System

Abstract

A system is provided.SOLUTION: A system comprising: means for reporting disaster information using a web application; means for transmitting the reported information to a server; means for analyzing the information received at the server using generative artificial intelligence and natural language processing to determine authenticity; and means for notifying a rescue organization based on the determined information.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] Current disaster notification systems that use telephone lines have the problem that it is difficult to increase the number of lines and operators during disasters when the number of callers increases explosively, making it difficult to process calls smoothly. Furthermore, duplicate and false reports further confuse the process, potentially delaying rescue efforts and resulting in the loss of many lives. The goal of this project is to solve this problem and quickly obtain accurate information during disasters, enabling efficient rescue efforts. [Means for solving the problem]

[0005] The present invention provides a disaster notification system that includes a means for reporting disaster information using a web application, a means for transmitting the reported information to a server, a means for analyzing the information received by the server using generative artificial intelligence and natural language processing to determine whether it is true or false, and a means for notifying rescue organizations based on the determined information. Furthermore, by including a means for checking for duplication and filtering of the received information and a means for transmitting the generated notification message to multiple related rescue organizations, the system can achieve fast and accurate notification processing and improve the efficiency of rescue operations.

[0006] A "web application" is software that runs on a browser connected to the Internet and is programmed to provide specific functions.

[0007] "Disaster information" refers to information related to natural disasters, accidents, etc., and is data provided by reporters through the reporting system.

[0008] The "means for reporting" is a set of functions including a user interface and its operations that allow users to enter disaster information and send it to the system.

[0009] A "server" is a computer system that processes data received from web applications over a network and performs analysis using generative artificial intelligence and natural language processing.

[0010] "Generative artificial intelligence" is a type of artificial intelligence that generates and analyzes new information based on large amounts of data.

[0011] "Natural language processing" is a technology that understands and processes human language on a computer, enabling the analysis of text data and understanding of intent.

[0012] "Means for determining authenticity" refers to programs and algorithms for determining whether received disaster information is accurate and reliable.

[0013] The "means of notification" refers to a set of functions including a communication function and its operation for transmitting the contents of the notification to the relevant organizations based on the analyzed information.

[0014] "Duplicate check" is the process of checking whether the same report has been made multiple times.

[0015] "Filtering" is the process of removing unnecessary or false information from received report data. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0024] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0037] Overall overview

[0038] This invention is a system that realizes fast and accurate reporting during disasters by migrating the reporting system from telephone lines to a web system and utilizing generative artificial intelligence (AI) and natural language processing (NLP) technology. This is expected to result in efficient reporting during disasters, accelerating rescue operations and improving the effectiveness of lifesaving.

[0039] System Configuration

[0040] This system consists of the following main elements:

[0041] 1. User Device

[0042] 2. Web Server

[0043] 3. Generative AI and Natural Language Processing Server

[0044] 4. Notification system for rescue agencies

[0045] DETAILED DESCRIPTION OF THE EMBODIMENTS

[0046] 1. Reporting via user terminal

[0047] A user accesses a web application and logs in by entering their authentication information.

[0048] After logging in, the user fills in the necessary information in the form to make a report.

[0049] Type of disaster (e.g. earthquake, fire)

[0050] Current location (auto-detect or manual input)

[0051] Details of the situation (free description)

[0052] Images and videos (optional)

[0053] When the user enters the report content and clicks the "Send" button, the data is serialized and sent to the web server.

[0054] 2. Data reception by the web server

[0055] The web server receives the data as an HTTP POST request and passes it to a generative artificial intelligence and natural language processing server for analysis.

[0056] The server has mechanisms for securely receiving and storing data.

[0057] 3. Data analysis using generative artificial intelligence and natural language processing

[0058] The received data is analyzed using generative artificial intelligence and natural language processing technology to determine its authenticity.

[0059] The report content is analyzed in detail using natural language processing, and the reliability of the content is evaluated.

[0060] The data whose authenticity has been determined is stored in a database.

[0061] Duplicate checking and filtering of data also occurs at this stage.

[0062] 4. Notifying rescue agencies

[0063] Once the authenticity has been determined, the data is automatically communicated to the relevant rescue agencies.

