System

Abstract

A system is provided.SOLUTION: The system includes a means for acquiring typhoon course prediction data, a means for analyzing the acquired typhoon course prediction data to specify a disaster occurrence prediction area, a means for collating position information of a user with the disaster occurrence prediction area to generate a list of affected users, a means for transmitting a warning notification based on the generated list of the affected users, a means for mapping information of the disaster occurrence prediction area on a map and posting it on a homepage, a means for providing a communication continuation means to a desired user, and a means for specifying a base station in the disaster occurrence prediction area and procuring necessary equipment.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] In today's world, with the frequent occurrence of natural disasters such as typhoons, advance prediction and appropriate countermeasures are required. However, current systems do not adequately provide forecast information, notifications regarding the continuation of communications, and safety assurance. Furthermore, preparations and responses regarding the maintenance of base stations are insufficient, resulting in long recovery times. In particular, there are limited means for providing real-time notification services that combine users' location information with disaster prediction information, and for providing communications support to individual users who request it. These issues can make it difficult to ensure users' safety and continue communications. The purpose of this invention is to provide an effective solution to these issues. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for acquiring typhoon path forecast data, a means for analyzing the acquired typhoon path forecast data to identify predicted disaster areas, a means for generating a list of affected users by comparing user location information with the predicted disaster areas, a means for sending alert notifications based on the generated list of affected users, a means for mapping information about the predicted disaster areas on a map and posting it on a website, a means for providing communication continuity means to users who request it, and a means for identifying base stations within the predicted disaster areas and procuring necessary equipment. This system enables the provision of real-time forecast information, notification to users, and support for communication continuity in the event of a disaster such as a typhoon, and also enables the prompt implementation of base station maintenance measures. Furthermore, by periodically acquiring and analyzing typhoon path forecast data, prediction accuracy can be improved. This is expected to ensure user safety and improve the stability of communication infrastructure.

[0006] "Typhoon path forecast data" is data that includes information such as the typhoon's path, speed, scale, and area of ​​impact, and is generated by AI and weather forecasting systems.

[0007] "Means of acquisition" refers to elements that have the function of receiving necessary data from databases, APIs, sensor networks, etc. and incorporating it into the system.

[0008] "Means of analysis" refers to the algorithms, software, and hardware used to process and analyze acquired data and extract meaningful information.

[0009] "Disaster-predicted area" refers to the geographical area that is predicted to be affected by the typhoon based on the acquired typhoon path prediction data.

[0010] "User location information" refers to geographical location data such as latitude and longitude obtained from smartphones, GPS devices, etc.

[0011] The "list of affected users" is a list of users to whom a warning notice should be sent, created based on the location information of users who are included in the disaster predicted area.

[0012] A "warning notification" is a message sent in advance to users living in areas where a disaster is predicted to occur, encouraging them to ensure their safety and evacuate.

[0013] "Means of mapping" refers to map drawing libraries and tools for visually displaying geographic information of disaster-prone areas.

[0014] "Means of posting on the homepage" refers to the technology used to display and update the acquired data and analysis results on a web page in real time.

[0015] "Means for continued communication" refers to equipment and services provided to enable users to continue communication even during a disaster, such as indoor Femto.

[0016] A "base station" is an important infrastructure facility that constitutes a wireless communication network and communicates with user devices.

[0017] "Necessary equipment" refers to tools and parts prepared in advance to maintain base station functionality and enable early recovery in the event of a disaster.

[0018] A "supply chain" refers to a series of processes and a network of people involved in procuring and providing necessary goods and services. [Brief explanation of the drawings]

[0019] [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

[0020] 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.

[0021] First, the terms used in the following description will be explained.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 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.

[0030] 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).

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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."

[0040] This system notifies users of disasters in advance based on typhoon path forecast data, lists predicted disaster areas on the website, and provides support for maintaining communications.The system also prepares base station maintenance measures in advance, enabling rapid recovery in the event of damage.

[0041] System configuration

[0042] This system consists of the following main components:

[0043] server

[0044] User device (smartphone, PC, etc.)

[0045] Home page

[0046] Indoor Femto

[0047] Base Station and Maintenance Equipment

[0048] Program processing

[0049] Acquisition and analysis of typhoon path forecast data

[0050] The server periodically obtains typhoon path prediction data generated by weather forecasting systems and AI via API, updating the latest forecast data every 24 hours, for example.

[0051] The server analyzes the acquired typhoon path prediction data, including the typhoon's path, speed, scale, and latitude and longitude of the areas it will affect. Once this analysis is complete, it identifies areas where disasters are predicted to occur.

[0052] The server compares users' location information with predicted disaster areas and creates a list of users who are likely to be affected.

[0053] User notification

[0054] The server generates a warning notice based on the list of affected users, including information on the storm's path, expected impacts, and safety advice.

[0055] The server will send a warning notice to affected users via email or SMS, which will be displayed on their smartphones or PCs.

[0056] The device displays the received notification as a pop-up to warn the user. For example, a message such as "A typhoon is approaching your area. Please evacuate to a safe place" may be displayed.

[0057] Posted on the homepage

[0058] The server uses a map drawing library to map information about areas where disasters are predicted to occur, and this mapped information is posted on the website in real time.

[0059] By accessing the website, users can check the predicted disaster areas for themselves and their surrounding areas, allowing them to take safety measures in advance.

[0060] Support for continued communication

[0061] The server then processes the request to provide indoor Femto to users who request it to continue communications. When a user expresses their desire, the system will ship the indoor Femto based on the user's address information.

[0062] Users can receive an indoor Femto and install it in their homes to ensure stable communications even during disasters. Specifically, they follow the instructions to set it up and connect their device to the Femto.

[0063] base station maintenance

[0064] The server identifies base stations within the predicted disaster area and procures the necessary equipment in advance.

[0065] The server generates a list of required equipment for each base station and sends the orders to the supply chain system.

[0066] The user (maintenance worker) deploys the necessary equipment to the site before a disaster occurs and performs maintenance work promptly after the disaster occurs.

[0067] Specific examples

[0068] For example, if the AI ​​predicts that a typhoon will approach the Tokyo area 48 hours in advance, the server will analyze the information and send a warning to all users living in the Tokyo area. It will also map areas that overlap with the predicted disaster area and post the information on the website in real time.

[0069] If a user requests an indoor Femto, the server will receive the request and ship the indoor Femto to the user's address. Once the user receives the Femto, they can install it and continue communicating securely.

[0070] In addition, the server will procure the necessary equipment for base stations in the Tokyo area in advance, supporting early recovery after a disaster occurs.

[0071] The processing flow will be explained below.

[0072] Acquisition and analysis of typhoon path forecast data

[0073] Step 1:

[0074] The server periodically sends an HTTP request to the specified API endpoint to obtain the latest typhoon track forecast data, which is received in JSON format.

[0075] Step 2:

[0076] The server parses the received JSON data and extracts information on the typhoon's path, speed, size, and latitude and longitude of the affected area.

[0077] Step 3:

[0078] The server uses the extracted information to identify areas where disasters are predicted to occur and stores the information in a database.

[0079] User notification

[0080] Step 1:

[0081] The server uses the latitude and longitude information of the disaster predicted area to compare with the user location information in the database, thereby generating a list of affected users.

[0082] Step 2:

[0083] The server generates a warning notification message to be sent to each user based on the affected user list. The message includes typhoon information and safety advice.

[0084] Step 3:

[0085] The server uses an email sending API or an SMS sending API to send the generated warning notification message to the affected user.

[0086] Step 4:

[0087] The device will display received emails and SMS as pop-up notifications to alert the user.

[0088] Posted on the homepage

[0089] Step 1:

[0090] The server passes the geographical information of the disaster-prone area to a map drawing library (e.g., Leaflet.js) and maps it on a map.

[0091] Step 2:

[0092] The server uploads the mapped information using the homepage update API and reflects it on the homepage in real time.

[0093] Step 3:

[0094] The user accesses the homepage from a browser and checks information about areas where disasters are predicted to occur.

[0095] Support for continued communication

[0096] Step 1:

[0097] The user contacts the server to request the provision of a means for continuing communication (indoor Femto).

[0098] Step 2:

[0099] The server checks the list of interested users and begins the shipping process for the indoor Femto based on the user's address information.

[0100] Step 3:

[0101] The server sends shipping instructions to the shipping management system and ships the indoor Femto to the relevant user.

[0102] Step 4:

[0103] Once the indoor Femto arrives, users can install it according to the manual to ensure stable communication at home.

[0104] base station maintenance

[0105] Step 1:

[0106] The server identifies base stations within the disaster-prone area in a database.

[0107] Step 2:

[0108] The server generates a list of equipment required for each base station and places orders using the supply chain system API.

[0109] Step 3:

[0110] The server arranges for the procured equipment to be delivered to the designated base station.

[0111] Step 4:

[0112] The user (maintenance worker) uses the equipment procured in advance to carry out maintenance work (inspection, reinforcement, etc.) on the base station before a disaster occurs.

[0113] Step 5:

[0114] After a disaster occurs, the user (maintenance worker) promptly goes to the site and uses the equipment to quickly restore the base station.

[0115] Example 1

[0116] 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."

[0117] With conventional disaster notification systems, it is difficult to efficiently obtain and analyze path prediction data for meteorological disasters such as typhoons, making it impossible to notify users in a timely manner. Furthermore, due to insufficient maintenance of communication infrastructure and the provision of continuous communication methods when a disaster occurs, a rapid response is not possible when a disaster occurs.

[0118] 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.

[0119] In this invention, the server includes means for acquiring weather forecast data, means for analyzing the acquired weather forecast data to identify a disaster-predicted area, means for generating an affected user list by comparing user location information with the disaster-predicted area, means for sending a warning notice based on the generated affected user list, means for mapping information about the disaster-predicted area on a map and posting it on a website, means for providing communication continuity devices to users who request them, and means for identifying communication bases within the disaster-predicted area and procuring the necessary materials. This makes it possible to quickly acquire and analyze weather disaster path forecast data, issue timely warning notices to affected users, and maintain communication infrastructure and provide continuous communication means during a disaster.

[0120] "Weather forecast data" refers to forecast information regarding the path, speed, scale, precipitation amount, etc. of typhoons and other weather phenomena provided by meteorological agencies and weather analysis systems.

[0121] "Disaster-prone area" refers to the area where a specific weather disaster is likely to occur based on analyzed weather forecast data.

[0122] "User location information" refers to information that indicates the user's actual location, such as address information provided by the user or current location data obtained from GPS.

[0123] "Affected User List" means a list of users who reside within or near a disaster-prone area and who are identified as likely to be affected by a disaster.

[0124] "Warning Notice" refers to a warning message sent to affected users that includes the path of the disaster, predicted impacts, and safety advice.

[0125] "Mapping on a map" refers to the process of visually displaying information on areas where disasters are predicted to occur on a map, thereby enabling users to intuitively grasp the danger zone.

[0126] "Posting on the website" refers to uploading map information of disaster-prone areas to the website in real time and making it accessible to the general public.

[0127] "Communication continuity device" refers to equipment that allows users to continue using communication services such as the Internet and telephone even if communication infrastructure is damaged or stopped during a disaster.

[0128] A "communications base" is a basic facility for mobile communications and broadband communications, and refers to infrastructure including antennas, transmitting and receiving equipment, etc.

[0129] "Necessary materials" refers to the equipment, tools, parts, etc. required to maintain and repair communications bases in disaster-prone areas.

[0130] This system uses weather disaster path forecast data to notify users of disasters in advance, publishes disaster-prone areas on a website, and provides support for maintaining communications. It also prepares preservation measures for communications bases in advance, enabling rapid restoration in the event of damage.

[0131] Key components of the system

[0132] This system consists of the following main components:

[0133] server

[0134] User device (smartphone, PC, etc.)

[0135] Website

[0136] Indoor communication devices (e.g. Femto)

[0137] Communications bases and maintenance equipment

[0138] Hardware and Software Configuration

[0139] The server periodically obtains typhoon path forecast data using a weather forecasting system or a generative AI model (e.g., OpenAI (registered trademark) API). Specifically, it obtains JSON-formatted data from the weather data providing API using an HTTP request. The obtained data is stored in a database.

[0140] The server then analyzes this data using a data analysis module (e.g., Python's Pandas or NumPy library). The analysis involves extracting the typhoon's path, speed, and scale, as well as the latitude and longitude of the area it will affect. The disaster-prone area information identified here is then geographically mapped using a geocoding API (e.g., Google (registered trademark) Maps API).

[0141] The server then compares users' location information stored in a database with the identified disaster-prone areas. This comparison generates a list of users likely to be affected. Based on this list, the server generates a warning notice, which includes information on the typhoon's path, predicted impacts, and safety advice.

[0142] To send notifications, the server uses an email sending API or a short message service API (e.g., Twilio) to send the generated notification to the user's smartphone or PC. The device then displays the received notification as a pop-up to alert the user.

[0143] The server then maps the information on the disaster-prone areas using a map drawing library (e.g., Google Maps API) and posts it on a website in real time. Users can access this website to check the disaster-prone areas for themselves and their surroundings.

[0144] To support continued communications, the server will provide a communications device (Femto) to the user if the user requests it. When the user expresses their desire, the system will ship the device based on the user's address information. The user can then install the device in their home and continue secure communications.

[0145] As a maintenance measure for communication bases, the server identifies communication bases located within disaster-prone areas and procures the necessary materials in advance. The server generates a list of materials required for each communication base and sends an order to the supply chain system. The user (maintenance worker) deploys the necessary materials to the site before a disaster occurs and performs maintenance work quickly after the disaster occurs.

[0146] Specific examples

[0147] For example, if the generative AI model predicts a typhoon approaching the Tokyo area 48 hours in advance, the server will analyze this information and send a warning to all users living in the Tokyo area. It will also map areas that overlap with the predicted disaster zone and post the information on the website in real time.

[0148] When a user requests a communication device, the server receives the request and ships the device to the user's address. The user can then install the device and continue communicating safely. In addition, the server pre-procures the materials needed for communication bases in the Tokyo area to support early recovery after a disaster.

[0149] Prompt Sentence Examples

[0150] "A typhoon is approaching your area. Please evacuate to a safe place."

[0151] As described above, the present invention is a system that provides a rapid and accurate response to meteorological disasters, and is equipped with various functions for minimizing damage.

[0152] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0153] Step 1: Obtain weather forecast data

[0154] The server periodically obtains typhoon path forecast data using a weather forecasting system and generative AI model. It accesses the weather data provision API as input and receives JSON-formatted data. This data includes the typhoon's path, speed, scale, and the latitude and longitude of the area it will affect. Specifically, the server calls an API endpoint such as "GET / api / typhoon-forecast" to obtain the latest forecast data. The obtained weather forecast data is obtained as output.

[0155] Step 2: Analyze weather forecast data

[0156] The server analyzes the acquired weather forecast data using a data analysis module (e.g., Python's Pandas or NumPy library). The JSON-formatted weather forecast data acquired in step 1 is used as input. Data analysis extracts the typhoon's path, speed, scale, and the latitude and longitude of the area it will affect. Specifically, the server uses a data analysis library to analyze the data and extract the necessary information. The output is information on disaster-prone areas as a result of the analysis.

[0157] Step 3: Identifying disaster-prone areas

[0158] The server identifies areas where disasters are predicted to occur based on the analyzed data. The information on areas where disasters are predicted obtained in step 2 is used as input. Specifically, the server uses a geocoding API (e.g., Google Maps API) to obtain latitude and longitude information from the analyzed data, and uses this information to map the predicted areas. The output is information on the identified areas where disasters are predicted to occur.

[0159] Step 4: Matching with user location information

[0160] The server compares the user location information stored in the database in advance with the predicted disaster zones identified in step 3. The server uses the user location information and the predicted disaster zone information as input. Specifically, the server executes a database query to extract data on users located within the predicted zones. The output is a list of affected users who are likely to be affected.

[0161] Step 5: Generate a warning notification

[0162] The server generates an alert based on the list of affected users generated in step 4. As input, it uses the list of affected users, information on the typhoon's path, predicted impacts, and safety advice. Specifically, the server uses a text generation library (e.g., a template engine) to generate a customized notification for each user. As output, it obtains an alert for each user.

[0163] Step 6: Sending and displaying notifications

[0164] The server sends the alert notification generated in step 5 to the affected user using an email sending API or a short message service API (e.g., Twilio). The generated alert notification and the affected user's contact information are used as input. Specifically, the server sends the notification data to these APIs and sends the notification. The device displays the received notification as a pop-up to alert the user. As output, the notification is displayed to the user.

[0165] Step 7: Map the disaster zone

[0166] The server uses a map rendering library (e.g., Google Maps API) to map information about disaster-prone areas and post it on a website in real time. The server uses information about disaster-prone areas as input. Specifically, the server uses the map rendering library to generate JavaScript code and embeds it in the HTML of the website. The output is the mapping information about disaster-prone areas displayed on the website in real time.

[0167] Step 8: Providing communication continuity support

[0168] The server then carries out the process of providing indoor communication devices (Femto) to users who wish to continue communication. The user's desired information and address information are used as input. Specifically, the server sends the order data to the order management system, and delivery arrangements are made automatically. The user then installs the received indoor communication device and continues communication safely. The output is that the communication device is provided to the user, ensuring stable communication even during a disaster.

[0169] Step 9: Secure your communications base

[0170] The server identifies communication bases located within areas where disasters are predicted to occur and procures the necessary materials in advance. The input is the predicted disaster area and the location information of the communication bases. Specifically, the server generates a list of communication bases, lists the materials needed for each base, and sends order data to the supply chain system. The user (maintenance worker) deploys the necessary materials to the site before a disaster occurs and performs prompt maintenance work after the disaster occurs. The output is that communication bases can be quickly maintained and repaired.

[0171] (Application example 1)

[0172] 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."

[0173] In recent years, natural disasters such as typhoons have become more frequent, and providing prompt and accurate information is essential to minimize damage. However, current systems lack the technology to link disaster prediction information with user location information and provide appropriate warning notifications. Furthermore, disaster notifications and evacuation route guidance are not provided to autonomous vehicles, making ensuring safety during disasters a challenge. Furthermore, maintenance measures for communication infrastructure such as base stations are insufficient, and a means to ensure communication continuity is also needed.

[0174] 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.

[0175] In this invention, the server includes means for acquiring typhoon path forecast data, means for analyzing the acquired typhoon path forecast data to identify predicted disaster areas, means for generating a list of affected users by comparing user location information with the predicted disaster areas, means for sending alert notifications based on the generated list of affected users, means for mapping information about the predicted disaster areas and posting it on a website, means for providing means for continued communication to users who request it, means for identifying base stations within the predicted disaster areas and procuring necessary equipment, and means for sending disaster alert notifications to autonomous vehicles based on the typhoon path forecast data and suggesting safe evacuation routes. This makes it possible to ensure the safety of users and preserve the communications infrastructure by issuing prompt and accurate alert notifications based on typhoon path information and issuing evacuation instructions to autonomous vehicles.

[0176] "Typhoon path forecast data" is data generated by weather forecasting systems and artificial intelligence, including information on a typhoon's path, speed, size, and the area it will affect.

[0177] A "disaster-prone area" is a geographical area that is likely to be affected by a typhoon, identified based on typhoon path forecast data.

[0178] "Affected users" refers to users who are located within the disaster-prone area and who may be affected by the typhoon.

[0179] A "warning notice" is a warning message sent to affected users that includes information on the typhoon's path, expected impacts, and safety advice.

[0180] "Mapping on a map" means visually displaying information about areas where disasters are predicted to occur using a geographic information system or the like.

[0181] "Website" means an online platform for providing information that is publicly available and accessible to users via the Internet.

[0182] "Means for continued communication" refers to devices and technologies that ensure stable communication even during disasters, and a specific example is indoor Femto.

[0183] A "base station" is a wireless communication facility used to maintain and manage mobile communication networks, and its preservation is crucial in times of disaster.

[0184] An "autonomous vehicle" is a vehicle that is capable of driving autonomously without human operation.

[0185] An "evacuation route" is a recommended route for evacuating to a safe place in the event of a disaster, and is set to avoid the path of a typhoon.

[0186] A "generative AI model" is an artificial intelligence model that learns from large amounts of data and performs tasks such as predicting the path of typhoons and providing evacuation route guidance.

[0187] A "prompt" is an input text given to a generative AI model, and is an instruction that causes the model to provide appropriate answers or information.

[0188] Description: Detailed Description of the Invention

[0189] The present invention relates to a system that provides disaster warning notifications and evacuation route guidance to autonomous vehicles based on typhoon path prediction data.

[0190] System configuration

[0191] The system consists of the following main components:

[0192] 1. Server

[0193] 2. User devices (smartphones, PCs, autonomous vehicle computers)

[0194] 3. Website

[0195] 4. Indoor Femto

[0196] 5. Base Station and Maintenance Equipment

[0197] Program processing

[0198] Acquisition and analysis of typhoon path forecast data

[0199] The server periodically obtains typhoon path prediction data generated by the weather forecasting system and the AI ​​generation model via API. For example, the latest prediction data is updated every 24 hours. The obtained typhoon path prediction data includes the typhoon's path, speed, scale, and the latitude and longitude of the areas it will affect. The server analyzes the obtained typhoon path prediction data and identifies areas where disasters are predicted to occur. Based on the results of this analysis, it generates information on areas where disasters are predicted to occur.

[0200] User notification

[0201] The server compares users' location information with the predicted disaster area and creates a list of users who are likely to be affected. It then generates a warning notice based on the list of affected users and sends it to them via email or SMS. The notice includes information on the typhoon's path, expected impact, and advice on how to ensure safety. The user's device displays the received notice as a pop-up to warn the user.

[0202] Website listing

[0203] The server uses a map drawing library to map information about areas where disasters are predicted to occur. This mapped information is posted on a website in real time. Users can access the website to check the predicted disaster areas for themselves and their surrounding areas, enabling them to take safety measures in advance.

[0204] Support for continued communication

[0205] The server then processes the procedures to provide indoor Femto to users who request it to support continued communications. When a user expresses their desire, the system ships the indoor Femto based on the user's address information. By receiving the indoor Femto and installing it in their home, users can ensure stable communications even in the event of a disaster. Specifically, they follow the manual to set it up and connect their device to the Femto.

[0206] base station maintenance

[0207] The server identifies base stations within the predicted disaster area and procures the necessary equipment in advance. It generates a list of the equipment needed for each base station and sends the order to the supply chain system. The necessary equipment is deployed on-site before a disaster occurs, and maintenance work is carried out promptly after the disaster occurs.

[0208] Disaster alert notifications and evacuation route guidance for autonomous vehicles

[0209] The server sends disaster alert notifications to autonomous vehicles based on typhoon path prediction data. The notifications include typhoon path information, evacuation instructions, and safe evacuation routes. Based on the received alert notifications, the autonomous vehicle's computer sets appropriate evacuation routes and displays instructions to the driver.

[0210] Specific examples

[0211] For example, if a generative AI model predicts a typhoon approaching the Tokyo area 48 hours in advance, the server analyzes the information and sends a warning to all users living in the Tokyo area. It also maps areas overlapping with predicted disaster areas and posts them on a website in real time. If a user requests an indoor Femto, the server receives the request and ships it to the user's address. The user can then install the Femto in their home and continue secure communications. Furthermore, the server pre-procures the necessary equipment for base stations in the Tokyo area to support early recovery after a disaster. For autonomous vehicles, it sets up appropriate evacuation routes based on the typhoon's path in real time and displays instructions to the driver.

