to the server, means for the server to acquire information from a public database necessary for risk assessment of the address, means for the server to analyze disaster prevention risk using a generative AI model based on the address information, site photos, and public database information, means for the server to generate a disaster prevention risk report from the analysis results, and means for the server to send the generated disaster prevention risk report to the user's terminal. This enables highly accurate disaster prevention risk assessment that integrates user-provided site information and public data.

[0517] "User" refers to any person or entity that utilizes the System to provide their address information and site photos.

[0518] "Address Information" means data indicating a geographic location provided by a user for the purpose of conducting a disaster risk assessment.

[0519] "Site photos" refer to image data provided by users that show the exterior of a building and its surroundings.

[0520] "Terminal" refers to an electronic device, such as a computer, smartphone, or tablet, that a user uses to access the system and enter and transmit data.

[0521] "Server" refers to a computer system that receives, processes, and analyzes data sent by users.

[0522] "Public database" refers to a database managed by government agencies and public institutions that provides disaster prevention information on earthquakes, floods, storm surges, etc.

[0523] "Generative AI model" refers to an artificial intelligence system that uses machine learning techniques to analyze and integrate data to assess disaster risk.

[0524] "Disaster prevention risk" refers to the possibility of disasters occurring in a particular area, such as earthquakes, floods, and storm surges, and their impacts.

[0525] A "disaster prevention risk report" refers to a report on disaster prevention risk assessments of areas and buildings and specific countermeasures, created based on the analysis results of a generative AI model.

[0526] This system uses address information and site photos provided by users, as well as public databases, to evaluate disaster prevention risks in detail and provide the results to users. This system operates in cooperation with each stakeholder (user, terminal, server).

[0527] First, users access the system's web interface, enter their address information, and then take photos of the exterior of their home and surroundings using a smartphone or digital camera and upload them to the system, providing the data the system needs for analysis.

[0528] Next, the device sends the address information and photo data entered by the user to the server using encrypted communication such as SSL / TLS, ensuring the safety of the user's personal information. Communication is performed using a POST request between the web browser and the backend server.

[0529] The server retrieves the necessary information from relevant public databases based on the received address information. For example, it uses the API of the National Research Institute for Earth Science and Disaster Resilience to obtain earthquake risk information for the specified address, and the API of the Geospatial Information Authority of Japan to collect flood risk data. This data is saved in a structured format such as JSON and used for subsequent analysis.

[0530] The server then uses a generative AI model to analyze disaster risk. It preprocesses the address information and site photos uploaded by the user and converts them into an easy-to-analyze format, such as a data frame. During preprocessing, image recognition technology (e.g., OpenCV or deep learning models) is used to analyze the building's earthquake resistance and the status of surrounding drainage facilities. The generative AI model then combines the results of this analysis with information obtained from public databases to perform a comprehensive risk assessment.

[0531] Based on the analysis results of the AI ​​model, the server generates a disaster risk report. This report is created in PDF or HTML format and includes specific risk assessments and countermeasures. For example, it may include information such as "earthquake risk is high," "flood risk is low," "seismic reinforcement work is recommended," and "evacuation routes need to be checked."

[0532] The completed disaster risk report is sent from the server to the user's device. The report may be sent via email or a download link may be provided. The user receives the report and reviews the detailed disaster risk assessment and recommended measures.

[0533] An example of a prompt is:

[0534] "Based on the address information provided by the user ('Nishi-Shinjuku, Shinjuku-ku, Tokyo') and site photos, please use public databases to assess disaster prevention risks. Assessment items include earthquake risk, flood risk, and storm surge risk. Please also include specific measures to address each risk."

[0535] In this way, it is possible to utilize a generative AI model based on information provided by users and public data to quickly and accurately assess disaster risk and provide detailed reports.

[0536] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0537] Step 1:

[0538] User

[0539] Users access the system's web interface, enter address information, and take photos of the site (e.g., the exterior of the house and surrounding area) using a smartphone or digital camera and upload them to the system.

[0540] Input: Address information, site photo

[0541] Output: Data stored on the user's device

[0542] Step 2:

[0543] Terminal

[0544] The device sends the address information and photo data entered by the user to the server using encrypted communication such as SSL / TLS, ensuring that the user's personal information is securely protected. Communication uses a POST request between the web browser and the backend server.

[0545] Input: User-uploaded address information and photo

[0546] Output: Data sent to the server (address information, site photos)

[0547] Step 3:

[0548] server

[0549] The server retrieves the necessary information from relevant public databases based on the received address information. The server uses the API of the National Research Institute for Earth Science and Disaster Resilience to obtain earthquake risk information for the specified address, and also collects flood risk data using the API of the Geospatial Information Authority of Japan. These data are saved in JSON format.

[0550] Input: Address information

[0551] Output: Public data (earthquake risk information, flood risk data)

[0552] Step 4:

[0553] server

[0554] The server preprocesses the address information and site photos sent by the user and converts them into a data format that is easy for the generative AI model to handle. Preprocessing uses image recognition technology (e.g., OpenCV or deep learning models) to analyze the building's earthquake resistance and the status of surrounding drainage facilities. This converts the image data into a format that can be analyzed.

[0555] Input: Address information, site photo

[0556] Output: Preprocessed data (data frames, analyzable image data)

[0557] Step 5:

[0558] server

[0559] The server inputs pre-processed data and information obtained from public databases into a generative AI model to perform a comprehensive disaster risk assessment. The AI ​​model integrates this information to assess earthquake risk, flood risk, storm surge risk, etc.

[0560] Input: Preprocessed data, public data

[0561] Output: Risk assessment results (assessment of earthquake risk, flood risk, and storm surge risk)

[0562] Step 6:

[0563] server

[0564] The server generates a disaster prevention risk report based on the analysis results of the generation AI. This report is created in PDF or HTML format using a template engine (e.g., Jinja2) and includes a risk assessment and specific countermeasures.

[0565] Input: Risk assessment results

[0566] Output: Disaster risk report (PDF, HTML format)

[0567] Step 7:

[0568] server

[0569] The server sends the generated disaster risk report to the user's device, which may be sent via email or a download link may be provided.

[0570] Input: Disaster Risk Report

[0571] Output: Report sent to user (email, download link)

[0572] Step 8:

[0573] User

[0574] Users can open the disaster risk report they receive on their device and check the specific risks and recommended measures for their home and surrounding area. Based on the contents of the report, they can take specific measures, such as consulting with a specialist company to request earthquake-resistant reinforcement work.

[0575] Input: Report sent to user

[0576] Output: User action (countermeasure implementation)

[0577] (Application example 1)

[0578] 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."

[0579] In modern disaster prevention measures, it is important to thoroughly assess the specific environmental risks of individual homes and facilities and take appropriate measures. However, conventional methods make it difficult for users to grasp the detailed risks themselves, making it difficult to quickly develop appropriate disaster prevention measures. In addition, there is a lack of easy ways to obtain and analyze reliable information on risk assessments of natural disasters such as earthquakes and floods.

[0580] 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.

[0581] In this invention, the server includes: a means for a user to upload address information and site photos; a means for the server to acquire information from public databases necessary for risk assessment of the address; a means for the server to analyze disaster prevention risks using a generation AI based on the address information, site photos, and public database information; a means for the server to generate a disaster prevention risk report from the analysis results; a means for the server to send the generated disaster prevention risk report to the user's terminal; and a means for a smartphone application to notify the user of the disaster prevention risk report and present the risk assessment results and recommended measures. This allows the user to easily obtain detailed risk assessment results and quickly take appropriate disaster prevention measures.

[0582] "User" refers to an individual or company that uses the disaster prevention risk assessment system.

[0583] "Address information" is data on the address or location that a user inputs to indicate a specific location such as a home or facility.

[0584] "Site photos" are image data uploaded by users of the building and its surroundings that are the subject of risk assessment.

[0585] "Server" means a computer system that receives information from users and retrieves and analyzes data in conjunction with public databases.

[0586] "Public databases" are collections of highly reliable information related to disaster risk provided by government agencies and local governments.

[0587] "Generative AI" is an artificial intelligence model that automatically analyzes disaster prevention risks based on address information provided by users, site photos, and data from public databases.

[0588] "Disaster prevention risks" are dangers related to natural disasters such as earthquakes, floods, and storm surges.

[0589] A "disaster prevention risk report" is a document that summarizes individual risk assessments and countermeasures, created based on the results of analysis by the generating AI.

[0590] "User's device" refers to an electronic device such as a smartphone or computer that a user uses to receive and view disaster prevention risk reports.

[0591] A "smartphone application" is software that users install on their smartphones to access the disaster prevention risk assessment system.

[0592] "Notification" is a function in which the smartphone application informs the user of disaster risk assessment results and countermeasures.

[0593] The "risk assessment results" are detailed information on disaster prevention risks analyzed by the generating AI.

[0594] "Recommended measures" are proposals for specific disaster prevention measures that users should take based on the risk assessment results.

[0595] The present invention provides a system for evaluating disaster prevention risks in detail using address information and site photos provided by a user, as well as public databases, and providing the results to the user. This system is specifically implemented as follows.

[0596] 1. Obtaining user information

[0597] First, users access the system through a smartphone application and upload their address and photos of the site from their device. For example, a user enters an address such as "Nishi-Shinjuku, Shinjuku-ku, Tokyo," takes and uploads multiple photos showing the exterior of the house and the surrounding area. The application transmits the data using encryption protocols such as SSL / TLS.

[0598] 2. Uploading data

[0599] The device sends the address information and site photos entered by the user to the server, which then aggregates data related to the user's address and surrounding environment at the center.

[0600] 3. Acquisition of information from public databases

[0601] The server retrieves the necessary information from public disaster prevention databases based on the received address information. For example, earthquake risk information for the specified address is retrieved through a disaster prevention API, as well as data on flood risk and storm surge risk. This includes hazard maps and meteorological data provided by national and local governments.

[0602] 4. Analysis and integration with generative AI

[0603] The server preprocesses the address information and site photos sent by the user and converts them into a data format that the AI ​​model can easily handle. The generative AI model uses this data and information obtained from public databases to analyze disaster prevention risks. For example, the generative AI analyzes that the address provided by the server is in an earthquake-prone area and is near a river that is prone to flooding, and performs a risk assessment based on that information.

[0604] 5. Generation and distribution of disaster risk reports

[0605] The server creates a disaster risk report based on the analysis results of the generation AI. The report includes risk assessments for earthquakes, floods, and storm surges, as well as specific countermeasures for each risk. For example, it may include recommendations such as "Seismic reinforcement work on buildings is recommended" or "Evacuation routes must be checked." The report is provided in a format that users can easily view, such as PDF or HTML, and is notified to the user via a smartphone application.

[0606] 6. Viewing the report

[0607] Users can check the disaster risk report on their smartphone application to understand the specific risks and recommended measures for their home and surrounding area. For example, users can consult with a specialist based on the contents of the report and request earthquake-resistance reinforcement work.

[0608] Specific examples

[0609] For example, if a user uploads "Nishi-Shinjuku, Shinjuku-ku, Tokyo" as their address and images of the exterior of their home and surrounding area as site photos, the server will obtain earthquake risk information through a disaster prevention-related API based on that address, and also collect flood risk data using the Geospatial Information Authority of Japan's API. Furthermore, if the generation AI analyzes the photo data and determines that the building has poor earthquake resistance, the server will assess it as having a "high earthquake risk" or "low flood risk," and generate a disaster prevention risk report with specific countermeasures, such as "seismic reinforcement work is recommended" or "evacuation routes must be confirmed." Based on this report, users can take specific disaster prevention measures.

[0610] Prompt Sentence Examples

[0611] Please conduct a detailed disaster risk assessment based on the address and photo information below. In your results, please include specific risks and countermeasures.

[0612] Address: Nishi-Shinjuku, Shinjuku-ku, Tokyo

[0613] Photo information: Base64 encoded image data

[0614] Please assess earthquake risks, flood risks, storm surge risks, etc., and include proposals for countermeasures for each.

[0615] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0616] Step 1:

[0617] User uploads address information and site photos.

[0618] How it works: A user launches the smartphone application and accesses the system. The user enters the address of their home or facility, takes photos of the site (exterior and surrounding area images), and uploads them.

[0619] Input: User-entered address information and site photos taken.

[0620] Output: Encrypted address information and scene photo data.

[0621] Step 2:

[0622] The terminal transmits the address information and photo acquired from the user to the server.

[0623] How it works: The device securely transmits address information and site photo data to the server using encryption protocols such as SSL / TLS.

[0624] Input: Encrypted address information and scene photo data.

[0625] Output: Address information and site photo data received by the server.

[0626] Step 3:

[0627] The server retrieves the information required for risk assessment from public databases.

[0628] Operation: Based on the received address information, the server retrieves the necessary data from public disaster prevention databases (e.g., earthquake risk information API, hazard maps, etc.).

[0629] Input: Address information.

[0630] Output: Risk-related data obtained from public databases.

[0631] Step 4:

[0632] The server analyzes disaster prevention risks using generated AI based on address information, site photos, and public database information.

[0633] How it works: As a preprocessing step, the server converts on-site photos into a data format suitable for the AI ​​model. The generative AI model analyzes address information, risk data from public databases, and on-site photos to assess specific disaster prevention risks, such as earthquake risk, flood risk, and storm surge risk.

[0634] Input: Address information, official data, pre-processed site photos.

[0635] Output: Disaster risk assessment results.

[0636] Step 5:

[0637] The server generates a disaster risk report and sends it to the user's terminal.

[0638] How it works: Based on the analysis results of the generation AI, the server creates a disaster risk report. The report includes a risk assessment and specific countermeasures (e.g., recommended seismic reinforcement work, confirmation of evacuation routes). The server generates this report in PDF or HTML format and sends it to the user's device.

[0639] Input: Disaster risk assessment results.

[0640] Output: Disaster risk report.

[0641] Step 6:

[0642] The smartphone application notifies users of disaster risk reports and presents risk assessment results and recommended countermeasures.

[0643] How it works: The smartphone application notifies the user when a report arrives. When the user opens the report, the application displays specific risk assessment results and recommended measures. The user can then take specific disaster prevention measures based on this information.

[0644] Input: Disaster Risk Report.

[0645] Output: Risk assessment results and recommended measures communicated to the user.

[0646] 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.

[0647] The present invention is a system that uses address information and site photos provided by the user, as well as public databases, to perform a detailed assessment of disaster prevention risks and provide the results to the user. A feature of the present invention is that it incorporates an emotion engine that recognizes the user's emotions. This system is specifically implemented as follows.

[0648] Obtaining user information

[0649] User

[0650] First, users log in to the system and upload photos of their address and the site from their terminal. For example, they enter the address of "Nishi-Shinjuku, Shinjuku-ku, Tokyo," take and upload multiple photos showing the exterior of the house and the surrounding area.

[0651] Uploading data

[0652] Terminal

[0653] The device organizes the entered address information and photo data and sends them to the server. The address information is sent in text format, and the photo data is sent in image file format.

[0654] Obtaining information from public databases

[0655] server

[0656] Based on the address information received by the server, the API of the relevant public database is called to obtain the necessary information. For example, earthquake risk data is obtained from the API of the National Research Institute for Earth Science and Disaster Prevention, and flood risk data is obtained from the API of the Geospatial Information Authority of Japan.

[0657] Risk data for floods, storm surges, etc. will also be obtained, including hazard maps and meteorological data provided by national and local governments.

[0658] Analysis and synthesis with generative AI

[0659] server

[0660] The server preprocesses the address information and site photos sent by the user and converts them into a format that the AI ​​model can analyze, for example, adjusting the resolution of the photos and extracting key building features (such as earthquake resistance and drainage facilities).

[0661] The AI ​​model uses information obtained from public databases and pre-processed photo data for analysis. The generative AI analyzes the building's earthquake resistance and the status of surrounding drainage facilities to identify and assess risks.

[0662] For example, the generating AI analyzes that the address provided by the server is in an earthquake-prone area and that there are rivers nearby that are prone to flooding, and then performs a risk assessment based on that.