[0064] Notifications are generated using messages based on the parsed data.

[0065] Example: "Emergency call: Earthquake occurred at point A. Situation: Building collapsed, injured."

[0066] Notifications are sent simultaneously to multiple rescue agencies, allowing for a rapid response.

[0067] Specific examples

[0068] As a concrete example, consider the occurrence of an earthquake.

[0069] When a user confirms that an earthquake has occurred, they open the web application and log in.

[0070] The user inputs "earthquake," "current location (automatically detected)," and "details of the situation (buildings have collapsed and many injured)," and presses the send button.

[0071] The user terminal transmits this data to the web server.

[0072] The server receives the data and uses generative artificial intelligence and natural language processing technology to analyze it, determine its authenticity, and perform duplicate checking and filtering.

[0073] The server sends notifications to relevant rescue agencies based on the analysis results.

[0074] Rescue agencies are notified and rush to the scene.

[0075] In this way, the system will streamline reporting during disasters and enable rapid rescue operations.

[0076] The processing flow will be explained below.

[0077] Step 1:

[0078] A user accesses the web application. The user opens a browser and logs in to the disaster notification system website. The user enters their authentication information (username and password) and presses the login button.

[0079] Step 2:

[0080] The user opens the report form. After logging in, the user clicks the "Report" button to open a form for entering disaster information. The user enters the following items:

[0081] Type of disaster (e.g. earthquake, fire)

[0082] Current location (auto-detect or manual input)

[0083] Details of the situation (free description)

[0084] Images and videos (optional)

[0085] Step 3:

[0086] The user submits the input data. The user enters the necessary information into the report form and clicks the "Submit" button. This causes the device to serialize the input data and send it to the server.

[0087] Step 4:

[0088] The device sends the serialized data to the web server as an HTTP POST request. The data includes the type of disaster, current location, details of the situation, and images and videos.

[0089] Step 5:

[0090] The server receives the data. The server parses the received HTTP POST request and extracts the data. The server prepares the received data to be passed to the generative artificial intelligence and natural language processing server.

[0091] Step 6:

[0092] The server analyzes the data. The received data is then analyzed using generative artificial intelligence and natural language processing technology. Natural language processing analyzes the report in detail and evaluates its reliability. The generative artificial intelligence determines whether the data is true or false, and the results are stored in a database.

[0093] Step 7:

[0094] The server checks for duplicate reports and filters them. The server checks against existing data in the database to ensure there are no duplicate reports with the same content. It also filters out false or unnecessary information.

[0095] Step 8:

[0096] The server sends a notification to the rescue organization. Based on the truth-checked and filtered data, the server generates a notification message to the relevant rescue organization. The notification message contains the parsed data.

[0097] Step 9:

[0098] The server sends a message to the rescue organization. The server then sends the generated notification message to multiple related rescue organizations, enabling a rapid response. The notification message includes the type of disaster, location, and details of the situation.

[0099] Step 10:

[0100] The user can later access the web application and view the history of the notifications they have sent, including the notification date, type of disaster, and details of the situation.

[0101] Example 1

[0102] 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."

[0103] Conventional disaster notification systems transmit information over telephone lines, making it difficult to transmit information quickly when communication lines are congested or multiple reports are made simultaneously, making them unsuitable for disasters that require immediate response. They are also prone to human error and delays in information transmission. Furthermore, they lack a mechanism for determining the authenticity of reports, which can sometimes prevent rescue agencies from responding appropriately. This can result in delays and reduced efficiency in rescue operations, hindering the ability to save lives. To address these issues, it is necessary to provide a system that can transmit disaster notifications more efficiently and quickly, and that can properly determine information and check for duplication.

[0104] 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.

[0105] In this invention, the server includes means for reporting disaster information using a user terminal, means for transmitting the reported information to the server via the Internet, means for analyzing the information received by the server in detail using generative artificial intelligence and natural language processing to determine the authenticity of the information, means for checking for duplication and filtering the determined information and storing highly reliable information in a database, and means for notifying rescue organizations of a notification message generated based on the determined information. This enables quick and accurate information transmission and analysis in the event of a disaster, thereby realizing efficient and rapid rescue operations.