[0212] Prompt Sentence Examples

[0213] "Analyze the latest typhoon path forecast data to determine if it will affect the Tokyo area. If so, generate an alert notification with evacuation routes and send it to the driver of the autonomous vehicle. The data will be provided in the following format:

[0214] {

[0215] 'typhoon': {

[0216] 'path': 'Typhoon path information',

[0217] 'speed': 'speed of the typhoon',

[0218] 'scale': 'scale of the typhoon',

[0219] 'affected_areas': 'List of affected areas'

[0220] }

[0221] }"

[0222] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0223] Step 1:

[0224] The server periodically obtains typhoon path prediction data generated by the weather forecasting system and generative AI model via the API. The typhoon path prediction data obtained from the API as input includes the typhoon's path, speed, scale, and the latitude and longitude of the area it will affect. The server saves this data as output and prepares it for analysis.

[0225] Step 2:

[0226] The server analyzes the acquired typhoon path prediction data to identify areas where disasters are predicted to occur. The input data analysis includes the path, speed, scale, and latitude and longitude of the affected areas, and the resulting output is the predicted disaster areas. Specifically, the server applies a data analysis algorithm to calculate the degree of impact for each area.

[0227] Step 3:

[0228] The server compares the user's location information with the predicted disaster area and creates a list of users who are likely to be affected. The input location information is stored in a database and is used for comparison. The output is a list of affected users. The server performs the matching process using a comparison algorithm.

[0229] Step 4:

[0230] The server generates a warning notification based on the list of affected users and sends it to them via email or SMS. The notification content includes information on the typhoon's path, expected impacts, and safety advice. The input is the generated warning notification message, and the output is the warning notification to be sent to the user. Specifically, the server sends the message using an SMTP or SMS gateway.

[0231] Step 5:

[0232] The server uses a map drawing library to map information on disaster-prone areas and publishes it on a website in real time. The input is map drawing data, and the website is updated using an API. The output is the updated map information displayed on the website. The server visually processes the mapping using the map drawing library.

[0233] Step 6:

[0234] The server performs the procedure to provide indoor Femto to requesting users to support continued communications. The input is the desired request and address information, and the output is a shipping instruction. Specifically, the server works in conjunction with the logistics system to send a shipping instruction for the indoor Femto.

[0235] Step 7:

[0236] The server identifies base stations within the predicted disaster area and procures the necessary equipment in advance. The input includes base station information and a list of required equipment, and the output includes instructions for procuring the equipment. The server then sends the order to the supply chain system.

[0237] Step 8:

[0238] The server sends disaster alert notifications to autonomous vehicles based on typhoon path prediction data and suggests safe evacuation routes. The input includes path information and evacuation routes, and the output includes evacuation instructions to be displayed on the autonomous vehicle's display. Specifically, the server uses a generative AI model to calculate appropriate evacuation routes and generates notifications using prompt text.

[0239] 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.

[0240] This invention combines a system that notifies users in advance of disasters based on typhoon path forecast data, publishes predicted disaster areas on a website, and provides support for maintaining communications, with an emotion engine that recognizes the user's emotions.The invention also prepares base station maintenance measures in advance, enables rapid recovery in the event of damage, and responds appropriately according to the user's emotional state.

[0241] System configuration

[0242] This system consists of the following main components:

[0243] server

[0244] User device (smartphone, PC, etc.)

[0245] Home page

[0246] Indoor Femto

[0247] Base Station and Maintenance Equipment

[0248] Emotion Engine

[0249] Program processing

[0250] Acquisition and analysis of typhoon path forecast data

[0251] The server periodically obtains typhoon path prediction data generated by weather forecasting systems and AI via API, updating the latest forecast data every 24 hours, for example.

[0252] The server analyzes the acquired typhoon path prediction data, including the typhoon's path, speed, scale, and latitude and longitude of the areas it will affect. Once this analysis is complete, it identifies areas where disasters are predicted to occur.

[0253] The server compares users' location information with predicted disaster areas and creates a list of users who are likely to be affected.

[0254] Emotion recognition by emotion engine

[0255] The device periodically captures the user's facial expressions and voice using sensors such as a camera and microphone, and sends the data to a server.

[0256] The server analyzes the received sensor data using an emotion engine to identify the user's emotional state (e.g., stress level or anxiety).

[0257] User notification

[0258] The server generates a warning notification message to be sent to each user based on the affected user list.

[0259] The server customizes the content of the alert notification depending on the user's emotional state as analyzed by the emotion engine, for example adding more specific safety advice if high stress levels are detected.

[0260] The server uses an email sending API or an SMS sending API to send the generated warning notification message to the affected user.

[0261] The device will display received emails and SMS as pop-up notifications to alert the user.

[0262] Posted on the homepage

[0263] The server uses a map drawing library to map the geographical information of disaster-prone areas, and this mapped information is posted on the website in real time.

[0264] By accessing the website, users can check the predicted disaster areas for themselves and their surrounding areas, allowing them to take safety measures in advance.

[0265] Support for continued communication

[0266] The server will then process the provision of indoor Femto to users who request it to support continued communications. When a user requests it, the server will ship the indoor Femto based on the user's address information.

[0267] Users receive an indoor Femto and install it in their homes to ensure stable communications even in the event of a disaster. Specifically, they follow the instructions to set it up and connect their device to the Femto.

[0268] base station maintenance

[0269] The server identifies base stations within the predicted disaster area and procures the necessary equipment in advance.

[0270] The server generates a list of required equipment for each base station and sends the orders to the supply chain system.

[0271] The user (maintenance worker) deploys the necessary equipment to the site before a disaster occurs and performs maintenance work promptly after the disaster occurs.

[0272] Specific examples

[0273] For example, if the AI ​​predicts that a typhoon will approach the Tokyo area 48 hours in advance, the server will analyze the information and send a warning notice to all users living in the Tokyo area.

[0274] If the emotion engine detects that a particular user is showing high stress levels, the server will send more detailed advice to that user, such as providing specific evacuation locations. It also maps areas that overlap with predicted disaster areas and posts the information on the website in real time.

[0275] If a user requests an indoor Femto, the server will receive the request and ship the indoor Femto to the user's address. Once the user receives the Femto, they can install it and continue communicating securely.

[0276] In addition, the server will procure the necessary equipment for base stations in the Tokyo area in advance, supporting early recovery after a disaster occurs.

[0277] The processing flow will be explained below.

[0278] Acquisition and analysis of typhoon path forecast data

[0279] Step 1:

[0280] The server sends an HTTP request to the specified API endpoint every 24 hours to obtain the latest typhoon track forecast data, which is received in JSON format.

[0281] Step 2:

[0282] The server parses the received JSON data and extracts information about the typhoon's path, speed, size, and latitude and longitude of the area it will affect.

[0283] Step 3:

[0284] The server uses the extracted information to identify areas where disasters are predicted to occur and stores the information in a database.

[0285] Emotion recognition by emotion engine

[0286] Step 1:

[0287] The device periodically captures the user's facial expressions and voice using sensors such as a camera and microphone, and sends the data to a server.

[0288] Step 2:

[0289] The server analyzes the received sensor data using an emotion engine to identify the user's emotional state (e.g., stress level or anxiety).

[0290] Step 3:

[0291] The server stores the identified emotional states in a database.

[0292] User notification

[0293] Step 1:

[0294] The server uses the latitude and longitude information of the disaster predicted area to compare with the user location information in the database, thereby generating a list of affected users.

[0295] Step 2:

[0296] The server generates a warning notification message to be sent to each user based on the affected user list. The message includes typhoon information and safety advice.

[0297] Step 3:

[0298] The server customizes the content of the alert notification depending on the user's emotional state as analyzed by the emotion engine, for example adding specific safety advice if high stress levels are detected.

[0299] Step 4:

[0300] The server uses an email sending API or an SMS sending API to send the generated warning notification message to the affected user.

[0301] Step 5:

[0302] The device will display received emails and SMS as pop-up notifications to alert the user.

[0303] Posted on the homepage

[0304] Step 1:

[0305] The server passes the geographical information of the disaster-prone area to a map drawing library (e.g., Leaflet.js) and maps it on a map.

[0306] Step 2:

[0307] The server uploads the mapped information using the homepage update API and reflects it on the homepage in real time.

[0308] Step 3:

[0309] The user accesses the homepage from a browser and checks information about areas where disasters are predicted to occur.

[0310] Support for continued communication

[0311] Step 1:

[0312] The user contacts the server to request the provision of a means for continuing communication (indoor Femto).

[0313] Step 2:

[0314] The server checks the list of interested users and begins the shipping process for the indoor Femto based on the user's address information.

[0315] Step 3:

[0316] The server sends shipping instructions to the shipping management system and ships the indoor Femto to the relevant user.

[0317] Step 4:

[0318] Once the indoor Femto arrives, users can install it according to the manual to ensure stable communication at home.

[0319] base station maintenance

[0320] Step 1:

[0321] The server identifies base stations within the disaster-prone area in a database.

[0322] Step 2:

[0323] The server generates a list of equipment required for each base station and places orders using the supply chain system API.

[0324] Step 3:

[0325] The server arranges for the procured equipment to be delivered to the designated base station.

[0326] Step 4:

[0327] The user (maintenance worker) uses the equipment procured in advance to carry out maintenance work (inspection, reinforcement, etc.) on the base station before a disaster occurs.

[0328] Step 5:

[0329] After a disaster occurs, the user (maintenance worker) promptly goes to the site and uses the equipment to quickly restore the base station.

[0330] Example 2

[0331] 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."

[0332] Conventional typhoon path prediction systems predict the path of a typhoon and issue warnings to users, but they are unable to address the emotional state of users or the maintenance of communication infrastructure. Providing appropriate countermeasures is particularly important when users are experiencing high levels of stress or anxiety. It is also important to ensure the continuity of communications during disasters and to quickly maintain base stations. Therefore, it is desirable to provide a notification system that can respond to disasters from multiple angles and takes into account the emotional state of users.

[0333] 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.

[0334] In this invention, the server includes means for acquiring typhoon path forecast data, means for analyzing the acquired typhoon path forecast data to identify a disaster-predicted area, means for generating a list of affected users by comparing user location information with the disaster-predicted area, means for collecting and analyzing emotional data of affected users, means for customizing and sending alert notification messages based on the emotion analysis results, means for sending alert notifications based on the generated list of affected users, means for mapping information about the disaster-predicted area on a map and posting it on a website, means for providing means for continuing communications to users who request it, and means for identifying base stations within the disaster-predicted area and procuring the necessary equipment. This makes it possible to provide alert notifications customized in consideration of the emotional state of users, thereby enabling continued communications and rapid base station maintenance in the event of a disaster.

[0335] "Typhoon path forecast data" is information about a typhoon's path, speed, scale, and area of ​​impact, generated by weather forecasting systems and artificial intelligence.

[0336] "Disaster-predicted areas" refer to geographical locations that are highly likely to be affected by disasters, as analyzed based on typhoon path prediction data.

[0337] "User location information" refers to the user's current location or specified address information.

[0338] The "list of affected users" is a list of users who are likely to be affected by a disaster, generated by comparing the predicted disaster area with the location information of the users.

[0339] "Emotional data" is data captured from a user's facial expressions, voice, etc., and used to analyze the user's emotional state.

[0340] "Emotion analysis results" are the results of analyzing the user's emotional state (stress level, anxiety, etc.) based on emotion data.

[0341] A "warning notification message" is a notification sent to users in an area where a disaster is predicted to occur, and includes specific evacuation actions and countermeasures.

[0342] "Mapping" refers to drawing geographical information of areas where disasters are predicted to occur on a map.

[0343] "Means for continuing communication" refers to equipment and methods for ensuring communication stability during disasters, such as indoor Femto.

[0344] A "base station" is a relay device in a communication network, and is a facility for communicating with mobile terminals.

[0345] "Necessary supplies" refers to the equipment, parts, materials, etc. required to maintain or restore the functions of base stations in the event of a disaster.

[0346] This invention combines a system that notifies users in advance of disasters based on typhoon path forecast data, publishes predicted disaster areas on a website, and provides support for maintaining communications, with an emotion engine that recognizes the user's emotions. Furthermore, it can prepare base station maintenance measures in advance, enable rapid recovery in the event of damage, and respond appropriately according to the user's emotional state.

[0347] The system is configured as follows: The main components include a server, user terminals (smartphones, PCs, etc.), a homepage, indoor Femto, base stations and maintenance equipment, and an emotion engine.

[0348] Acquisition and analysis of typhoon path forecast data

[0349] The server periodically obtains typhoon path prediction data generated by weather forecasting systems and artificial intelligence via API. For example, it calls "Weather API XYZ" every 24 hours and stores the data. The server then analyzes the data using "Data Analysis Library ABC" to identify the typhoon's path, speed, scale, and affected areas (latitude, longitude, etc.). Based on the analysis results, it identifies areas where disasters are predicted to occur and compares them with users' location information to create a list of users who are likely to be affected. As a specific example, if a typhoon is predicted to approach the Tokyo area, users who reside in Tokyo will be listed.

[0350] Emotion recognition by emotion engine

[0351] The device periodically captures the user's facial expressions and voice using sensors such as a camera and microphone, encrypts the data, and sends it to a server. The server then uses the "Emotion Analysis Engine XYZ" to analyze the received sensor data and identify the user's emotional state (such as stress level or anxiety). This process allows the user's emotional state to be understood.

[0352] User notification

[0353] The server generates a warning notification message based on the list of affected users. It uses the "Message Generation Library ABC" to create a notification message that includes details about the typhoon and recommended actions. It also customizes the content of the warning notification based on the analysis results of the emotion engine. For example, for users with high stress levels, it could include specific evacuation locations and countermeasures. The server uses an email sending API or SMS sending API to send the generated warning notification message to affected users. The device displays the received email or SMS as a pop-up notification to alert the user.

[0354] Posted on the homepage

[0355] The server maps the geographical information of disaster-prone areas using the "Map Drawing Library GeoLib XYZ." This mapped information is posted on the website in real time. By accessing the website, users can check the disaster-prone areas and take safety measures in advance.

[0356] Support for continued communication

[0357] When the server receives a request for communication continuity support from a user, it ships an indoor Femto based on the user's address information. Specifically, it generates a shipping instruction and connects it to the logistics system. The user receives the indoor Femto and installs it in their home, ensuring stable communication even in the event of a disaster. The installation procedure is carried out according to the enclosed manual.

[0358] base station maintenance

[0359] The server identifies base stations within areas where disasters are predicted to occur and procures the necessary equipment in advance. It uses a geographic information system to list the applicable base stations, generates an equipment list for each base station, and sends orders to the supply chain system. The user (maintenance worker) deploys the necessary equipment on-site before a disaster occurs, and then quickly performs maintenance work on the base stations after the disaster occurs.

[0360] Examples of concrete examples and prompts

[0361] For example, if the AI ​​predicts that a typhoon will approach the Tokyo area 48 hours in advance, the server will analyze the information and send a warning to users living in the Tokyo area. If the emotion engine detects that a particular user is showing high stress levels, the server will send more detailed advice to that user, such as providing specific evacuation locations. The server will also map areas predicted to be affected by disasters and post them on the website in real time.

[0362] Example prompt: "A typhoon is approaching the Tokyo area. Generate an appropriate warning notification message based on the disaster forecast and the user's emotional state."

[0363] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0364] Step 1: Obtaining typhoon track forecast data

[0365] The server periodically obtains the latest typhoon path forecast data generated by weather forecasting systems and artificial intelligence via API. The input is typhoon path forecast data obtained from "Weather API XYZ," and the output is raw data stored in a database on the server. Specifically, the server schedules an API call every 24 hours, receives the response data in JSON format, and stores it in the database.

[0366] Step 2: Analysis of typhoon track forecast data

[0367] The server analyzes the acquired typhoon path prediction data and identifies the typhoon's path, speed, scale, and the latitude and longitude of the area it will affect. The input is the raw data acquired earlier, and the output is the analyzed typhoon information (path, speed, scale, latitude and longitude). Specifically, it uses the "Data Analysis Library ABC" to analyze and extract various typhoon data and convert it into an easy-to-understand format.

[0368] Step 3: Identifying areas where disasters are likely to occur

[0369] The server identifies areas where disasters are predicted to occur based on the analysis results. The input is the analyzed typhoon information, and the output is geographic information on the areas where disasters are predicted to occur. Specifically, the affected area is mapped using a geographic information system (GIS) and the data is saved.

[0370] Step 4: List affected users

[0371] The server compares the predicted disaster area with user location information and generates a list of users who are likely to be affected. The input is a database of user location information and predicted disaster area information, and the output is a list of affected users. Specifically, it runs an SQL query based on the location information to extract and list the relevant users.

[0372] Step 5: Capturing and Sending Sensor Data

[0373] The device periodically captures the user's facial expressions and voice using sensors such as a camera and microphone, and sends the data to a server. The input is the facial expression and voice data captured by the device, and the output is the emotion data sent to the server. Specifically, the data is collected every hour using a facial recognition API and a voice analysis API, encrypted, and sent to the server.

[0374] Step 6: Sentiment Analysis

[0375] The server analyzes the received sensor data using the "Emotion Analysis Engine XYZ" to identify the user's emotional state. The input is sensor data, and the output is the result of identifying the emotional state. Specifically, it uses algorithms that analyze facial muscle movements and tone of voice to identify emotional states such as stress levels and anxiety.

[0376] Step 7: Generate a warning notification message

[0377] The server generates a warning notification message based on the affected user list. The input is the affected user list and disaster predicted area information, and the output is a warning notification message. Furthermore, the notification content is customized according to the results of sentiment analysis. Specifically, the "Message Generation Library ABC" is used to create a notification message that includes details of the typhoon and evacuation instructions.

[0378] Step 8: Sending alert notifications

[0379] The server then uses an email or SMS API to send the generated alert notification message to affected users. The input is the alert notification message, and the output is the sent notification. Specifically, the API is called and a message is sent to each user's contact information.

[0380] Step 9: Post disaster information on your website

[0381] The server maps the geographic information of disaster-predicted areas using the "Map Drawing Library GeoLib XYZ" and posts it on the website in real time. The input is the geographic information of disaster-predicted areas, and the output is the updated content of the website. Specifically, the map information is updated regularly and reflected on the website in real time using an API.

[0382] Step 10: Providing communication continuity support

[0383] The server receives a request for communication continuity support from the user and ships the indoor Femto based on the user's address information. The input is the request information and the user's address information, and the output is a shipping instruction. Specifically, it works in conjunction with the logistics system to carry out the procedures for shipping the necessary equipment.

[0384] Step 11: Prepare for base station maintenance work

[0385] The server identifies base stations within disaster-predicted areas and procures the necessary equipment in advance. The input is base station data and disaster-predicted area information, and the output is an equipment list and ordering information. Specifically, it uses GIS to list the applicable base stations, and creates and orders a list of the necessary equipment.

[0386] Step 12: Carry out base station maintenance work

[0387] The user (maintenance worker) deploys the necessary equipment for each identified base station on-site and performs maintenance work promptly after a disaster occurs. The input is an equipment list and base station information, and the output is the maintenance status of the base station. Specifically, the user travels to the site and performs the necessary maintenance work to support rapid recovery.

[0388] (Application example 2)

[0389] 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."

[0390] The problem that this invention aims to solve is to provide users with prompt and accurate notifications when a natural disaster such as a typhoon is approaching, and to provide information customized to the user's emotional state. This will increase the accuracy of the information received by users, reduce stress and anxiety, and support the continuity of communications and the rapid recovery of base stations.

[0391] 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.

[0392] In this invention, the server includes means for acquiring typhoon path forecast data, means for analyzing the acquired typhoon path forecast data to identify a disaster-predicted area, means for generating a list of affected users by comparing user location information with the disaster-predicted area, means for transmitting a warning notice based on the generated list of affected users, means for capturing the user's facial expression and voice using a sensor in the user terminal and analyzing it with an emotion engine to identify the user's emotional state, means for customizing the content of the warning notice according to the user's emotional state, means for mapping information about the disaster-predicted area on a map and posting it on a homepage, means for providing means for communication continuity to users who request it, and means for identifying base stations within the disaster-predicted area and procuring the necessary equipment. This allows for the server to provide users with emergency disaster information and send customized notifications according to the user's emotional state, enabling the continuation of communication and the rapid restoration of base stations.

[0393] "Typhoon path forecast data" is data that includes information on the path, speed, scale, and areas affected by a typhoon, calculated using weather forecasting systems and artificial intelligence.

[0394] "Disaster-prone areas" are areas that are likely to be affected by typhoons, as identified by analyzing typhoon path prediction data.

[0395] "User Location Information" means geographic data about a User's current location obtained from a smartphone or other GPS-enabled device.

[0396] The "list of affected users" is a list of users who are likely to be affected by the typhoon, generated by comparing the predicted disaster area with the user's location information.

[0397] A "warning notice" is a message sent to affected users to warn them in advance about the approach and impact of a typhoon.

[0398] An "emotion engine" is a software system that analyzes sensor data to identify a user's emotional state (e.g., stress level or anxiety).

[0399] "Mapping on a map" means displaying information about disaster-prone areas on a geographical map.

[0400] A "home page" is a page that is part of a website accessible on the Internet and provides information to users.

[0401] "Means for continued communication" refers to equipment and services provided to ensure stable communication even during disasters.

[0402] A "base station" is a facility or equipment for communicating with mobile terminals in a wireless communication network.

[0403] "Essential equipment" refers to spare parts and equipment required for the base station to continue to function normally.

[0404] A "sensor" is a device used to capture a user's facial expressions and voice.

[0405] "Emotional state" refers to the user's psychological state (e.g., stress, anxiety, etc.).

[0406] A "customized notification" is an alert notification message whose content is tailored to the user's emotional state.

[0407] A "prompt" is text that is input to a generative AI model and serves as an instruction to execute a specific generation task.

[0408] The present invention relates to a system that notifies users of disasters in advance based on typhoon path forecast data and provides information customized according to the user's emotional state. This system is composed of the following hardware and software.

[0409] Program processing and technology used

[0410] 1. Acquisition and analysis of typhoon track forecast data

[0411] The server periodically retrieves typhoon path prediction data from the API via a weather forecasting system and AI (artificial intelligence). The specific software used is the Python requests library.

[0412] The acquired data is analyzed to identify the typhoon's path, speed, scale, and affected area. For the analysis, Python data analysis libraries (e.g., Pandas, NumPy) are used.

[0413] 2. Identifying areas where disasters are predicted to occur and creating a list of affected users

[0414] The server identifies areas where disasters are predicted to occur based on the typhoon path prediction data it has acquired. This area information is then mapped onto a map using geographic information system (GIS) software (e.g., Leaflet, Mapbox).

[0415] The server compares users' location information with predicted disaster areas and generates a "list of affected users" who are likely to be affected by the typhoon.

[0416] 3. User Emotion Recognition and Notification Message Customization

[0417] The device uses the smartphone's camera and microphone to capture the user's facial expressions and voice, and sends the data to a server using OpenCV (an image processing library) and deep learning frameworks (e.g., TENSORFLOW (registered trademark), Keras).

[0418] The server analyzes the received sensor data using an emotion engine to identify the user's emotional state (stress level and anxiety).

[0419] The server customizes the alert notification content according to the user's emotional state based on the analysis results of the emotion engine, and generates a prompt using a generative AI model. Examples of prompts include:

[0420] A typhoon is forecast to approach your area within the next 48 hours. Please prepare to evacuate. High stress levels have been detected. Please confirm specific evacuation locations and emergency contact information.

[0421] 4. Notifications and Website Posting

[0422] Based on the generated list of affected users, the server uses an email sending API or an SMS sending API to send a customized warning notification message to each user.