[0663] Recognizing user emotions with an emotion engine

[0664] server

[0665] The server uses an emotion engine to recognize the user's emotional state based on the photos uploaded by the user and the voice data provided by the user. The emotion engine reads facial expressions from the photos and analyzes tone and vocabulary from the voice data.

[0666] Generate and adjust disaster risk reports

[0667] server

[0668] The server then creates a disaster risk report based on the analysis results of the AI. The report includes risk assessments for earthquakes, floods, storm surges, etc., along with specific countermeasures for each risk. For example, the report may include recommendations such as "Seismic reinforcement work on buildings is recommended" or "Evacuation routes must be checked."

[0669] The emotion engine recognizes the user's emotional state and adjusts the content and tone of the report based on that. For example, if the user is feeling anxious, the report will be more friendly and emphasize specific disaster prevention measures.

[0670] Report distribution

[0671] server

[0672] The server sends the generated disaster risk report to the user's device. The report is provided in a format that users can easily view, such as PDF or HTML.

[0673] Viewing the report

[0674] User

[0675] Users can receive and view disaster risk reports on their devices. Based on the reports, they can take specific disaster prevention measures. For example, they can consult with a specialist to request earthquake-resistance reinforcement work or create an evacuation plan.

[0676] Specific examples

[0677] For example, suppose a user uploads "Nishi-Shinjuku, Shinjuku-ku, Tokyo" as their address and images of the house's exterior and surrounding area as site photos. Based on that address, the server obtains earthquake risk information through the API of the National Research Institute for Earth Science and Disaster Prevention, and also collects flood risk data using the API of the Geospatial Information Authority of Japan. Furthermore, if the generation AI analyzes the photo data and determines that the building has poor earthquake resistance, the server will assess it as having a "high earthquake risk" or "low flood risk," and generate a disaster prevention risk report with specific countermeasures, such as "seismic reinforcement work is recommended" or "evacuation routes should be confirmed." If the emotion engine detects the user's anxiety, it will adjust the tone of the report accordingly. Based on this report, the user can take specific disaster prevention measures.

[0678] This invention allows users to understand the specific disaster prevention risks at home or on-site in detail and take appropriate disaster prevention measures. By utilizing generative AI, it is possible to integrate public data and individual on-site data to provide highly accurate risk assessments, enabling faster and more accurate countermeasure planning than conventional methods. Furthermore, by utilizing an emotion engine, it is possible to respond flexibly by taking into account the user's emotional state, thereby reducing the user's psychological burden.

[0679] The processing flow will be explained below.

[0680] Step 1:

[0681] User

[0682] The user logs into the system, enters address information and site photos, and uploads them. For example, they enter an address in Nishi-Shinjuku, Shinjuku-ku, Tokyo, and select photos of the exterior of the house and its surroundings. If the user chooses, they can also record and upload a voice message.

[0683] Step 2:

[0684] Terminal

[0685] The terminal organizes the entered address information, photo data, and voice message, and sends them to the server. The address information is sent in text format, the photo data in image file format, and the voice message in voice file format.

[0686] Step 3:

[0687] server

[0688] Based on the address information received by the server, the API of the relevant public database is called to obtain the necessary information. For example, earthquake risk data is obtained from the API of the National Research Institute for Earth Science and Disaster Prevention, and flood risk data is obtained from the API of the Geospatial Information Authority of Japan. Data on storm surge risk is also obtained in the same way.

[0689] Step 4:

[0690] server

[0691] The server stores the public database information it has acquired in an internal database and prepares it for analysis. It also organizes and stores various risk data in association with address information.

[0692] Step 5:

[0693] server

[0694] The server preprocesses the uploaded photos and converts them into a format that can be analyzed by the generative AI, for example, adjusting the resolution of the photos and extracting key building features (such as earthquake resistance and drainage facilities).

[0695] Step 6:

[0696] server

[0697] The server provides address information, public database information, and preprocessed photo data to the generation AI, which then analyzes this input data and assesses disaster risk. For example, it assesses earthquake risk, flood risk, and storm surge risk, and then performs a risk assessment for each.

[0698] Step 7:

[0699] server

[0700] The server provides the uploaded voice messages and photo data to the emotion engine, which analyzes the user's emotions from this data and evaluates their emotional state, such as anxiety, relief, or excitement.

[0701] Step 8:

[0702] server

[0703] A disaster prevention risk report is generated based on the analysis results of the generation AI and the emotional state evaluation of the emotion engine. The report includes earthquake risk, flood risk, and storm surge risk, along with specific countermeasures. The tone and presentation of the report are adjusted according to the user's emotional state. For example, if the user is feeling anxious, the report will be adjusted to include specific and detailed countermeasures in a friendly tone.

[0704] Step 9:

[0705] server

[0706] The server sends the generated disaster risk report to the user's device. The report is provided in a format that users can easily view, such as PDF or HTML.

[0707] Step 10:

[0708] User

[0709] Users can receive and view disaster risk reports on their devices. Based on the reports, they can take specific disaster prevention measures. For example, they can consult with a specialist to request earthquake-resistance reinforcement work or create an evacuation plan. In addition, the emotion engine adjusts the tone of the information, reducing stress while receiving it.

[0710] Example 2

[0711] 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."

[0712] Conventional disaster risk assessment systems lacked sufficient functionality to integrate public databases and individual on-site data to perform risk assessments, making it difficult to provide accurate risk assessments and appropriate countermeasures to individual users. Furthermore, there was no way to communicate risk information that took into account the user's psychological state, which could cause unnecessary anxiety to users. This placed a heavy psychological burden on users when taking disaster prevention measures, making it difficult to respond quickly and accurately.

[0713] 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.

[0714] In this invention, the server includes: means for a user to upload address information and site photos; means for the server to acquire information from public databases necessary for risk assessment of the address; means for the server to analyze disaster prevention risks using a generation AI based on the address information, site photos, and public database information; means for the server to evaluate the analysis results using the generation AI and generate a disaster prevention risk report; emotion recognition means for the server to adjust the disaster prevention risk report based on the user's emotional state; and means for the server to send the generated disaster prevention risk report to the user's terminal. This allows the user to receive a detailed risk assessment that integrates public databases and individual site data, and enables the user to take appropriate disaster prevention measures while reducing psychological burden through the emotion recognition function.

[0715] "User" refers to an individual or organization that utilizes this system to provide address information and site photos and undergo a disaster risk assessment.

[0716] "Address information" is text data that indicates the location of a specific building or piece of land, and is information required to retrieve related information from public databases.

[0717] "Site photos" are photographic data provided by users that visually show the exterior of a building and its surrounding environment.

[0718] The "server" is the central computing device of this system, which receives data, analyzes and evaluates it, and generates reports.

[0719] A "public database" is a database containing disaster prevention-related information provided by national agencies or local governments, and the necessary information can be obtained through API.

[0720] "Generative AI" refers to a type of artificial intelligence model that analyzes user-provided data and information obtained from public databases to assess disaster risk.

[0721] "Disaster prevention risk" refers to the potential danger of natural disasters such as earthquakes, floods, and storm surges, and evaluates the impact on buildings and the surrounding environment.

[0722] A "disaster prevention risk report" is a document created by the server based on the analysis results of the AI, and includes an assessment of disaster prevention risks and specific countermeasures.

[0723] "Emotion recognition means" refers to devices or software that analyze and recognize a user's emotional state, and has the ability to read facial expressions from photographs and analyze voice tone and vocabulary from audio data.

[0724] "Terminal" means an electronic device that allows a user to input and upload address information and site photos and communicate with the server.

[0725] "Preprocessing" is the process of converting user-provided site photos and other data into an analyzable format, which is used to improve the accuracy of the analysis.

[0726] The present invention is a system that uses address information and site photos provided by the user, as well as public databases, to perform a detailed assessment of disaster prevention risks and provide the results to the user. A feature of the present invention is that it recognizes the user's emotions and reflects them in the presentation of the assessment results. Specific embodiments for implementing the present invention are described below.

[0727] This system mainly uses the following hardware and software:

[0728] User devices (smartphones, tablets, PCs, etc.)

[0729] server

[0730] Generative AI models for image analysis

[0731] Emotion Recognition Engine

[0732] User operations

[0733] First, a user logs in to the system, enters their address and photos of the site on their terminal, and uploads them. For example, a user enters the address "Nishi-Shinjuku, Shinjuku-ku, Tokyo," takes multiple photos showing the exterior of the house and the surrounding area, and uploads them to the system. At this time, the address information is entered in text format, and the photo data is entered in image file format.

[0734] Sending data

[0735] The device organizes the entered address information and photo data and sends them to the server. Specifically, the address data is stored in the "address text field," and the photo data is saved in the "photo folder" before being transferred to the server.

[0736] Obtaining information from public databases

[0737] Based on the received address information, the server calls the API of public databases to obtain the necessary disaster prevention information. For example, earthquake risk data is obtained from the API of the National Research Institute for Earth Science and Disaster Prevention, and flood risk data is obtained using the API of the Geospatial Information Authority of Japan. In addition, other risk data such as high tides is also obtained in the same way.

[0738] Data preprocessing and analysis using generative AI models

[0739] The server preprocesses the address information and site photos sent by the user and converts them into a format that the AI ​​model can analyze. The resolution of the photo data is standardized, and key features such as the building's earthquake resistance and drainage facilities are extracted using image analysis technology. The generative AI model identifies and evaluates disaster prevention risks based on the preprocessed data and acquired public data. For example, it makes risk assessments such as "the building has poor earthquake resistance" or "there is a river nearby that is prone to flooding."

[0740] Understanding the user's emotional state through emotion recognition

[0741] The server inputs the photos uploaded by the user and the voice data provided into an emotion engine to recognize the user's emotional state. By reading facial expressions from the photos and analyzing the tone of voice and vocabulary from the voice data, it determines whether the user is feeling "anxiety" or "relief."

[0742] Generate and adjust disaster risk reports

[0743] The server creates a disaster risk report based on the analysis results of the generation AI and the user's emotional state. The report includes an assessment of each risk (e.g., earthquake, flood, storm surge) and specific countermeasures. For example, it may include, "Due to the high earthquake risk, seismic reinforcement work on buildings is recommended," or "Due to the low flood risk, no special countermeasures are necessary." If the user feels anxious, the report's language is softer and uses reassuring language. For example, it may include phrases such as, "There's no need to worry, but just to be safe, check your evacuation routes."

[0744] Report distribution

[0745] The server sends the generated disaster risk report to the user's device. The report is provided in a format that the user can easily view, such as PDF or HTML. For example, it can be sent as an email attachment or a link that the user can download after logging in.

[0746] View reports and take action

[0747] Users can receive disaster risk reports on their devices and review the details. They can open the PDF file to read the risk assessment and recommended measures. Based on the report, they can hire a specialist to carry out earthquake-resistance reinforcement work or create an evacuation plan with their family.

[0748] For example, if a user uploads an address in "Nishi-Shinjuku, Shinjuku-ku, Tokyo" and photos of the exterior and surrounding area of ​​the house, the server will retrieve earthquake risk information and flood risk data from a public database based on that address. If the server analyzes the photo data and determines that the building is not earthquake-resistant, it will report the results as "high earthquake risk" or "low flood risk," along with specific measures such as "recommended earthquake reinforcement work" and "need to check evacuation routes." If the emotion engine detects the user's anxiety, it will use expressions that alleviate that anxiety. Based on this report, the user can take specific disaster prevention measures.

[0749] This system allows users to gain a detailed understanding of disaster prevention risks in their living environment and take appropriate measures. By using generative AI and emotion recognition functions, it is possible to provide quick and accurate risk assessments and psychologically considerate advice.

[0750] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0751] Step 1:

[0752] User

[0753] A user logs in to the system, enters address information and site photos from a terminal, and uploads them. The input data is address information (e.g., "Nishi-Shinjuku, Shinjuku-ku, Tokyo") and multiple site photos. This allows the system to obtain the initial data it needs.

[0754] Step 2:

[0755] Terminal

[0756] The terminal organizes the entered address information and photo data and sends them to the server. The address information is saved in text format, and the photo data is saved in image file format. The server converts this data into a format that can be received and sends it. The output data is the address information in text format and the photo data in image file format, which are sent to the server.

[0757] Step 3:

[0758] server

[0759] Based on the address information received by the server, the API of a public database is called to obtain the necessary disaster prevention information. The input data is address information, and risk data obtained through the API (e.g., earthquake risk data, flood risk data) is output. Specifically, risk information is obtained from the APIs of the National Research Institute for Earth Science and Disaster Prevention and the Geospatial Information Authority of Japan.

[0760] Step 4:

[0761] server

[0762] The server preprocesses the address information and site photos sent by the user and converts them into a format that can be analyzed by the generative AI model. Specific preprocessing operations include standardizing the resolution of the photo data and extracting key features (e.g., earthquake resistance, drainage facilities). The input data is the photo data, and the output data is preprocessed data in an analyzable format.

[0763] Step 5:

[0764] server

[0765] The generative AI model identifies and assesses disaster prevention risks based on preprocessed data and information obtained from public databases. The input data is preprocessed photo data and acquired risk data, and the output data is the risk assessment results. The generative AI model analyzes the earthquake resistance and flood risk of buildings, and identifies specific disaster prevention risks.

[0766] Step 6:

[0767] server

[0768] The server inputs photos uploaded by the user and voice data provided by the user into the emotion engine to recognize the user's emotional state. The input data is photo data and voice data, and the output data is the emotion recognition results. The emotion engine analyzes facial expressions and tone of voice to identify the user's emotion (e.g., anxiety, relief).

[0769] Step 7:

[0770] server

[0771] The server generates a disaster risk report based on the AI's analysis results and emotion recognition results, and adjusts it based on the user's emotional state. The input data are the risk assessment results and emotion recognition results, and the output data is an adjusted disaster risk report. Specific measures (e.g., recommending earthquake-resistant reinforcement work, checking evacuation routes) are included, and the report is created in a format that matches the user's psychological state.

[0772] Step 8:

[0773] server

[0774] The server sends the generated disaster risk report to the user's device. The input data is the disaster risk report, and the output data is the report sent to the user's device. The report is provided in PDF or HTML format.

[0775] Step 9:

[0776] User

[0777] The user receives the disaster prevention risk report on their device and checks the details. The input data is the received disaster prevention risk report, and the output data is the disaster prevention risk information and countermeasures that the user understands. The user takes specific disaster prevention measures based on the report (e.g., requesting earthquake-resistance reinforcement work by a specialist company, drawing up an evacuation plan).

[0778] (Application example 2)

[0779] 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."

[0780] Conventional disaster risk assessment systems are limited to risk assessments using user address information and public data, and lack the ability to analyze on-site photos or take into account the user's emotions. Furthermore, when creating disaster risk reports, adjustments are not made to reflect the user's emotional state, resulting in insufficient feedback to the user. Furthermore, simply displaying risks does not provide specific advice on what measures the user should take, making the systems ineffective.

[0781] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0782] In this invention, the server includes a means for uploading a user's address information and site photos, a means for acquiring information necessary for risk assessment from a public database, a means for recognizing the user's emotional state using an emotion engine, and a means for generating a disaster risk report and adjusting the content and tone based on the analysis results and the user's emotional state. This enables detailed risk assessment and countermeasure suggestions tailored to the user's specific emotional state. It also enables the provision of more specific and feasible disaster prevention measures while reducing the user's anxiety.

[0783] "User information" refers to address information and site photo data provided by the user.

[0784] "Public databases" are databases containing information on disaster prevention risks provided by local governments and national agencies.

[0785] "Generative AI" is a system that uses artificial intelligence technology to analyze disaster prevention risks.

[0786] The "Emotion Engine" is a system that analyzes a user's emotional state from their photo and voice data.

[0787] A "disaster prevention risk report" is a report provided to a user that includes analysis results and proposed countermeasures.

[0788] "Preprocessing of on-site photos" is the process of converting uploaded photos into a format that is easy to analyze.

[0789] "Earthquake risk" is a risk that evaluates whether the user's location is susceptible to the effects of earthquakes.

[0790] "Flood Risk" is a risk assessment of whether the user's location is susceptible to flooding.

[0791] "Storm surge risk" is a risk that evaluates whether the user's location is susceptible to the effects of a storm surge.