[0106] A "user terminal" is an electronic device used by a user to report disaster information.

[0107] A "web application" is software that users access via the Internet to input and send disaster information.

[0108] The "server" is a central processing unit that analyzes received disaster information and notifies rescue organizations.

[0109] "Generative AI" is a type of AI technology used to analyze received information and determine its authenticity.

[0110] "Natural language processing" is a technology for analyzing text data and understanding its meaning and intent.

[0111] The "Internet" is a global network for communicating data between user terminals and servers.

[0112] "Duplicate check" is a process for detecting duplication when the same or similar information is reported multiple times.

[0113] "Filtering" is a process for removing unnecessary or inaccurate information and extracting reliable information.

[0114] A "database" is a data management system that stores analyzed information for later reference.

[0115] A "notification message" is a message that is generated based on the determined disaster information and sent to rescue organizations.

[0116] "Rescue organization" means an organization or agency that carries out rescue operations in the event of a disaster.

[0117] The present invention provides a notification system for use in disaster situations, which utilizes the Internet and the latest artificial intelligence technology to enable rapid and accurate information transmission. How this system is implemented will be explained below.

[0118] Reporting via user terminal

[0119] Users use a user device such as a smartphone, tablet, or PC to access the web application. After logging in by entering their authentication information, they can access a form for entering disaster information. The form includes fields for the type of disaster (e.g., earthquake, fire), current location (automatic detection or manual entry), details of the situation (free text), and the ability to upload images and videos. After the user enters the required information and clicks the "Submit" button, the data is serialized and sent to the web server.

[0120] Data reception by the web server

[0121] The server receives data sent from the user terminal as an HTTP POST request. The received data is then forwarded to the generative artificial intelligence and natural language processing server for analysis. The server is equipped with security functions to ensure the safety of the received data.

[0122] Data analysis using generative artificial intelligence and natural language processing

[0123] The server analyzes the received data using generative artificial intelligence (e.g., GPT-4) and natural language processing technology (e.g., SpaCy). Through this analysis, it evaluates the authenticity of disaster information and determines its reliability. It also checks for duplication and filters the data to remove duplicate or unreliable information. Through this process, highly reliable data is stored in the database.

[0124] Notifying rescue agencies

[0125] The server generates a notification message based on the determined truthfulness of the information. The generated notification message is then sent to the relevant rescue organizations. The notification is sent simultaneously to multiple rescue organizations via a messaging API (e.g., Twilio) to enable a rapid response. An example of a notification message is "Emergency call: Earthquake occurred at location A. Situation: Building collapsed, injured."

[0126] Specific examples

[0127] As a concrete example, consider the processing flow when an earthquake occurs. The user confirms the earthquake, accesses the web application, and logs in. Next, they enter "earthquake," "current location (automatically detected)," and "details of the situation (a building has collapsed and many injured people)" and press the send button. The user's device sends this data to the web server. The server receives the data and uses generative artificial intelligence and natural language processing technology to analyze it, determine its authenticity, and perform duplication checks and filtering. The server then sends a notification to the relevant rescue organizations based on the analysis results. The rescue organizations receive the notification and rush to the scene.

[0128] Prompt Sentence Examples

[0129] "An earthquake has occurred. Buildings have collapsed and many people are injured. Rescue is needed."

[0130] In this way, the present invention provides a system that makes reporting during disasters more efficient and supports rapid and accurate rescue operations.

[0131] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0132] Step 1:

[0133] A user accesses a web application and logs in by entering their credentials.

[0134] Specifically, a user opens a browser, enters a URL to access the login page of a web application, enters a username and password, and clicks the "Login" button.

[0135] Input details: Authentication information (user name, password)

[0136] Output: Authentication result, redirect to dashboard

[0137] Step 2:

[0138] After logging in, the user enters the necessary information into the report form.

[0139] Specifically, users access the form, select the type of disaster from a drop-down menu, press a button to automatically detect their "current location" or enter it manually, write details about the situation in the text box, and upload images and videos if necessary.

[0140] Input information: type of disaster, current location, details of the situation, images and videos

[0141] Output content: Input data confirmation screen

[0142] Step 3:

[0143] When the user clicks the "Submit" button, the input data is serialized and sent to the web server.