[0423] The device displays received emails and SMS as pop-up notifications, prompting the user to take appropriate action.

[0424] Information on predicted disaster areas is posted in real time on the website using a map drawing library, allowing users to access the website and check the predicted disaster areas for themselves and their surrounding areas.

[0425] 5. Support for continued communications and base station maintenance

[0426] The server will then process the delivery of an indoor Femto to requesting users to support continued communications. When a user requests an indoor Femto, the server will ship the Femto based on the user's address information.

[0427] The server identifies base stations within the predicted disaster area, generates an equipment list, and procures the necessary equipment in advance. To support the rapid recovery of base stations, the server uses a supply chain system to deploy the necessary equipment to the site.

[0428] Specific examples

[0429] For example, if the AI ​​predicts a typhoon approaching the Tokyo area 48 hours in advance, the server analyzes the information and sends a warning to all users living in the Tokyo area. If the emotion engine detects a high stress level, the server sends detailed advice to the user, such as providing specific evacuation locations. The server also maps areas that overlap with predicted disaster areas and posts the information on the website in real time. If a user requests an indoor Femto, the server receives the request and ships the Femto to the user's address. The user can then install the Femto and continue communications. Furthermore, the server procures the necessary equipment for base stations in the Tokyo area in advance to support rapid recovery after a disaster occurs.

[0430] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0431] Step 1:

[0432] The server periodically obtains typhoon path forecast data generated by weather forecasting systems and AI via an API. This is done using the Python requests library. The input is the typhoon path forecast data obtained from the API, and the output is raw data that can be analyzed.

[0433] Step 2:

[0434] The server analyzes the acquired typhoon path prediction data and extracts information on the typhoon's path, speed, scale, and the area it will affect (latitude and longitude). This analysis uses data analysis libraries such as Python's Pandas and NumPy. The input is the acquired raw data, and the output is a dataset containing the analysis results.

[0435] Step 3:

[0436] The server uses the analysis results to identify areas where disasters are predicted to occur using geographic information system (GIS) software (e.g., Leaflet, Mapbox). The input is a dataset containing the analysis results, and the output is map data drawn by the GIS software.

[0437] Step 4:

[0438] The server compares the user's location information with the predicted disaster area and generates a list of affected users. The input is the user's location information and map data drawn by GIS software, and the output is the list of affected users.

[0439] Step 5:

[0440] The device uses the smartphone's camera and microphone to capture the user's facial expressions and voice, and sends the data to the server. The technology used is OpenCV (an image processing library). The input is the raw data of the user's facial expressions and voice, and the output is the sensor data sent to the server.

[0441] Step 6:

[0442] The server identifies the user's emotional state (stress level, anxiety, etc.) based on the sensor data analyzed by the emotion engine. The software used is a deep learning framework such as TensorFlow or Keras. The input is the sensor data, and the output is the analysis result of the emotional state.

[0443] Step 7:

[0444] The server customizes the content of the alert notification message based on the results of the emotional state analysis and generates a prompt using a generative AI model. For example, it generates a prompt such as, "A typhoon is predicted to approach your area within 48 hours. Please prepare for evacuation. High stress levels have been detected. Please confirm specific evacuation locations and emergency contact information." The input is the results of the emotional state analysis, and the output is a customized notification message.

[0445] Step 8:

[0446] The server uses the email sending API or SMS sending API to send a customized warning notification message to each user based on the generated affected user list. The input is the customized notification message and the affected user list, and the output is the sent warning notification message.

[0447] Step 9:

[0448] The terminal displays the received email or SMS as a pop-up notification to alert the user. The input is the sent warning notification message, and the output is the pop-up notification displayed on the terminal.

[0449] Step 10:

[0450] The server maps information about disaster-predicted areas onto a map and posts it on the website in real time. The software used is a map drawing library (e.g., Leaflet, Mapbox). The input is information about disaster-predicted areas, and the output is updated map data for the website.

[0451] Step 11:

[0452] The server performs the procedure to provide indoor Femto to requesting users to support continuous communication. When a user expresses a desire, the server ships the indoor Femto based on the user's address information. The input is the user's wish list and address information, and the output is the completion data of the shipping procedure.

[0453] Step 12:

[0454] The server identifies base stations within the predicted disaster area, generates an equipment list, and procures the necessary equipment in advance. The technology used is a supply chain system. The input is base station information and data on the predicted disaster area, and the output is the generated equipment list.

[0455] Step 13:

[0456] The server deploys the necessary equipment to the site through the supply chain system, and the maintenance worker carries out the maintenance work. The input is an equipment list, and the output is the deployed equipment and the completion data of the maintenance work.

[0457] 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.

[0458] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0459] 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.

[0460] [Second embodiment]

[0461] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0462] 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.

[0463] 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).

[0464] 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.

[0465] 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.

[0466] 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).

[0467] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0468] 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.

[0469] 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.

[0470] 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.

[0471] 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.

[0472] 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."

[0473] This system notifies users of disasters in advance based on typhoon path forecast data, lists predicted disaster areas on the website, and provides support for maintaining communications.The system also prepares base station maintenance measures in advance, enabling rapid recovery in the event of damage.

[0474] System configuration

[0475] This system consists of the following main components:

[0476] server

[0477] User device (smartphone, PC, etc.)

[0478] Home page

[0479] Indoor Femto

[0480] Base Station and Maintenance Equipment

[0481] Program processing

[0482] Acquisition and analysis of typhoon path forecast data

[0483] The server periodically obtains typhoon path prediction data generated by weather forecasting systems and AI via API, updating the latest forecast data every 24 hours, for example.

[0484] The server analyzes the acquired typhoon path prediction data, including the typhoon's path, speed, scale, and latitude and longitude of the areas it will affect. Once this analysis is complete, it identifies areas where disasters are predicted to occur.

[0485] The server compares users' location information with predicted disaster areas and creates a list of users who are likely to be affected.

[0486] User notification

[0487] The server generates a warning notice based on the list of affected users, including information on the storm's path, expected impacts, and safety advice.

[0488] The server will send a warning notice to affected users via email or SMS, which will be displayed on their smartphones or PCs.

[0489] The device displays the received notification as a pop-up to warn the user. For example, a message such as "A typhoon is approaching your area. Please evacuate to a safe place" may be displayed.

[0490] Posted on the homepage

[0491] The server uses a map drawing library to map information about areas where disasters are predicted to occur, and this mapped information is posted on the website in real time.

[0492] By accessing the website, users can check the predicted disaster areas for themselves and their surrounding areas, allowing them to take safety measures in advance.

[0493] Support for continued communication

[0494] The server then processes the request to provide indoor Femto to users who request it to continue communications. When a user expresses their desire, the system will ship the indoor Femto based on the user's address information.

[0495] Users can receive an indoor Femto and install it in their homes to ensure stable communications even during disasters. Specifically, they follow the instructions to set it up and connect their device to the Femto.

[0496] base station maintenance

[0497] The server identifies base stations within the predicted disaster area and procures the necessary equipment in advance.

[0498] The server generates a list of required equipment for each base station and sends the orders to the supply chain system.

[0499] The user (maintenance worker) deploys the necessary equipment to the site before a disaster occurs and performs maintenance work promptly after the disaster occurs.

[0500] Specific examples

[0501] For example, if the AI ​​predicts that a typhoon will approach the Tokyo area 48 hours in advance, the server will analyze the information and send a warning to all users living in the Tokyo area. It will also map areas that overlap with the predicted disaster area and post the information on the website in real time.

[0502] If a user requests an indoor Femto, the server will receive the request and ship the indoor Femto to the user's address. Once the user receives the Femto, they can install it and continue communicating securely.

[0503] In addition, the server will procure the necessary equipment for base stations in the Tokyo area in advance, supporting early recovery after a disaster occurs.

[0504] The processing flow will be explained below.

[0505] Acquisition and analysis of typhoon path forecast data

[0506] Step 1:

[0507] The server periodically sends an HTTP request to the specified API endpoint to obtain the latest typhoon track forecast data, which is received in JSON format.

[0508] Step 2:

[0509] The server parses the received JSON data and extracts information on the typhoon's path, speed, size, and latitude and longitude of the affected area.

[0510] Step 3:

[0511] The server uses the extracted information to identify areas where disasters are predicted to occur and stores the information in a database.

[0512] User notification

[0513] Step 1:

[0514] The server uses the latitude and longitude information of the disaster predicted area to compare with the user location information in the database, thereby generating a list of affected users.

[0515] Step 2:

[0516] The server generates a warning notification message to be sent to each user based on the affected user list. The message includes typhoon information and safety advice.

[0517] Step 3:

[0518] The server uses an email sending API or an SMS sending API to send the generated warning notification message to the affected user.

[0519] Step 4:

[0520] The device will display received emails and SMS as pop-up notifications to alert the user.

[0521] Posted on the homepage

[0522] Step 1:

[0523] The server passes the geographical information of the disaster-prone area to a map drawing library (e.g., Leaflet.js) and maps it on a map.

[0524] Step 2:

[0525] The server uploads the mapped information using the homepage update API and reflects it on the homepage in real time.

[0526] Step 3:

[0527] The user accesses the homepage from a browser and checks information about areas where disasters are predicted to occur.

[0528] Support for continued communication

[0529] Step 1:

[0530] The user contacts the server to request the provision of a means for continuing communication (indoor Femto).

[0531] Step 2:

[0532] The server checks the list of interested users and begins the shipping process for the indoor Femto based on the user's address information.

[0533] Step 3:

[0534] The server sends shipping instructions to the shipping management system and ships the indoor Femto to the relevant user.

[0535] Step 4:

[0536] Once the indoor Femto arrives, users can install it according to the manual to ensure stable communication at home.

[0537] base station maintenance

[0538] Step 1:

[0539] The server identifies base stations within the disaster-prone area in a database.

[0540] Step 2:

[0541] The server generates a list of equipment required for each base station and places orders using the supply chain system API.

[0542] Step 3:

[0543] The server arranges for the procured equipment to be delivered to the designated base station.

[0544] Step 4:

[0545] The user (maintenance worker) uses the equipment procured in advance to carry out maintenance work (inspection, reinforcement, etc.) on the base station before a disaster occurs.

[0546] Step 5:

[0547] After a disaster occurs, the user (maintenance worker) promptly goes to the site and uses the equipment to quickly restore the base station.

[0548] Example 1

[0549] 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."

[0550] With conventional disaster notification systems, it is difficult to efficiently obtain and analyze path prediction data for meteorological disasters such as typhoons, making it impossible to notify users in a timely manner. Furthermore, due to insufficient maintenance of communication infrastructure and the provision of continuous communication methods when a disaster occurs, a rapid response is not possible when a disaster occurs.

[0551] 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.

[0552] In this invention, the server includes means for acquiring weather forecast data, means for analyzing the acquired weather forecast data to identify a disaster-predicted area, means for generating an affected user list by comparing user location information with the disaster-predicted area, means for sending a warning notice based on the generated affected user list, means for mapping information about the disaster-predicted area on a map and posting it on a website, means for providing communication continuity devices to users who request them, and means for identifying communication bases within the disaster-predicted area and procuring the necessary materials. This makes it possible to quickly acquire and analyze weather disaster path forecast data, issue timely warning notices to affected users, and maintain communication infrastructure and provide continuous communication means during a disaster.

[0553] "Weather forecast data" refers to forecast information regarding the path, speed, scale, precipitation amount, etc. of typhoons and other weather phenomena provided by meteorological agencies and weather analysis systems.

[0554] "Disaster-prone area" refers to the area where a specific weather disaster is likely to occur based on analyzed weather forecast data.

[0555] "User location information" refers to information that indicates the user's actual location, such as address information provided by the user or current location data obtained from GPS.

[0556] "Affected User List" means a list of users who reside within or near a disaster-prone area and who are identified as likely to be affected by a disaster.

[0557] "Warning Notice" refers to a warning message sent to affected users that includes the path of the disaster, predicted impacts, and safety advice.

[0558] "Mapping on a map" refers to the process of visually displaying information on areas where disasters are predicted to occur on a map, thereby enabling users to intuitively grasp the danger zone.

[0559] "Posting on the website" refers to uploading map information of disaster-prone areas to the website in real time and making it accessible to the general public.

[0560] "Communication continuity device" refers to equipment that allows users to continue using communication services such as the Internet and telephone even if communication infrastructure is damaged or stopped during a disaster.

[0561] A "communications base" is a basic facility for mobile communications and broadband communications, and refers to infrastructure including antennas, transmitting and receiving equipment, etc.

[0562] "Necessary materials" refers to the equipment, tools, parts, etc. required to maintain and repair communications bases in disaster-prone areas.

[0563] This system uses weather disaster path forecast data to notify users of disasters in advance, publishes disaster-prone areas on a website, and provides support for maintaining communications. It also prepares preservation measures for communications bases in advance, enabling rapid restoration in the event of damage.

[0564] Key components of the system

[0565] This system consists of the following main components:

[0566] server

[0567] User device (smartphone, PC, etc.)

[0568] Website

[0569] Indoor communication devices (e.g. Femto)

[0570] Communications bases and maintenance equipment

[0571] Hardware and Software Configuration

[0572] The server periodically obtains typhoon path forecast data using a weather forecasting system or a generative AI model (e.g., OpenAI API). Specifically, it obtains JSON-formatted data from the weather data providing API using an HTTP request. The obtained data is stored in a database.

[0573] The server then analyzes this data using a data analysis module (e.g., Python's Pandas or NumPy library). The analysis involves extracting the typhoon's path, speed, and scale, as well as the latitude and longitude of the area it will affect. The disaster-prone area information identified here is then geographically mapped using a geocoding API (e.g., Google Maps API).

[0574] The server then compares users' location information stored in a database with the identified disaster-prone areas. This comparison generates a list of users likely to be affected. Based on this list, the server generates a warning notice, which includes information on the typhoon's path, predicted impacts, and safety advice.

[0575] To send notifications, the server uses an email sending API or a short message service API (e.g., Twilio) to send the generated notification to the user's smartphone or PC. The device then displays the received notification as a pop-up to alert the user.

[0576] The server then maps the information on the disaster-prone areas using a map drawing library (e.g., Google Maps API) and posts it on a website in real time. Users can access this website to check the disaster-prone areas for themselves and their surroundings.

[0577] To support continued communications, the server will provide a communications device (Femto) to the user if the user requests it. When the user expresses their desire, the system will ship the device based on the user's address information. The user can then install the device in their home and continue secure communications.

[0578] As a maintenance measure for communication bases, the server identifies communication bases located within disaster-prone areas and procures the necessary materials in advance. The server generates a list of materials required for each communication base and sends an order to the supply chain system. The user (maintenance worker) deploys the necessary materials to the site before a disaster occurs and performs maintenance work quickly after the disaster occurs.

[0579] Specific examples

[0580] For example, if the generative AI model predicts a typhoon approaching the Tokyo area 48 hours in advance, the server will analyze this information and send a warning to all users living in the Tokyo area. It will also map areas that overlap with the predicted disaster zone and post the information on the website in real time.

[0581] When a user requests a communication device, the server receives the request and ships the device to the user's address. The user can then install the device and continue communicating safely. In addition, the server pre-procures the materials needed for communication bases in the Tokyo area to support early recovery after a disaster.

[0582] Prompt Sentence Examples

[0583] "A typhoon is approaching your area. Please evacuate to a safe place."

[0584] As described above, the present invention is a system that provides a rapid and accurate response to meteorological disasters, and is equipped with various functions for minimizing damage.

[0585] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0586] Step 1: Obtain weather forecast data

[0587] The server periodically obtains typhoon path forecast data using a weather forecasting system and generative AI model. It accesses the weather data provision API as input and receives JSON-formatted data. This data includes the typhoon's path, speed, scale, and the latitude and longitude of the area it will affect. Specifically, the server calls an API endpoint such as "GET / api / typhoon-forecast" to obtain the latest forecast data. The obtained weather forecast data is obtained as output.

[0588] Step 2: Analyze weather forecast data

[0589] The server analyzes the acquired weather forecast data using a data analysis module (e.g., Python's Pandas or NumPy library). The JSON-formatted weather forecast data acquired in step 1 is used as input. Data analysis extracts the typhoon's path, speed, scale, and the latitude and longitude of the area it will affect. Specifically, the server uses a data analysis library to analyze the data and extract the necessary information. The output is information on disaster-prone areas as a result of the analysis.

[0590] Step 3: Identifying disaster-prone areas

[0591] The server identifies areas where disasters are predicted to occur based on the analyzed data. The information on areas where disasters are predicted obtained in step 2 is used as input. Specifically, the server uses a geocoding API (e.g., Google Maps API) to obtain latitude and longitude information from the analyzed data, and uses this information to map the predicted areas. The output is information on the identified areas where disasters are predicted to occur.

[0592] Step 4: Matching with user location information

[0593] The server compares the user location information stored in the database in advance with the predicted disaster zones identified in step 3. The server uses the user location information and the predicted disaster zone information as input. Specifically, the server executes a database query to extract data on users located within the predicted zones. The output is a list of affected users who are likely to be affected.

[0594] Step 5: Generate a warning notification

[0595] The server generates an alert based on the list of affected users generated in step 4. As input, it uses the list of affected users, information on the typhoon's path, predicted impacts, and safety advice. Specifically, the server uses a text generation library (e.g., a template engine) to generate a customized notification for each user. As output, it obtains an alert for each user.

[0596] Step 6: Sending and displaying notifications

[0597] The server sends the alert notification generated in step 5 to the affected user using an email sending API or a short message service API (e.g., Twilio). The generated alert notification and the affected user's contact information are used as input. Specifically, the server sends the notification data to these APIs and sends the notification. The device displays the received notification as a pop-up to alert the user. As output, the notification is displayed to the user.

[0598] Step 7: Map the disaster zone

[0599] The server uses a map rendering library (e.g., Google Maps API) to map information about disaster-prone areas and post it on a website in real time. Information about disaster-prone areas is used as input. Specifically, the server uses the map rendering library to generate JavaScript code and embeds it in the website's HTML. As output, the mapping information about disaster-prone areas is displayed on the website in real time.

[0600] Step 8: Providing communication continuity support

[0601] The server then carries out the process of providing indoor communication devices (Femto) to users who wish to continue communication. The user's desired information and address information are used as input. Specifically, the server sends the order data to the order management system, and delivery arrangements are made automatically. The user then installs the received indoor communication device and continues communication safely. The output is that the communication device is provided to the user, ensuring stable communication even during a disaster.

[0602] Step 9: Secure your communications base

[0603] The server identifies communication bases located within areas where disasters are predicted to occur and procures the necessary materials in advance. The input is the predicted disaster area and the location information of the communication bases. Specifically, the server generates a list of communication bases, lists the materials needed for each base, and sends order data to the supply chain system. The user (maintenance worker) deploys the necessary materials to the site before a disaster occurs and performs prompt maintenance work after the disaster occurs. The output is that communication bases can be quickly maintained and repaired.

[0604] (Application example 1)

[0605] 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."

[0606] In recent years, natural disasters such as typhoons have become more frequent, and providing prompt and accurate information is essential to minimize damage. However, current systems lack the technology to link disaster prediction information with user location information and provide appropriate warning notifications. Furthermore, disaster notifications and evacuation route guidance are not provided to autonomous vehicles, making ensuring safety during disasters a challenge. Furthermore, maintenance measures for communication infrastructure such as base stations are insufficient, and a means to ensure communication continuity is also needed.

[0607] 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.

[0608] In this invention, the server includes means for acquiring typhoon path forecast data, means for analyzing the acquired typhoon path forecast data to identify predicted disaster areas, means for generating a list of affected users by comparing user location information with the predicted disaster areas, means for sending alert notifications based on the generated list of affected users, means for mapping information about the predicted disaster areas and posting it on a website, means for providing means for continued communication to users who request it, means for identifying base stations within the predicted disaster areas and procuring necessary equipment, and means for sending disaster alert notifications to autonomous vehicles based on the typhoon path forecast data and suggesting safe evacuation routes. This makes it possible to ensure the safety of users and preserve the communications infrastructure by issuing prompt and accurate alert notifications based on typhoon path information and issuing evacuation instructions to autonomous vehicles.

[0609] "Typhoon path forecast data" is data generated by weather forecasting systems and artificial intelligence, including information on a typhoon's path, speed, size, and the area it will affect.

[0610] A "disaster-prone area" is a geographical area that is likely to be affected by a typhoon, identified based on typhoon path forecast data.

[0611] "Affected users" refers to users who are located within the disaster-prone area and who may be affected by the typhoon.

[0612] A "warning notice" is a warning message sent to affected users that includes information on the typhoon's path, expected impacts, and safety advice.

[0613] "Mapping on a map" means visually displaying information about areas where disasters are predicted to occur using a geographic information system or the like.

[0614] "Website" means an online platform for providing information that is publicly available and accessible to users via the Internet.

[0615] "Means for continued communication" refers to devices and technologies that ensure stable communication even during disasters, and a specific example is indoor Femto.

[0616] A "base station" is a wireless communication facility used to maintain and manage mobile communication networks, and its preservation is crucial in times of disaster.

[0617] An "autonomous vehicle" is a vehicle that is capable of driving autonomously without human operation.

[0618] An "evacuation route" is a recommended route for evacuating to a safe place in the event of a disaster, and is set to avoid the path of a typhoon.

[0619] A "generative AI model" is an artificial intelligence model that learns from large amounts of data and performs tasks such as predicting the path of typhoons and providing evacuation route guidance.

[0620] A "prompt" is an input text given to a generative AI model, and is an instruction that causes the model to provide appropriate answers or information.

[0621] Description: Detailed Description of the Invention

[0622] The present invention relates to a system that provides disaster warning notifications and evacuation route guidance to autonomous vehicles based on typhoon path prediction data.

[0623] System configuration

[0624] The system consists of the following main components:

[0625] 1. Server

[0626] 2. User devices (smartphones, PCs, autonomous vehicle computers)

[0627] 3. Website

[0628] 4. Indoor Femto

[0629] 5. Base Station and Maintenance Equipment

[0630] Program processing

[0631] Acquisition and analysis of typhoon path forecast data

[0632] The server periodically obtains typhoon path prediction data generated by the weather forecasting system and the AI ​​generation model via API. For example, the latest prediction data is updated every 24 hours. The obtained typhoon path prediction data includes the typhoon's path, speed, scale, and the latitude and longitude of the areas it will affect. The server analyzes the obtained typhoon path prediction data and identifies areas where disasters are predicted to occur. Based on the results of this analysis, it generates information on areas where disasters are predicted to occur.

[0633] User notification

[0634] The server compares users' location information with the predicted disaster area and creates a list of users who are likely to be affected. It then generates a warning notice based on the list of affected users and sends it to them via email or SMS. The notice includes information on the typhoon's path, expected impact, and advice on how to ensure safety. The user's device displays the received notice as a pop-up to warn the user.

[0635] Website listing

[0636] The server uses a map drawing library to map information about areas where disasters are predicted to occur. This mapped information is posted on a website in real time. Users can access the website to check the predicted disaster areas for themselves and their surrounding areas, enabling them to take safety measures in advance.

[0637] Support for continued communication

[0638] The server then processes the procedures to provide indoor Femto to users who request it to support continued communications. When a user expresses their desire, the system ships the indoor Femto based on the user's address information. By receiving the indoor Femto and installing it in their home, users can ensure stable communications even in the event of a disaster. Specifically, they follow the manual to set it up and connect their device to the Femto.

[0639] base station maintenance

[0640] The server identifies base stations within the predicted disaster area and procures the necessary equipment in advance. It generates a list of the equipment needed for each base station and sends the order to the supply chain system. The necessary equipment is deployed on-site before a disaster occurs, and maintenance work is carried out promptly after the disaster occurs.