[0792] System configuration

[0793] This invention is a system that evaluates disaster prevention risks in detail using address information and site photos provided by the user, as well as data obtained from public databases, and provides the results to the user.Furthermore, it is characterized by combining an emotion engine to respond according to the user's emotional state.

[0794] Obtaining user information

[0795] First, a user logs into the system and uploads photos of their address and the location from their device. For example, a user enters the address "Nishi-Shinjuku, Shinjuku-ku, Tokyo," takes and uploads several photos showing the exterior of the house and the surrounding area. The device organizes the entered address information and photo data and sends them to the server. The address information is sent in text format, and the photo data is sent as an image file.

[0796] Obtaining information from public databases

[0797] Based on the address information received by the server, the API of the relevant public database is called to obtain the necessary information. For example, earthquake risk data is obtained from the API of a public institution, and flood risk data is obtained from the API of a local government. Risk data for floods, storm surges, etc. is also obtained in the same way. This includes hazard maps and weather data provided by national and local agencies.

[0798] Analysis and synthesis with generative AI

[0799] The server preprocesses the address information and site photos sent by the user and converts them into a format that the AI ​​model can analyze. For example, it adjusts the resolution of the photos and extracts the building's key features (earthquake resistance, drainage facilities, etc.). The generation AI performs analysis using information obtained from public databases and the preprocessed photo data. The AI ​​model analyzes the building's earthquake resistance and the surrounding drainage facilities, and identifies and assesses risks. For example, the generation AI analyzes that the address provided by the server is in an earthquake-prone area and there are rivers nearby that are prone to flooding, and performs a risk assessment based on that information.

[0800] Recognizing user emotions with an emotion engine

[0801] The server uses an emotion engine to recognize the user's emotional state based on the photos uploaded by the user and the voice data provided by the user. The emotion engine reads facial expressions from the photos and analyzes tone and vocabulary from the voice data.

[0802] Generate and adjust disaster risk reports

[0803] The server creates a disaster risk report based on the analysis results of the generation AI. The report includes risk assessments for earthquakes, floods, storm surges, etc., along with specific countermeasures for each risk. For example, "Seismic reinforcement work on buildings is recommended" or "Evacuation routes must be checked." The emotion engine adjusts the content and tone of the report based on the user's emotional state. For example, if the user is feeling anxious, the report's language will be more friendly and specific disaster prevention measures will be emphasized.

[0804] Report distribution

[0805] The server sends the generated disaster risk report to the user's device. The report is provided in a format that users can easily view, such as PDF or HTML. Based on this report, users can take specific disaster prevention measures. For example, they can consult with a specialist to request earthquake-resistance reinforcement work or create an evacuation plan.

[0806] Specific examples

[0807] For example, suppose a user uploads "Nishi-Shinjuku, Shinjuku-ku, Tokyo" as their address and images of the house's exterior and surrounding area as site photos. The server obtains earthquake risk information through a public institution's API based on the address, and also collects flood risk data using a local government's API. If the generation AI analyzes the photo data and determines that the building has poor earthquake resistance, the server will evaluate it as having a "high earthquake risk" or "low flood risk," and generate a disaster prevention risk report with specific countermeasures such as "seismic reinforcement work is recommended" and "evacuation routes must be confirmed." If the emotion engine detects the user's anxiety, it will adjust the tone of the report accordingly. The user can then take specific disaster prevention measures based on this report.

[0808] Prompt Sentence Examples

[0809] User: "I want to use a disaster risk assessment app. First, I need to upload my home address and a photo."

[0810] App: "Address and photo upload complete. Disaster risk analysis is currently underway."

[0811] App: "The results are in. The earthquake risk is high. We recommend earthquake-resistance reinforcement work. We also recommend checking evacuation routes."

[0812] User: "Okay, thank you. That puts my mind at ease."

[0813] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0814] Step 1:

[0815] The user uploads address information and site photos from the terminal.

[0816] Input: Address information (text format), site photo (image file format)

[0817] Output: Organized information (address information and photo data)

[0818] What happens: A user launches the app, logs in, enters address information, and takes or selects and uploads a site photo.

[0819] Step 2:

[0820] The terminal transmits the entered address information and photo data to the server.

[0821] Input: Organized address information and photo data

[0822] Output: Data sent to the server

[0823] Specific operation: The device transfers address information and photo data in text and image file format to the server and confirms receipt of the data.

[0824] Step 3:

[0825] Based on the address information received by the server, the API of a public database is called to obtain the necessary information.

[0826] Input: User's address information

[0827] Output: Risk data obtained from public databases (earthquake risk, flood risk, storm surge risk, etc.)

[0828] Specific operation: The server requests risk data based on address information from each public database (API of national agencies and local governments), and stores and organizes the obtained data.

[0829] Step 4:

[0830] The server preprocesses the received address information and site photos and provides input data for the generative AI model.

[0831] Input: User address information, risk data from public databases, scene photos

[0832] Output: Data in a format suitable for generative AI models

[0833] Specific operation: The server adjusts the resolution of the photo, extracts necessary features (such as the building's earthquake resistance and drainage facilities), and creates data to be input into the generative AI model.

[0834] Step 5:

[0835] Using a generative AI model, disaster prevention risks are analyzed based on the user's address information, site photos, and public database information.

[0836] Input: Data in a format suitable for generative AI models

[0837] Output: Detailed disaster risk assessment results (earthquake risk, flood risk, storm surge risk, etc.)

[0838] How it works: The generative AI model analyzes addresses in earthquake-prone areas and the presence of rivers prone to flooding, and performs risk assessments.

[0839] Step 6:

[0840] The server uses an emotion engine to recognize the user's emotional state.

[0841] Input: User-uploaded photos and audio data

[0842] Output: User's emotional state (anxious, relieved, etc.)

[0843] Specific operation: The server analyzes the user's facial expressions from photos and analyzes tone and vocabulary from audio data to recognize their emotional state.

[0844] Step 7:

[0845] The server generates a disaster risk report based on the analysis results of the generation AI and the user's emotional state, and adjusts the content and tone.

[0846] Input: Disaster risk assessment results, user's emotional state

[0847] Output: Adjusted disaster risk report

[0848] Specific actions: The server describes specific countermeasures for each risk based on the risk assessment results, and changes the content and tone of the report depending on the user's emotional state.

[0849] Step 8:

[0850] The server transmits the generated disaster risk report to the user's terminal.

[0851] Input: Adjusted Disaster Risk Report

[0852] Output: Report sent to the user's device

[0853] Specific operation: The server generates a risk report in PDF or HTML format and sends it to the user's device.

[0854] 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.

[0855] 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.

[0856] 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.

[0857] [Third embodiment]

[0858] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0859] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0860] 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).

[0861] 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.

[0862] 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.

[0863] 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).

[0864] 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.

[0865] 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.

[0866] 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.

[0867] 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.

[0868] 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.

[0869] 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."

[0870] The present invention provides a system for evaluating disaster prevention risks in detail using address information and site photos provided by a user, as well as public databases, and providing the results to the user. This system is specifically implemented as follows.

[0871] Obtaining user information

[0872] User

[0873] First, a user accesses the system and uploads photos of their address and the site from their terminal. For example, a user enters an address in Nishi-Shinjuku, Shinjuku-ku, Tokyo, and takes and uploads multiple photos showing the exterior of the house and the surrounding area.

[0874] Uploading data

[0875] Terminal

[0876] The device sends the address information and photo entered by the user to the server. For security reasons, it is recommended to use encrypted communication such as SSL / TLS.

[0877] Obtaining information from public databases

[0878] server

[0879] The server retrieves necessary information from relevant public databases based on the received address information, such as earthquake risk information for the specified address via a disaster prevention API.

[0880] Risk data for floods, storm surges, etc. will also be obtained, including hazard maps and meteorological data provided by national and local governments.

[0881] Analysis and synthesis with generative AI

[0882] server

[0883] The server preprocesses the address information and site photos sent by the user and converts them into a data format that is easy for the AI ​​model to handle.

[0884] The AI ​​model uses information obtained from public databases and pre-processed photo data for analysis. The generative AI analyzes the building's earthquake resistance and the status of surrounding drainage facilities to identify and assess risks.

[0885] For example, the generating AI analyzes that the address provided by the server is in an earthquake-prone area and that there are rivers nearby that are prone to flooding, and then performs a risk assessment based on that.

[0886] Generate disaster risk reports

[0887] server

[0888] The server then creates a disaster risk report based on the analysis results of the AI. The report includes risk assessments for earthquakes, floods, storm surges, etc., along with specific countermeasures for each risk. For example, the report may include recommendations such as "Seismic reinforcement work on buildings is recommended" or "Evacuation routes must be checked."

[0889] Report distribution

[0890] server

[0891] The server sends the generated disaster risk report to the user's device in a format that is easy for the user to view, such as PDF or HTML.

[0892] Viewing the report

[0893] User

[0894] Users can check the disaster risk report received on their device and understand the specific risks and recommended measures for their home and surrounding area. For example, based on the contents of the report, users can consult with a specialist company and request earthquake-resistance reinforcement work.

[0895] Specific examples

[0896] For example, suppose a user uploads "Nishi-Shinjuku, Shinjuku-ku, Tokyo" as their address information and images of the exterior of their house and surrounding area as site photos. Based on that address, the server obtains earthquake risk information through the API of the National Research Institute for Earth Science and Disaster Prevention, and also collects flood risk data using the API of the Geospatial Information Authority of Japan. Furthermore, if the generation AI analyzes the photo data and determines that the building has poor earthquake resistance, the server will evaluate it as "high earthquake risk" or "low flood risk," and generate a disaster prevention risk report with specific countermeasures such as "seismic reinforcement work is recommended" and "evacuation routes need to be confirmed." Based on this report, users can take specific disaster prevention measures.

[0897] This invention allows users to understand the specific disaster prevention risks at home or on-site in detail and take appropriate disaster prevention measures. By utilizing generative AI, it is possible to integrate public data and individual on-site data to provide highly accurate risk assessments, making it possible to plan countermeasures more quickly and accurately than conventional methods.

[0898] The processing flow will be explained below.

[0899] Step 1:

[0900] User

[0901] The user logs in to the system, enters address information and site photos, and uploads them. For example, they enter the address of "Nishi-Shinjuku, Shinjuku-ku, Tokyo," and select photos of the exterior of the house and its surroundings.

[0902] Step 2:

[0903] Terminal

[0904] The device organizes the entered address information and photo data and sends them to the server. The address information is sent in text format, and the photo data is sent in image file format.

[0905] Step 3:

[0906] server

[0907] Based on the address information received by the server, the API of the relevant public database is called to obtain the necessary information. For example, earthquake risk data is obtained from the API of the National Research Institute for Earth Science and Disaster Prevention, and flood risk data is obtained from the API of the Geospatial Information Authority of Japan.

[0908] Step 4:

[0909] server

[0910] The server stores the public database information it has acquired in an internal database and prepares it for analysis. It also organizes and stores various risk data in association with address information.

[0911] Step 5:

[0912] server

[0913] The server preprocesses the uploaded photos and converts them into a format that can be analyzed by the generative AI, for example, adjusting the resolution of the photos and extracting key building features (such as earthquake resistance and drainage facilities).

[0914] Step 6:

[0915] server

[0916] The server provides address information, public database information, and preprocessed photo data to the generation AI, which then analyzes this input data and assesses disaster risk.

[0917] Step 7:

[0918] server

[0919] Based on the analysis results of the generation AI, the server generates a disaster prevention risk report, which includes earthquake risk, flood risk, and storm surge risk, along with recommended countermeasures.

[0920] Step 8:

[0921] server

[0922] The server sends the generated disaster risk report to the user's device. The report is provided in a format that users can easily view, such as PDF or HTML.

[0923] Step 9:

[0924] User

[0925] Users can receive and view disaster risk reports on their devices. Based on the reports, they can take specific disaster prevention measures. For example, they can consider earthquake-resistance reinforcement work or check evacuation routes.

[0926] Example 1

[0927] 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."

[0928] In disaster risk assessment, there is a need for a method that can efficiently and accurately integrate user-provided on-site information with public data to quickly and specifically assess individual risks. However, current systems only refer to public databases and are unable to properly utilize user-provided on-site information. Furthermore, manual data analysis is required, making it difficult to perform rapid risk assessment.

[0929] 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.

[0930] In this invention, the server includes means for a user to upload address information and site photos, means for a terminal to send the address information and photos entered by the user to the server, means for the server to acquire information from a public database necessary for risk assessment of the address, means for the server to analyze disaster prevention risk using a generative AI model based on the address information, site photos, and public database information, means for the server to generate a disaster prevention risk report from the analysis results, and means for the server to send the generated disaster prevention risk report to the user's terminal. This enables highly accurate disaster prevention risk assessment that integrates user-provided site information and public data.

[0931] "User" refers to any person or entity that utilizes the System to provide their address information and site photos.

[0932] "Address Information" means data indicating a geographic location provided by a user for the purpose of conducting a disaster risk assessment.

[0933] "Site photos" refer to image data provided by users that show the exterior of a building and its surroundings.

[0934] "Terminal" refers to an electronic device, such as a computer, smartphone, or tablet, that a user uses to access the system and enter and transmit data.

[0935] "Server" refers to a computer system that receives, processes, and analyzes data sent by users.

[0936] "Public database" refers to a database managed by government agencies and public institutions that provides disaster prevention information on earthquakes, floods, storm surges, etc.

[0937] "Generative AI model" refers to an artificial intelligence system that uses machine learning techniques to analyze and integrate data to assess disaster risk.

[0938] "Disaster prevention risk" refers to the possibility of disasters occurring in a particular area, such as earthquakes, floods, and storm surges, and their impacts.

[0939] A "disaster prevention risk report" refers to a report on disaster prevention risk assessments of areas and buildings and specific countermeasures, created based on the analysis results of a generative AI model.

[0940] This system uses address information and site photos provided by users, as well as public databases, to evaluate disaster prevention risks in detail and provide the results to users. This system operates in cooperation with each stakeholder (user, terminal, server).

[0941] First, users access the system's web interface, enter their address information, and then take photos of the exterior of their home and surroundings using a smartphone or digital camera and upload them to the system, providing the data the system needs for analysis.

[0942] Next, the device sends the address information and photo data entered by the user to the server using encrypted communication such as SSL / TLS, ensuring the safety of the user's personal information. Communication is performed using a POST request between the web browser and the backend server.

[0943] The server retrieves the necessary information from relevant public databases based on the received address information. For example, it uses the API of the National Research Institute for Earth Science and Disaster Resilience to obtain earthquake risk information for the specified address, and the API of the Geospatial Information Authority of Japan to collect flood risk data. This data is saved in a structured format such as JSON and used for subsequent analysis.

[0944] The server then uses a generative AI model to analyze disaster risk. It preprocesses the address information and site photos uploaded by the user and converts them into an easy-to-analyze format, such as a data frame. During preprocessing, image recognition technology (e.g., OpenCV or deep learning models) is used to analyze the building's earthquake resistance and the status of surrounding drainage facilities. The generative AI model then combines the results of this analysis with information obtained from public databases to perform a comprehensive risk assessment.

[0945] Based on the analysis results of the AI ​​model, the server generates a disaster risk report. This report is created in PDF or HTML format and includes specific risk assessments and countermeasures. For example, it may include information such as "earthquake risk is high," "flood risk is low," "seismic reinforcement work is recommended," and "evacuation routes need to be checked."

[0946] The completed disaster risk report is sent from the server to the user's device. The report may be sent via email or a download link may be provided. The user receives the report and reviews the detailed disaster risk assessment and recommended measures.

[0947] An example of a prompt is:

[0948] "Based on the address information provided by the user ('Nishi-Shinjuku, Shinjuku-ku, Tokyo') and site photos, please use public databases to assess disaster prevention risks. Assessment items include earthquake risk, flood risk, and storm surge risk. Please also include specific measures to address each risk."

[0949] In this way, it is possible to utilize a generative AI model based on information provided by users and public data to quickly and accurately assess disaster risk and provide detailed reports.