[0144] Specifically, when you click the "Submit" button, the form data is converted to JSON format and sent to the server as an HTTP POST request.

[0145] Input: Clicking the submit button, serialized data

[0146] Output: HTTP POST request to the server

[0147] Step 4:

[0148] The server receives the HTTP POST request sent from the user terminal, analyzes the received data, and forwards it to the generative artificial intelligence and natural language processing server.

[0149] Specifically, the server parses the JSON data in the request body and extracts the type of disaster, current location, details of the situation, and images and videos. This data is then transferred to the generative artificial intelligence and natural language processing server via a dedicated API.

[0150] Input: HTTP POST request, serialized data

[0151] Output contents: Analysis results, data transferred to generative artificial intelligence and natural language processing servers

[0152] Step 5:

[0153] Generative artificial intelligence and natural language processing servers analyze the received data and determine its authenticity.

[0154] Specifically, it uses generative artificial intelligence (e.g., GPT-4) and natural language processing (e.g., SpaCy) to analyze text content and evaluate the reliability and authenticity of information. It also checks for duplicates and filters out unreliable information.

[0155] Input information: type of disaster, current location, details of the situation, images and videos

[0156] Output contents: True / false judgment results, filtered data

[0157] Step 6:

[0158] The server stores reliable data based on the analysis results in a database.

[0159] Specifically, it uses a query to compare the data with existing records in the database, filters out duplicates, and then stores the newly parsed data in the database.

[0160] Input: Filtered data

[0161] Output contents: Results stored in the database

[0162] Step 7:

[0163] The server generates a notification message based on the information whose truth or falsity has been determined.

[0164] Specifically, the system inserts the analyzed data into an automatically generated message template, generating a message such as "Emergency call: Earthquake occurred at point A. Situation: Building collapsed, injured."

[0165] Input: Filtered data

[0166] Output content: Notification message

[0167] Step 8:

[0168] The server sends a notification message to the relevant rescue agency.

[0169] Specifically, notification messages are sent simultaneously to multiple rescue agency contacts via a message sending API (e.g., Twilio).

[0170] Input content: Notification message

[0171] Output content: Notification result to rescue agency

[0172] In this way, the system processes disaster reports quickly and accurately, and notifies relevant rescue organizations appropriately, enabling prompt rescue operations.

[0173] (Application example 1)

[0174] 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."

[0175] Conventional disaster response systems mainly rely on telephone lines for reporting, which often hinders the accuracy of reports and the speed of rescue operations. Specifically, it is difficult to properly convey detailed information about the situation when reporting, and auxiliary information such as location information and images and videos of the scene is often lacking. This makes it difficult for rescue agencies to respond quickly and appropriately, resulting in a decrease in the efficiency of lifesaving efforts.

[0176] 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.

[0177] In this invention, the server includes means for reporting disaster information using a web application, means for transmitting the reported information to the server, means for analyzing the information received by the server using generative artificial intelligence and natural language processing to determine its authenticity, means for automatically acquiring location information of the user device, means for attaching and transmitting images and videos related to the disaster situation, and means for notifying rescue organizations based on the determined information. This enables the transmission of detailed report content including location information and images / videos and the rapid determination of authenticity by generative AI, enabling rescue organizations to respond quickly and accurately.

[0178] A "web application" is software that can be used by users over the Internet.

[0179] "Means for reporting disaster information" refers to an interface that allows users to report the situation when a disaster occurs.

[0180] A "server" is a computer system that processes and stores data on a network.

[0181] "Generative artificial intelligence" refers to artificial intelligence technology that has the ability to generate new information based on input data.

[0182] "Natural language processing" is a technology that uses computers to understand, analyze, and generate human language.

[0183] "Means for determining authenticity" refers to the process of analyzing and evaluating whether the reported information is correct.

[0184] "User terminal" refers to any device used by a user, including smartphones and tablets.

[0185] "Means for automatically obtaining location information" refers to a function that automatically obtains the user's current location using technology such as GPS.

[0186] "Means for attaching and sending images and videos related to the disaster situation" refers to a function that allows users to attach images and videos they have taken to the report and send them.