[0641] Disaster alert notifications and evacuation route guidance for autonomous vehicles

[0642] The server sends disaster alert notifications to autonomous vehicles based on typhoon path prediction data. The notifications include typhoon path information, evacuation instructions, and safe evacuation routes. Based on the received alert notifications, the autonomous vehicle's computer sets appropriate evacuation routes and displays instructions to the driver.

[0643] Specific examples

[0644] For example, if a generative AI model predicts a typhoon approaching the Tokyo area 48 hours in advance, the server analyzes the information and sends a warning to all users living in the Tokyo area. It also maps areas overlapping with predicted disaster areas and posts them on a website in real time. If a user requests an indoor Femto, the server receives the request and ships it to the user's address. The user can then install the Femto in their home and continue secure communications. Furthermore, the server pre-procures the necessary equipment for base stations in the Tokyo area to support early recovery after a disaster. For autonomous vehicles, it sets up appropriate evacuation routes based on the typhoon's path in real time and displays instructions to the driver.

[0645] Prompt Sentence Examples

[0646] "Analyze the latest typhoon path forecast data to determine if it will affect the Tokyo area. If so, generate an alert notification with evacuation routes and send it to the driver of the autonomous vehicle. The data will be provided in the following format:

[0647] {

[0648] 'typhoon': {

[0649] 'path': 'Typhoon path information',

[0650] 'speed': 'speed of the typhoon',

[0651] 'scale': 'scale of the typhoon',

[0652] 'affected_areas': 'List of affected areas'

[0653] }

[0654] }"

[0655] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0656] Step 1:

[0657] The server periodically obtains typhoon path prediction data generated by the weather forecasting system and generative AI model via the API. The typhoon path prediction data obtained from the API as input includes the typhoon's path, speed, scale, and the latitude and longitude of the area it will affect. The server saves this data as output and prepares it for analysis.

[0658] Step 2:

[0659] The server analyzes the acquired typhoon path prediction data to identify areas where disasters are predicted to occur. The input data analysis includes the path, speed, scale, and latitude and longitude of the affected areas, and the resulting output is the predicted disaster areas. Specifically, the server applies a data analysis algorithm to calculate the degree of impact for each area.

[0660] Step 3:

[0661] The server compares the user's location information with the predicted disaster area and creates a list of users who are likely to be affected. The input location information is stored in a database and is used for comparison. The output is a list of affected users. The server performs the matching process using a comparison algorithm.

[0662] Step 4:

[0663] The server generates a warning notification based on the list of affected users and sends it to them via email or SMS. The notification content includes information on the typhoon's path, expected impacts, and safety advice. The input is the generated warning notification message, and the output is the warning notification to be sent to the user. Specifically, the server sends the message using an SMTP or SMS gateway.

[0664] Step 5:

[0665] The server uses a map drawing library to map information on disaster-prone areas and publishes it on a website in real time. The input is map drawing data, and the website is updated using an API. The output is the updated map information displayed on the website. The server visually processes the mapping using the map drawing library.

[0666] Step 6:

[0667] The server performs the procedure to provide indoor Femto to requesting users to support continued communications. The input is the desired request and address information, and the output is a shipping instruction. Specifically, the server works in conjunction with the logistics system to send a shipping instruction for the indoor Femto.

[0668] Step 7:

[0669] The server identifies base stations within the predicted disaster area and procures the necessary equipment in advance. The input includes base station information and a list of required equipment, and the output includes instructions for procuring the equipment. The server then sends the order to the supply chain system.

[0670] Step 8:

[0671] The server sends disaster alert notifications to autonomous vehicles based on typhoon path prediction data and suggests safe evacuation routes. The input includes path information and evacuation routes, and the output includes evacuation instructions to be displayed on the autonomous vehicle's display. Specifically, the server uses a generative AI model to calculate appropriate evacuation routes and generates notifications using prompt text.

[0672] 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.

[0673] This invention combines a system that notifies users in advance of disasters based on typhoon path forecast data, publishes predicted disaster areas on a website, and provides support for maintaining communications, with an emotion engine that recognizes the user's emotions.The invention also prepares base station maintenance measures in advance, enables rapid recovery in the event of damage, and responds appropriately according to the user's emotional state.

[0674] System configuration

[0675] This system consists of the following main components:

[0676] server

[0677] User device (smartphone, PC, etc.)

[0678] Home page

[0679] Indoor Femto

[0680] Base Station and Maintenance Equipment

[0681] Emotion Engine

[0682] Program processing

[0683] Acquisition and analysis of typhoon path forecast data

[0684] The server periodically obtains typhoon path prediction data generated by weather forecasting systems and AI via API, updating the latest forecast data every 24 hours, for example.

[0685] The server analyzes the acquired typhoon path prediction data, including the typhoon's path, speed, scale, and latitude and longitude of the areas it will affect. Once this analysis is complete, it identifies areas where disasters are predicted to occur.

[0686] The server compares users' location information with predicted disaster areas and creates a list of users who are likely to be affected.

[0687] Emotion recognition by emotion engine

[0688] The device periodically captures the user's facial expressions and voice using sensors such as a camera and microphone, and sends the data to a server.

[0689] The server analyzes the received sensor data using an emotion engine to identify the user's emotional state (e.g., stress level or anxiety).

[0690] User notification

[0691] The server generates a warning notification message to be sent to each user based on the affected user list.

[0692] The server customizes the content of the alert notification depending on the user's emotional state as analyzed by the emotion engine, for example adding more specific safety advice if high stress levels are detected.

[0693] The server uses an email sending API or an SMS sending API to send the generated warning notification message to the affected user.

[0694] The device will display received emails and SMS as pop-up notifications to alert the user.

[0695] Posted on the homepage

[0696] The server uses a map drawing library to map the geographical information of disaster-prone areas, and this mapped information is posted on the website in real time.

[0697] By accessing the website, users can check the predicted disaster areas for themselves and their surrounding areas, allowing them to take safety measures in advance.

[0698] Support for continued communication

[0699] The server will then process the provision of indoor Femto to users who request it to support continued communications. When a user requests it, the server will ship the indoor Femto based on the user's address information.

[0700] Users receive an indoor Femto and install it in their homes to ensure stable communications even in the event of a disaster. Specifically, they follow the instructions to set it up and connect their device to the Femto.

[0701] base station maintenance

[0702] The server identifies base stations within the predicted disaster area and procures the necessary equipment in advance.

[0703] The server generates a list of required equipment for each base station and sends the orders to the supply chain system.

[0704] The user (maintenance worker) deploys the necessary equipment to the site before a disaster occurs and performs maintenance work promptly after the disaster occurs.

[0705] Specific examples

[0706] For example, if the AI ​​predicts that a typhoon will approach the Tokyo area 48 hours in advance, the server will analyze the information and send a warning notice to all users living in the Tokyo area.

[0707] If the emotion engine detects that a particular user is showing high stress levels, the server will send more detailed advice to that user, such as providing specific evacuation locations. It also maps areas that overlap with predicted disaster areas and posts the information on the website in real time.

[0708] If a user requests an indoor Femto, the server will receive the request and ship the indoor Femto to the user's address. Once the user receives the Femto, they can install it and continue communicating securely.

[0709] In addition, the server will procure the necessary equipment for base stations in the Tokyo area in advance, supporting early recovery after a disaster occurs.

[0710] The processing flow will be explained below.

[0711] Acquisition and analysis of typhoon path forecast data

[0712] Step 1:

[0713] The server sends an HTTP request to the specified API endpoint every 24 hours to obtain the latest typhoon track forecast data, which is received in JSON format.

[0714] Step 2:

[0715] The server parses the received JSON data and extracts information about the typhoon's path, speed, size, and latitude and longitude of the area it will affect.

[0716] Step 3:

[0717] The server uses the extracted information to identify areas where disasters are predicted to occur and stores the information in a database.

[0718] Emotion recognition by emotion engine

[0719] Step 1:

[0720] The device periodically captures the user's facial expressions and voice using sensors such as a camera and microphone, and sends the data to a server.

[0721] Step 2:

[0722] The server analyzes the received sensor data using an emotion engine to identify the user's emotional state (e.g., stress level or anxiety).

[0723] Step 3:

[0724] The server stores the identified emotional states in a database.

[0725] User notification

[0726] Step 1:

[0727] The server uses the latitude and longitude information of the disaster predicted area to compare with the user location information in the database, thereby generating a list of affected users.

[0728] Step 2:

[0729] The server generates a warning notification message to be sent to each user based on the affected user list. The message includes typhoon information and safety advice.

[0730] Step 3:

[0731] The server customizes the content of the alert notification depending on the user's emotional state as analyzed by the emotion engine, for example adding specific safety advice if high stress levels are detected.

[0732] Step 4:

[0733] The server uses an email sending API or an SMS sending API to send the generated warning notification message to the affected user.

[0734] Step 5:

[0735] The device will display received emails and SMS as pop-up notifications to alert the user.

[0736] Posted on the homepage

[0737] Step 1:

[0738] The server passes the geographical information of the disaster-prone area to a map drawing library (e.g., Leaflet.js) and maps it on a map.

[0739] Step 2:

[0740] The server uploads the mapped information using the homepage update API and reflects it on the homepage in real time.

[0741] Step 3:

[0742] The user accesses the homepage from a browser and checks information about areas where disasters are predicted to occur.

[0743] Support for continued communication

[0744] Step 1:

[0745] The user contacts the server to request the provision of a means for continuing communication (indoor Femto).

[0746] Step 2:

[0747] The server checks the list of interested users and begins the shipping process for the indoor Femto based on the user's address information.

[0748] Step 3:

[0749] The server sends shipping instructions to the shipping management system and ships the indoor Femto to the relevant user.

[0750] Step 4:

[0751] Once the indoor Femto arrives, users can install it according to the manual to ensure stable communication at home.

[0752] base station maintenance

[0753] Step 1:

[0754] The server identifies base stations within the disaster-prone area in a database.

[0755] Step 2:

[0756] The server generates a list of equipment required for each base station and places orders using the supply chain system API.

[0757] Step 3:

[0758] The server arranges for the procured equipment to be delivered to the designated base station.

[0759] Step 4:

[0760] The user (maintenance worker) uses the equipment procured in advance to carry out maintenance work (inspection, reinforcement, etc.) on the base station before a disaster occurs.

[0761] Step 5:

[0762] After a disaster occurs, the user (maintenance worker) promptly goes to the site and uses the equipment to quickly restore the base station.

[0763] Example 2

[0764] 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."

[0765] Conventional typhoon path prediction systems predict the path of a typhoon and issue warnings to users, but they are unable to address the emotional state of users or the maintenance of communication infrastructure. Providing appropriate countermeasures is particularly important when users are experiencing high levels of stress or anxiety. It is also important to ensure the continuity of communications during disasters and to quickly maintain base stations. Therefore, it is desirable to provide a notification system that can respond to disasters from multiple angles and takes into account the emotional state of users.

[0766] 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.

[0767] In this invention, the server includes means for acquiring typhoon path forecast data, means for analyzing the acquired typhoon path forecast data to identify a disaster-predicted area, means for generating a list of affected users by comparing user location information with the disaster-predicted area, means for collecting and analyzing emotional data of affected users, means for customizing and sending alert notification messages based on the emotion analysis results, means for sending alert notifications based on the generated list of affected users, means for mapping information about the disaster-predicted area on a map and posting it on a website, means for providing means for continuing communications to users who request it, and means for identifying base stations within the disaster-predicted area and procuring the necessary equipment. This makes it possible to provide alert notifications customized in consideration of the emotional state of users, thereby enabling continued communications and rapid base station maintenance in the event of a disaster.

[0768] "Typhoon path forecast data" is information about a typhoon's path, speed, scale, and area of ​​impact, generated by weather forecasting systems and artificial intelligence.

[0769] "Disaster-predicted areas" refer to geographical locations that are highly likely to be affected by disasters, as analyzed based on typhoon path prediction data.

[0770] "User location information" refers to the user's current location or specified address information.

[0771] The "list of affected users" is a list of users who are likely to be affected by a disaster, generated by comparing the predicted disaster area with the location information of the users.

[0772] "Emotional data" is data captured from a user's facial expressions, voice, etc., and used to analyze the user's emotional state.

[0773] "Emotion analysis results" are the results of analyzing the user's emotional state (stress level, anxiety, etc.) based on emotion data.

[0774] A "warning notification message" is a notification sent to users in an area where a disaster is predicted to occur, and includes specific evacuation actions and countermeasures.

[0775] "Mapping" refers to drawing geographical information of areas where disasters are predicted to occur on a map.

[0776] "Means for continuing communication" refers to equipment and methods for ensuring communication stability during disasters, such as indoor Femto.

[0777] A "base station" is a relay device in a communication network, and is a facility for communicating with mobile terminals.

[0778] "Necessary supplies" refers to the equipment, parts, materials, etc. required to maintain or restore the functions of base stations in the event of a disaster.

[0779] This invention combines a system that notifies users in advance of disasters based on typhoon path forecast data, publishes predicted disaster areas on a website, and provides support for maintaining communications, with an emotion engine that recognizes the user's emotions. Furthermore, it can prepare base station maintenance measures in advance, enable rapid recovery in the event of damage, and respond appropriately according to the user's emotional state.

[0780] The system is configured as follows: The main components include a server, user terminals (smartphones, PCs, etc.), a homepage, indoor Femto, base stations and maintenance equipment, and an emotion engine.

[0781] Acquisition and analysis of typhoon path forecast data

[0782] The server periodically obtains typhoon path prediction data generated by weather forecasting systems and artificial intelligence via API. For example, it calls "Weather API XYZ" every 24 hours and stores the data. The server then analyzes the data using "Data Analysis Library ABC" to identify the typhoon's path, speed, scale, and affected areas (latitude, longitude, etc.). Based on the analysis results, it identifies areas where disasters are predicted to occur and compares them with users' location information to create a list of users who are likely to be affected. As a specific example, if a typhoon is predicted to approach the Tokyo area, users who reside in Tokyo will be listed.

[0783] Emotion recognition by emotion engine

[0784] The device periodically captures the user's facial expressions and voice using sensors such as a camera and microphone, encrypts the data, and sends it to a server. The server then uses the "Emotion Analysis Engine XYZ" to analyze the received sensor data and identify the user's emotional state (such as stress level or anxiety). This process allows the user's emotional state to be understood.

[0785] User notification

[0786] The server generates a warning notification message based on the list of affected users. It uses the "Message Generation Library ABC" to create a notification message that includes details about the typhoon and recommended actions. It also customizes the content of the warning notification based on the analysis results of the emotion engine. For example, for users with high stress levels, it could include specific evacuation locations and countermeasures. The server uses an email sending API or SMS sending API to send the generated warning notification message to affected users. The device displays the received email or SMS as a pop-up notification to alert the user.

[0787] Posted on the homepage

[0788] The server maps the geographical information of disaster-prone areas using the "Map Drawing Library GeoLib XYZ." This mapped information is posted on the website in real time. By accessing the website, users can check the disaster-prone areas and take safety measures in advance.

[0789] Support for continued communication

[0790] When the server receives a request for communication continuity support from a user, it ships an indoor Femto based on the user's address information. Specifically, it generates a shipping instruction and connects it to the logistics system. The user receives the indoor Femto and installs it in their home, ensuring stable communication even in the event of a disaster. The installation procedure is carried out according to the enclosed manual.

[0791] base station maintenance

[0792] The server identifies base stations within areas where disasters are predicted to occur and procures the necessary equipment in advance. It uses a geographic information system to list the applicable base stations, generates an equipment list for each base station, and sends orders to the supply chain system. The user (maintenance worker) deploys the necessary equipment on-site before a disaster occurs, and then quickly performs maintenance work on the base stations after the disaster occurs.

[0793] Examples of concrete examples and prompts

[0794] For example, if the AI ​​predicts that a typhoon will approach the Tokyo area 48 hours in advance, the server will analyze the information and send a warning to users living in the Tokyo area. If the emotion engine detects that a particular user is showing high stress levels, the server will send more detailed advice to that user, such as providing specific evacuation locations. The server will also map areas predicted to be affected by disasters and post them on the website in real time.

[0795] Example prompt: "A typhoon is approaching the Tokyo area. Generate an appropriate warning notification message based on the disaster forecast and the user's emotional state."

[0796] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0797] Step 1: Obtaining typhoon track forecast data

[0798] The server periodically obtains the latest typhoon path forecast data generated by weather forecasting systems and artificial intelligence via API. The input is typhoon path forecast data obtained from "Weather API XYZ," and the output is raw data stored in a database on the server. Specifically, the server schedules an API call every 24 hours, receives the response data in JSON format, and stores it in the database.

[0799] Step 2: Analysis of typhoon track forecast data

[0800] The server analyzes the acquired typhoon path prediction data and identifies the typhoon's path, speed, scale, and the latitude and longitude of the area it will affect. The input is the raw data acquired earlier, and the output is the analyzed typhoon information (path, speed, scale, latitude and longitude). Specifically, it uses the "Data Analysis Library ABC" to analyze and extract various typhoon data and convert it into an easy-to-understand format.

[0801] Step 3: Identifying areas where disasters are likely to occur

[0802] The server identifies areas where disasters are predicted to occur based on the analysis results. The input is the analyzed typhoon information, and the output is geographic information on the areas where disasters are predicted to occur. Specifically, the affected area is mapped using a geographic information system (GIS) and the data is saved.

[0803] Step 4: List affected users

[0804] The server compares the predicted disaster area with user location information and generates a list of users who are likely to be affected. The input is a database of user location information and predicted disaster area information, and the output is a list of affected users. Specifically, it runs an SQL query based on the location information to extract and list the relevant users.

[0805] Step 5: Capturing and Sending Sensor Data

[0806] The device periodically captures the user's facial expressions and voice using sensors such as a camera and microphone, and sends the data to a server. The input is the facial expression and voice data captured by the device, and the output is the emotion data sent to the server. Specifically, the data is collected every hour using a facial recognition API and a voice analysis API, encrypted, and sent to the server.

[0807] Step 6: Sentiment Analysis

[0808] The server analyzes the received sensor data using the "Emotion Analysis Engine XYZ" to identify the user's emotional state. The input is sensor data, and the output is the result of identifying the emotional state. Specifically, it uses algorithms that analyze facial muscle movements and tone of voice to identify emotional states such as stress levels and anxiety.

[0809] Step 7: Generate a warning notification message

[0810] The server generates a warning notification message based on the affected user list. The input is the affected user list and disaster predicted area information, and the output is a warning notification message. Furthermore, the notification content is customized according to the results of sentiment analysis. Specifically, the "Message Generation Library ABC" is used to create a notification message that includes details of the typhoon and evacuation instructions.

[0811] Step 8: Sending alert notifications

[0812] The server then uses an email or SMS API to send the generated alert notification message to affected users. The input is the alert notification message, and the output is the sent notification. Specifically, the API is called and a message is sent to each user's contact information.

[0813] Step 9: Post disaster information on your website

[0814] The server maps the geographic information of disaster-predicted areas using the "Map Drawing Library GeoLib XYZ" and posts it on the website in real time. The input is the geographic information of disaster-predicted areas, and the output is the updated content of the website. Specifically, the map information is updated regularly and reflected on the website in real time using an API.

[0815] Step 10: Providing communication continuity support

[0816] The server receives a request for communication continuity support from the user and ships the indoor Femto based on the user's address information. The input is the request information and the user's address information, and the output is a shipping instruction. Specifically, it works in conjunction with the logistics system to carry out the procedures for shipping the necessary equipment.

[0817] Step 11: Prepare for base station maintenance work

[0818] The server identifies base stations within disaster-predicted areas and procures the necessary equipment in advance. The input is base station data and disaster-predicted area information, and the output is an equipment list and ordering information. Specifically, it uses GIS to list the applicable base stations, and creates and orders a list of the necessary equipment.

[0819] Step 12: Carry out base station maintenance work

[0820] The user (maintenance worker) deploys the necessary equipment for each identified base station on-site and performs maintenance work promptly after a disaster occurs. The input is an equipment list and base station information, and the output is the maintenance status of the base station. Specifically, the user travels to the site and performs the necessary maintenance work to support rapid recovery.

[0821] (Application example 2)

[0822] 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."

[0823] The problem that this invention aims to solve is to provide users with prompt and accurate notifications when a natural disaster such as a typhoon is approaching, and to provide information customized to the user's emotional state. This will increase the accuracy of the information received by users, reduce stress and anxiety, and support the continuity of communications and the rapid recovery of base stations.

[0824] 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.

[0825] In this invention, the server includes means for acquiring typhoon path forecast data, means for analyzing the acquired typhoon path forecast data to identify a disaster-predicted area, means for generating a list of affected users by comparing user location information with the disaster-predicted area, means for transmitting a warning notice based on the generated list of affected users, means for capturing the user's facial expression and voice using a sensor in the user terminal and analyzing it with an emotion engine to identify the user's emotional state, means for customizing the content of the warning notice according to the user's emotional state, means for mapping information about the disaster-predicted area on a map and posting it on a homepage, means for providing means for communication continuity to users who request it, and means for identifying base stations within the disaster-predicted area and procuring the necessary equipment. This allows for the server to provide users with emergency disaster information and send customized notifications according to the user's emotional state, enabling the continuation of communication and the rapid restoration of base stations.

[0826] "Typhoon path forecast data" is data that includes information on the path, speed, scale, and areas affected by a typhoon, calculated using weather forecasting systems and artificial intelligence.

[0827] "Disaster-prone areas" are areas that are likely to be affected by typhoons, as identified by analyzing typhoon path prediction data.

[0828] "User Location Information" means geographic data about a User's current location obtained from a smartphone or other GPS-enabled device.

[0829] The "list of affected users" is a list of users who are likely to be affected by the typhoon, generated by comparing the predicted disaster area with the user's location information.

[0830] A "warning notice" is a message sent to affected users to warn them in advance about the approach and impact of a typhoon.

[0831] An "emotion engine" is a software system that analyzes sensor data to identify a user's emotional state (e.g., stress level or anxiety).

[0832] "Mapping on a map" means displaying information about disaster-prone areas on a geographical map.

[0833] A "home page" is a page that is part of a website accessible on the Internet and provides information to users.

[0834] "Means for continued communication" refers to equipment and services provided to ensure stable communication even during disasters.

[0835] A "base station" is a facility or equipment for communicating with mobile terminals in a wireless communication network.

[0836] "Essential equipment" refers to spare parts and equipment required for the base station to continue to function normally.

[0837] A "sensor" is a device used to capture a user's facial expressions and voice.

[0838] "Emotional state" refers to the user's psychological state (e.g., stress, anxiety, etc.).

[0839] A "customized notification" is an alert notification message whose content is tailored to the user's emotional state.

[0840] A "prompt" is text that is input to a generative AI model and serves as an instruction to execute a specific generation task.

[0841] The present invention relates to a system that notifies users of disasters in advance based on typhoon path forecast data and provides information customized according to the user's emotional state. This system is composed of the following hardware and software.

[0842] Program processing and technology used

[0843] 1. Acquisition and analysis of typhoon track forecast data

[0844] The server periodically retrieves typhoon path prediction data from the API via a weather forecasting system and AI (artificial intelligence). The specific software used is the Python requests library.

[0845] The acquired data is analyzed to identify the typhoon's path, speed, scale, and affected area. For the analysis, Python data analysis libraries (e.g., Pandas, NumPy) are used.