[0950] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0951] Step 1:

[0952] User

[0953] Users access the system's web interface, enter address information, and take photos of the site (e.g., the exterior of the house and surrounding area) using a smartphone or digital camera and upload them to the system.

[0954] Input: Address information, site photo

[0955] Output: Data stored on the user's device

[0956] Step 2:

[0957] Terminal

[0958] The device sends the address information and photo data entered by the user to the server using encrypted communication such as SSL / TLS, ensuring that the user's personal information is securely protected. Communication uses a POST request between the web browser and the backend server.

[0959] Input: User-uploaded address information and photo

[0960] Output: Data sent to the server (address information, site photos)

[0961] Step 3:

[0962] server

[0963] The server retrieves the necessary information from relevant public databases based on the received address information. The server uses the API of the National Research Institute for Earth Science and Disaster Resilience to obtain earthquake risk information for the specified address, and also collects flood risk data using the API of the Geospatial Information Authority of Japan. These data are saved in JSON format.

[0964] Input: Address information

[0965] Output: Public data (earthquake risk information, flood risk data)

[0966] Step 4:

[0967] server

[0968] The server preprocesses the address information and site photos sent by the user and converts them into a data format that is easy for the generative AI model to handle. Preprocessing uses image recognition technology (e.g., OpenCV or deep learning models) to analyze the building's earthquake resistance and the status of surrounding drainage facilities. This converts the image data into a format that can be analyzed.

[0969] Input: Address information, site photo

[0970] Output: Preprocessed data (data frames, analyzable image data)

[0971] Step 5:

[0972] server

[0973] The server inputs pre-processed data and information obtained from public databases into a generative AI model to perform a comprehensive disaster risk assessment. The AI ​​model integrates this information to assess earthquake risk, flood risk, storm surge risk, etc.

[0974] Input: Preprocessed data, public data

[0975] Output: Risk assessment results (assessment of earthquake risk, flood risk, and storm surge risk)

[0976] Step 6:

[0977] server

[0978] The server generates a disaster prevention risk report based on the analysis results of the generation AI. This report is created in PDF or HTML format using a template engine (e.g., Jinja2) and includes a risk assessment and specific countermeasures.

[0979] Input: Risk assessment results

[0980] Output: Disaster risk report (PDF, HTML format)

[0981] Step 7:

[0982] server

[0983] The server sends the generated disaster risk report to the user's device, which may be sent via email or a download link may be provided.

[0984] Input: Disaster Risk Report

[0985] Output: Report sent to user (email, download link)

[0986] Step 8:

[0987] User

[0988] Users can open the disaster risk report they receive on their device and check the specific risks and recommended measures for their home and surrounding area. Based on the contents of the report, they can take specific measures, such as consulting with a specialist company to request earthquake-resistant reinforcement work.

[0989] Input: Report sent to user

[0990] Output: User action (countermeasure implementation)

[0991] (Application example 1)

[0992] 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."

[0993] In modern disaster prevention measures, it is important to thoroughly assess the specific environmental risks of individual homes and facilities and take appropriate measures. However, conventional methods make it difficult for users to grasp the detailed risks themselves, making it difficult to quickly develop appropriate disaster prevention measures. In addition, there is a lack of easy ways to obtain and analyze reliable information on risk assessments of natural disasters such as earthquakes and floods.

[0994] 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.

[0995] In this invention, the server includes: a means for a user to upload address information and site photos; a means for the server to acquire information from public databases necessary for risk assessment of the address; a means for the server to analyze disaster prevention risks using a generation AI based on the address information, site photos, and public database information; a means for the server to generate a disaster prevention risk report from the analysis results; a means for the server to send the generated disaster prevention risk report to the user's terminal; and a means for a smartphone application to notify the user of the disaster prevention risk report and present the risk assessment results and recommended measures. This allows the user to easily obtain detailed risk assessment results and quickly take appropriate disaster prevention measures.

[0996] "User" refers to an individual or company that uses the disaster prevention risk assessment system.

[0997] "Address information" is data on the address or location that a user inputs to indicate a specific location such as a home or facility.

[0998] "Site photos" are image data uploaded by users of the building and its surroundings that are the subject of risk assessment.

[0999] "Server" means a computer system that receives information from users and retrieves and analyzes data in conjunction with public databases.

[1000] "Public databases" are collections of highly reliable information related to disaster risk provided by government agencies and local governments.

[1001] "Generative AI" is an artificial intelligence model that automatically analyzes disaster prevention risks based on address information provided by users, site photos, and data from public databases.

[1002] "Disaster prevention risks" are dangers related to natural disasters such as earthquakes, floods, and storm surges.

[1003] A "disaster prevention risk report" is a document that summarizes individual risk assessments and countermeasures, created based on the results of analysis by the generating AI.

[1004] "User's device" refers to an electronic device such as a smartphone or computer that a user uses to receive and view disaster prevention risk reports.

[1005] A "smartphone application" is software that users install on their smartphones to access the disaster prevention risk assessment system.

[1006] "Notification" is a function in which the smartphone application informs the user of disaster risk assessment results and countermeasures.

[1007] The "risk assessment results" are detailed information on disaster prevention risks analyzed by the generating AI.

[1008] "Recommended measures" are proposals for specific disaster prevention measures that users should take based on the risk assessment results.

[1009] The present invention provides a system for evaluating disaster prevention risks in detail using address information and site photos provided by a user, as well as public databases, and providing the results to the user. This system is specifically implemented as follows.

[1010] 1. Obtaining user information

[1011] First, users access the system through a smartphone application and upload their address and photos of the site from their device. For example, a user enters an address such as "Nishi-Shinjuku, Shinjuku-ku, Tokyo," takes and uploads multiple photos showing the exterior of the house and the surrounding area. The application transmits the data using encryption protocols such as SSL / TLS.

[1012] 2. Uploading data

[1013] The device sends the address information and site photos entered by the user to the server, which then aggregates data related to the user's address and surrounding environment at the center.

[1014] 3. Acquisition of information from public databases

[1015] The server retrieves the necessary information from public disaster prevention databases based on the received address information. For example, earthquake risk information for the specified address is retrieved through a disaster prevention API, as well as data on flood risk and storm surge risk. This includes hazard maps and meteorological data provided by national and local governments.

[1016] 4. Analysis and integration with generative AI

[1017] The server preprocesses the address information and site photos sent by the user and converts them into a data format that the AI ​​model can easily handle. The generative AI model uses this data and information obtained from public databases to analyze disaster prevention risks. For example, the generative AI analyzes that the address provided by the server is in an earthquake-prone area and is near a river that is prone to flooding, and performs a risk assessment based on that information.

[1018] 5. Generation and distribution of disaster risk reports

[1019] The server creates a disaster risk report based on the analysis results of the generation AI. The report includes risk assessments for earthquakes, floods, and storm surges, as well as specific countermeasures for each risk. For example, it may include recommendations such as "Seismic reinforcement work on buildings is recommended" or "Evacuation routes must be checked." The report is provided in a format that users can easily view, such as PDF or HTML, and is notified to the user via a smartphone application.

[1020] 6. Viewing the report

[1021] Users can check the disaster risk report on their smartphone application to understand the specific risks and recommended measures for their home and surrounding area. For example, users can consult with a specialist based on the contents of the report and request earthquake-resistance reinforcement work.

[1022] Specific examples

[1023] For example, if a user uploads "Nishi-Shinjuku, Shinjuku-ku, Tokyo" as their address and images of the exterior of their home and surrounding area as site photos, the server will obtain earthquake risk information through a disaster prevention-related API based on that address, and also collect flood risk data using the Geospatial Information Authority of Japan's API. Furthermore, if the generation AI analyzes the photo data and determines that the building has poor earthquake resistance, the server will assess it as having a "high earthquake risk" or "low flood risk," and generate a disaster prevention risk report with specific countermeasures, such as "seismic reinforcement work is recommended" or "evacuation routes must be confirmed." Based on this report, users can take specific disaster prevention measures.

[1024] Prompt Sentence Examples

[1025] Please conduct a detailed disaster risk assessment based on the address and photo information below. In your results, please include specific risks and countermeasures.

[1026] Address: Nishi-Shinjuku, Shinjuku-ku, Tokyo

[1027] Photo information: Base64 encoded image data

[1028] Please assess earthquake risks, flood risks, storm surge risks, etc., and include proposals for countermeasures for each.

[1029] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1030] Step 1:

[1031] User uploads address information and site photos.

[1032] How it works: A user launches the smartphone application and accesses the system. The user enters the address of their home or facility, takes photos of the site (exterior and surrounding area images), and uploads them.

[1033] Input: User-entered address information and site photos taken.

[1034] Output: Encrypted address information and scene photo data.

[1035] Step 2:

[1036] The terminal transmits the address information and photo acquired from the user to the server.

[1037] How it works: The device securely transmits address information and site photo data to the server using encryption protocols such as SSL / TLS.

[1038] Input: Encrypted address information and scene photo data.

[1039] Output: Address information and site photo data received by the server.

[1040] Step 3:

[1041] The server retrieves the information required for risk assessment from public databases.

[1042] Operation: Based on the received address information, the server retrieves the necessary data from public disaster prevention databases (e.g., earthquake risk information API, hazard maps, etc.).

[1043] Input: Address information.

[1044] Output: Risk-related data obtained from public databases.

[1045] Step 4:

[1046] The server analyzes disaster prevention risks using generated AI based on address information, site photos, and public database information.

[1047] How it works: As a preprocessing step, the server converts on-site photos into a data format suitable for the AI ​​model. The generative AI model analyzes address information, risk data from public databases, and on-site photos to assess specific disaster prevention risks, such as earthquake risk, flood risk, and storm surge risk.

[1048] Input: Address information, official data, pre-processed site photos.

[1049] Output: Disaster risk assessment results.

[1050] Step 5:

[1051] The server generates a disaster risk report and sends it to the user's terminal.

[1052] How it works: Based on the analysis results of the generation AI, the server creates a disaster risk report. The report includes a risk assessment and specific countermeasures (e.g., recommended seismic reinforcement work, confirmation of evacuation routes). The server generates this report in PDF or HTML format and sends it to the user's device.

[1053] Input: Disaster risk assessment results.

[1054] Output: Disaster risk report.

[1055] Step 6:

[1056] The smartphone application notifies users of disaster risk reports and presents risk assessment results and recommended countermeasures.

[1057] How it works: The smartphone application notifies the user when a report arrives. When the user opens the report, the application displays specific risk assessment results and recommended measures. The user can then take specific disaster prevention measures based on this information.

[1058] Input: Disaster Risk Report.

[1059] Output: Risk assessment results and recommended measures communicated to the user.

[1060] 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.

[1061] The present invention is a system that uses address information and site photos provided by the user, as well as public databases, to perform a detailed assessment of disaster prevention risks and provide the results to the user. A feature of the present invention is that it incorporates an emotion engine that recognizes the user's emotions. This system is specifically implemented as follows.

[1062] Obtaining user information

[1063] User

[1064] First, users log in to the system and upload photos of their address and the site from their terminal. For example, they enter the address of "Nishi-Shinjuku, Shinjuku-ku, Tokyo," take and upload multiple photos showing the exterior of the house and the surrounding area.

[1065] Uploading data

[1066] Terminal

[1067] The device organizes the entered address information and photo data and sends them to the server. The address information is sent in text format, and the photo data is sent in image file format.

[1068] Obtaining information from public databases

[1069] server

[1070] Based on the address information received by the server, the API of the relevant public database is called to obtain the necessary information. For example, earthquake risk data is obtained from the API of the National Research Institute for Earth Science and Disaster Prevention, and flood risk data is obtained from the API of the Geospatial Information Authority of Japan.

[1071] Risk data for floods, storm surges, etc. will also be obtained, including hazard maps and meteorological data provided by national and local governments.

[1072] Analysis and synthesis with generative AI

[1073] server

[1074] The server preprocesses the address information and site photos sent by the user and converts them into a format that the AI ​​model can analyze, for example, adjusting the resolution of the photos and extracting key building features (such as earthquake resistance and drainage facilities).

[1075] The AI ​​model uses information obtained from public databases and pre-processed photo data for analysis. The generative AI analyzes the building's earthquake resistance and the status of surrounding drainage facilities to identify and assess risks.

[1076] For example, the generating AI analyzes that the address provided by the server is in an earthquake-prone area and that there are rivers nearby that are prone to flooding, and then performs a risk assessment based on that.

[1077] Recognizing user emotions with an emotion engine

[1078] server

[1079] The server uses an emotion engine to recognize the user's emotional state based on the photos uploaded by the user and the voice data provided by the user. The emotion engine reads facial expressions from the photos and analyzes tone and vocabulary from the voice data.

[1080] Generate and adjust disaster risk reports

[1081] server

[1082] The server then creates a disaster risk report based on the analysis results of the AI. The report includes risk assessments for earthquakes, floods, storm surges, etc., along with specific countermeasures for each risk. For example, the report may include recommendations such as "Seismic reinforcement work on buildings is recommended" or "Evacuation routes must be checked."

[1083] The emotion engine recognizes the user's emotional state and adjusts the content and tone of the report based on that. For example, if the user is feeling anxious, the report will be more friendly and emphasize specific disaster prevention measures.

[1084] Report distribution

[1085] server

[1086] The server sends the generated disaster risk report to the user's device. The report is provided in a format that users can easily view, such as PDF or HTML.

[1087] Viewing the report

[1088] User

[1089] Users can receive and view disaster risk reports on their devices. Based on the reports, they can take specific disaster prevention measures. For example, they can consult with a specialist to request earthquake-resistance reinforcement work or create an evacuation plan.

[1090] Specific examples

[1091] For example, suppose a user uploads "Nishi-Shinjuku, Shinjuku-ku, Tokyo" as their address and images of the house's exterior and surrounding area as site photos. Based on that address, the server obtains earthquake risk information through the API of the National Research Institute for Earth Science and Disaster Prevention, and also collects flood risk data using the API of the Geospatial Information Authority of Japan. Furthermore, if the generation AI analyzes the photo data and determines that the building has poor earthquake resistance, the server will assess it as having a "high earthquake risk" or "low flood risk," and generate a disaster prevention risk report with specific countermeasures, such as "seismic reinforcement work is recommended" or "evacuation routes should be confirmed." If the emotion engine detects the user's anxiety, it will adjust the tone of the report accordingly. Based on this report, the user can take specific disaster prevention measures.

[1092] This invention allows users to understand the specific disaster prevention risks at home or on-site in detail and take appropriate disaster prevention measures. By utilizing generative AI, it is possible to integrate public data and individual on-site data to provide highly accurate risk assessments, enabling faster and more accurate countermeasure planning than conventional methods. Furthermore, by utilizing an emotion engine, it is possible to respond flexibly by taking into account the user's emotional state, thereby reducing the user's psychological burden.

[1093] The processing flow will be explained below.

[1094] Step 1:

[1095] User

[1096] The user logs into the system, enters address information and site photos, and uploads them. For example, they enter an address in Nishi-Shinjuku, Shinjuku-ku, Tokyo, and select photos of the exterior of the house and its surroundings. If the user chooses, they can also record and upload a voice message.

[1097] Step 2:

[1098] Terminal

[1099] The terminal organizes the entered address information, photo data, and voice message, and sends them to the server. The address information is sent in text format, the photo data in image file format, and the voice message in voice file format.

[1100] Step 3:

[1101] server

[1102] Based on the address information received by the server, the API of the relevant public database is called to obtain the necessary information. For example, earthquake risk data is obtained from the API of the National Research Institute for Earth Science and Disaster Prevention, and flood risk data is obtained from the API of the Geospatial Information Authority of Japan. Data on storm surge risk is also obtained in the same way.

[1103] Step 4:

[1104] server

[1105] The server stores the public database information it has acquired in an internal database and prepares it for analysis. It also organizes and stores various risk data in association with address information.

[1106] Step 5:

[1107] server

[1108] The server preprocesses the uploaded photos and converts them into a format that can be analyzed by the generative AI, for example, adjusting the resolution of the photos and extracting key building features (such as earthquake resistance and drainage facilities).

[1109] Step 6:

[1110] server

[1111] The server provides address information, public database information, and preprocessed photo data to the generation AI, which then analyzes this input data and assesses disaster risk. For example, it assesses earthquake risk, flood risk, and storm surge risk, and then performs a risk assessment for each.