[0187] "Means of notification" refers to the process of contacting rescue organizations based on the analyzed information.

[0188] System Program

[0189] The system of this invention begins with a user reporting disaster information using a web application and sending it to a server. The server then analyzes the reported information using generative artificial intelligence and natural language processing to determine its authenticity. Next, the user's device automatically acquires location information and sends it along with images and videos of the disaster situation. Finally, the server notifies rescue organizations based on the determined information.

[0190] Hardware and software used

[0191] Hardware: smartphones, tablets, servers

[0192] Software: GPS module, Python, Geopy library, Requests library, generative AI model, natural language processing technology (NLP)

[0193] Natural language processing explanation

[0194] 1. Data transmission by user terminal

[0195] Users use their smartphones or tablets to report disaster information through a web application. At this time, they input the necessary information, such as the type of disaster, detailed situation, and current location. Location information is automatically obtained using a GPS module. Users can also attach images and videos showing the current state of the disaster within the app. This information is serialized and sent to the server via a secure communication channel.

[0196] 2. Data analysis by the server

[0197] The server analyzes the received information using generative artificial intelligence and natural language processing technology. Natural language processing understands the text entered by the user, and generative AI evaluates the veracity of the content. For example, if a report is made that "a building has collapsed and many people are injured," the AI ​​analyzes the context and evaluates its reliability.

[0198] 3. Notifying rescue agencies

[0199] Once the information has been determined to be true or false, it is automatically sent to rescue agencies by the server. This notification includes a specific message generated by the generative AI. For example, it could read, "Emergency call: An earthquake has occurred at the specified location. Situation: A building has collapsed and many people are injured. Please respond quickly."

[0200] Specific examples

[0201] As a concrete example, consider the occurrence of an earthquake. A user opens a web application on their smartphone, selects "earthquake," and enters "buildings have collapsed and many injured." Location information is automatically acquired via GPS, and images and videos are attached. This information is sent to a server, where it is analyzed and evaluated using generative AI and natural language processing technology. As a result, a notification is sent to rescue agencies stating, "Emergency call: An earthquake has occurred at the specified location. Situation: buildings have collapsed and many injured. Please respond quickly."

[0202] Prompt Sentence Examples

[0203] input

[0204] Disaster type: Earthquake

[0205] Details: Buildings collapsed, many injured

[0206] Location information: Automatically acquired (latitude and longitude)

[0207] Attachment: Images and videos of the disaster site

[0208] output

[0209] "Emergency message: Earthquake occurred at specified location. Situation: Building collapsed, many injured. Please respond quickly."

[0210] This allows for accurate and prompt reporting and response.

[0211] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0212] Step 1:

[0213] Users access the web application using a smartphone or tablet, access the disaster information reporting form, and enter the necessary information, such as the type of disaster, current location (automatically obtained), details of the situation, and images and videos.

[0214] input:

[0215] Types of disasters

[0216] Current location (automatically obtained by GPS)

[0217] Details of the situation

[0218] Images and videos

[0219] output:

[0220] Serialized report data

[0221] Specific behavior:

[0222] Converts information entered into a web form into a serialized format such as JSON and prepares it for transmission to the server.

[0223] Step 2:

[0224] The user device sends the processed disaster information to the server, where the data is sent using a secure communication protocol (such as HTTPS).

[0225] input:

[0226] Serialized report data

[0227] output:

[0228] Report data received by the server

[0229] Specific behavior:

[0230] The serialized data is sent to the server as an HTTPS request.

[0231] Step 3:

[0232] The server analyzes the received report data using generative artificial intelligence and natural language processing technology to determine its authenticity.

[0233] input:

[0234] Report data received by the server

[0235] output:

[0236] Data that has been judged to be true or false

[0237] Specific behavior:

[0238] It uses a natural language processing engine to analyze text data and uses generative AI to evaluate the reliability of the information.

[0239] Step 4:

[0240] The server performs duplication checks and filtering on the parsed data, eliminating redundant and meaningless information.

[0241] input:

[0242] Data that has been judged to be true or false

[0243] output:

[0244] Duplicate checked and filtered data

[0245] Specific behavior:

[0246] Matching data with existing data in the database to remove duplicate information and filtering out incomplete or unnecessary data.