[0846] 2. Identifying areas where disasters are predicted to occur and creating a list of affected users

[0847] The server identifies areas where disasters are predicted to occur based on the typhoon path prediction data it has acquired. This area information is then mapped onto a map using geographic information system (GIS) software (e.g., Leaflet, Mapbox).

[0848] The server compares users' location information with predicted disaster areas and generates a "list of affected users" who are likely to be affected by the typhoon.

[0849] 3. User Emotion Recognition and Notification Message Customization

[0850] The device uses the smartphone's camera and microphone to capture the user's facial expressions and voice, and sends the data to a server using OpenCV (an image processing library) and deep learning frameworks (e.g., TensorFlow and Keras).

[0851] The server analyzes the received sensor data using an emotion engine to identify the user's emotional state (stress level and anxiety).

[0852] The server customizes the alert notification content according to the user's emotional state based on the analysis results of the emotion engine, and generates a prompt using a generative AI model. Examples of prompts include:

[0853] A typhoon is forecast to approach your area within the next 48 hours. Please prepare to evacuate. High stress levels have been detected. Please confirm specific evacuation locations and emergency contact information.

[0854] 4. Notifications and Website Posting

[0855] Based on the generated list of affected users, the server uses an email sending API or an SMS sending API to send a customized warning notification message to each user.

[0856] The device displays received emails and SMS as pop-up notifications, prompting the user to take appropriate action.

[0857] Information on predicted disaster areas is posted in real time on the website using a map drawing library, allowing users to access the website and check the predicted disaster areas for themselves and their surrounding areas.

[0858] 5. Support for continued communications and base station maintenance

[0859] The server will then process the delivery of an indoor Femto to requesting users to support continued communications. When a user requests an indoor Femto, the server will ship the Femto based on the user's address information.

[0860] The server identifies base stations within the predicted disaster area, generates an equipment list, and procures the necessary equipment in advance. To support the rapid recovery of base stations, the server uses a supply chain system to deploy the necessary equipment to the site.

[0861] Specific examples

[0862] For example, if the AI ​​predicts a typhoon approaching the Tokyo area 48 hours in advance, the server analyzes the information and sends a warning to all users living in the Tokyo area. If the emotion engine detects a high stress level, the server sends detailed advice to the user, such as providing specific evacuation locations. The server also maps areas that overlap with predicted disaster areas and posts the information on the website in real time. If a user requests an indoor Femto, the server receives the request and ships the Femto to the user's address. The user can then install the Femto and continue communications. Furthermore, the server procures the necessary equipment for base stations in the Tokyo area in advance to support rapid recovery after a disaster occurs.

[0863] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0864] Step 1:

[0865] The server periodically obtains typhoon path forecast data generated by weather forecasting systems and AI via an API. This is done using the Python requests library. The input is the typhoon path forecast data obtained from the API, and the output is raw data that can be analyzed.

[0866] Step 2:

[0867] The server analyzes the acquired typhoon path prediction data and extracts information on the typhoon's path, speed, scale, and the area it will affect (latitude and longitude). This analysis uses data analysis libraries such as Python's Pandas and NumPy. The input is the acquired raw data, and the output is a dataset containing the analysis results.

[0868] Step 3:

[0869] The server uses the analysis results to identify areas where disasters are predicted to occur using geographic information system (GIS) software (e.g., Leaflet, Mapbox). The input is a dataset containing the analysis results, and the output is map data drawn by the GIS software.

[0870] Step 4:

[0871] The server compares the user's location information with the predicted disaster area and generates a list of affected users. The input is the user's location information and map data drawn by GIS software, and the output is the list of affected users.

[0872] Step 5:

[0873] The device uses the smartphone's camera and microphone to capture the user's facial expressions and voice, and sends the data to the server. The technology used is OpenCV (an image processing library). The input is the raw data of the user's facial expressions and voice, and the output is the sensor data sent to the server.

[0874] Step 6:

[0875] The server identifies the user's emotional state (stress level, anxiety, etc.) based on the sensor data analyzed by the emotion engine. The software used is a deep learning framework such as TensorFlow or Keras. The input is the sensor data, and the output is the analysis result of the emotional state.

[0876] Step 7:

[0877] The server customizes the content of the alert notification message based on the results of the emotional state analysis and generates a prompt using a generative AI model. For example, it generates a prompt such as, "A typhoon is predicted to approach your area within 48 hours. Please prepare for evacuation. High stress levels have been detected. Please confirm specific evacuation locations and emergency contact information." The input is the results of the emotional state analysis, and the output is a customized notification message.

[0878] Step 8:

[0879] The server uses the email sending API or SMS sending API to send a customized warning notification message to each user based on the generated affected user list. The input is the customized notification message and the affected user list, and the output is the sent warning notification message.

[0880] Step 9:

[0881] The terminal displays the received email or SMS as a pop-up notification to alert the user. The input is the sent warning notification message, and the output is the pop-up notification displayed on the terminal.

[0882] Step 10:

[0883] The server maps information about disaster-predicted areas onto a map and posts it on the website in real time. The software used is a map drawing library (e.g., Leaflet, Mapbox). The input is information about disaster-predicted areas, and the output is updated map data for the website.

[0884] Step 11:

[0885] The server performs the procedure to provide indoor Femto to requesting users to support continuous communication. When a user expresses a desire, the server ships the indoor Femto based on the user's address information. The input is the user's wish list and address information, and the output is the completion data of the shipping procedure.

[0886] Step 12:

[0887] The server identifies base stations within the predicted disaster area, generates an equipment list, and procures the necessary equipment in advance. The technology used is a supply chain system. The input is base station information and data on the predicted disaster area, and the output is the generated equipment list.

[0888] Step 13:

[0889] The server deploys the necessary equipment to the site through the supply chain system, and the maintenance worker carries out the maintenance work. The input is an equipment list, and the output is the deployed equipment and the completion data of the maintenance work.

[0890] 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.

[0891] 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.

[0892] 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.

[0893] [Third embodiment]

[0894] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0895] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0896] 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).

[0897] 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.

[0898] 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.

[0899] 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).

[0900] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0901] 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.

[0902] 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.

[0903] 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.

[0904] 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.

[0905] 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."

[0906] This system notifies users of disasters in advance based on typhoon path forecast data, lists predicted disaster areas on the website, and provides support for maintaining communications.The system also prepares base station maintenance measures in advance, enabling rapid recovery in the event of damage.

[0907] System configuration

[0908] This system consists of the following main components:

[0909] server

[0910] User device (smartphone, PC, etc.)

[0911] Home page

[0912] Indoor Femto

[0913] Base Station and Maintenance Equipment

[0914] Program processing

[0915] Acquisition and analysis of typhoon path forecast data

[0916] The server periodically obtains typhoon path prediction data generated by weather forecasting systems and AI via API, updating the latest forecast data every 24 hours, for example.

[0917] The server analyzes the acquired typhoon path prediction data, including the typhoon's path, speed, scale, and latitude and longitude of the areas it will affect. Once this analysis is complete, it identifies areas where disasters are predicted to occur.

[0918] The server compares users' location information with predicted disaster areas and creates a list of users who are likely to be affected.

[0919] User notification

[0920] The server generates a warning notice based on the list of affected users, including information on the storm's path, expected impacts, and safety advice.

[0921] The server will send a warning notice to affected users via email or SMS, which will be displayed on their smartphones or PCs.

[0922] The device displays the received notification as a pop-up to warn the user. For example, a message such as "A typhoon is approaching your area. Please evacuate to a safe place" may be displayed.

[0923] Posted on the homepage

[0924] The server uses a map drawing library to map information about areas where disasters are predicted to occur, and this mapped information is posted on the website in real time.

[0925] By accessing the website, users can check the predicted disaster areas for themselves and their surrounding areas, allowing them to take safety measures in advance.

[0926] Support for continued communication

[0927] The server then processes the request to provide indoor Femto to users who request it to continue communications. When a user expresses their desire, the system will ship the indoor Femto based on the user's address information.

[0928] Users can receive an indoor Femto and install it in their homes to ensure stable communications even during disasters. Specifically, they follow the instructions to set it up and connect their device to the Femto.

[0929] base station maintenance

[0930] The server identifies base stations within the predicted disaster area and procures the necessary equipment in advance.

[0931] The server generates a list of required equipment for each base station and sends the orders to the supply chain system.

[0932] The user (maintenance worker) deploys the necessary equipment to the site before a disaster occurs and performs maintenance work promptly after the disaster occurs.

[0933] Specific examples

[0934] For example, if the AI ​​predicts that a typhoon will approach the Tokyo area 48 hours in advance, the server will analyze the information and send a warning to all users living in the Tokyo area. It will also map areas that overlap with the predicted disaster area and post the information on the website in real time.

[0935] If a user requests an indoor Femto, the server will receive the request and ship the indoor Femto to the user's address. Once the user receives the Femto, they can install it and continue communicating securely.

[0936] In addition, the server will procure the necessary equipment for base stations in the Tokyo area in advance, supporting early recovery after a disaster occurs.

[0937] The processing flow will be explained below.

[0938] Acquisition and analysis of typhoon path forecast data

[0939] Step 1:

[0940] The server periodically sends an HTTP request to the specified API endpoint to obtain the latest typhoon track forecast data, which is received in JSON format.

[0941] Step 2:

[0942] The server parses the received JSON data and extracts information on the typhoon's path, speed, size, and latitude and longitude of the affected area.

[0943] Step 3:

[0944] The server uses the extracted information to identify areas where disasters are predicted to occur and stores the information in a database.

[0945] User notification

[0946] Step 1:

[0947] The server uses the latitude and longitude information of the disaster predicted area to compare with the user location information in the database, thereby generating a list of affected users.

[0948] Step 2:

[0949] The server generates a warning notification message to be sent to each user based on the affected user list. The message includes typhoon information and safety advice.

[0950] Step 3:

[0951] The server uses an email sending API or an SMS sending API to send the generated warning notification message to the affected user.

[0952] Step 4:

[0953] The device will display received emails and SMS as pop-up notifications to alert the user.

[0954] Posted on the homepage

[0955] Step 1:

[0956] The server passes the geographical information of the disaster-prone area to a map drawing library (e.g., Leaflet.js) and maps it on a map.

[0957] Step 2:

[0958] The server uploads the mapped information using the homepage update API and reflects it on the homepage in real time.

[0959] Step 3:

[0960] The user accesses the homepage from a browser and checks information about areas where disasters are predicted to occur.

[0961] Support for continued communication

[0962] Step 1:

[0963] The user contacts the server to request the provision of a means for continuing communication (indoor Femto).

[0964] Step 2:

[0965] The server checks the list of interested users and begins the shipping process for the indoor Femto based on the user's address information.

[0966] Step 3:

[0967] The server sends shipping instructions to the shipping management system and ships the indoor Femto to the relevant user.

[0968] Step 4:

[0969] Once the indoor Femto arrives, users can install it according to the manual to ensure stable communication at home.

[0970] base station maintenance

[0971] Step 1:

[0972] The server identifies base stations within the disaster-prone area in a database.

[0973] Step 2:

[0974] The server generates a list of equipment required for each base station and places orders using the supply chain system API.

[0975] Step 3:

[0976] The server arranges for the procured equipment to be delivered to the designated base station.

[0977] Step 4:

[0978] The user (maintenance worker) uses the equipment procured in advance to carry out maintenance work (inspection, reinforcement, etc.) on the base station before a disaster occurs.

[0979] Step 5:

[0980] After a disaster occurs, the user (maintenance worker) promptly goes to the site and uses the equipment to quickly restore the base station.

[0981] Example 1

[0982] 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."

[0983] With conventional disaster notification systems, it is difficult to efficiently obtain and analyze path prediction data for meteorological disasters such as typhoons, making it impossible to notify users in a timely manner. Furthermore, due to insufficient maintenance of communication infrastructure and the provision of continuous communication methods when a disaster occurs, a rapid response is not possible when a disaster occurs.

[0984] 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.

[0985] In this invention, the server includes means for acquiring weather forecast data, means for analyzing the acquired weather forecast data to identify a disaster-predicted area, means for generating an affected user list by comparing user location information with the disaster-predicted area, means for sending a warning notice based on the generated affected user list, means for mapping information about the disaster-predicted area on a map and posting it on a website, means for providing communication continuity devices to users who request them, and means for identifying communication bases within the disaster-predicted area and procuring the necessary materials. This makes it possible to quickly acquire and analyze weather disaster path forecast data, issue timely warning notices to affected users, and maintain communication infrastructure and provide continuous communication means during a disaster.

[0986] "Weather forecast data" refers to forecast information regarding the path, speed, scale, precipitation amount, etc. of typhoons and other weather phenomena provided by meteorological agencies and weather analysis systems.

[0987] "Disaster-prone area" refers to the area where a specific weather disaster is likely to occur based on analyzed weather forecast data.

[0988] "User location information" refers to information that indicates the user's actual location, such as address information provided by the user or current location data obtained from GPS.

[0989] "Affected User List" means a list of users who reside within or near a disaster-prone area and who are identified as likely to be affected by a disaster.

[0990] "Warning Notice" refers to a warning message sent to affected users that includes the path of the disaster, predicted impacts, and safety advice.

[0991] "Mapping on a map" refers to the process of visually displaying information on areas where disasters are predicted to occur on a map, thereby enabling users to intuitively grasp the danger zone.

[0992] "Posting on the website" refers to uploading map information of disaster-prone areas to the website in real time and making it accessible to the general public.

[0993] "Communication continuity device" refers to equipment that allows users to continue using communication services such as the Internet and telephone even if communication infrastructure is damaged or stopped during a disaster.

[0994] A "communications base" is a basic facility for mobile communications and broadband communications, and refers to infrastructure including antennas, transmitting and receiving equipment, etc.

[0995] "Necessary materials" refers to the equipment, tools, parts, etc. required to maintain and repair communications bases in disaster-prone areas.

[0996] This system uses weather disaster path forecast data to notify users of disasters in advance, publishes disaster-prone areas on a website, and provides support for maintaining communications. It also prepares preservation measures for communications bases in advance, enabling rapid restoration in the event of damage.

[0997] Key components of the system

[0998] This system consists of the following main components:

[0999] server

[1000] User device (smartphone, PC, etc.)

[1001] Website

[1002] Indoor communication devices (e.g. Femto)

[1003] Communications bases and maintenance equipment

[1004] Hardware and Software Configuration

[1005] The server periodically obtains typhoon path forecast data using a weather forecasting system or a generative AI model (e.g., OpenAI API). Specifically, it obtains JSON-formatted data from the weather data providing API using an HTTP request. The obtained data is stored in a database.

[1006] The server then analyzes this data using a data analysis module (e.g., Python's Pandas or NumPy library). The analysis involves extracting the typhoon's path, speed, and scale, as well as the latitude and longitude of the area it will affect. The disaster-prone area information identified here is then geographically mapped using a geocoding API (e.g., Google Maps API).

[1007] The server then compares users' location information stored in a database with the identified disaster-prone areas. This comparison generates a list of users likely to be affected. Based on this list, the server generates a warning notice, which includes information on the typhoon's path, predicted impacts, and safety advice.

[1008] To send notifications, the server uses an email sending API or a short message service API (e.g., Twilio) to send the generated notification to the user's smartphone or PC. The device then displays the received notification as a pop-up to alert the user.

[1009] The server then maps the information on the disaster-prone areas using a map drawing library (e.g., Google Maps API) and posts it on a website in real time. Users can access this website to check the disaster-prone areas for themselves and their surroundings.

[1010] To support continued communications, the server will provide a communications device (Femto) to the user if the user requests it. When the user expresses their desire, the system will ship the device based on the user's address information. The user can then install the device in their home and continue secure communications.

[1011] As a maintenance measure for communication bases, the server identifies communication bases located within disaster-prone areas and procures the necessary materials in advance. The server generates a list of materials required for each communication base and sends an order to the supply chain system. The user (maintenance worker) deploys the necessary materials to the site before a disaster occurs and performs maintenance work quickly after the disaster occurs.

[1012] Specific examples

[1013] For example, if the generative AI model predicts a typhoon approaching the Tokyo area 48 hours in advance, the server will analyze this information and send a warning to all users living in the Tokyo area. It will also map areas that overlap with the predicted disaster zone and post the information on the website in real time.

[1014] When a user requests a communication device, the server receives the request and ships the device to the user's address. The user can then install the device and continue communicating safely. In addition, the server pre-procures the materials needed for communication bases in the Tokyo area to support early recovery after a disaster.

[1015] Prompt Sentence Examples

[1016] "A typhoon is approaching your area. Please evacuate to a safe place."

[1017] As described above, the present invention is a system that provides a rapid and accurate response to meteorological disasters, and is equipped with various functions for minimizing damage.

[1018] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1019] Step 1: Obtain weather forecast data

[1020] The server periodically obtains typhoon path forecast data using a weather forecasting system and generative AI model. It accesses the weather data provision API as input and receives JSON-formatted data. This data includes the typhoon's path, speed, scale, and the latitude and longitude of the area it will affect. Specifically, the server calls an API endpoint such as "GET / api / typhoon-forecast" to obtain the latest forecast data. The obtained weather forecast data is obtained as output.

[1021] Step 2: Analyze weather forecast data

[1022] The server analyzes the acquired weather forecast data using a data analysis module (e.g., Python's Pandas or NumPy library). The JSON-formatted weather forecast data acquired in step 1 is used as input. Data analysis extracts the typhoon's path, speed, scale, and the latitude and longitude of the area it will affect. Specifically, the server uses a data analysis library to analyze the data and extract the necessary information. The output is information on disaster-prone areas as a result of the analysis.

[1023] Step 3: Identifying disaster-prone areas

[1024] The server identifies areas where disasters are predicted to occur based on the analyzed data. The information on areas where disasters are predicted obtained in step 2 is used as input. Specifically, the server uses a geocoding API (e.g., Google Maps API) to obtain latitude and longitude information from the analyzed data, and uses this information to map the predicted areas. The output is information on the identified areas where disasters are predicted to occur.

[1025] Step 4: Matching with user location information

[1026] The server compares the user location information stored in the database in advance with the predicted disaster zones identified in step 3. The server uses the user location information and the predicted disaster zone information as input. Specifically, the server executes a database query to extract data on users located within the predicted zones. The output is a list of affected users who are likely to be affected.

[1027] Step 5: Generate a warning notification

[1028] The server generates an alert based on the list of affected users generated in step 4. As input, it uses the list of affected users, information on the typhoon's path, predicted impacts, and safety advice. Specifically, the server uses a text generation library (e.g., a template engine) to generate a customized notification for each user. As output, it obtains an alert for each user.

[1029] Step 6: Sending and displaying notifications

[1030] The server sends the alert notification generated in step 5 to the affected user using an email sending API or a short message service API (e.g., Twilio). The generated alert notification and the affected user's contact information are used as input. Specifically, the server sends the notification data to these APIs and sends the notification. The device displays the received notification as a pop-up to alert the user. As output, the notification is displayed to the user.

[1031] Step 7: Map the disaster zone

[1032] The server uses a map rendering library (e.g., Google Maps API) to map information about disaster-prone areas and post it on a website in real time. Information about disaster-prone areas is used as input. Specifically, the server uses the map rendering library to generate JavaScript code and embeds it in the website's HTML. As output, the mapping information about disaster-prone areas is displayed on the website in real time.

[1033] Step 8: Providing communication continuity support

[1034] The server then carries out the process of providing indoor communication devices (Femto) to users who wish to continue communication. The user's desired information and address information are used as input. Specifically, the server sends the order data to the order management system, and delivery arrangements are made automatically. The user then installs the received indoor communication device and continues communication safely. The output is that the communication device is provided to the user, ensuring stable communication even during a disaster.

[1035] Step 9: Secure your communications base

[1036] The server identifies communication bases located within areas where disasters are predicted to occur and procures the necessary materials in advance. The input is the predicted disaster area and the location information of the communication bases. Specifically, the server generates a list of communication bases, lists the materials needed for each base, and sends order data to the supply chain system. The user (maintenance worker) deploys the necessary materials to the site before a disaster occurs and performs prompt maintenance work after the disaster occurs. The output is that communication bases can be quickly maintained and repaired.

[1037] (Application example 1)

[1038] 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."

[1039] In recent years, natural disasters such as typhoons have become more frequent, and providing prompt and accurate information is essential to minimize damage. However, current systems lack the technology to link disaster prediction information with user location information and provide appropriate warning notifications. Furthermore, disaster notifications and evacuation route guidance are not provided to autonomous vehicles, making ensuring safety during disasters a challenge. Furthermore, maintenance measures for communication infrastructure such as base stations are insufficient, and a means to ensure communication continuity is also needed.

[1040] 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.

[1041] In this invention, the server includes means for acquiring typhoon path forecast data, means for analyzing the acquired typhoon path forecast data to identify predicted disaster areas, means for generating a list of affected users by comparing user location information with the predicted disaster areas, means for sending alert notifications based on the generated list of affected users, means for mapping information about the predicted disaster areas and posting it on a website, means for providing means for continued communication to users who request it, means for identifying base stations within the predicted disaster areas and procuring necessary equipment, and means for sending disaster alert notifications to autonomous vehicles based on the typhoon path forecast data and suggesting safe evacuation routes. This makes it possible to ensure the safety of users and preserve the communications infrastructure by issuing prompt and accurate alert notifications based on typhoon path information and issuing evacuation instructions to autonomous vehicles.

[1042] "Typhoon path forecast data" is data generated by weather forecasting systems and artificial intelligence, including information on a typhoon's path, speed, size, and the area it will affect.

[1043] A "disaster-prone area" is a geographical area that is likely to be affected by a typhoon, identified based on typhoon path forecast data.

[1044] "Affected users" refers to users who are located within the disaster-prone area and who may be affected by the typhoon.

[1045] A "warning notice" is a warning message sent to affected users that includes information on the typhoon's path, expected impacts, and safety advice.

[1046] "Mapping on a map" means visually displaying information about areas where disasters are predicted to occur using a geographic information system or the like.

[1047] "Website" means an online platform for providing information that is publicly available and accessible to users via the Internet.

[1048] "Means for continued communication" refers to devices and technologies that ensure stable communication even during disasters, and a specific example is indoor Femto.

[1049] A "base station" is a wireless communication facility used to maintain and manage mobile communication networks, and its preservation is crucial in times of disaster.

[1050] An "autonomous vehicle" is a vehicle that is capable of driving autonomously without human operation.

[1051] An "evacuation route" is a recommended route for evacuating to a safe place in the event of a disaster, and is set to avoid the path of a typhoon.

[1052] A "generative AI model" is an artificial intelligence model that learns from large amounts of data and performs tasks such as predicting the path of typhoons and providing evacuation route guidance.

[1053] A "prompt" is an input text given to a generative AI model, and is an instruction that causes the model to provide appropriate answers or information.

[1054] Description: Detailed Description of the Invention

[1055] The present invention relates to a system that provides disaster warning notifications and evacuation route guidance to autonomous vehicles based on typhoon path prediction data.

[1056] System configuration

[1057] The system consists of the following main components:

[1058] 1. Server

[1059] 2. User devices (smartphones, PCs, autonomous vehicle computers)

[1060] 3. Website

[1061] 4. Indoor Femto

[1062] 5. Base Station and Maintenance Equipment

[1063] Program processing

[1064] Acquisition and analysis of typhoon path forecast data

[1065] The server periodically obtains typhoon path prediction data generated by the weather forecasting system and the AI ​​generation model via API. For example, the latest prediction data is updated every 24 hours. The obtained typhoon path prediction data includes the typhoon's path, speed, scale, and the latitude and longitude of the areas it will affect. The server analyzes the obtained typhoon path prediction data and identifies areas where disasters are predicted to occur. Based on the results of this analysis, it generates information on areas where disasters are predicted to occur.