[1112] Step 7:

[1113] server

[1114] The server provides the uploaded voice messages and photo data to the emotion engine, which analyzes the user's emotions from this data and evaluates their emotional state, such as anxiety, relief, or excitement.

[1115] Step 8:

[1116] server

[1117] A disaster prevention risk report is generated based on the analysis results of the generation AI and the emotional state evaluation of the emotion engine. The report includes earthquake risk, flood risk, and storm surge risk, along with specific countermeasures. The tone and presentation of the report are adjusted according to the user's emotional state. For example, if the user is feeling anxious, the report will be adjusted to include specific and detailed countermeasures in a friendly tone.

[1118] Step 9:

[1119] server

[1120] The server sends the generated disaster risk report to the user's device. The report is provided in a format that users can easily view, such as PDF or HTML.

[1121] Step 10:

[1122] User

[1123] Users can receive and view disaster risk reports on their devices. Based on the reports, they can take specific disaster prevention measures. For example, they can consult with a specialist to request earthquake-resistance reinforcement work or create an evacuation plan. In addition, the emotion engine adjusts the tone of the information, reducing stress while receiving it.

[1124] Example 2

[1125] 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."

[1126] Conventional disaster risk assessment systems lacked sufficient functionality to integrate public databases and individual on-site data to perform risk assessments, making it difficult to provide accurate risk assessments and appropriate countermeasures to individual users. Furthermore, there was no way to communicate risk information that took into account the user's psychological state, which could cause unnecessary anxiety to users. This placed a heavy psychological burden on users when taking disaster prevention measures, making it difficult to respond quickly and accurately.

[1127] 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.

[1128] In this invention, the server includes: means for a user to upload address information and site photos; means for the server to acquire information from public databases necessary for risk assessment of the address; means for the server to analyze disaster prevention risks using a generation AI based on the address information, site photos, and public database information; means for the server to evaluate the analysis results using the generation AI and generate a disaster prevention risk report; emotion recognition means for the server to adjust the disaster prevention risk report based on the user's emotional state; and means for the server to send the generated disaster prevention risk report to the user's terminal. This allows the user to receive a detailed risk assessment that integrates public databases and individual site data, and enables the user to take appropriate disaster prevention measures while reducing psychological burden through the emotion recognition function.

[1129] "User" refers to an individual or organization that utilizes this system to provide address information and site photos and undergo a disaster risk assessment.

[1130] "Address information" is text data that indicates the location of a specific building or piece of land, and is information required to retrieve related information from public databases.

[1131] "Site photos" are photographic data provided by users that visually show the exterior of a building and its surrounding environment.

[1132] The "server" is the central computing device of this system, which receives data, analyzes and evaluates it, and generates reports.

[1133] A "public database" is a database containing disaster prevention-related information provided by national agencies or local governments, and the necessary information can be obtained through API.

[1134] "Generative AI" refers to a type of artificial intelligence model that analyzes user-provided data and information obtained from public databases to assess disaster risk.

[1135] "Disaster prevention risk" refers to the potential danger of natural disasters such as earthquakes, floods, and storm surges, and evaluates the impact on buildings and the surrounding environment.

[1136] A "disaster prevention risk report" is a document created by the server based on the analysis results of the AI, and includes an assessment of disaster prevention risks and specific countermeasures.

[1137] "Emotion recognition means" refers to devices or software that analyze and recognize a user's emotional state, and has the ability to read facial expressions from photographs and analyze voice tone and vocabulary from audio data.

[1138] "Terminal" means an electronic device that allows a user to input and upload address information and site photos and communicate with the server.

[1139] "Preprocessing" is the process of converting user-provided site photos and other data into an analyzable format, which is used to improve the accuracy of the analysis.

[1140] The present invention is a system that uses address information and site photos provided by the user, as well as public databases, to perform a detailed assessment of disaster prevention risks and provide the results to the user. A feature of the present invention is that it recognizes the user's emotions and reflects them in the presentation of the assessment results. Specific embodiments for implementing the present invention are described below.

[1141] This system mainly uses the following hardware and software:

[1142] User devices (smartphones, tablets, PCs, etc.)

[1143] server

[1144] Generative AI models for image analysis

[1145] Emotion Recognition Engine

[1146] User operations

[1147] First, a user logs in to the system, enters their address and photos of the site on their terminal, and uploads them. For example, a user enters the address "Nishi-Shinjuku, Shinjuku-ku, Tokyo," takes multiple photos showing the exterior of the house and the surrounding area, and uploads them to the system. At this time, the address information is entered in text format, and the photo data is entered in image file format.

[1148] Sending data

[1149] The device organizes the entered address information and photo data and sends them to the server. Specifically, the address data is stored in the "address text field," and the photo data is saved in the "photo folder" before being transferred to the server.

[1150] Obtaining information from public databases

[1151] Based on the received address information, the server calls the API of public databases to obtain the necessary disaster prevention information. For example, earthquake risk data is obtained from the API of the National Research Institute for Earth Science and Disaster Prevention, and flood risk data is obtained using the API of the Geospatial Information Authority of Japan. In addition, other risk data such as high tides is also obtained in the same way.

[1152] Data preprocessing and analysis using generative AI models

[1153] The server preprocesses the address information and site photos sent by the user and converts them into a format that the AI ​​model can analyze. The resolution of the photo data is standardized, and key features such as the building's earthquake resistance and drainage facilities are extracted using image analysis technology. The generative AI model identifies and evaluates disaster prevention risks based on the preprocessed data and acquired public data. For example, it makes risk assessments such as "the building has poor earthquake resistance" or "there is a river nearby that is prone to flooding."

[1154] Understanding the user's emotional state through emotion recognition

[1155] The server inputs the photos uploaded by the user and the voice data provided into an emotion engine to recognize the user's emotional state. By reading facial expressions from the photos and analyzing the tone of voice and vocabulary from the voice data, it determines whether the user is feeling "anxiety" or "relief."

[1156] Generate and adjust disaster risk reports

[1157] The server creates a disaster risk report based on the analysis results of the generation AI and the user's emotional state. The report includes an assessment of each risk (e.g., earthquake, flood, storm surge) and specific countermeasures. For example, it may include, "Due to the high earthquake risk, seismic reinforcement work on buildings is recommended," or "Due to the low flood risk, no special countermeasures are necessary." If the user feels anxious, the report's language is softer and uses reassuring language. For example, it may include phrases such as, "There's no need to worry, but just to be safe, check your evacuation routes."

[1158] Report distribution

[1159] The server sends the generated disaster risk report to the user's device. The report is provided in a format that the user can easily view, such as PDF or HTML. For example, it can be sent as an email attachment or a link that the user can download after logging in.

[1160] View reports and take action

[1161] Users can receive disaster risk reports on their devices and review the details. They can open the PDF file to read the risk assessment and recommended measures. Based on the report, they can hire a specialist to carry out earthquake-resistance reinforcement work or create an evacuation plan with their family.

[1162] For example, if a user uploads an address in "Nishi-Shinjuku, Shinjuku-ku, Tokyo" and photos of the exterior and surrounding area of ​​the house, the server will retrieve earthquake risk information and flood risk data from a public database based on that address. If the server analyzes the photo data and determines that the building is not earthquake-resistant, it will report the results as "high earthquake risk" or "low flood risk," along with specific measures such as "recommended earthquake reinforcement work" and "need to check evacuation routes." If the emotion engine detects the user's anxiety, it will use expressions that alleviate that anxiety. Based on this report, the user can take specific disaster prevention measures.

[1163] This system allows users to gain a detailed understanding of disaster prevention risks in their living environment and take appropriate measures. By using generative AI and emotion recognition functions, it is possible to provide quick and accurate risk assessments and psychologically considerate advice.

[1164] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1165] Step 1:

[1166] User

[1167] A user logs in to the system, enters address information and site photos from a terminal, and uploads them. The input data is address information (e.g., "Nishi-Shinjuku, Shinjuku-ku, Tokyo") and multiple site photos. This allows the system to obtain the initial data it needs.

[1168] Step 2:

[1169] Terminal

[1170] The terminal organizes the entered address information and photo data and sends them to the server. The address information is saved in text format, and the photo data is saved in image file format. The server converts this data into a format that can be received and sends it. The output data is the address information in text format and the photo data in image file format, which are sent to the server.

[1171] Step 3:

[1172] server

[1173] Based on the address information received by the server, the API of a public database is called to obtain the necessary disaster prevention information. The input data is address information, and risk data obtained through the API (e.g., earthquake risk data, flood risk data) is output. Specifically, risk information is obtained from the APIs of the National Research Institute for Earth Science and Disaster Prevention and the Geospatial Information Authority of Japan.

[1174] Step 4:

[1175] server

[1176] The server preprocesses the address information and site photos sent by the user and converts them into a format that can be analyzed by the generative AI model. Specific preprocessing operations include standardizing the resolution of the photo data and extracting key features (e.g., earthquake resistance, drainage facilities). The input data is the photo data, and the output data is preprocessed data in an analyzable format.

[1177] Step 5:

[1178] server

[1179] The generative AI model identifies and assesses disaster prevention risks based on preprocessed data and information obtained from public databases. The input data is preprocessed photo data and acquired risk data, and the output data is the risk assessment results. The generative AI model analyzes the earthquake resistance and flood risk of buildings, and identifies specific disaster prevention risks.

[1180] Step 6:

[1181] server

[1182] The server inputs photos uploaded by the user and voice data provided by the user into the emotion engine to recognize the user's emotional state. The input data is photo data and voice data, and the output data is the emotion recognition results. The emotion engine analyzes facial expressions and tone of voice to identify the user's emotion (e.g., anxiety, relief).

[1183] Step 7:

[1184] server

[1185] The server generates a disaster risk report based on the AI's analysis results and emotion recognition results, and adjusts it based on the user's emotional state. The input data are the risk assessment results and emotion recognition results, and the output data is an adjusted disaster risk report. Specific measures (e.g., recommending earthquake-resistant reinforcement work, checking evacuation routes) are included, and the report is created in a format that matches the user's psychological state.

[1186] Step 8:

[1187] server

[1188] The server sends the generated disaster risk report to the user's device. The input data is the disaster risk report, and the output data is the report sent to the user's device. The report is provided in PDF or HTML format.

[1189] Step 9:

[1190] User

[1191] The user receives the disaster prevention risk report on their device and checks the details. The input data is the received disaster prevention risk report, and the output data is the disaster prevention risk information and countermeasures that the user understands. The user takes specific disaster prevention measures based on the report (e.g., requesting earthquake-resistance reinforcement work by a specialist company, drawing up an evacuation plan).

[1192] (Application example 2)

[1193] 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."

[1194] Conventional disaster risk assessment systems are limited to risk assessments using user address information and public data, and lack the ability to analyze on-site photos or take into account the user's emotions. Furthermore, when creating disaster risk reports, adjustments are not made to reflect the user's emotional state, resulting in insufficient feedback to the user. Furthermore, simply displaying risks does not provide specific advice on what measures the user should take, making the systems ineffective.

[1195] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1196] In this invention, the server includes a means for uploading a user's address information and site photos, a means for acquiring information necessary for risk assessment from a public database, a means for recognizing the user's emotional state using an emotion engine, and a means for generating a disaster risk report and adjusting the content and tone based on the analysis results and the user's emotional state. This enables detailed risk assessment and countermeasure suggestions tailored to the user's specific emotional state. It also enables the provision of more specific and feasible disaster prevention measures while reducing the user's anxiety.

[1197] "User information" refers to address information and site photo data provided by the user.

[1198] "Public databases" are databases containing information on disaster prevention risks provided by local governments and national agencies.

[1199] "Generative AI" is a system that uses artificial intelligence technology to analyze disaster prevention risks.

[1200] The "Emotion Engine" is a system that analyzes a user's emotional state from their photo and voice data.

[1201] A "disaster prevention risk report" is a report provided to a user that includes analysis results and proposed countermeasures.

[1202] "Preprocessing of on-site photos" is the process of converting uploaded photos into a format that is easy to analyze.

[1203] "Earthquake risk" is a risk that evaluates whether the user's location is susceptible to the effects of earthquakes.

[1204] "Flood Risk" is a risk assessment of whether the user's location is susceptible to flooding.

[1205] "Storm surge risk" is a risk that evaluates whether the user's location is susceptible to the effects of a storm surge.

[1206] System configuration

[1207] This invention is a system that evaluates disaster prevention risks in detail using address information and site photos provided by the user, as well as data obtained from public databases, and provides the results to the user.Furthermore, it is characterized by combining an emotion engine to respond according to the user's emotional state.

[1208] Obtaining user information

[1209] First, a user logs into the system and uploads their address and photos of the location from their device. For example, a user enters the address "Nishi-Shinjuku, Shinjuku-ku, Tokyo," takes and uploads several photos showing the exterior of the house and the surrounding area. The device organizes the entered address information and photo data and sends them to the server. The address information is sent in text format, and the photo data is sent as an image file.

[1210] Obtaining information from public databases

[1211] Based on the address information received by the server, the API of the relevant public database is called to obtain the necessary information. For example, earthquake risk data is obtained from the API of a public institution, and flood risk data is obtained from the API of a local government. Risk data for floods, storm surges, etc. is also obtained in the same way. This includes hazard maps and weather data provided by national and local agencies.

[1212] Analysis and synthesis with generative AI

[1213] The server preprocesses the address information and site photos sent by the user and converts them into a format that the AI ​​model can analyze. For example, it adjusts the resolution of the photos and extracts the building's key features (earthquake resistance, drainage facilities, etc.). The generation AI performs analysis using information obtained from public databases and the preprocessed photo data. The AI ​​model analyzes the building's earthquake resistance and the surrounding drainage facilities, and identifies and assesses risks. For example, the generation AI analyzes that the address provided by the server is in an earthquake-prone area and there are rivers nearby that are prone to flooding, and performs a risk assessment based on that information.

[1214] Recognizing user emotions with an emotion engine

[1215] The server uses an emotion engine to recognize the user's emotional state based on the photos uploaded by the user and the voice data provided by the user. The emotion engine reads facial expressions from the photos and analyzes tone and vocabulary from the voice data.

[1216] Generate and adjust disaster risk reports

[1217] The server creates a disaster risk report based on the analysis results of the generation AI. The report includes risk assessments for earthquakes, floods, storm surges, etc., along with specific countermeasures for each risk. For example, "Seismic reinforcement work on buildings is recommended" or "Evacuation routes must be checked." The emotion engine adjusts the content and tone of the report based on the user's emotional state. For example, if the user is feeling anxious, the report's language will be more friendly and specific disaster prevention measures will be emphasized.

[1218] Report distribution

[1219] The server sends the generated disaster risk report to the user's device. The report is provided in a format that users can easily view, such as PDF or HTML. Based on this report, users can take specific disaster prevention measures. For example, they can consult with a specialist to request earthquake-resistance reinforcement work or create an evacuation plan.

[1220] Specific examples

[1221] For example, suppose a user uploads "Nishi-Shinjuku, Shinjuku-ku, Tokyo" as their address and images of the house's exterior and surrounding area as site photos. The server obtains earthquake risk information through a public institution's API based on the address, and also collects flood risk data using a local government's API. If the generation AI analyzes the photo data and determines that the building has poor earthquake resistance, the server will evaluate it as having a "high earthquake risk" or "low flood risk," and generate a disaster prevention risk report with specific countermeasures such as "seismic reinforcement work is recommended" and "evacuation routes must be confirmed." If the emotion engine detects the user's anxiety, it will adjust the tone of the report accordingly. The user can then take specific disaster prevention measures based on this report.

[1222] Prompt Sentence Examples

[1223] User: "I want to use a disaster risk assessment app. First, I need to upload my home address and a photo."

[1224] App: "Address and photo upload complete. Disaster risk analysis is currently underway."

[1225] App: "The results are in. The earthquake risk is high. We recommend earthquake-resistance reinforcement work. We also recommend checking evacuation routes."

[1226] User: "Okay, thank you. That puts my mind at ease."