[0247] Step 5:

[0248] The server then notifies rescue agencies based on the filtered data, with the notification being an emergency message generated by generative AI.

[0249] input:

[0250] Duplicate checked and filtered data

[0251] output:

[0252] Emergency message sent to rescue agencies

[0253] Specific behavior:

[0254] Generative AI models are used to generate appropriate emergency messages based on the content of the call and send them to relevant rescue agencies.

[0255] Step 6:

[0256] Rescue agencies will receive notifications and respond quickly, specifically by dispatching the necessary rescue teams and resources to the scene based on the notification message.

[0257] input:

[0258] Emergency message sent to rescue agencies

[0259] output:

[0260] Rapid response from rescue agencies

[0261] Specific behavior:

[0262] Rescue agencies analyze the messages they receive, determine the appropriate response, and quickly begin action.

[0263] This overall system processing flow enables faster reporting and more accurate information transmission in the event of a disaster, improving the efficiency of rescue operations.

[0264] 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.

[0265] Overall overview

[0266] This invention is a system that recognizes user emotions and evaluates the importance and prioritization of report data by combining an emotion engine with a disaster reporting system, thereby enabling high-urgency reports to be processed quickly and enabling effective rescue operations.

[0267] System Configuration

[0268] This system consists of the following main elements:

[0269] 1. User Device

[0270] 2. Web Server

[0271] 3. Generative AI and Natural Language Processing Server

[0272] 4. Emotion Engine

[0273] 5. Notification system for rescue agencies

[0274] DETAILED DESCRIPTION OF THE EMBODIMENTS

[0275] 1. Reporting via user terminal

[0276] A user accesses a web application and logs in by entering their authentication information.

[0277] After logging in, the user fills in the necessary information in the form to make a report.

[0278] Type of disaster (e.g. earthquake, fire)

[0279] Current location (auto-detect or manual input)

[0280] Details of the situation (free description)

[0281] Images and videos (optional)

[0282] When the user enters the report content and clicks the "Send" button, the data is serialized and sent to the web server.

[0283] 2. Data reception by the web server

[0284] The web server receives the data as an HTTP POST request and passes it to a generative artificial intelligence and natural language processing server for analysis.

[0285] The server prepares to pass the received data to the emotion engine.

[0286] 3. Data analysis using generative artificial intelligence and natural language processing

[0287] The received data is analyzed using generative artificial intelligence and natural language processing techniques.

[0288] The report content is analyzed in detail using natural language processing, and the reliability of the content is evaluated.

[0289] Generative artificial intelligence determines the truth or falsity of the data and stores the results in a database.

[0290] Duplicate checking and filtering of data also occurs at this stage.

[0291] 4. Emotion Recognition by Emotion Engine

[0292] The emotion engine analyzes the text and voice data sent by the user and recognizes the user's emotions.

[0293] The recognized emotion information is added to the message data and used to evaluate the importance of the message data.

[0294] 5. Notifying rescue agencies

[0295] Data that is rated as highly important by the emotion engine is processed with priority.

[0296] When a notification is sent to rescue agencies, the emotion information is included along with the analyzed data.

[0297] Specifically, the following notification message is generated:

[0298] Example: "Emergency call: Earthquake occurred at location A. Situation: Building collapsed, people injured. User stress level: High."

[0299] Notifications are sent simultaneously to multiple rescue agencies, allowing for a rapid response.

[0300] Specific examples

[0301] As a concrete example, consider the occurrence of an earthquake.

[0302] When a user confirms that an earthquake has occurred, they open the web application and log in.

[0303] The user inputs "earthquake," "current location (automatically detected)," and "details of the situation (buildings have collapsed and many injured)," and presses the send button.

[0304] The user terminal transmits this data to the web server.

[0305] The server receives the data and analyzes it using generative artificial intelligence and natural language processing techniques.

[0306] The emotion engine analyzes user input and voice data to recognize the user's stress level and emotions.

[0307] The server sends a notification to the relevant rescue organization based on the analysis results and the emotion information. The notification message includes the type of disaster, location, details of the situation, and the user's emotion information.