[1066] User notification

[1067] The server compares users' location information with the predicted disaster area and creates a list of users who are likely to be affected. It then generates a warning notice based on the list of affected users and sends it to them via email or SMS. The notice includes information on the typhoon's path, expected impact, and advice on how to ensure safety. The user's device displays the received notice as a pop-up to warn the user.

[1068] Website listing

[1069] The server uses a map drawing library to map information about areas where disasters are predicted to occur. This mapped information is posted on a website in real time. Users can access the website to check the predicted disaster areas for themselves and their surrounding areas, enabling them to take safety measures in advance.

[1070] Support for continued communication

[1071] The server then processes the procedures to provide indoor Femto to users who request it to support continued communications. When a user expresses their desire, the system ships the indoor Femto based on the user's address information. By receiving the indoor Femto and installing it in their home, users can ensure stable communications even in the event of a disaster. Specifically, they follow the manual to set it up and connect their device to the Femto.

[1072] base station maintenance

[1073] The server identifies base stations within the predicted disaster area and procures the necessary equipment in advance. It generates a list of the equipment needed for each base station and sends the order to the supply chain system. The necessary equipment is deployed on-site before a disaster occurs, and maintenance work is carried out promptly after the disaster occurs.

[1074] Disaster alert notifications and evacuation route guidance for autonomous vehicles

[1075] The server sends disaster alert notifications to autonomous vehicles based on typhoon path prediction data. The notifications include typhoon path information, evacuation instructions, and safe evacuation routes. Based on the received alert notifications, the autonomous vehicle's computer sets appropriate evacuation routes and displays instructions to the driver.

[1076] Specific examples

[1077] For example, if a generative AI model predicts a typhoon approaching the Tokyo area 48 hours in advance, the server analyzes the information and sends a warning to all users living in the Tokyo area. It also maps areas overlapping with predicted disaster areas and posts them on a website in real time. If a user requests an indoor Femto, the server receives the request and ships it to the user's address. The user can then install the Femto in their home and continue secure communications. Furthermore, the server pre-procures the necessary equipment for base stations in the Tokyo area to support early recovery after a disaster. For autonomous vehicles, it sets up appropriate evacuation routes based on the typhoon's path in real time and displays instructions to the driver.

[1078] Prompt Sentence Examples

[1079] "Analyze the latest typhoon path forecast data to determine if it will affect the Tokyo area. If so, generate an alert notification with evacuation routes and send it to the driver of the autonomous vehicle. The data will be provided in the following format:

[1080] {

[1081] 'typhoon': {

[1082] 'path': 'Typhoon path information',

[1083] 'speed': 'speed of the typhoon',

[1084] 'scale': 'scale of the typhoon',

[1085] 'affected_areas': 'List of affected areas'

[1086] }

[1087] }"

[1088] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1089] Step 1:

[1090] The server periodically obtains typhoon path prediction data generated by the weather forecasting system and generative AI model via the API. The typhoon path prediction data obtained from the API as input includes the typhoon's path, speed, scale, and the latitude and longitude of the area it will affect. The server saves this data as output and prepares it for analysis.

[1091] Step 2:

[1092] The server analyzes the acquired typhoon path prediction data to identify areas where disasters are predicted to occur. The input data analysis includes the path, speed, scale, and latitude and longitude of the affected areas, and the resulting output is the predicted disaster areas. Specifically, the server applies a data analysis algorithm to calculate the degree of impact for each area.

[1093] Step 3:

[1094] The server compares the user's location information with the predicted disaster area and creates a list of users who are likely to be affected. The input location information is stored in a database and is used for comparison. The output is a list of affected users. The server performs the matching process using a comparison algorithm.

[1095] Step 4:

[1096] The server generates a warning notification based on the list of affected users and sends it to them via email or SMS. The notification content includes information on the typhoon's path, expected impacts, and safety advice. The input is the generated warning notification message, and the output is the warning notification to be sent to the user. Specifically, the server sends the message using an SMTP or SMS gateway.

[1097] Step 5:

[1098] The server uses a map drawing library to map information on disaster-prone areas and publishes it on a website in real time. The input is map drawing data, and the website is updated using an API. The output is the updated map information displayed on the website. The server visually processes the mapping using the map drawing library.

[1099] Step 6:

[1100] The server performs the procedure to provide indoor Femto to requesting users to support continued communications. The input is the desired request and address information, and the output is a shipping instruction. Specifically, the server works in conjunction with the logistics system to send a shipping instruction for the indoor Femto.

[1101] Step 7:

[1102] The server identifies base stations within the predicted disaster area and procures the necessary equipment in advance. The input includes base station information and a list of required equipment, and the output includes instructions for procuring the equipment. The server then sends the order to the supply chain system.

[1103] Step 8:

[1104] The server sends disaster alert notifications to autonomous vehicles based on typhoon path prediction data and suggests safe evacuation routes. The input includes path information and evacuation routes, and the output includes evacuation instructions to be displayed on the autonomous vehicle's display. Specifically, the server uses a generative AI model to calculate appropriate evacuation routes and generates notifications using prompt text.

[1105] 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.

[1106] This invention combines a system that notifies users in advance of disasters based on typhoon path forecast data, publishes predicted disaster areas on a website, and provides support for maintaining communications, with an emotion engine that recognizes the user's emotions.The invention also prepares base station maintenance measures in advance, enables rapid recovery in the event of damage, and responds appropriately according to the user's emotional state.

[1107] System configuration

[1108] This system consists of the following main components:

[1109] server

[1110] User device (smartphone, PC, etc.)

[1111] Home page

[1112] Indoor Femto

[1113] Base Station and Maintenance Equipment

[1114] Emotion Engine

[1115] Program processing

[1116] Acquisition and analysis of typhoon path forecast data

[1117] The server periodically obtains typhoon path prediction data generated by weather forecasting systems and AI via API, updating the latest forecast data every 24 hours, for example.

[1118] The server analyzes the acquired typhoon path prediction data, including the typhoon's path, speed, scale, and latitude and longitude of the areas it will affect. Once this analysis is complete, it identifies areas where disasters are predicted to occur.

[1119] The server compares users' location information with predicted disaster areas and creates a list of users who are likely to be affected.

[1120] Emotion recognition by emotion engine

[1121] The device periodically captures the user's facial expressions and voice using sensors such as a camera and microphone, and sends the data to a server.

[1122] The server analyzes the received sensor data using an emotion engine to identify the user's emotional state (e.g., stress level or anxiety).

[1123] User notification

[1124] The server generates a warning notification message to be sent to each user based on the affected user list.

[1125] The server customizes the content of the alert notification depending on the user's emotional state as analyzed by the emotion engine, for example adding more specific safety advice if high stress levels are detected.

[1126] The server uses an email sending API or an SMS sending API to send the generated warning notification message to the affected user.

[1127] The device will display received emails and SMS as pop-up notifications to alert the user.

[1128] Posted on the homepage

[1129] The server uses a map drawing library to map the geographical information of disaster-prone areas, and this mapped information is posted on the website in real time.

[1130] By accessing the website, users can check the predicted disaster areas for themselves and their surrounding areas, allowing them to take safety measures in advance.

[1131] Support for continued communication

[1132] The server will then process the provision of indoor Femto to users who request it to support continued communications. When a user requests it, the server will ship the indoor Femto based on the user's address information.

[1133] Users receive an indoor Femto and install it in their homes to ensure stable communications even in the event of a disaster. Specifically, they follow the instructions to set it up and connect their device to the Femto.

[1134] base station maintenance

[1135] The server identifies base stations within the predicted disaster area and procures the necessary equipment in advance.

[1136] The server generates a list of required equipment for each base station and sends the orders to the supply chain system.

[1137] The user (maintenance worker) deploys the necessary equipment to the site before a disaster occurs and performs maintenance work promptly after the disaster occurs.

[1138] Specific examples

[1139] For example, if the AI ​​predicts that a typhoon will approach the Tokyo area 48 hours in advance, the server will analyze the information and send a warning notice to all users living in the Tokyo area.

[1140] If the emotion engine detects that a particular user is showing high stress levels, the server will send more detailed advice to that user, such as providing specific evacuation locations. It also maps areas that overlap with predicted disaster areas and posts the information on the website in real time.

[1141] If a user requests an indoor Femto, the server will receive the request and ship the indoor Femto to the user's address. Once the user receives the Femto, they can install it and continue communicating securely.

[1142] In addition, the server will procure the necessary equipment for base stations in the Tokyo area in advance, supporting early recovery after a disaster occurs.

[1143] The processing flow will be explained below.

[1144] Acquisition and analysis of typhoon path forecast data

[1145] Step 1:

[1146] The server sends an HTTP request to the specified API endpoint every 24 hours to obtain the latest typhoon track forecast data, which is received in JSON format.

[1147] Step 2:

[1148] The server parses the received JSON data and extracts information about the typhoon's path, speed, size, and latitude and longitude of the area it will affect.

[1149] Step 3:

[1150] The server uses the extracted information to identify areas where disasters are predicted to occur and stores the information in a database.

[1151] Emotion recognition by emotion engine

[1152] Step 1:

[1153] The device periodically captures the user's facial expressions and voice using sensors such as a camera and microphone, and sends the data to a server.

[1154] Step 2:

[1155] The server analyzes the received sensor data using an emotion engine to identify the user's emotional state (e.g., stress level or anxiety).

[1156] Step 3:

[1157] The server stores the identified emotional states in a database.

[1158] User notification

[1159] Step 1:

[1160] The server uses the latitude and longitude information of the disaster predicted area to compare with the user location information in the database, thereby generating a list of affected users.

[1161] Step 2:

[1162] The server generates a warning notification message to be sent to each user based on the affected user list. The message includes typhoon information and safety advice.

[1163] Step 3:

[1164] The server customizes the content of the alert notification depending on the user's emotional state as analyzed by the emotion engine, for example adding specific safety advice if high stress levels are detected.

[1165] Step 4:

[1166] The server uses an email sending API or an SMS sending API to send the generated warning notification message to the affected user.

[1167] Step 5:

[1168] The device will display received emails and SMS as pop-up notifications to alert the user.

[1169] Posted on the homepage

[1170] Step 1:

[1171] The server passes the geographical information of the disaster-prone area to a map drawing library (e.g., Leaflet.js) and maps it on a map.

[1172] Step 2:

[1173] The server uploads the mapped information using the homepage update API and reflects it on the homepage in real time.

[1174] Step 3:

[1175] The user accesses the homepage from a browser and checks information about areas where disasters are predicted to occur.

[1176] Support for continued communication

[1177] Step 1:

[1178] The user contacts the server to request the provision of a means for continuing communication (indoor Femto).

[1179] Step 2:

[1180] The server checks the list of interested users and begins the shipping process for the indoor Femto based on the user's address information.

[1181] Step 3:

[1182] The server sends shipping instructions to the shipping management system and ships the indoor Femto to the relevant user.

[1183] Step 4:

[1184] Once the indoor Femto arrives, users can install it according to the manual to ensure stable communication at home.

[1185] base station maintenance

[1186] Step 1:

[1187] The server identifies base stations within the disaster-prone area in a database.

[1188] Step 2:

[1189] The server generates a list of equipment required for each base station and places orders using the supply chain system API.

[1190] Step 3:

[1191] The server arranges for the procured equipment to be delivered to the designated base station.

[1192] Step 4:

[1193] The user (maintenance worker) uses the equipment procured in advance to carry out maintenance work (inspection, reinforcement, etc.) on the base station before a disaster occurs.

[1194] Step 5:

[1195] After a disaster occurs, the user (maintenance worker) promptly goes to the site and uses the equipment to quickly restore the base station.

[1196] Example 2

[1197] 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."

[1198] Conventional typhoon path prediction systems predict the path of a typhoon and issue warnings to users, but they are unable to address the emotional state of users or the maintenance of communication infrastructure. Providing appropriate countermeasures is particularly important when users are experiencing high levels of stress or anxiety. It is also important to ensure the continuity of communications during disasters and to quickly maintain base stations. Therefore, it is desirable to provide a notification system that can respond to disasters from multiple angles and takes into account the emotional state of users.

[1199] 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.

[1200] In this invention, the server includes means for acquiring typhoon path forecast data, means for analyzing the acquired typhoon path forecast data to identify a disaster-predicted area, means for generating a list of affected users by comparing user location information with the disaster-predicted area, means for collecting and analyzing emotional data of affected users, means for customizing and sending alert notification messages based on the emotion analysis results, means for sending alert notifications based on the generated list of affected users, means for mapping information about the disaster-predicted area on a map and posting it on a website, means for providing means for continuing communications to users who request it, and means for identifying base stations within the disaster-predicted area and procuring the necessary equipment. This makes it possible to provide alert notifications customized in consideration of the emotional state of users, thereby enabling continued communications and rapid base station maintenance in the event of a disaster.

[1201] "Typhoon path forecast data" is information about a typhoon's path, speed, scale, and area of ​​impact, generated by weather forecasting systems and artificial intelligence.

[1202] "Disaster-predicted areas" refer to geographical locations that are highly likely to be affected by disasters, as analyzed based on typhoon path prediction data.

[1203] "User location information" refers to the user's current location or specified address information.

[1204] The "list of affected users" is a list of users who are likely to be affected by a disaster, generated by comparing the predicted disaster area with the location information of the users.

[1205] "Emotional data" is data captured from a user's facial expressions, voice, etc., and used to analyze the user's emotional state.

[1206] "Emotion analysis results" are the results of analyzing the user's emotional state (stress level, anxiety, etc.) based on emotion data.

[1207] A "warning notification message" is a notification sent to users in an area where a disaster is predicted to occur, and includes specific evacuation actions and countermeasures.

[1208] "Mapping" refers to drawing geographical information of areas where disasters are predicted to occur on a map.

[1209] "Means for continuing communication" refers to equipment and methods for ensuring communication stability during disasters, such as indoor Femto.

[1210] A "base station" is a relay device in a communication network, and is a facility for communicating with mobile terminals.

[1211] "Necessary supplies" refers to the equipment, parts, materials, etc. required to maintain or restore the functions of base stations in the event of a disaster.

[1212] This invention combines a system that notifies users in advance of disasters based on typhoon path forecast data, publishes predicted disaster areas on a website, and provides support for maintaining communications, with an emotion engine that recognizes the user's emotions. Furthermore, it can prepare base station maintenance measures in advance, enable rapid recovery in the event of damage, and respond appropriately according to the user's emotional state.

[1213] The system is configured as follows: The main components include a server, user terminals (smartphones, PCs, etc.), a homepage, indoor Femto, base stations and maintenance equipment, and an emotion engine.

[1214] Acquisition and analysis of typhoon path forecast data

[1215] The server periodically obtains typhoon path prediction data generated by weather forecasting systems and artificial intelligence via API. For example, it calls "Weather API XYZ" every 24 hours and stores the data. The server then analyzes the data using "Data Analysis Library ABC" to identify the typhoon's path, speed, scale, and affected areas (latitude, longitude, etc.). Based on the analysis results, it identifies areas where disasters are predicted to occur and compares them with users' location information to create a list of users who are likely to be affected. As a specific example, if a typhoon is predicted to approach the Tokyo area, users who reside in Tokyo will be listed.

[1216] Emotion recognition by emotion engine

[1217] The device periodically captures the user's facial expressions and voice using sensors such as a camera and microphone, encrypts the data, and sends it to a server. The server then uses the "Emotion Analysis Engine XYZ" to analyze the received sensor data and identify the user's emotional state (such as stress level or anxiety). This process allows the user's emotional state to be understood.

[1218] User notification

[1219] The server generates a warning notification message based on the list of affected users. It uses the "Message Generation Library ABC" to create a notification message that includes details about the typhoon and recommended actions. It also customizes the content of the warning notification based on the analysis results of the emotion engine. For example, for users with high stress levels, it could include specific evacuation locations and countermeasures. The server uses an email sending API or SMS sending API to send the generated warning notification message to affected users. The device displays the received email or SMS as a pop-up notification to alert the user.

[1220] Posted on the homepage

[1221] The server maps the geographical information of disaster-prone areas using the "Map Drawing Library GeoLib XYZ." This mapped information is posted on the website in real time. By accessing the website, users can check the disaster-prone areas and take safety measures in advance.

[1222] Support for continued communication

[1223] When the server receives a request for communication continuity support from a user, it ships an indoor Femto based on the user's address information. Specifically, it generates a shipping instruction and connects it to the logistics system. The user receives the indoor Femto and installs it in their home, ensuring stable communication even in the event of a disaster. The installation procedure is carried out according to the enclosed manual.

[1224] base station maintenance

[1225] The server identifies base stations within areas where disasters are predicted to occur and procures the necessary equipment in advance. It uses a geographic information system to list the applicable base stations, generates an equipment list for each base station, and sends orders to the supply chain system. The user (maintenance worker) deploys the necessary equipment on-site before a disaster occurs, and then quickly performs maintenance work on the base stations after the disaster occurs.

[1226] Examples of concrete examples and prompts

[1227] For example, if the AI ​​predicts that a typhoon will approach the Tokyo area 48 hours in advance, the server will analyze the information and send a warning to users living in the Tokyo area. If the emotion engine detects that a particular user is showing high stress levels, the server will send more detailed advice to that user, such as providing specific evacuation locations. The server will also map areas predicted to be affected by disasters and post them on the website in real time.

[1228] Example prompt: "A typhoon is approaching the Tokyo area. Generate an appropriate warning notification message based on the disaster forecast and the user's emotional state."

[1229] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1230] Step 1: Obtaining typhoon track forecast data

[1231] The server periodically obtains the latest typhoon path forecast data generated by weather forecasting systems and artificial intelligence via API. The input is typhoon path forecast data obtained from "Weather API XYZ," and the output is raw data stored in a database on the server. Specifically, the server schedules an API call every 24 hours, receives the response data in JSON format, and stores it in the database.

[1232] Step 2: Analysis of typhoon track forecast data

[1233] The server analyzes the acquired typhoon path prediction data and identifies the typhoon's path, speed, scale, and the latitude and longitude of the area it will affect. The input is the raw data acquired earlier, and the output is the analyzed typhoon information (path, speed, scale, latitude and longitude). Specifically, it uses the "Data Analysis Library ABC" to analyze and extract various typhoon data and convert it into an easy-to-understand format.

[1234] Step 3: Identifying areas where disasters are likely to occur

[1235] The server identifies areas where disasters are predicted to occur based on the analysis results. The input is the analyzed typhoon information, and the output is geographic information on the areas where disasters are predicted to occur. Specifically, the affected area is mapped using a geographic information system (GIS) and the data is saved.

[1236] Step 4: List affected users

[1237] The server compares the predicted disaster area with user location information and generates a list of users who are likely to be affected. The input is a database of user location information and predicted disaster area information, and the output is a list of affected users. Specifically, it runs an SQL query based on the location information to extract and list the relevant users.

[1238] Step 5: Capturing and Sending Sensor Data

[1239] The device periodically captures the user's facial expressions and voice using sensors such as a camera and microphone, and sends the data to a server. The input is the facial expression and voice data captured by the device, and the output is the emotion data sent to the server. Specifically, the data is collected every hour using a facial recognition API and a voice analysis API, encrypted, and sent to the server.

[1240] Step 6: Sentiment Analysis

[1241] The server analyzes the received sensor data using the "Emotion Analysis Engine XYZ" to identify the user's emotional state. The input is sensor data, and the output is the result of identifying the emotional state. Specifically, it uses algorithms that analyze facial muscle movements and tone of voice to identify emotional states such as stress levels and anxiety.

[1242] Step 7: Generate a warning notification message

[1243] The server generates a warning notification message based on the affected user list. The input is the affected user list and disaster predicted area information, and the output is a warning notification message. Furthermore, the notification content is customized according to the results of sentiment analysis. Specifically, the "Message Generation Library ABC" is used to create a notification message that includes details of the typhoon and evacuation instructions.

[1244] Step 8: Sending alert notifications

[1245] The server then uses an email or SMS API to send the generated alert notification message to affected users. The input is the alert notification message, and the output is the sent notification. Specifically, the API is called and a message is sent to each user's contact information.

[1246] Step 9: Post disaster information on your website

[1247] The server maps the geographic information of disaster-predicted areas using the "Map Drawing Library GeoLib XYZ" and posts it on the website in real time. The input is the geographic information of disaster-predicted areas, and the output is the updated content of the website. Specifically, the map information is updated regularly and reflected on the website in real time using an API.

[1248] Step 10: Providing communication continuity support

[1249] The server receives a request for communication continuity support from the user and ships the indoor Femto based on the user's address information. The input is the request information and the user's address information, and the output is a shipping instruction. Specifically, it works in conjunction with the logistics system to carry out the procedures for shipping the necessary equipment.

[1250] Step 11: Prepare for base station maintenance work

[1251] The server identifies base stations within disaster-predicted areas and procures the necessary equipment in advance. The input is base station data and disaster-predicted area information, and the output is an equipment list and ordering information. Specifically, it uses GIS to list the applicable base stations, and creates and orders a list of the necessary equipment.

[1252] Step 12: Carry out base station maintenance work

[1253] The user (maintenance worker) deploys the necessary equipment for each identified base station on-site and performs maintenance work promptly after a disaster occurs. The input is an equipment list and base station information, and the output is the maintenance status of the base station. Specifically, the user travels to the site and performs the necessary maintenance work to support rapid recovery.

[1254] (Application example 2)

[1255] 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."

[1256] The problem that this invention aims to solve is to provide users with prompt and accurate notifications when a natural disaster such as a typhoon is approaching, and to provide information customized to the user's emotional state. This will increase the accuracy of the information received by users, reduce stress and anxiety, and support the continuity of communications and the rapid recovery of base stations.

[1257] 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.

[1258] In this invention, the server includes means for acquiring typhoon path forecast data, means for analyzing the acquired typhoon path forecast data to identify a disaster-predicted area, means for generating a list of affected users by comparing user location information with the disaster-predicted area, means for transmitting a warning notice based on the generated list of affected users, means for capturing the user's facial expression and voice using a sensor in the user terminal and analyzing it with an emotion engine to identify the user's emotional state, means for customizing the content of the warning notice according to the user's emotional state, means for mapping information about the disaster-predicted area on a map and posting it on a homepage, means for providing means for communication continuity to users who request it, and means for identifying base stations within the disaster-predicted area and procuring the necessary equipment. This allows for the server to provide users with emergency disaster information and send customized notifications according to the user's emotional state, enabling the continuation of communication and the rapid restoration of base stations.

[1259] "Typhoon path forecast data" is data that includes information on the path, speed, scale, and areas affected by a typhoon, calculated using weather forecasting systems and artificial intelligence.

[1260] "Disaster-prone areas" are areas that are likely to be affected by typhoons, as identified by analyzing typhoon path prediction data.

[1261] "User Location Information" means geographic data about a User's current location obtained from a smartphone or other GPS-enabled device.

[1262] The "list of affected users" is a list of users who are likely to be affected by the typhoon, generated by comparing the predicted disaster area with the user's location information.

[1263] A "warning notice" is a message sent to affected users to warn them in advance about the approach and impact of a typhoon.

[1264] An "emotion engine" is a software system that analyzes sensor data to identify a user's emotional state (e.g., stress level or anxiety).

[1265] "Mapping on a map" means displaying information about disaster-prone areas on a geographical map.

[1266] A "home page" is a page that is part of a website accessible on the Internet and provides information to users.

[1267] "Means for continued communication" refers to equipment and services provided to ensure stable communication even during disasters.

[1268] A "base station" is a facility or equipment for communicating with mobile terminals in a wireless communication network.