[1227] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1228] Step 1:

[1229] The user uploads address information and site photos from the terminal.

[1230] Input: Address information (text format), site photo (image file format)

[1231] Output: Organized information (address information and photo data)

[1232] What happens: A user launches the app, logs in, enters address information, and takes or selects and uploads a site photo.

[1233] Step 2:

[1234] The terminal transmits the entered address information and photo data to the server.

[1235] Input: Organized address information and photo data

[1236] Output: Data sent to the server

[1237] Specific operation: The device transfers address information and photo data in text and image file format to the server and confirms receipt of the data.

[1238] Step 3:

[1239] Based on the address information received by the server, the API of a public database is called to obtain the necessary information.

[1240] Input: User's address information

[1241] Output: Risk data obtained from public databases (earthquake risk, flood risk, storm surge risk, etc.)

[1242] Specific operation: The server requests risk data based on address information from each public database (API of national agencies and local governments), and stores and organizes the obtained data.

[1243] Step 4:

[1244] The server preprocesses the received address information and site photos and provides input data for the generative AI model.

[1245] Input: User address information, risk data from public databases, scene photos

[1246] Output: Data in a format suitable for generative AI models

[1247] Specific operation: The server adjusts the resolution of the photo, extracts necessary features (such as the building's earthquake resistance and drainage facilities), and creates data to be input into the generative AI model.

[1248] Step 5:

[1249] Using a generative AI model, disaster prevention risks are analyzed based on the user's address information, site photos, and public database information.

[1250] Input: Data in a format suitable for generative AI models

[1251] Output: Detailed disaster risk assessment results (earthquake risk, flood risk, storm surge risk, etc.)

[1252] How it works: The generative AI model analyzes addresses in earthquake-prone areas and the presence of rivers prone to flooding, and performs risk assessments.

[1253] Step 6:

[1254] The server uses an emotion engine to recognize the user's emotional state.

[1255] Input: User-uploaded photos and audio data

[1256] Output: User's emotional state (anxious, relieved, etc.)

[1257] Specific operation: The server analyzes the user's facial expressions from photos and analyzes tone and vocabulary from audio data to recognize their emotional state.

[1258] Step 7:

[1259] The server generates a disaster risk report based on the analysis results of the generation AI and the user's emotional state, and adjusts the content and tone.

[1260] Input: Disaster risk assessment results, user's emotional state

[1261] Output: Adjusted disaster risk report

[1262] Specific actions: The server describes specific countermeasures for each risk based on the risk assessment results, and changes the content and tone of the report depending on the user's emotional state.

[1263] Step 8:

[1264] The server transmits the generated disaster risk report to the user's terminal.

[1265] Input: Adjusted Disaster Risk Report

[1266] Output: Report sent to the user's device

[1267] Specific operation: The server generates a risk report in PDF or HTML format and sends it to the user's device.

[1268] 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.

[1269] 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.

[1270] 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.

[1271] [Fourth embodiment]

[1272] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1273] 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.

[1274] 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).

[1275] 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.

[1276] 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.

[1277] 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).

[1278] 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.

[1279] 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.

[1280] 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.

[1281] 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.

[1282] 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.

[1283] 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.

[1284] 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."

[1285] The present invention provides a system for evaluating disaster prevention risks in detail using address information and site photos provided by a user, as well as public databases, and providing the results to the user. This system is specifically implemented as follows.

[1286] Obtaining user information

[1287] User

[1288] First, a user accesses the system and uploads photos of their address and the site from their terminal. For example, a user enters an address in Nishi-Shinjuku, Shinjuku-ku, Tokyo, and takes and uploads multiple photos showing the exterior of the house and the surrounding area.

[1289] Uploading data

[1290] Terminal

[1291] The device sends the address information and photo entered by the user to the server. For security reasons, it is recommended to use encrypted communication such as SSL / TLS.

[1292] Obtaining information from public databases

[1293] server

[1294] The server retrieves necessary information from relevant public databases based on the received address information, such as earthquake risk information for the specified address via a disaster prevention API.

[1295] Risk data for floods, storm surges, etc. will also be obtained, including hazard maps and meteorological data provided by national and local governments.

[1296] Analysis and synthesis with generative AI

[1297] server

[1298] The server preprocesses the address information and site photos sent by the user and converts them into a data format that is easy for the AI ​​model to handle.

[1299] The AI ​​model uses information obtained from public databases and pre-processed photo data for analysis. The generative AI analyzes the building's earthquake resistance and the status of surrounding drainage facilities to identify and assess risks.

[1300] For example, the generating AI analyzes that the address provided by the server is in an earthquake-prone area and that there are rivers nearby that are prone to flooding, and then performs a risk assessment based on that.

[1301] Generate disaster risk reports

[1302] server

[1303] The server then creates a disaster risk report based on the analysis results of the AI. The report includes risk assessments for earthquakes, floods, storm surges, etc., along with specific countermeasures for each risk. For example, the report may include recommendations such as "Seismic reinforcement work on buildings is recommended" or "Evacuation routes must be checked."

[1304] Report distribution

[1305] server

[1306] The server sends the generated disaster risk report to the user's device in a format that is easy for the user to view, such as PDF or HTML.

[1307] Viewing the report

[1308] User

[1309] Users can check the disaster risk report received on their device and understand the specific risks and recommended measures for their home and surrounding area. For example, based on the contents of the report, users can consult with a specialist company and request earthquake-resistance reinforcement work.

[1310] Specific examples

[1311] For example, suppose a user uploads "Nishi-Shinjuku, Shinjuku-ku, Tokyo" as their address information and images of the exterior of their house and surrounding area as site photos. Based on that address, the server obtains earthquake risk information through the API of the National Research Institute for Earth Science and Disaster Prevention, and also collects flood risk data using the API of the Geospatial Information Authority of Japan. Furthermore, if the generation AI analyzes the photo data and determines that the building has poor earthquake resistance, the server will evaluate it as "high earthquake risk" or "low flood risk," and generate a disaster prevention risk report with specific countermeasures such as "seismic reinforcement work is recommended" and "evacuation routes need to be confirmed." Based on this report, users can take specific disaster prevention measures.

[1312] This invention allows users to understand the specific disaster prevention risks at home or on-site in detail and take appropriate disaster prevention measures. By utilizing generative AI, it is possible to integrate public data and individual on-site data to provide highly accurate risk assessments, making it possible to plan countermeasures more quickly and accurately than conventional methods.

[1313] The processing flow will be explained below.

[1314] Step 1:

[1315] User

[1316] The user logs in to the system, enters address information and site photos, and uploads them. For example, they enter the address of "Nishi-Shinjuku, Shinjuku-ku, Tokyo," and select photos of the exterior of the house and its surroundings.

[1317] Step 2:

[1318] Terminal

[1319] The device organizes the entered address information and photo data and sends them to the server. The address information is sent in text format, and the photo data is sent in image file format.

[1320] Step 3:

[1321] server

[1322] Based on the address information received by the server, the API of the relevant public database is called to obtain the necessary information. For example, earthquake risk data is obtained from the API of the National Research Institute for Earth Science and Disaster Prevention, and flood risk data is obtained from the API of the Geospatial Information Authority of Japan.

[1323] Step 4:

[1324] server

[1325] The server stores the public database information it has acquired in an internal database and prepares it for analysis. It also organizes and stores various risk data in association with address information.

[1326] Step 5:

[1327] server

[1328] The server preprocesses the uploaded photos and converts them into a format that can be analyzed by the generative AI, for example, adjusting the resolution of the photos and extracting key building features (such as earthquake resistance and drainage facilities).

[1329] Step 6:

[1330] server

[1331] The server provides address information, public database information, and preprocessed photo data to the generation AI, which then analyzes this input data and assesses disaster risk.

[1332] Step 7:

[1333] server

[1334] Based on the analysis results of the generation AI, the server generates a disaster prevention risk report, which includes earthquake risk, flood risk, and storm surge risk, along with recommended countermeasures.

[1335] Step 8:

[1336] server

[1337] The server sends the generated disaster risk report to the user's device. The report is provided in a format that users can easily view, such as PDF or HTML.

[1338] Step 9:

[1339] User

[1340] Users can receive and view disaster risk reports on their devices. Based on the reports, they can take specific disaster prevention measures. For example, they can consider earthquake-resistance reinforcement work or check evacuation routes.

[1341] Example 1

[1342] 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."

[1343] In disaster risk assessment, there is a need for a method that can efficiently and accurately integrate user-provided on-site information with public data to quickly and specifically assess individual risks. However, current systems only refer to public databases and are unable to properly utilize user-provided on-site information. Furthermore, manual data analysis is required, making it difficult to perform rapid risk assessment.

[1344] 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.

[1345] In this invention, the server includes means for a user to upload address information and site photos, means for a terminal to send the address information and photos entered by the user to the server, means for the server to acquire information from a public database necessary for risk assessment of the address, means for the server to analyze disaster prevention risk using a generative AI model based on the address information, site photos, and public database information, means for the server to generate a disaster prevention risk report from the analysis results, and means for the server to send the generated disaster prevention risk report to the user's terminal. This enables highly accurate disaster prevention risk assessment that integrates user-provided site information and public data.

[1346] "User" refers to any person or entity that utilizes the System to provide their address information and site photos.

[1347] "Address Information" means data indicating a geographic location provided by a user for the purpose of conducting a disaster risk assessment.

[1348] "Site photos" refer to image data provided by users that show the exterior of a building and its surroundings.

[1349] "Terminal" refers to an electronic device, such as a computer, smartphone, or tablet, that a user uses to access the system and enter and transmit data.

[1350] "Server" refers to a computer system that receives, processes, and analyzes data sent by users.

[1351] "Public database" refers to a database managed by government agencies and public institutions that provides disaster prevention information on earthquakes, floods, storm surges, etc.

[1352] "Generative AI model" refers to an artificial intelligence system that uses machine learning techniques to analyze and integrate data to assess disaster risk.

[1353] "Disaster prevention risk" refers to the possibility of disasters occurring in a particular area, such as earthquakes, floods, and storm surges, and their impacts.

[1354] A "disaster prevention risk report" refers to a report on disaster prevention risk assessments of areas and buildings and specific countermeasures, created based on the analysis results of a generative AI model.

[1355] This system uses address information and site photos provided by users, as well as public databases, to evaluate disaster prevention risks in detail and provide the results to users. This system operates in cooperation with each stakeholder (user, terminal, server).

[1356] First, users access the system's web interface, enter their address information, and then take photos of the exterior of their home and surroundings using a smartphone or digital camera and upload them to the system, providing the data the system needs for analysis.

[1357] Next, the device sends the address information and photo data entered by the user to the server using encrypted communication such as SSL / TLS, ensuring the safety of the user's personal information. Communication is performed using a POST request between the web browser and the backend server.

[1358] The server retrieves the necessary information from relevant public databases based on the received address information. For example, it uses the API of the National Research Institute for Earth Science and Disaster Resilience to obtain earthquake risk information for the specified address, and the API of the Geospatial Information Authority of Japan to collect flood risk data. This data is saved in a structured format such as JSON and used for subsequent analysis.

[1359] The server then uses a generative AI model to analyze disaster risk. It preprocesses the address information and site photos uploaded by the user and converts them into an easy-to-analyze format, such as a data frame. During preprocessing, image recognition technology (e.g., OpenCV or deep learning models) is used to analyze the building's earthquake resistance and the status of surrounding drainage facilities. The generative AI model then combines the results of this analysis with information obtained from public databases to perform a comprehensive risk assessment.

[1360] Based on the analysis results of the AI ​​model, the server generates a disaster risk report. This report is created in PDF or HTML format and includes specific risk assessments and countermeasures. For example, it may include information such as "earthquake risk is high," "flood risk is low," "seismic reinforcement work is recommended," and "evacuation routes need to be checked."

[1361] The completed disaster risk report is sent from the server to the user's device. The report may be sent via email or a download link may be provided. The user receives the report and reviews the detailed disaster risk assessment and recommended measures.

[1362] An example of a prompt is:

[1363] "Based on the address information provided by the user ('Nishi-Shinjuku, Shinjuku-ku, Tokyo') and site photos, please use public databases to assess disaster prevention risks. Assessment items include earthquake risk, flood risk, and storm surge risk. Please also include specific measures to address each risk."

[1364] In this way, it is possible to utilize a generative AI model based on information provided by users and public data to quickly and accurately assess disaster risk and provide detailed reports.

[1365] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1366] Step 1:

[1367] User

[1368] Users access the system's web interface, enter address information, and take photos of the site (e.g., the exterior of the house and surrounding area) using a smartphone or digital camera and upload them to the system.

[1369] Input: Address information, site photo

[1370] Output: Data stored on the user's device

[1371] Step 2:

[1372] Terminal

[1373] The device sends the address information and photo data entered by the user to the server using encrypted communication such as SSL / TLS, ensuring that the user's personal information is securely protected. Communication uses a POST request between the web browser and the backend server.

[1374] Input: User-uploaded address information and photo

[1375] Output: Data sent to the server (address information, site photos)

[1376] Step 3:

[1377] server

[1378] The server retrieves the necessary information from relevant public databases based on the received address information. The server uses the API of the National Research Institute for Earth Science and Disaster Resilience to obtain earthquake risk information for the specified address, and also collects flood risk data using the API of the Geospatial Information Authority of Japan. These data are saved in JSON format.

[1379] Input: Address information

[1380] Output: Public data (earthquake risk information, flood risk data)

[1381] Step 4:

[1382] server

[1383] The server preprocesses the address information and site photos sent by the user and converts them into a data format that is easy for the generative AI model to handle. Preprocessing uses image recognition technology (e.g., OpenCV or deep learning models) to analyze the building's earthquake resistance and the status of surrounding drainage facilities. This converts the image data into a format that can be analyzed.

[1384] Input: Address information, site photo

[1385] Output: Preprocessed data (data frames, analyzable image data)

[1386] Step 5:

[1387] server

[1388] The server inputs pre-processed data and information obtained from public databases into a generative AI model to perform a comprehensive disaster risk assessment. The AI ​​model integrates this information to assess earthquake risk, flood risk, storm surge risk, etc.

[1389] Input: Preprocessed data, public data

[1390] Output: Risk assessment results (assessment of earthquake risk, flood risk, and storm surge risk)

[1391] Step 6:

[1392] server

[1393] The server generates a disaster prevention risk report based on the analysis results of the generation AI. This report is created in PDF or HTML format using a template engine (e.g., Jinja2) and includes a risk assessment and specific countermeasures.

[1394] Input: Risk assessment results

[1395] Output: Disaster risk report (PDF, HTML format)

[1396] Step 7:

[1397] server

[1398] The server sends the generated disaster risk report to the user's device, which may be sent via email or a download link may be provided.

[1399] Input: Disaster Risk Report

[1400] Output: Report sent to user (email, download link)

[1401] Step 8:

[1402] User

[1403] Users can open the disaster risk report they received on their device and check the specific risks and recommended measures for their home and surrounding area. Based on the contents of the report, they can take specific measures, such as consulting with a specialist company to request earthquake-resistant reinforcement work.

[1404] Input: Report sent to user

[1405] Output: User action (countermeasure implementation)

[1406] (Application example 1)

[1407] 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."

[1408] In modern disaster prevention measures, it is important to thoroughly assess the specific environmental risks of individual homes and facilities and take appropriate measures. However, conventional methods make it difficult for users to grasp the detailed risks themselves, making it difficult to quickly develop appropriate disaster prevention measures. In addition, there is a lack of easy ways to obtain and analyze reliable information on risk assessments of natural disasters such as earthquakes and floods.

[1409] 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.

[1410] In this invention, the server includes: a means for a user to upload address information and site photos; a means for the server to acquire information from public databases necessary for risk assessment of the address; a means for the server to analyze disaster prevention risks using a generation AI based on the address information, site photos, and public database information; a means for the server to generate a disaster prevention risk report from the analysis results; a means for the server to send the generated disaster prevention risk report to the user's terminal; and a means for a smartphone application to notify the user of the disaster prevention risk report and present the risk assessment results and recommended measures. This allows the user to easily obtain detailed risk assessment results and quickly take appropriate disaster prevention measures.