[0308] Rescue agencies are notified and rush to the scene.

[0309] In this way, this system improves the efficiency of reporting during disasters and enables rapid rescue operations by utilizing users' emotional information.

[0310] The processing flow will be explained below.

[0311] Step 1:

[0312] A user accesses a web application.

[0313] The user opens a browser on their personal computer or smartphone, accesses the disaster notification system website, and logs in. The user enters their authentication information (username and password) and presses the login button.

[0314] Step 2:

[0315] The user opens the report form.

[0316] After logging in, users click the "Report" button from the main menu to open a form for reporting disaster information. Users must enter the following information:

[0317] Type of disaster (e.g. earthquake, fire)

[0318] Current location (auto-detect or manual input)

[0319] Details of the situation (free description)

[0320] Images and videos (optional)

[0321] Step 3:

[0322] The user sends the notification data.

[0323] The user enters disaster information and clicks the "Send" button, which causes the device to serialize all the entered data and prepare it to be sent to the web server.

[0324] Step 4:

[0325] The device sends the data to the server.

[0326] The device sends the serialized data to the web server as an HTTP POST request, which includes the type of disaster, current location, details of the situation, and images and videos.

[0327] Step 5:

[0328] The server receives the data.

[0329] The server analyzes the received HTTP POST request and extracts data from each field. The analyzed data is then passed to the generative artificial intelligence and natural language processing server.

[0330] Step 6:

[0331] The server analyzes the data.

[0332] The received data is analyzed using generative artificial intelligence and natural language processing technology. Natural language processing analyzes the contents of the report in detail and evaluates its reliability. The generative artificial intelligence determines whether the data is true or false, and the results are stored in a database.

[0333] Step 7:

[0334] The server performs duplicate checking and filtering.

[0335] The server checks existing data in the database to ensure there are no duplicate reports with the same content, and also filters out false or unnecessary information.

[0336] Step 8:

[0337] The server passes the data to the emotion engine.

[0338] The server passes the received text and voice data to the emotion engine for analysis, which analyzes the user's emotions.

[0339] Step 9:

[0340] The emotion engine recognizes the user's emotions.

[0341] The emotion engine analyzes the data sent by the user and evaluates the user's emotions, especially their stress level. The recognized emotion information is added to the report data.

[0342] Step 10:

[0343] The server sends a notification to the rescue agency.

[0344] Data that is evaluated as having high importance by the emotion engine is processed with priority.The server generates notification messages to relevant rescue organizations based on the analyzed data and emotion information.

[0345] Step 11:

[0346] The server sends a message to a rescue agency.

[0347] The server then sends the generated notification message to multiple related rescue organizations. The notification message includes the type of disaster, location, details of the situation, and the user's emotional state, allowing rescue organizations to respond to the scene quickly.

[0348] Step 12:

[0349] The user checks the report history.

[0350] Users can later revisit the web application and view the history of their submitted alerts, including the alert date, type of incident, situation details, and any attached emotional information.

[0351] Example 2

[0352] 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."

[0353] Conventional disaster reporting systems have difficulty in quickly determining the urgency of reports, and when many reports are received at the same time, important reports are buried. In addition, because they do not take into account the emotional information of the caller, it is difficult to accurately grasp situations with a high level of urgency.

[0354] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for analyzing received information using generative artificial intelligence and natural language processing to determine whether the information is true or false, a means for evaluating the importance of the report data based on the determined information and the user's emotional information, and a means for notifying a rescue organization based on the evaluated information. This makes it possible to evaluate the urgency of the report content with high accuracy and quickly notify an appropriate rescue organization.

[0355] A "web application" is software that runs on a web browser and can be accessed by users via the Internet.

[0356] "Disaster information" refers to detailed information about disasters such as earthquakes, fires, and floods reported by users.

[0357] "Reporting" is the act of a user providing disaster information through a web application.

[0358] A "server" is a computer system that receives, processes, and stores data from user terminals over a network.

[0359] "Generative artificial intelligence" is a technology that uses algorithms based on machine learning and deep learning to generate and analyze new data and patterns.

[0360] "Natural language processing" is the technology that enables computers to understand, interpret, and generate human language.