[1269] "Essential equipment" refers to spare parts and equipment required for the base station to continue to function normally.

[1270] A "sensor" is a device used to capture a user's facial expressions and voice.

[1271] "Emotional state" refers to the user's psychological state (e.g., stress, anxiety, etc.).

[1272] A "customized notification" is an alert notification message whose content is tailored to the user's emotional state.

[1273] A "prompt" is text that is input to a generative AI model and serves as an instruction to execute a specific generation task.

[1274] The present invention relates to a system that notifies users of disasters in advance based on typhoon path forecast data and provides information customized according to the user's emotional state. This system is composed of the following hardware and software.

[1275] Program processing and technology used

[1276] 1. Acquisition and analysis of typhoon track forecast data

[1277] The server periodically retrieves typhoon path prediction data from the API via a weather forecasting system and AI (artificial intelligence). The specific software used is the Python requests library.

[1278] The acquired data is analyzed to identify the typhoon's path, speed, scale, and affected area. For the analysis, Python data analysis libraries (e.g., Pandas, NumPy) are used.

[1279] 2. Identifying areas where disasters are predicted to occur and creating a list of affected users

[1280] The server identifies areas where disasters are predicted to occur based on the typhoon path prediction data it has acquired. This area information is then mapped onto a map using geographic information system (GIS) software (e.g., Leaflet, Mapbox).

[1281] The server compares users' location information with predicted disaster areas and generates a "list of affected users" who are likely to be affected by the typhoon.

[1282] 3. User Emotion Recognition and Notification Message Customization

[1283] The device uses the smartphone's camera and microphone to capture the user's facial expressions and voice, and sends the data to a server using OpenCV (an image processing library) and deep learning frameworks (e.g., TensorFlow and Keras).

[1284] The server analyzes the received sensor data using an emotion engine to identify the user's emotional state (stress level and anxiety).

[1285] The server customizes the alert notification content according to the user's emotional state based on the analysis results of the emotion engine, and generates a prompt using a generative AI model. Examples of prompts include:

[1286] A typhoon is forecast to approach your area within the next 48 hours. Please prepare to evacuate. High stress levels have been detected. Please confirm specific evacuation locations and emergency contact information.

[1287] 4. Notifications and Website Posting

[1288] Based on the generated list of affected users, the server uses an email sending API or an SMS sending API to send a customized warning notification message to each user.

[1289] The device displays received emails and SMS as pop-up notifications, prompting the user to take appropriate action.

[1290] Information on predicted disaster areas is posted in real time on the website using a map drawing library, allowing users to access the website and check the predicted disaster areas for themselves and their surrounding areas.

[1291] 5. Support for continued communications and base station maintenance

[1292] The server will then process the delivery of an indoor Femto to requesting users to support continued communications. When a user requests an indoor Femto, the server will ship the Femto based on the user's address information.

[1293] The server identifies base stations within the predicted disaster area, generates an equipment list, and procures the necessary equipment in advance. To support the rapid recovery of base stations, the server uses a supply chain system to deploy the necessary equipment to the site.

[1294] Specific examples

[1295] For example, if the AI ​​predicts a typhoon approaching the Tokyo area 48 hours in advance, the server analyzes the information and sends a warning to all users living in the Tokyo area. If the emotion engine detects a high stress level, the server sends detailed advice to the user, such as providing specific evacuation locations. The server also maps areas that overlap with predicted disaster areas and posts the information on the website in real time. If a user requests an indoor Femto, the server receives the request and ships the Femto to the user's address. The user can then install the Femto and continue communications. Furthermore, the server procures the necessary equipment for base stations in the Tokyo area in advance to support rapid recovery after a disaster occurs.

[1296] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1297] Step 1:

[1298] The server periodically obtains typhoon path forecast data generated by weather forecasting systems and AI via an API. This is done using the Python requests library. The input is the typhoon path forecast data obtained from the API, and the output is raw data that can be analyzed.

[1299] Step 2:

[1300] The server analyzes the acquired typhoon path prediction data and extracts information on the typhoon's path, speed, scale, and the area it will affect (latitude and longitude). This analysis uses data analysis libraries such as Python's Pandas and NumPy. The input is the acquired raw data, and the output is a dataset containing the analysis results.

[1301] Step 3:

[1302] The server uses the analysis results to identify areas where disasters are predicted to occur using geographic information system (GIS) software (e.g., Leaflet, Mapbox). The input is a dataset containing the analysis results, and the output is map data drawn by the GIS software.

[1303] Step 4:

[1304] The server compares the user's location information with the predicted disaster area and generates a list of affected users. The input is the user's location information and map data drawn by GIS software, and the output is the list of affected users.

[1305] Step 5:

[1306] The device uses the smartphone's camera and microphone to capture the user's facial expressions and voice, and sends the data to the server. The technology used is OpenCV (an image processing library). The input is the raw data of the user's facial expressions and voice, and the output is the sensor data sent to the server.

[1307] Step 6:

[1308] The server identifies the user's emotional state (stress level, anxiety, etc.) based on the sensor data analyzed by the emotion engine. The software used is a deep learning framework such as TensorFlow or Keras. The input is the sensor data, and the output is the analysis result of the emotional state.

[1309] Step 7:

[1310] The server customizes the content of the alert notification message based on the results of the emotional state analysis and generates a prompt using a generative AI model. For example, it generates a prompt such as, "A typhoon is predicted to approach your area within 48 hours. Please prepare for evacuation. High stress levels have been detected. Please confirm specific evacuation locations and emergency contact information." The input is the results of the emotional state analysis, and the output is a customized notification message.

[1311] Step 8:

[1312] The server uses the email sending API or SMS sending API to send a customized warning notification message to each user based on the generated affected user list. The input is the customized notification message and the affected user list, and the output is the sent warning notification message.

[1313] Step 9:

[1314] The terminal displays the received email or SMS as a pop-up notification to alert the user. The input is the sent warning notification message, and the output is the pop-up notification displayed on the terminal.

[1315] Step 10:

[1316] The server maps information about disaster-predicted areas onto a map and posts it on the website in real time. The software used is a map drawing library (e.g., Leaflet, Mapbox). The input is information about disaster-predicted areas, and the output is updated map data for the website.

[1317] Step 11:

[1318] The server performs the procedure to provide indoor Femto to requesting users to support continuous communication. When a user expresses a desire, the server ships the indoor Femto based on the user's address information. The input is the user's wish list and address information, and the output is the completion data of the shipping procedure.

[1319] Step 12:

[1320] The server identifies base stations within the predicted disaster area, generates an equipment list, and procures the necessary equipment in advance. The technology used is a supply chain system. The input is base station information and data on the predicted disaster area, and the output is the generated equipment list.

[1321] Step 13:

[1322] The server deploys the necessary equipment to the site through the supply chain system, and the maintenance worker carries out the maintenance work. The input is an equipment list, and the output is the deployed equipment and the completion data of the maintenance work.

[1323] 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.

[1324] 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.

[1325] 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.

[1326] [Fourth embodiment]

[1327] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1328] 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.

[1329] 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).

[1330] 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.

[1331] 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.

[1332] 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).

[1333] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1334] 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.

[1335] 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.

[1336] 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.

[1337] 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.

[1338] 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.

[1339] 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."

[1340] This system notifies users of disasters in advance based on typhoon path forecast data, lists predicted disaster areas on the website, and provides support for maintaining communications.The system also prepares base station maintenance measures in advance, enabling rapid recovery in the event of damage.

[1341] System configuration

[1342] This system consists of the following main components:

[1343] server

[1344] User device (smartphone, PC, etc.)

[1345] Home page

[1346] Indoor Femto

[1347] Base Station and Maintenance Equipment

[1348] Program processing

[1349] Acquisition and analysis of typhoon path forecast data

[1350] The server periodically obtains typhoon path prediction data generated by weather forecasting systems and AI via API, updating the latest forecast data every 24 hours, for example.

[1351] The server analyzes the acquired typhoon path prediction data, including the typhoon's path, speed, scale, and latitude and longitude of the areas it will affect. Once this analysis is complete, it identifies areas where disasters are predicted to occur.

[1352] The server compares users' location information with predicted disaster areas and creates a list of users who are likely to be affected.

[1353] User notification

[1354] The server generates a warning notice based on the list of affected users, including information on the storm's path, expected impacts, and safety advice.

[1355] The server will send a warning notice to affected users via email or SMS, which will be displayed on their smartphones or PCs.

[1356] The device displays the received notification as a pop-up to warn the user. For example, a message such as "A typhoon is approaching your area. Please evacuate to a safe place" may be displayed.

[1357] Posted on the homepage

[1358] The server uses a map drawing library to map information about areas where disasters are predicted to occur, and this mapped information is posted on the website in real time.

[1359] By accessing the website, users can check the predicted disaster areas for themselves and their surrounding areas, allowing them to take safety measures in advance.

[1360] Support for continued communication

[1361] The server then processes the request to provide indoor Femto to users who request it to continue communications. When a user expresses their desire, the system will ship the indoor Femto based on the user's address information.

[1362] Users can receive an indoor Femto and install it in their homes to ensure stable communications even during disasters. Specifically, they follow the instructions to set it up and connect their device to the Femto.

[1363] base station maintenance

[1364] The server identifies base stations within the predicted disaster area and procures the necessary equipment in advance.

[1365] The server generates a list of required equipment for each base station and sends the orders to the supply chain system.

[1366] The user (maintenance worker) deploys the necessary equipment to the site before a disaster occurs and performs maintenance work promptly after the disaster occurs.

[1367] Specific examples

[1368] For example, if the AI ​​predicts that a typhoon will approach the Tokyo area 48 hours in advance, the server will analyze the information and send a warning to all users living in the Tokyo area. It will also map areas that overlap with the predicted disaster area and post the information on the website in real time.

[1369] If a user requests an indoor Femto, the server will receive the request and ship the indoor Femto to the user's address. Once the user receives the Femto, they can install it and continue communicating securely.

[1370] In addition, the server will procure the necessary equipment for base stations in the Tokyo area in advance, supporting early recovery after a disaster occurs.

[1371] The processing flow will be explained below.

[1372] Acquisition and analysis of typhoon path forecast data

[1373] Step 1:

[1374] The server periodically sends an HTTP request to the specified API endpoint to obtain the latest typhoon track forecast data, which is received in JSON format.

[1375] Step 2:

[1376] The server parses the received JSON data and extracts information on the typhoon's path, speed, size, and latitude and longitude of the affected area.

[1377] Step 3:

[1378] The server uses the extracted information to identify areas where disasters are predicted to occur and stores the information in a database.

[1379] User notification

[1380] Step 1:

[1381] The server uses the latitude and longitude information of the disaster predicted area to compare with the user location information in the database, thereby generating a list of affected users.

[1382] Step 2:

[1383] The server generates a warning notification message to be sent to each user based on the affected user list. The message includes typhoon information and safety advice.

[1384] Step 3:

[1385] The server uses an email sending API or an SMS sending API to send the generated warning notification message to the affected user.

[1386] Step 4:

[1387] The device will display received emails and SMS as pop-up notifications to alert the user.

[1388] Posted on the homepage

[1389] Step 1:

[1390] The server passes the geographical information of the disaster-prone area to a map drawing library (e.g., Leaflet.js) and maps it on a map.

[1391] Step 2:

[1392] The server uploads the mapped information using the homepage update API and reflects it on the homepage in real time.

[1393] Step 3:

[1394] The user accesses the homepage from a browser and checks information about areas where disasters are predicted to occur.

[1395] Support for continued communication

[1396] Step 1:

[1397] The user contacts the server to request the provision of a means for continuing communication (indoor Femto).

[1398] Step 2:

[1399] The server checks the list of interested users and begins the shipping process for the indoor Femto based on the user's address information.

[1400] Step 3:

[1401] The server sends shipping instructions to the shipping management system and ships the indoor Femto to the relevant user.

[1402] Step 4:

[1403] Once the indoor Femto arrives, users can install it according to the manual to ensure stable communication at home.

[1404] base station maintenance

[1405] Step 1:

[1406] The server identifies base stations within the disaster-prone area in a database.

[1407] Step 2:

[1408] The server generates a list of equipment required for each base station and places orders using the supply chain system API.

[1409] Step 3:

[1410] The server arranges for the procured equipment to be delivered to the designated base station.

[1411] Step 4:

[1412] The user (maintenance worker) uses the equipment procured in advance to carry out maintenance work (inspection, reinforcement, etc.) on the base station before a disaster occurs.

[1413] Step 5:

[1414] After a disaster occurs, the user (maintenance worker) promptly goes to the site and uses the equipment to quickly restore the base station.

[1415] Example 1

[1416] 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."

[1417] With conventional disaster notification systems, it is difficult to efficiently obtain and analyze path prediction data for meteorological disasters such as typhoons, making it impossible to notify users in a timely manner. Furthermore, due to insufficient maintenance of communication infrastructure and the provision of continuous communication methods when a disaster occurs, a rapid response is not possible when a disaster occurs.

[1418] 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.

[1419] In this invention, the server includes means for acquiring weather forecast data, means for analyzing the acquired weather forecast data to identify a disaster-predicted area, means for generating an affected user list by comparing user location information with the disaster-predicted area, means for sending a warning notice based on the generated affected user list, means for mapping information about the disaster-predicted area on a map and posting it on a website, means for providing communication continuity devices to users who request them, and means for identifying communication bases within the disaster-predicted area and procuring the necessary materials. This makes it possible to quickly acquire and analyze weather disaster path forecast data, issue timely warning notices to affected users, and maintain communication infrastructure and provide continuous communication means during a disaster.

[1420] "Weather forecast data" refers to forecast information regarding the path, speed, scale, precipitation amount, etc. of typhoons and other weather phenomena provided by meteorological agencies and weather analysis systems.

[1421] "Disaster-prone area" refers to the area where a specific weather disaster is likely to occur based on analyzed weather forecast data.

[1422] "User location information" refers to information that indicates the user's actual location, such as address information provided by the user or current location data obtained from GPS.

[1423] "Affected User List" means a list of users who reside within or near a disaster-prone area and who are identified as likely to be affected by a disaster.

[1424] "Warning Notice" refers to a warning message sent to affected users that includes the path of the disaster, predicted impacts, and safety advice.

[1425] "Mapping on a map" refers to the process of visually displaying information on areas where disasters are predicted to occur on a map, thereby enabling users to intuitively grasp the danger zone.

[1426] "Posting on the website" refers to uploading map information of disaster-prone areas to the website in real time and making it accessible to the general public.

[1427] "Communication continuity device" refers to equipment that allows users to continue using communication services such as the Internet and telephone even if communication infrastructure is damaged or stopped during a disaster.

[1428] A "communications base" is a basic facility for mobile communications and broadband communications, and refers to infrastructure including antennas, transmitting and receiving equipment, etc.

[1429] "Necessary materials" refers to the equipment, tools, parts, etc. required to maintain and repair communications bases in disaster-prone areas.

[1430] This system uses weather disaster path forecast data to notify users of disasters in advance, publishes disaster-prone areas on a website, and provides support for maintaining communications. It also prepares preservation measures for communications bases in advance, enabling rapid restoration in the event of damage.

[1431] Key components of the system

[1432] This system consists of the following main components:

[1433] server

[1434] User device (smartphone, PC, etc.)

[1435] Website

[1436] Indoor communication devices (e.g. Femto)

[1437] Communications bases and maintenance equipment

[1438] Hardware and Software Configuration

[1439] The server periodically obtains typhoon path forecast data using a weather forecasting system or a generative AI model (e.g., OpenAI API). Specifically, it obtains JSON-formatted data from the weather data providing API using an HTTP request. The obtained data is stored in a database.

[1440] The server then analyzes this data using a data analysis module (e.g., Python's Pandas or NumPy library). The analysis involves extracting the typhoon's path, speed, and scale, as well as the latitude and longitude of the area it will affect. The disaster-prone area information identified here is then geographically mapped using a geocoding API (e.g., Google Maps API).

[1441] The server then compares users' location information stored in a database with the identified disaster-prone areas. This comparison generates a list of users likely to be affected. Based on this list, the server generates a warning notice, which includes information on the typhoon's path, predicted impacts, and safety advice.

[1442] To send notifications, the server uses an email sending API or a short message service API (e.g., Twilio) to send the generated notification to the user's smartphone or PC. The device then displays the received notification as a pop-up to alert the user.

[1443] The server then maps the information on the disaster-prone areas using a map drawing library (e.g., Google Maps API) and posts it on a website in real time. Users can access this website to check the disaster-prone areas for themselves and their surroundings.

[1444] To support continued communications, the server will provide a communications device (Femto) to the user if the user requests it. When the user expresses their desire, the system will ship the device based on the user's address information. The user can then install the device in their home and continue secure communications.

[1445] As a maintenance measure for communication bases, the server identifies communication bases located within disaster-prone areas and procures the necessary materials in advance. The server generates a list of materials required for each communication base and sends an order to the supply chain system. The user (maintenance worker) deploys the necessary materials to the site before a disaster occurs and performs maintenance work quickly after the disaster occurs.

[1446] Specific examples

[1447] For example, if the generative AI model predicts a typhoon approaching the Tokyo area 48 hours in advance, the server will analyze this information and send a warning to all users living in the Tokyo area. It will also map areas that overlap with the predicted disaster zone and post the information on the website in real time.

[1448] When a user requests a communication device, the server receives the request and ships the device to the user's address. The user can then install the device and continue communicating safely. In addition, the server pre-procures the materials needed for communication bases in the Tokyo area to support early recovery after a disaster.

[1449] Prompt Sentence Examples

[1450] "A typhoon is approaching your area. Please evacuate to a safe place."

[1451] As described above, the present invention is a system that provides a rapid and accurate response to meteorological disasters, and is equipped with various functions for minimizing damage.

[1452] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1453] Step 1: Obtain weather forecast data

[1454] The server periodically obtains typhoon path forecast data using a weather forecasting system and generative AI model. It accesses the weather data provision API as input and receives JSON-formatted data. This data includes the typhoon's path, speed, scale, and the latitude and longitude of the area it will affect. Specifically, the server calls an API endpoint such as "GET / api / typhoon-forecast" to obtain the latest forecast data. The obtained weather forecast data is obtained as output.

[1455] Step 2: Analyze weather forecast data

[1456] The server analyzes the acquired weather forecast data using a data analysis module (e.g., Python's Pandas or NumPy library). The JSON-formatted weather forecast data acquired in step 1 is used as input. Data analysis extracts the typhoon's path, speed, scale, and the latitude and longitude of the area it will affect. Specifically, the server uses a data analysis library to analyze the data and extract the necessary information. The output is information on disaster-prone areas as a result of the analysis.

[1457] Step 3: Identifying disaster-prone areas

[1458] The server identifies areas where disasters are predicted to occur based on the analyzed data. The information on areas where disasters are predicted obtained in step 2 is used as input. Specifically, the server uses a geocoding API (e.g., Google Maps API) to obtain latitude and longitude information from the analyzed data, and uses this information to map the predicted areas. The output is information on the identified areas where disasters are predicted to occur.

[1459] Step 4: Matching with user location information

[1460] The server compares the user location information stored in the database in advance with the predicted disaster zones identified in step 3. The server uses the user location information and the predicted disaster zone information as input. Specifically, the server executes a database query to extract data on users located within the predicted zones. The output is a list of affected users who are likely to be affected.

[1461] Step 5: Generate a warning notification

[1462] The server generates an alert based on the list of affected users generated in step 4. As input, it uses the list of affected users, information on the typhoon's path, predicted impacts, and safety advice. Specifically, the server uses a text generation library (e.g., a template engine) to generate a customized notification for each user. As output, it obtains an alert for each user.

[1463] Step 6: Sending and displaying notifications

[1464] The server sends the alert notification generated in step 5 to the affected user using an email sending API or a short message service API (e.g., Twilio). The generated alert notification and the affected user's contact information are used as input. Specifically, the server sends the notification data to these APIs and sends the notification. The device displays the received notification as a pop-up to alert the user. As output, the notification is displayed to the user.

[1465] Step 7: Map the disaster zone

[1466] The server uses a map rendering library (e.g., Google Maps API) to map information about disaster-prone areas and post it on a website in real time. Information about disaster-prone areas is used as input. Specifically, the server uses the map rendering library to generate JavaScript code and embeds it in the website's HTML. As output, the mapping information about disaster-prone areas is displayed on the website in real time.

[1467] Step 8: Providing communication continuity support

[1468] The server then carries out the process of providing indoor communication devices (Femto) to users who wish to continue communication. The user's desired information and address information are used as input. Specifically, the server sends the order data to the order management system, and delivery arrangements are made automatically. The user then installs the received indoor communication device and continues communication safely. The output is that the communication device is provided to the user, ensuring stable communication even during a disaster.

[1469] Step 9: Secure your communications base

[1470] The server identifies communication bases located within areas where disasters are predicted to occur and procures the necessary materials in advance. The input is the predicted disaster area and the location information of the communication bases. Specifically, the server generates a list of communication bases, lists the materials needed for each base, and sends order data to the supply chain system. The user (maintenance worker) deploys the necessary materials to the site before a disaster occurs and performs prompt maintenance work after the disaster occurs. The output is that communication bases can be quickly maintained and repaired.

[1471] (Application example 1)

[1472] 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."

[1473] In recent years, natural disasters such as typhoons have become more frequent, and providing prompt and accurate information is essential to minimize damage. However, current systems lack the technology to link disaster prediction information with user location information and provide appropriate warning notifications. Furthermore, disaster notifications and evacuation route guidance are not provided to autonomous vehicles, making ensuring safety during disasters a challenge. Furthermore, maintenance measures for communication infrastructure such as base stations are insufficient, and a means to ensure communication continuity is also needed.

[1474] 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.

[1475] In this invention, the server includes means for acquiring typhoon path forecast data, means for analyzing the acquired typhoon path forecast data to identify predicted disaster areas, means for generating a list of affected users by comparing user location information with the predicted disaster areas, means for sending alert notifications based on the generated list of affected users, means for mapping information about the predicted disaster areas and posting it on a website, means for providing means for continued communication to users who request it, means for identifying base stations within the predicted disaster areas and procuring necessary equipment, and means for sending disaster alert notifications to autonomous vehicles based on the typhoon path forecast data and suggesting safe evacuation routes. This makes it possible to ensure the safety of users and preserve the communications infrastructure by issuing prompt and accurate alert notifications based on typhoon path information and issuing evacuation instructions to autonomous vehicles.

[1476] "Typhoon path forecast data" is data generated by weather forecasting systems and artificial intelligence, including information on a typhoon's path, speed, size, and the area it will affect.

[1477] A "disaster-prone area" is a geographical area that is likely to be affected by a typhoon, identified based on typhoon path forecast data.

[1478] "Affected users" refers to users who are located within the disaster-prone area and who may be affected by the typhoon.

[1479] A "warning notice" is a warning message sent to affected users that includes information on the typhoon's path, expected impacts, and safety advice.

[1480] "Mapping on a map" means visually displaying information about areas where disasters are predicted to occur using a geographic information system or the like.

[1481] "Website" means an online platform for providing information that is publicly available and accessible to users via the Internet.

[1482] "Means for continued communication" refers to devices and technologies that ensure stable communication even during disasters, and a specific example is indoor Femto.

[1483] A "base station" is a wireless communication facility used to maintain and manage mobile communication networks, and its preservation is crucial in times of disaster.

[1484] An "autonomous vehicle" is a vehicle that is capable of driving autonomously without human operation.

[1485] An "evacuation route" is a recommended route for evacuating to a safe place in the event of a disaster, and is set to avoid the path of a typhoon.