[1411] "User" refers to an individual or company that uses the disaster prevention risk assessment system.

[1412] "Address information" is data on the address or location that a user inputs to indicate a specific location such as a home or facility.

[1413] "Site photos" are image data uploaded by users of the building and its surroundings that are the subject of risk assessment.

[1414] "Server" means a computer system that receives information from users and retrieves and analyzes data in conjunction with public databases.

[1415] "Public databases" are collections of highly reliable information related to disaster risk provided by government agencies and local governments.

[1416] "Generative AI" is an artificial intelligence model that automatically analyzes disaster prevention risks based on address information provided by users, site photos, and data from public databases.

[1417] "Disaster prevention risks" are dangers related to natural disasters such as earthquakes, floods, and storm surges.

[1418] A "disaster prevention risk report" is a document that summarizes individual risk assessments and countermeasures, created based on the results of analysis by the generating AI.

[1419] "User's device" refers to an electronic device such as a smartphone or computer that a user uses to receive and view disaster prevention risk reports.

[1420] A "smartphone application" is software that users install on their smartphones to access the disaster prevention risk assessment system.

[1421] "Notification" is a function in which the smartphone application informs the user of disaster risk assessment results and countermeasures.

[1422] The "risk assessment results" are detailed information on disaster prevention risks analyzed by the generating AI.

[1423] "Recommended measures" are proposals for specific disaster prevention measures that users should take based on the risk assessment results.

[1424] The present invention provides a system for evaluating disaster prevention risks in detail using address information and site photos provided by a user, as well as public databases, and providing the results to the user. This system is specifically implemented as follows.

[1425] 1. Obtaining user information

[1426] First, users access the system through a smartphone application and upload their address and photos of the site from their device. For example, a user enters an address such as "Nishi-Shinjuku, Shinjuku-ku, Tokyo," takes and uploads multiple photos showing the exterior of the house and the surrounding area. The application transmits the data using encryption protocols such as SSL / TLS.

[1427] 2. Uploading data

[1428] The device sends the address information and site photos entered by the user to the server, which then aggregates data related to the user's address and surrounding environment at the center.

[1429] 3. Acquisition of information from public databases

[1430] The server retrieves the necessary information from public disaster prevention databases based on the received address information. For example, earthquake risk information for the specified address is retrieved through a disaster prevention API, as well as data on flood risk and storm surge risk. This includes hazard maps and meteorological data provided by national and local governments.

[1431] 4. Analysis and integration with generative AI

[1432] The server preprocesses the address information and site photos sent by the user and converts them into a data format that the AI ​​model can easily handle. The generative AI model uses this data and information obtained from public databases to analyze disaster prevention risks. For example, the generative AI analyzes that the address provided by the server is in an earthquake-prone area and is near a river that is prone to flooding, and performs a risk assessment based on that information.

[1433] 5. Generation and distribution of disaster risk reports

[1434] The server creates a disaster risk report based on the analysis results of the generation AI. The report includes risk assessments for earthquakes, floods, and storm surges, as well as specific countermeasures for each risk. For example, it may include recommendations such as "Seismic reinforcement work on buildings is recommended" or "Evacuation routes must be checked." The report is provided in a format that users can easily view, such as PDF or HTML, and is notified to the user via a smartphone application.

[1435] 6. Viewing the report

[1436] Users can check the disaster prevention risk report on their smartphone application to understand the specific risks and recommended measures for their home and surrounding area. For example, users can consult with a specialist based on the contents of the report and request earthquake-resistance reinforcement work.

[1437] Specific examples

[1438] For example, if a user uploads "Nishi-Shinjuku, Shinjuku-ku, Tokyo" as their address and images of the exterior of their home and surrounding area as site photos, the server will obtain earthquake risk information through a disaster prevention-related API based on that address, and also collect flood risk data using the Geospatial Information Authority of Japan's API. Furthermore, if the generation AI analyzes the photo data and determines that the building has poor earthquake resistance, the server will assess it as having a "high earthquake risk" or "low flood risk," and generate a disaster prevention risk report with specific countermeasures, such as "seismic reinforcement work is recommended" or "evacuation routes must be confirmed." Based on this report, users can take specific disaster prevention measures.

[1439] Prompt Sentence Examples

[1440] Please conduct a detailed disaster risk assessment based on the address and photo information below. In your results, please include specific risks and countermeasures.

[1441] Address: Nishi-Shinjuku, Shinjuku-ku, Tokyo

[1442] Photo information: Base64 encoded image data

[1443] Please assess earthquake risks, flood risks, storm surge risks, etc., and include proposals for countermeasures for each.

[1444] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1445] Step 1:

[1446] User uploads address information and site photos.

[1447] How it works: A user launches the smartphone application and accesses the system. The user enters the address of their home or facility, takes photos of the site (exterior and surrounding area images), and uploads them.

[1448] Input: User-entered address information and site photos taken.

[1449] Output: Encrypted address information and scene photo data.

[1450] Step 2:

[1451] The terminal transmits the address information and photo acquired from the user to the server.

[1452] How it works: The device securely transmits address information and site photo data to the server using encryption protocols such as SSL / TLS.

[1453] Input: Encrypted address information and scene photo data.

[1454] Output: Address information and site photo data received by the server.

[1455] Step 3:

[1456] The server retrieves the information required for risk assessment from public databases.

[1457] Operation: Based on the received address information, the server retrieves the necessary data from public disaster prevention databases (e.g., earthquake risk information API, hazard maps, etc.).

[1458] Input: Address information.

[1459] Output: Risk-related data obtained from public databases.

[1460] Step 4:

[1461] The server analyzes disaster prevention risks using generated AI based on address information, site photos, and public database information.

[1462] How it works: As a preprocessing step, the server converts on-site photos into a data format suitable for the AI ​​model. The generative AI model analyzes address information, risk data from public databases, and on-site photos to assess specific disaster prevention risks, such as earthquake risk, flood risk, and storm surge risk.

[1463] Input: Address information, official data, pre-processed site photos.

[1464] Output: Disaster risk assessment results.

[1465] Step 5:

[1466] The server generates a disaster risk report and sends it to the user's terminal.

[1467] How it works: Based on the analysis results of the generation AI, the server creates a disaster risk report. The report includes a risk assessment and specific countermeasures (e.g., recommended seismic reinforcement work, confirmation of evacuation routes). The server generates this report in PDF or HTML format and sends it to the user's device.

[1468] Input: Disaster risk assessment results.

[1469] Output: Disaster risk report.

[1470] Step 6:

[1471] The smartphone application notifies users of disaster risk reports and presents risk assessment results and recommended countermeasures.

[1472] How it works: The smartphone application notifies the user when a report arrives. When the user opens the report, the application displays specific risk assessment results and recommended measures. The user can then take specific disaster prevention measures based on this information.

[1473] Input: Disaster Risk Report.

[1474] Output: Risk assessment results and recommended measures communicated to the user.

[1475] 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.

[1476] The present invention is a system that uses address information and site photos provided by the user, as well as public databases, to perform a detailed assessment of disaster prevention risks and provide the results to the user. A feature of the present invention is that it incorporates an emotion engine that recognizes the user's emotions. This system is specifically implemented as follows.

[1477] Obtaining user information

[1478] User

[1479] First, users log in to the system and upload photos of their address and the site from their terminal. For example, they enter the address of "Nishi-Shinjuku, Shinjuku-ku, Tokyo," take and upload multiple photos showing the exterior of the house and the surrounding area.

[1480] Uploading data

[1481] Terminal

[1482] The device organizes the entered address information and photo data and sends them to the server. The address information is sent in text format, and the photo data is sent in image file format.

[1483] Obtaining information from public databases

[1484] server

[1485] Based on the address information received by the server, the API of the relevant public database is called to obtain the necessary information. For example, earthquake risk data is obtained from the API of the National Research Institute for Earth Science and Disaster Prevention, and flood risk data is obtained from the API of the Geospatial Information Authority of Japan.

[1486] Risk data for floods, storm surges, etc. will also be obtained, including hazard maps and meteorological data provided by national and local governments.

[1487] Analysis and synthesis with generative AI

[1488] server

[1489] The server preprocesses the address information and site photos sent by the user and converts them into a format that the AI ​​model can analyze, for example, adjusting the resolution of the photos and extracting key building features (such as earthquake resistance and drainage facilities).

[1490] The AI ​​model uses information obtained from public databases and pre-processed photo data for analysis. The generative AI analyzes the building's earthquake resistance and the status of surrounding drainage facilities to identify and assess risks.

[1491] For example, the generating AI analyzes that the address provided by the server is in an earthquake-prone area and that there are rivers nearby that are prone to flooding, and then performs a risk assessment based on that.

[1492] Recognizing user emotions with an emotion engine

[1493] server

[1494] The server uses an emotion engine to recognize the user's emotional state based on the photos uploaded by the user and the voice data provided by the user. The emotion engine reads facial expressions from the photos and analyzes tone and vocabulary from the voice data.

[1495] Generate and adjust disaster risk reports

[1496] server

[1497] The server then creates a disaster risk report based on the analysis results of the AI. The report includes risk assessments for earthquakes, floods, storm surges, etc., along with specific countermeasures for each risk. For example, the report may include recommendations such as "Seismic reinforcement work on buildings is recommended" or "Evacuation routes must be checked."

[1498] The emotion engine recognizes the user's emotional state and adjusts the content and tone of the report based on that. For example, if the user is feeling anxious, the report will be more friendly and emphasize specific disaster prevention measures.

[1499] Report distribution

[1500] server

[1501] The server sends the generated disaster risk report to the user's device. The report is provided in a format that users can easily view, such as PDF or HTML.

[1502] Viewing the report

[1503] User

[1504] Users can receive and view disaster risk reports on their devices. Based on the reports, they can take specific disaster prevention measures. For example, they can consult with a specialist to request earthquake-resistance reinforcement work or create an evacuation plan.

[1505] Specific examples

[1506] For example, suppose a user uploads "Nishi-Shinjuku, Shinjuku-ku, Tokyo" as their address and images of the house's exterior and surrounding area as site photos. Based on that address, the server obtains earthquake risk information through the API of the National Research Institute for Earth Science and Disaster Prevention, and also collects flood risk data using the API of the Geospatial Information Authority of Japan. Furthermore, if the generation AI analyzes the photo data and determines that the building has poor earthquake resistance, the server will assess it as having a "high earthquake risk" or "low flood risk," and generate a disaster prevention risk report with specific countermeasures, such as "seismic reinforcement work is recommended" or "evacuation routes should be confirmed." If the emotion engine detects the user's anxiety, it will adjust the tone of the report accordingly. Based on this report, the user can take specific disaster prevention measures.

[1507] This invention allows users to understand the specific disaster prevention risks at home or on-site in detail and take appropriate disaster prevention measures. By utilizing generative AI, it is possible to integrate public data and individual on-site data to provide highly accurate risk assessments, enabling faster and more accurate countermeasure planning than conventional methods. Furthermore, by utilizing an emotion engine, it is possible to respond flexibly by taking into account the user's emotional state, thereby reducing the user's psychological burden.

[1508] The processing flow will be explained below.

[1509] Step 1:

[1510] User

[1511] The user logs into the system, enters address information and site photos, and uploads them. For example, they enter an address in Nishi-Shinjuku, Shinjuku-ku, Tokyo, and select photos of the exterior of the house and its surroundings. If the user chooses, they can also record and upload a voice message.

[1512] Step 2:

[1513] Terminal

[1514] The terminal organizes the entered address information, photo data, and voice message, and sends them to the server. The address information is sent in text format, the photo data in image file format, and the voice message in voice file format.

[1515] Step 3:

[1516] server

[1517] Based on the address information received by the server, the API of the relevant public database is called to obtain the necessary information. For example, earthquake risk data is obtained from the API of the National Research Institute for Earth Science and Disaster Prevention, and flood risk data is obtained from the API of the Geospatial Information Authority of Japan. Data on storm surge risk is also obtained in the same way.

[1518] Step 4:

[1519] server

[1520] The server stores the public database information it has acquired in an internal database and prepares it for analysis. It also organizes and stores various risk data in association with address information.

[1521] Step 5:

[1522] server

[1523] The server preprocesses the uploaded photos and converts them into a format that can be analyzed by the generative AI, for example, adjusting the resolution of the photos and extracting key building features (such as earthquake resistance and drainage facilities).

[1524] Step 6:

[1525] server

[1526] The server provides address information, public database information, and preprocessed photo data to the generation AI, which then analyzes this input data and assesses disaster risk. For example, it assesses earthquake risk, flood risk, and storm surge risk, and then performs a risk assessment for each.

[1527] Step 7:

[1528] server

[1529] The server provides the uploaded voice messages and photo data to the emotion engine, which analyzes the user's emotions from this data and evaluates their emotional state, such as anxiety, relief, or excitement.

[1530] Step 8:

[1531] server

[1532] A disaster prevention risk report is generated based on the analysis results of the generation AI and the emotional state evaluation of the emotion engine. The report includes earthquake risk, flood risk, and storm surge risk, along with specific countermeasures. The tone and presentation of the report are adjusted according to the user's emotional state. For example, if the user is feeling anxious, the report will be adjusted to include specific and detailed countermeasures in a friendly tone.

[1533] Step 9:

[1534] server

[1535] The server sends the generated disaster risk report to the user's device. The report is provided in a format that users can easily view, such as PDF or HTML.

[1536] Step 10:

[1537] User

[1538] Users can receive and view disaster risk reports on their devices. Based on the reports, they can take specific disaster prevention measures. For example, they can consult with a specialist to request earthquake-resistance reinforcement work or create an evacuation plan. In addition, the emotion engine adjusts the tone of the information, reducing stress while receiving it.

[1539] Example 2

[1540] 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."

[1541] Conventional disaster risk assessment systems lacked sufficient functionality to integrate public databases and individual on-site data to perform risk assessments, making it difficult to provide accurate risk assessments and appropriate countermeasures to individual users. Furthermore, there was no way to communicate risk information that took into account the user's psychological state, which could cause unnecessary anxiety to users. This placed a heavy psychological burden on users when taking disaster prevention measures, making it difficult to respond quickly and accurately.

[1542] 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.

[1543] In this invention, the server includes: means for a user to upload address information and site photos; means for the server to acquire information from public databases necessary for risk assessment of the address; means for the server to analyze disaster prevention risks using a generation AI based on the address information, site photos, and public database information; means for the server to evaluate the analysis results using the generation AI and generate a disaster prevention risk report; emotion recognition means for the server to adjust the disaster prevention risk report based on the user's emotional state; and means for the server to send the generated disaster prevention risk report to the user's terminal. This allows the user to receive a detailed risk assessment that integrates public databases and individual site data, and enables the user to take appropriate disaster prevention measures while reducing psychological burden through the emotion recognition function.

[1544] "User" refers to an individual or organization that utilizes this system to provide address information and site photos and undergo a disaster risk assessment.

[1545] "Address information" is text data that indicates the location of a specific building or piece of land, and is information required to retrieve related information from public databases.

[1546] "Site photos" are photographic data provided by users that visually show the exterior of a building and its surrounding environment.

[1547] The "server" is the central computing device of this system, which receives data, analyzes and evaluates it, and generates reports.

[1548] A "public database" is a database containing disaster prevention-related information provided by national agencies or local governments, and the necessary information can be obtained through API.

[1549] "Generative AI" refers to a type of artificial intelligence model that analyzes user-provided data and information obtained from public databases to assess disaster risk.

[1550] "Disaster prevention risk" refers to the potential danger of natural disasters such as earthquakes, floods, and storm surges, and evaluates the impact on buildings and the surrounding environment.

[1551] A "disaster prevention risk report" is a document created by the server based on the analysis results of the AI, and includes an assessment of disaster prevention risks and specific countermeasures.

[1552] "Emotion recognition means" refers to devices or software that analyze and recognize a user's emotional state, and has the ability to read facial expressions from photographs and analyze voice tone and vocabulary from audio data.

[1553] "Terminal" means an electronic device that allows a user to input and upload address information and site photos and communicate with the server.

[1554] "Preprocessing" is the process of converting user-provided site photos and other data into an analyzable format, which is used to improve the accuracy of the analysis.

[1555] The present invention is a system that uses address information and site photos provided by the user, as well as public databases, to perform a detailed assessment of disaster prevention risks and provide the results to the user. A feature of the present invention is that it recognizes the user's emotions and reflects them in the presentation of the assessment results. Specific embodiments for implementing the present invention are described below.

[1556] This system mainly uses the following hardware and software:

[1557] User devices (smartphones, tablets, PCs, etc.)

[1558] server

[1559] Generative AI models for image analysis

[1560] Emotion Recognition Engine

[1561] User operations

[1562] First, a user logs in to the system, enters their address and photos of the site on their terminal, and uploads them. For example, a user enters the address "Nishi-Shinjuku, Shinjuku-ku, Tokyo," takes multiple photos showing the exterior of the house and the surrounding area, and uploads them to the system. At this time, the address information is entered in text format, and the photo data is entered in image file format.

[1563] Sending data

[1564] The device organizes the entered address information and photo data and sends them to the server. Specifically, the address data is stored in the "address text field," and the photo data is saved in the "photo folder" before being transferred to the server.

[1565] Obtaining information from public databases

[1566] Based on the received address information, the server calls the API of public databases to obtain the necessary disaster prevention information. For example, earthquake risk data is obtained from the API of the National Research Institute for Earth Science and Disaster Prevention, and flood risk data is obtained using the API of the Geospatial Information Authority of Japan. In addition, other risk data such as high tides is also obtained in the same way.

[1567] Data preprocessing and analysis using generative AI models

[1568] The server preprocesses the address information and site photos sent by the user and converts them into a format that the AI ​​model can analyze. The resolution of the photo data is standardized, and key features such as the building's earthquake resistance and drainage facilities are extracted using image analysis technology. The generative AI model identifies and evaluates disaster prevention risks based on the preprocessed data and acquired public data. For example, it makes risk assessments such as "the building has poor earthquake resistance" or "there is a river nearby that is prone to flooding."

[1569] Understanding the user's emotional state through emotion recognition

[1570] The server inputs the photos uploaded by the user and the voice data provided into an emotion engine to recognize the user's emotional state. By reading facial expressions from the photos and analyzing the tone of voice and vocabulary from the voice data, it determines whether the user is feeling "anxiety" or "relief."

[1571] Generate and adjust disaster risk reports

[1572] The server creates a disaster risk report based on the analysis results of the generation AI and the user's emotional state. The report includes an assessment of each risk (e.g., earthquake, flood, storm surge) and specific countermeasures. For example, it may include, "Due to the high earthquake risk, seismic reinforcement work on buildings is recommended," or "Due to the low flood risk, no special countermeasures are necessary." If the user feels anxious, the report's language is softer and uses reassuring language. For example, it may include phrases such as, "There's no need to worry, but just to be safe, check your evacuation routes."

[1573] Report distribution

[1574] The server sends the generated disaster risk report to the user's device. The report is provided in a format that the user can easily view, such as PDF or HTML. For example, it can be sent as an email attachment or a link that the user can download after logging in.

[1575] View reports and take action

[1576] Users can receive disaster risk reports on their devices and review the details. They can open the PDF file to read the risk assessment and recommended measures. Based on the report, they can hire a specialist to carry out earthquake-resistance reinforcement work or create an evacuation plan with their family.

[1577] For example, if a user uploads an address in "Nishi-Shinjuku, Shinjuku-ku, Tokyo" and photos of the exterior and surrounding area of ​​the house, the server will retrieve earthquake risk information and flood risk data from a public database based on that address. If the server analyzes the photo data and determines that the building is not earthquake-resistant, it will report the results as "high earthquake risk" or "low flood risk," along with specific measures such as "recommended earthquake reinforcement work" and "need to check evacuation routes." If the emotion engine detects the user's anxiety, it will use expressions that alleviate that anxiety. Based on this report, the user can take specific disaster prevention measures.

[1578] This system allows users to gain a detailed understanding of disaster prevention risks in their living environment and take appropriate measures. By using generative AI and emotion recognition functions, it is possible to provide quick and accurate risk assessments and psychologically considerate advice.

[1579] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1580] Step 1:

[1581] User

[1582] A user logs in to the system, enters address information and site photos from a terminal, and uploads them. The input data is address information (e.g., "Nishi-Shinjuku, Shinjuku-ku, Tokyo") and multiple site photos. This allows the system to obtain the initial data it needs.

[1583] Step 2:

[1584] Terminal

[1585] The terminal organizes the entered address information and photo data and sends them to the server. The address information is saved in text format, and the photo data is saved in image file format. The server converts this data into a format that can be received and sends it. The output data is the address information in text format and the photo data in image file format, which are sent to the server.

[1586] Step 3:

[1587] server

[1588] Based on the address information received by the server, the API of a public database is called to obtain the necessary disaster prevention information. The input data is address information, and risk data obtained through the API (e.g., earthquake risk data, flood risk data) is output. Specifically, risk information is obtained from the APIs of the National Research Institute for Earth Science and Disaster Prevention and the Geospatial Information Authority of Japan.

[1589] Step 4:

[1590] server

[1591] The server preprocesses the address information and site photos sent by the user and converts them into a format that can be analyzed by the generative AI model. Specific preprocessing operations include standardizing the resolution of the photo data and extracting key features (e.g., earthquake resistance, drainage facilities). The input data is the photo data, and the output data is preprocessed data in an analyzable format.

[1592] Step 5:

[1593] server

[1594] The generative AI model identifies and assesses disaster prevention risks based on preprocessed data and information obtained from public databases. The input data is preprocessed photo data and acquired risk data, and the output data is the risk assessment results. The generative AI model analyzes the earthquake resistance and flood risk of buildings, and identifies specific disaster prevention risks.

[1595] Step 6:

[1596] server

[1597] The server inputs photos uploaded by the user and voice data provided by the user into the emotion engine to recognize the user's emotional state. The input data is photo data and voice data, and the output data is the emotion recognition results. The emotion engine analyzes facial expressions and tone of voice to identify the user's emotion (e.g., anxiety, relief).

[1598] Step 7:

[1599] server

[1600] The server generates a disaster risk report based on the AI's analysis results and emotion recognition results, and adjusts it based on the user's emotional state. The input data are the risk assessment results and emotion recognition results, and the output data is an adjusted disaster risk report. Specific measures (e.g., recommending earthquake-resistant reinforcement work, checking evacuation routes) are included, and the report is created in a format that matches the user's psychological state.

[1601] Step 8:

[1602] server

[1603] The server sends the generated disaster risk report to the user's device. The input data is the disaster risk report, and the output data is the report sent to the user's device. The report is provided in PDF or HTML format.

[1604] Step 9:

[1605] User

[1606] The user receives the disaster prevention risk report on their device and checks the details. The input data is the received disaster prevention risk report, and the output data is the disaster prevention risk information and countermeasures that the user understands. The user takes specific disaster prevention measures based on the report (e.g., requesting earthquake-resistance reinforcement work by a specialist company, drawing up an evacuation plan).

[1607] (Application example 2)

[1608] 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."

[1609] Conventional disaster risk assessment systems are limited to risk assessments using user address information and public data, and lack the ability to analyze on-site photos or take into account the user's emotions. Furthermore, when creating disaster risk reports, adjustments are not made to reflect the user's emotional state, resulting in insufficient feedback to the user. Furthermore, simply displaying risks does not provide specific advice on what measures the user should take, making the systems ineffective.

[1610] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1611] In this invention, the server includes a means for uploading a user's address information and site photos, a means for acquiring information necessary for risk assessment from a public database, a means for recognizing the user's emotional state using an emotion engine, and a means for generating a disaster risk report and adjusting the content and tone based on the analysis results and the user's emotional state. This enables detailed risk assessment and countermeasure suggestions tailored to the user's specific emotional state. It also enables the provision of more specific and feasible disaster prevention measures while reducing the user's anxiety.

[1612] "User information" refers to address information and site photo data provided by the user.

[1613] "Public databases" are databases containing information on disaster prevention risks provided by local governments and national agencies.

[1614] "Generative AI" is a system that uses artificial intelligence technology to analyze disaster prevention risks.

[1615] The "Emotion Engine" is a system that analyzes a user's emotional state from their photo and voice data.

[1616] A "disaster prevention risk report" is a report provided to a user that includes analysis results and proposed countermeasures.

[1617] "Preprocessing of on-site photos" is the process of converting uploaded photos into a format that is easy to analyze.

[1618] "Earthquake risk" is a risk that evaluates whether the user's location is susceptible to the effects of earthquakes.

[1619] "Flood Risk" is a risk assessment of whether the user's location is susceptible to flooding.

[1620] "Storm surge risk" is a risk that evaluates whether the user's location is susceptible to the effects of a storm surge.

[1621] System configuration

[1622] This invention is a system that evaluates disaster prevention risks in detail using address information and site photos provided by the user, as well as data obtained from public databases, and provides the results to the user.Furthermore, it is characterized by combining an emotion engine to respond according to the user's emotional state.

[1623] Obtaining user information

[1624] First, a user logs into the system and uploads their address and photos of the location from their device. For example, a user enters the address "Nishi-Shinjuku, Shinjuku-ku, Tokyo," takes and uploads several photos showing the exterior of the house and the surrounding area. The device organizes the entered address information and photo data and sends them to the server. The address information is sent in text format, and the photo data is sent as an image file.

[1625] Obtaining information from public databases

[1626] Based on the address information received by the server, the API of the relevant public database is called to obtain the necessary information. For example, earthquake risk data is obtained from the API of a public institution, and flood risk data is obtained from the API of a local government. Risk data for floods, storm surges, etc. is also obtained in the same way. This includes hazard maps and weather data provided by national and local agencies.

[1627] Analysis and synthesis with generative AI

[1628] The server preprocesses the address information and site photos sent by the user and converts them into a format that the AI ​​model can analyze. For example, it adjusts the resolution of the photos and extracts the building's key features (earthquake resistance, drainage facilities, etc.). The generation AI performs analysis using information obtained from public databases and the preprocessed photo data. The AI ​​model analyzes the building's earthquake resistance and the surrounding drainage facilities, and identifies and assesses risks. For example, the generation AI analyzes that the address provided by the server is in an earthquake-prone area and there are rivers nearby that are prone to flooding, and performs a risk assessment based on that information.

[1629] Recognizing user emotions with an emotion engine

[1630] The server uses an emotion engine to recognize the user's emotional state based on the photos uploaded by the user and the voice data provided by the user. The emotion engine reads facial expressions from the photos and analyzes tone and vocabulary from the voice data.

[1631] Generate and adjust disaster risk reports

[1632] The server creates a disaster risk report based on the analysis results of the generation AI. The report includes risk assessments for earthquakes, floods, storm surges, etc., along with specific countermeasures for each risk. For example, "Seismic reinforcement work on buildings is recommended" or "Evacuation routes must be checked." The emotion engine adjusts the content and tone of the report based on the user's emotional state. For example, if the user is feeling anxious, the report's language will be more friendly and specific disaster prevention measures will be emphasized.

[1633] Report distribution

[1634] The server sends the generated disaster risk report to the user's device. The report is provided in a format that users can easily view, such as PDF or HTML. Based on this report, users can take specific disaster prevention measures. For example, they can consult with a specialist to request earthquake-resistance reinforcement work or create an evacuation plan.

[1635] Specific examples

[1636] For example, suppose a user uploads "Nishi-Shinjuku, Shinjuku-ku, Tokyo" as their address and images of the house's exterior and surrounding area as site photos. The server obtains earthquake risk information through a public institution's API based on the address, and also collects flood risk data using a local government's API. If the generation AI analyzes the photo data and determines that the building has poor earthquake resistance, the server will evaluate it as having a "high earthquake risk" or "low flood risk," and generate a disaster prevention risk report with specific countermeasures such as "seismic reinforcement work is recommended" and "evacuation routes must be confirmed." If the emotion engine detects the user's anxiety, it will adjust the tone of the report accordingly. The user can then take specific disaster prevention measures based on this report.

[1637] Prompt Sentence Examples

[1638] User: "I want to use a disaster risk assessment app. First, I need to upload my home address and a photo."

[1639] App: "Address and photo upload complete. Disaster risk analysis is currently underway."

[1640] App: "The results are in. The earthquake risk is high. We recommend earthquake-resistance reinforcement work. We also recommend checking evacuation routes."

[1641] User: "Okay, thank you. That puts my mind at ease."

[1642] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1643] Step 1:

[1644] The user uploads address information and site photos from the terminal.

[1645] Input: Address information (text format), site photo (image file format)

[1646] Output: Organized information (address information and photo data)

[1647] What happens: A user launches the app, logs in, enters address information, and takes or selects and uploads a site photo.

[1648] Step 2:

[1649] The terminal transmits the entered address information and photo data to the server.

[1650] Input: Organized address information and photo data

[1651] Output: Data sent to the server

[1652] Specific operation: The device transfers address information and photo data in text and image file format to the server and confirms receipt of the data.

[1653] Step 3:

[1654] Based on the address information received by the server, the API of a public database is called to obtain the necessary information.

[1655] Input: User's address information

[1656] Output: Risk data obtained from public databases (earthquake risk, flood risk, storm surge risk, etc.)

[1657] Specific operation: The server requests risk data based on address information from each public database (API of national agencies and local governments), and stores and organizes the obtained data.

[1658] Step 4:

[1659] The server preprocesses the received address information and site photos and provides input data for the generative AI model.

[1660] Input: User address information, risk data from public databases, scene photos

[1661] Output: Data in a format suitable for generative AI models

[1662] Specific operation: The server adjusts the resolution of the photo, extracts necessary features (such as the building's earthquake resistance and drainage facilities), and creates data to be input into the generative AI model.

[1663] Step 5:

[1664] Using a generative AI model, disaster prevention risks are analyzed based on the user's address information, site photos, and public database information.

[1665] Input: Data in a format suitable for generative AI models

[1666] Output: Detailed disaster risk assessment results (earthquake risk, flood risk, storm surge risk, etc.)

[1667] How it works: The generative AI model analyzes addresses in earthquake-prone areas and the presence of rivers prone to flooding, and performs risk assessments.

[1668] Step 6:

[1669] The server uses an emotion engine to recognize the user's emotional state.

[1670] Input: User-uploaded photos and audio data

[1671] Output: User's emotional state (anxious, relieved, etc.)

[1672] Specific operation: The server analyzes the user's facial expressions from photos and analyzes tone and vocabulary from audio data to recognize their emotional state.

[1673] Step 7:

[1674] The server generates a disaster risk report based on the analysis results of the generation AI and the user's emotional state, and adjusts the content and tone.

[1675] Input: Disaster risk assessment results, user's emotional state

[1676] Output: Adjusted disaster risk report

[1677] Specific actions: The server describes specific countermeasures for each risk based on the risk assessment results, and changes the content and tone of the report depending on the user's emotional state.

[1678] Step 8:

[1679] The server transmits the generated disaster risk report to the user's terminal.

[1680] Input: Adjusted Disaster Risk Report

[1681] Output: Report sent to the user's device

[1682] Specific operation: The server generates a risk report in PDF or HTML format and sends it to the user's device.

[1683] 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.

[1684] 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.

[1685] 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.

[1686] 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.

[1687] 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.

[1688] 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.

[1689] 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).

[1690] 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.

[1691] 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."

[1692] 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.

[1693] 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).

[1694] 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.

[1695] 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.

[1696] 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.

[1697] 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.

[1698] 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.

[1699] 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.

[1700] 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.

[1701] 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...

Claims

1. a means for users to upload address information and site photos; a means for the server to obtain information from public databases necessary for risk assessment of the address; A means for the server to analyze disaster prevention risks using generated AI based on address information, site photos, and public database information; A means for the server to generate a disaster prevention risk report from the analysis result; A means for transmitting the generated disaster prevention risk report to a user's terminal by the server; A system including:

2. The system of claim 1 , further comprising means for pre-processing site photos uploaded by users to provide input data to the generating AI.

3. The system of claim 1, further comprising means for evaluating earthquake risk, flood risk, and storm surge risk as risks analyzed by the generating AI.

Images