[1486] A "generative AI model" is an artificial intelligence model that learns from large amounts of data and performs tasks such as predicting the path of typhoons and providing evacuation route guidance.

[1487] A "prompt" is an input text given to a generative AI model, and is an instruction that causes the model to provide appropriate answers or information.

[1488] Description: Detailed Description of the Invention

[1489] The present invention relates to a system that provides disaster warning notifications and evacuation route guidance to autonomous vehicles based on typhoon path prediction data.

[1490] System configuration

[1491] The system consists of the following main components:

[1492] 1. Server

[1493] 2. User devices (smartphones, PCs, autonomous vehicle computers)

[1494] 3. Website

[1495] 4. Indoor Femto

[1496] 5. Base Station and Maintenance Equipment

[1497] Program processing

[1498] Acquisition and analysis of typhoon path forecast data

[1499] The server periodically obtains typhoon path prediction data generated by the weather forecasting system and the AI ​​generation model via API. For example, the latest prediction data is updated every 24 hours. The obtained typhoon path prediction data includes the typhoon's path, speed, scale, and the latitude and longitude of the areas it will affect. The server analyzes the obtained typhoon path prediction data and identifies areas where disasters are predicted to occur. Based on the results of this analysis, it generates information on areas where disasters are predicted to occur.

[1500] User notification

[1501] The server compares users' location information with the predicted disaster area and creates a list of users who are likely to be affected. It then generates a warning notice based on the list of affected users and sends it to them via email or SMS. The notice includes information on the typhoon's path, expected impact, and advice on how to ensure safety. The user's device displays the received notice as a pop-up to warn the user.

[1502] Website listing

[1503] The server uses a map drawing library to map information about areas where disasters are predicted to occur. This mapped information is posted on a website in real time. Users can access the website to check the predicted disaster areas for themselves and their surrounding areas, enabling them to take safety measures in advance.

[1504] Support for continued communication

[1505] The server then processes the procedures to provide indoor Femto to users who request it to support continued communications. When a user expresses their desire, the system ships the indoor Femto based on the user's address information. By receiving the indoor Femto and installing it in their home, users can ensure stable communications even in the event of a disaster. Specifically, they follow the manual to set it up and connect their device to the Femto.

[1506] base station maintenance

[1507] The server identifies base stations within the predicted disaster area and procures the necessary equipment in advance. It generates a list of the equipment needed for each base station and sends the order to the supply chain system. The necessary equipment is deployed on-site before a disaster occurs, and maintenance work is carried out promptly after the disaster occurs.

[1508] Disaster alert notifications and evacuation route guidance for autonomous vehicles

[1509] The server sends disaster alert notifications to autonomous vehicles based on typhoon path prediction data. The notifications include typhoon path information, evacuation instructions, and safe evacuation routes. Based on the received alert notifications, the autonomous vehicle's computer sets appropriate evacuation routes and displays instructions to the driver.

[1510] Specific examples

[1511] For example, if a generative AI model predicts a typhoon approaching the Tokyo area 48 hours in advance, the server analyzes the information and sends a warning to all users living in the Tokyo area. It also maps areas overlapping with predicted disaster areas and posts them on a website in real time. If a user requests an indoor Femto, the server receives the request and ships it to the user's address. The user can then install the Femto in their home and continue secure communications. Furthermore, the server pre-procures the necessary equipment for base stations in the Tokyo area to support early recovery after a disaster. For autonomous vehicles, it sets up appropriate evacuation routes based on the typhoon's path in real time and displays instructions to the driver.

[1512] Prompt Sentence Examples

[1513] "Analyze the latest typhoon path forecast data to determine if it will affect the Tokyo area. If so, generate an alert notification with evacuation routes and send it to the driver of the autonomous vehicle. The data will be provided in the following format:

[1514] {

[1515] 'typhoon': {

[1516] 'path': 'Typhoon path information',

[1517] 'speed': 'speed of the typhoon',

[1518] 'scale': 'scale of the typhoon',

[1519] 'affected_areas': 'List of affected areas'

[1520] }

[1521] }"

[1522] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1523] Step 1:

[1524] The server periodically obtains typhoon path prediction data generated by the weather forecasting system and generative AI model via the API. The typhoon path prediction data obtained from the API as input includes the typhoon's path, speed, scale, and the latitude and longitude of the area it will affect. The server saves this data as output and prepares it for analysis.

[1525] Step 2:

[1526] The server analyzes the acquired typhoon path prediction data to identify areas where disasters are predicted to occur. The input data analysis includes the path, speed, scale, and latitude and longitude of the affected areas, and the resulting output is the predicted disaster areas. Specifically, the server applies a data analysis algorithm to calculate the degree of impact for each area.

[1527] Step 3:

[1528] The server compares the user's location information with the predicted disaster area and creates a list of users who are likely to be affected. The input location information is stored in a database and is used for comparison. The output is a list of affected users. The server performs the matching process using a comparison algorithm.

[1529] Step 4:

[1530] The server generates a warning notification based on the list of affected users and sends it to them via email or SMS. The notification content includes information on the typhoon's path, expected impacts, and safety advice. The input is the generated warning notification message, and the output is the warning notification to be sent to the user. Specifically, the server sends the message using an SMTP or SMS gateway.

[1531] Step 5:

[1532] The server uses a map drawing library to map information on disaster-prone areas and publishes it on a website in real time. The input is map drawing data, and the website is updated using an API. The output is the updated map information displayed on the website. The server visually processes the mapping using the map drawing library.

[1533] Step 6:

[1534] The server performs the procedure to provide indoor Femto to requesting users to support continued communications. The input is the desired request and address information, and the output is a shipping instruction. Specifically, the server works in conjunction with the logistics system to send a shipping instruction for the indoor Femto.

[1535] Step 7:

[1536] The server identifies base stations within the predicted disaster area and procures the necessary equipment in advance. The input includes base station information and a list of required equipment, and the output includes instructions for procuring the equipment. The server then sends the order to the supply chain system.

[1537] Step 8:

[1538] The server sends disaster alert notifications to autonomous vehicles based on typhoon path prediction data and suggests safe evacuation routes. The input includes path information and evacuation routes, and the output includes evacuation instructions to be displayed on the autonomous vehicle's display. Specifically, the server uses a generative AI model to calculate appropriate evacuation routes and generates notifications using prompt text.

[1539] 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.

[1540] This invention combines a system that notifies users in advance of disasters based on typhoon path forecast data, publishes predicted disaster areas on a website, and provides support for maintaining communications, with an emotion engine that recognizes the user's emotions.The invention also prepares base station maintenance measures in advance, enables rapid recovery in the event of damage, and responds appropriately according to the user's emotional state.

[1541] System configuration

[1542] This system consists of the following main components:

[1543] server

[1544] User device (smartphone, PC, etc.)

[1545] Home page

[1546] Indoor Femto

[1547] Base Station and Maintenance Equipment

[1548] Emotion Engine

[1549] Program processing

[1550] Acquisition and analysis of typhoon path forecast data

[1551] The server periodically obtains typhoon path prediction data generated by weather forecasting systems and AI via API, updating the latest forecast data every 24 hours, for example.

[1552] The server analyzes the acquired typhoon path prediction data, including the typhoon's path, speed, scale, and latitude and longitude of the areas it will affect. Once this analysis is complete, it identifies areas where disasters are predicted to occur.

[1553] The server compares users' location information with predicted disaster areas and creates a list of users who are likely to be affected.

[1554] Emotion recognition by emotion engine

[1555] The device periodically captures the user's facial expressions and voice using sensors such as a camera and microphone, and sends the data to a server.

[1556] The server analyzes the received sensor data using an emotion engine to identify the user's emotional state (e.g., stress level or anxiety).

[1557] User notification

[1558] The server generates a warning notification message to be sent to each user based on the affected user list.

[1559] The server customizes the content of the alert notification depending on the user's emotional state as analyzed by the emotion engine, for example adding more specific safety advice if high stress levels are detected.

[1560] The server uses an email sending API or an SMS sending API to send the generated warning notification message to the affected user.

[1561] The device will display received emails and SMS as pop-up notifications to alert the user.

[1562] Posted on the homepage

[1563] The server uses a map drawing library to map the geographical information of disaster-prone areas, and this mapped information is posted on the website in real time.

[1564] By accessing the website, users can check the predicted disaster areas for themselves and their surrounding areas, allowing them to take safety measures in advance.

[1565] Support for continued communication

[1566] The server will then process the provision of indoor Femto to users who request it to support continued communications. When a user requests it, the server will ship the indoor Femto based on the user's address information.

[1567] Users receive an indoor Femto and install it in their homes to ensure stable communications even in the event of a disaster. Specifically, they follow the instructions to set it up and connect their device to the Femto.

[1568] base station maintenance

[1569] The server identifies base stations within the predicted disaster area and procures the necessary equipment in advance.

[1570] The server generates a list of required equipment for each base station and sends the orders to the supply chain system.

[1571] The user (maintenance worker) deploys the necessary equipment to the site before a disaster occurs and performs maintenance work promptly after the disaster occurs.

[1572] Specific examples

[1573] For example, if the AI ​​predicts that a typhoon will approach the Tokyo area 48 hours in advance, the server will analyze the information and send a warning notice to all users living in the Tokyo area.

[1574] If the emotion engine detects that a particular user is showing high stress levels, the server will send more detailed advice to that user, such as providing specific evacuation locations. It also maps areas that overlap with predicted disaster areas and posts the information on the website in real time.

[1575] If a user requests an indoor Femto, the server will receive the request and ship the indoor Femto to the user's address. Once the user receives the Femto, they can install it and continue communicating securely.

[1576] In addition, the server will procure the necessary equipment for base stations in the Tokyo area in advance, supporting early recovery after a disaster occurs.

[1577] The processing flow will be explained below.

[1578] Acquisition and analysis of typhoon path forecast data

[1579] Step 1:

[1580] The server sends an HTTP request to the specified API endpoint every 24 hours to obtain the latest typhoon track forecast data, which is received in JSON format.

[1581] Step 2:

[1582] The server parses the received JSON data and extracts information about the typhoon's path, speed, size, and latitude and longitude of the area it will affect.

[1583] Step 3:

[1584] The server uses the extracted information to identify areas where disasters are predicted to occur and stores the information in a database.

[1585] Emotion recognition by emotion engine

[1586] Step 1:

[1587] The device periodically captures the user's facial expressions and voice using sensors such as a camera and microphone, and sends the data to a server.

[1588] Step 2:

[1589] The server analyzes the received sensor data using an emotion engine to identify the user's emotional state (e.g., stress level or anxiety).

[1590] Step 3:

[1591] The server stores the identified emotional states in a database.

[1592] User notification

[1593] Step 1:

[1594] The server uses the latitude and longitude information of the disaster predicted area to compare with the user location information in the database, thereby generating a list of affected users.

[1595] Step 2:

[1596] The server generates a warning notification message to be sent to each user based on the affected user list. The message includes typhoon information and safety advice.

[1597] Step 3:

[1598] The server customizes the content of the alert notification depending on the user's emotional state as analyzed by the emotion engine, for example adding specific safety advice if high stress levels are detected.

[1599] Step 4:

[1600] The server uses an email sending API or an SMS sending API to send the generated warning notification message to the affected user.

[1601] Step 5:

[1602] The device will display received emails and SMS as pop-up notifications to alert the user.

[1603] Posted on the homepage

[1604] Step 1:

[1605] The server passes the geographical information of the disaster-prone area to a map drawing library (e.g., Leaflet.js) and maps it on a map.

[1606] Step 2:

[1607] The server uploads the mapped information using the homepage update API and reflects it on the homepage in real time.

[1608] Step 3:

[1609] The user accesses the homepage from a browser and checks information about areas where disasters are predicted to occur.

[1610] Support for continued communication

[1611] Step 1:

[1612] The user contacts the server to request the provision of a means for continuing communication (indoor Femto).

[1613] Step 2:

[1614] The server checks the list of interested users and begins the shipping process for the indoor Femto based on the user's address information.

[1615] Step 3:

[1616] The server sends shipping instructions to the shipping management system and ships the indoor Femto to the relevant user.

[1617] Step 4:

[1618] Once the indoor Femto arrives, users can install it according to the manual to ensure stable communication at home.

[1619] base station maintenance

[1620] Step 1:

[1621] The server identifies base stations within the disaster-prone area in a database.

[1622] Step 2:

[1623] The server generates a list of equipment required for each base station and places orders using the supply chain system API.

[1624] Step 3:

[1625] The server arranges for the procured equipment to be delivered to the designated base station.

[1626] Step 4:

[1627] The user (maintenance worker) uses the equipment procured in advance to carry out maintenance work (inspection, reinforcement, etc.) on the base station before a disaster occurs.

[1628] Step 5:

[1629] After a disaster occurs, the user (maintenance worker) promptly goes to the site and uses the equipment to quickly restore the base station.

[1630] Example 2

[1631] 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."

[1632] Conventional typhoon path prediction systems predict the path of a typhoon and issue warnings to users, but they are unable to address the emotional state of users or the maintenance of communication infrastructure. Providing appropriate countermeasures is particularly important when users are experiencing high levels of stress or anxiety. It is also important to ensure the continuity of communications during disasters and to quickly maintain base stations. Therefore, it is desirable to provide a notification system that can respond to disasters from multiple angles and takes into account the emotional state of users.

[1633] 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.

[1634] In this invention, the server includes means for acquiring typhoon path forecast data, means for analyzing the acquired typhoon path forecast data to identify a disaster-predicted area, means for generating a list of affected users by comparing user location information with the disaster-predicted area, means for collecting and analyzing emotional data of affected users, means for customizing and sending alert notification messages based on the emotion analysis results, means for sending alert notifications based on the generated list of affected users, means for mapping information about the disaster-predicted area on a map and posting it on a website, means for providing means for continuing communications to users who request it, and means for identifying base stations within the disaster-predicted area and procuring the necessary equipment. This makes it possible to provide alert notifications customized in consideration of the emotional state of users, thereby enabling continued communications and rapid base station maintenance in the event of a disaster.

[1635] "Typhoon path forecast data" is information about a typhoon's path, speed, scale, and area of ​​impact, generated by weather forecasting systems and artificial intelligence.

[1636] "Disaster-predicted areas" refer to geographical locations that are highly likely to be affected by disasters, as analyzed based on typhoon path prediction data.

[1637] "User location information" refers to the user's current location or specified address information.

[1638] The "list of affected users" is a list of users who are likely to be affected by a disaster, generated by comparing the predicted disaster area with the location information of the users.

[1639] "Emotional data" is data captured from a user's facial expressions, voice, etc., and used to analyze the user's emotional state.

[1640] "Emotion analysis results" are the results of analyzing the user's emotional state (stress level, anxiety, etc.) based on emotion data.

[1641] A "warning notification message" is a notification sent to users in an area where a disaster is predicted to occur, and includes specific evacuation actions and countermeasures.

[1642] "Mapping" refers to drawing geographical information of areas where disasters are predicted to occur on a map.

[1643] "Means for continuing communication" refers to equipment and methods for ensuring communication stability during disasters, such as indoor Femto.

[1644] A "base station" is a relay device in a communication network, and is a facility for communicating with mobile terminals.

[1645] "Necessary supplies" refers to the equipment, parts, materials, etc. required to maintain or restore the functions of base stations in the event of a disaster.

[1646] This invention combines a system that notifies users in advance of disasters based on typhoon path forecast data, publishes predicted disaster areas on a website, and provides support for maintaining communications, with an emotion engine that recognizes the user's emotions. Furthermore, it can prepare base station maintenance measures in advance, enable rapid recovery in the event of damage, and respond appropriately according to the user's emotional state.

[1647] The system is configured as follows: The main components include a server, user terminals (smartphones, PCs, etc.), a homepage, indoor Femto, base stations and maintenance equipment, and an emotion engine.

[1648] Acquisition and analysis of typhoon path forecast data

[1649] The server periodically obtains typhoon path prediction data generated by weather forecasting systems and artificial intelligence via API. For example, it calls "Weather API XYZ" every 24 hours and stores the data. The server then analyzes the data using "Data Analysis Library ABC" to identify the typhoon's path, speed, scale, and affected areas (latitude, longitude, etc.). Based on the analysis results, it identifies areas where disasters are predicted to occur and compares them with users' location information to create a list of users who are likely to be affected. As a specific example, if a typhoon is predicted to approach the Tokyo area, users who reside in Tokyo will be listed.

[1650] Emotion recognition by emotion engine

[1651] The device periodically captures the user's facial expressions and voice using sensors such as a camera and microphone, encrypts the data, and sends it to a server. The server then uses the "Emotion Analysis Engine XYZ" to analyze the received sensor data and identify the user's emotional state (such as stress level or anxiety). This process allows the user's emotional state to be understood.

[1652] User notification

[1653] The server generates a warning notification message based on the list of affected users. It uses the "Message Generation Library ABC" to create a notification message that includes details about the typhoon and recommended actions. It also customizes the content of the warning notification based on the analysis results of the emotion engine. For example, for users with high stress levels, it could include specific evacuation locations and countermeasures. The server uses an email sending API or SMS sending API to send the generated warning notification message to affected users. The device displays the received email or SMS as a pop-up notification to alert the user.

[1654] Posted on the homepage

[1655] The server maps the geographical information of disaster-prone areas using the "Map Drawing Library GeoLib XYZ." This mapped information is posted on the website in real time. By accessing the website, users can check the disaster-prone areas and take safety measures in advance.

[1656] Support for continued communication

[1657] When the server receives a request for communication continuity support from a user, it ships an indoor Femto based on the user's address information. Specifically, it generates a shipping instruction and connects it to the logistics system. The user receives the indoor Femto and installs it in their home, ensuring stable communication even in the event of a disaster. The installation procedure is carried out according to the enclosed manual.

[1658] base station maintenance

[1659] The server identifies base stations within areas where disasters are predicted to occur and procures the necessary equipment in advance. It uses a geographic information system to list the applicable base stations, generates an equipment list for each base station, and sends orders to the supply chain system. The user (maintenance worker) deploys the necessary equipment on-site before a disaster occurs, and then quickly performs maintenance work on the base stations after the disaster occurs.

[1660] Examples of concrete examples and prompts

[1661] For example, if the AI ​​predicts that a typhoon will approach the Tokyo area 48 hours in advance, the server will analyze the information and send a warning to users living in the Tokyo area. If the emotion engine detects that a particular user is showing high stress levels, the server will send more detailed advice to that user, such as providing specific evacuation locations. The server will also map areas predicted to be affected by disasters and post them on the website in real time.

[1662] Example prompt: "A typhoon is approaching the Tokyo area. Generate an appropriate warning notification message based on the disaster forecast and the user's emotional state."

[1663] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1664] Step 1: Obtaining typhoon track forecast data

[1665] The server periodically obtains the latest typhoon path forecast data generated by weather forecasting systems and artificial intelligence via API. The input is typhoon path forecast data obtained from "Weather API XYZ," and the output is raw data stored in a database on the server. Specifically, the server schedules an API call every 24 hours, receives the response data in JSON format, and stores it in the database.

[1666] Step 2: Analysis of typhoon track forecast data

[1667] The server analyzes the acquired typhoon path prediction data and identifies the typhoon's path, speed, scale, and the latitude and longitude of the area it will affect. The input is the raw data acquired earlier, and the output is the analyzed typhoon information (path, speed, scale, latitude and longitude). Specifically, it uses the "Data Analysis Library ABC" to analyze and extract various typhoon data and convert it into an easy-to-understand format.

[1668] Step 3: Identifying areas where disasters are likely to occur

[1669] The server identifies areas where disasters are predicted to occur based on the analysis results. The input is the analyzed typhoon information, and the output is geographic information on the areas where disasters are predicted to occur. Specifically, the affected area is mapped using a geographic information system (GIS) and the data is saved.

[1670] Step 4: List affected users

[1671] The server compares the predicted disaster area with user location information and generates a list of users who are likely to be affected. The input is a database of user location information and predicted disaster area information, and the output is a list of affected users. Specifically, it runs an SQL query based on the location information to extract and list the relevant users.

[1672] Step 5: Capturing and Sending Sensor Data

[1673] The device periodically captures the user's facial expressions and voice using sensors such as a camera and microphone, and sends the data to a server. The input is the facial expression and voice data captured by the device, and the output is the emotion data sent to the server. Specifically, the data is collected every hour using a facial recognition API and a voice analysis API, encrypted, and sent to the server.

[1674] Step 6: Sentiment Analysis

[1675] The server analyzes the received sensor data using the "Emotion Analysis Engine XYZ" to identify the user's emotional state. The input is sensor data, and the output is the result of identifying the emotional state. Specifically, it uses algorithms that analyze facial muscle movements and tone of voice to identify emotional states such as stress levels and anxiety.

[1676] Step 7: Generate a warning notification message

[1677] The server generates a warning notification message based on the affected user list. The input is the affected user list and disaster predicted area information, and the output is a warning notification message. Furthermore, the notification content is customized according to the results of sentiment analysis. Specifically, the "Message Generation Library ABC" is used to create a notification message that includes details of the typhoon and evacuation instructions.

[1678] Step 8: Sending alert notifications

[1679] The server then uses an email or SMS API to send the generated alert notification message to affected users. The input is the alert notification message, and the output is the sent notification. Specifically, the API is called and a message is sent to each user's contact information.

[1680] Step 9: Post disaster information on your website

[1681] The server maps the geographic information of disaster-predicted areas using the "Map Drawing Library GeoLib XYZ" and posts it on the website in real time. The input is the geographic information of disaster-predicted areas, and the output is the updated content of the website. Specifically, the map information is updated regularly and reflected on the website in real time using an API.

[1682] Step 10: Providing communication continuity support

[1683] The server receives a request for communication continuity support from the user and ships the indoor Femto based on the user's address information. The input is the request information and the user's address information, and the output is a shipping instruction. Specifically, it works in conjunction with the logistics system to carry out the procedures for shipping the necessary equipment.

[1684] Step 11: Prepare for base station maintenance work

[1685] The server identifies base stations within disaster-predicted areas and procures the necessary equipment in advance. The input is base station data and disaster-predicted area information, and the output is an equipment list and ordering information. Specifically, it uses GIS to list the applicable base stations, and creates and orders a list of the necessary equipment.

[1686] Step 12: Carry out base station maintenance work

[1687] The user (maintenance worker) deploys the necessary equipment fo...

Claims

1. A means for acquiring typhoon path forecast data; A means for analyzing the acquired typhoon path prediction data to identify areas where disasters are predicted to occur; A means for generating a list of affected users by comparing user location information with a disaster predicted area; means for sending a warning notice based on the generated list of affected users; A method for mapping information on disaster-prone areas and posting it on a website, A means for providing a means for continuing communication to users who wish to do so; A means of identifying base stations within the disaster-prone area and procuring necessary equipment; A system including:

2. A means for periodically obtaining typhoon path forecast data; A means of analyzing the acquired forecast data to extract the typhoon's course, speed, and latitude and longitude of the affected area; a means for generating a list of affected users using location information of users stored in a database; A means of sending notifications via email and SMS based on the generated list of affected users; A means to visualize information on disaster-prone areas using a map drawing library, and A means to upload map data using the homepage update API, The system of claim 1 , comprising:

3. A means of checking the list of users who have requested it and providing the relevant users with a means to continue communication; A means of procuring and shipping the necessary equipment in conjunction with the address information of the applicable user; A means for identifying a base station within a disaster predicted area using base station information; a means for ordering necessary equipment for each identified base station and for a maintenance worker to carry out maintenance work; The system of claim 1 , comprising:

Images