[0361] "Authenticity assessment" is the process of determining the accuracy and reliability of the information provided.

[0362] "Evaluating the importance of report data" is a process of determining how urgent the information is based on the disaster information provided and the user's emotional information.

[0363] "Notification" is the act of transmitting emergency information to relevant rescue organizations based on the evaluated information.

[0364] "Rescue agencies" are public institutions such as fire departments, police, and ambulance teams that respond to disasters.

[0365] "Emotional information" is data that indicates the emotional state (e.g., stress level or tension) that a user exhibits when making a report.

[0366] "Data duplication check" is a process to prevent multiple transmission of the same or similar report data.

[0367] "Filtering" is the process of eliminating irrelevant or erroneous information, leaving only the necessary data.

[0368] This invention is a system for realizing prompt and accurate reporting in the event of a disaster. This system analyzes disaster information and emotional information provided by users and evaluates the importance of the information, enabling prompt notification to rescue organizations.

[0369] System Configuration

[0370] This system consists of the following main elements:

[0371] 1. User Device

[0372] 2. Web Server

[0373] 3. Generative AI and Natural Language Processing Server

[0374] 4. Emotion Engine

[0375] 5. Notification system for rescue agencies

[0376] DETAILED DESCRIPTION OF THE EMBODIMENTS

[0377] 1. Report via user terminal:

[0378] Users access web applications using devices such as smartphones and personal computers.

[0379] Users log in by entering their authentication information (username and password), and then fill out a form with the type of disaster (e.g., earthquake, fire), their current location, details of the situation (such as the state of collapsed buildings), and images and videos (if necessary).

[0380] When the user presses the "Submit" button, the terminal serializes the entered data into JSON format and sends it to the web server using HTTPS.

[0381] 2. Data received by the web server:

[0382] The server receives the data sent from the user terminal as an HTTP POST request.

[0383] The server performs data integrity checks, filters out bad data, and temporarily stores the correct data in a database.

[0384] The received data is prepared to be passed to the generative artificial intelligence and natural language processing server for analysis, and also to the emotion engine.

[0385] 3. Data analysis using generative artificial intelligence and natural language processing:

[0386] The generative AI model analyzes the received data and determines the reliability and authenticity of the report.

[0387] Using natural language processing technology, key points from the report are extracted and the urgency of the disaster is assessed.

[0388] The AI ​​model stores the results in a database and performs duplicate checking and filtering of the data.

[0389] The server prepares to pass the analysis results to the emotion engine.

[0390] 4. Emotion Recognition with Emotion Engine:

[0391] The emotion engine receives the user's text data and voice data and uses emotion analysis algorithms to recognize the user's emotions.

[0392] The recognized emotion information is added to the message data and used to evaluate the importance of the message data.

[0393] 5. Notification to rescue agencies:

[0394] The server prioritizes processing of data that is evaluated as having high importance by the emotion engine.

[0395] The server generates a notification message containing the analysis results and emotion information and sends it to the relevant rescue organization. Specifically, a notification such as "Emergency call: Earthquake occurred at point A. Situation: Building collapse, many injured. User's stress level: High" is generated.

[0396] Rescue agencies are notified and rush to the scene.

[0397] Specific examples

[0398] As a concrete example, consider the occurrence of an earthquake.

[0399] The user sees the earthquake, opens the web application and logs in.

[0400] The user inputs "earthquake," "current location (automatically detected)," and "details of the situation (buildings have collapsed and many injured)," and then presses the send button.

[0401] The user terminal transmits this data to the web server.

[0402] A server receives the data and analyzes it using generative artificial intelligence and natural language processing.

[0403] The emotion engine analyzes the user's input data and voice data to recognize the user's stress level and emotions.

[0404] The server sends a notification to the relevant rescue organizations based on the analysis results and emotion information. The notification message includes the type of disaster, location, details of the situation, and the user's emotion information.

[0405] Rescue agencies are notified and rush to the scene.

[0406] Prompt Sentence Examples

[0407] Enter the following prompt into the generative AI model:

[0408] "Analyze the report data, recognize the user's emotions, and generate a notification message that includes the type of disaster, current location, details of the situation, and the user's stress level."

[0409] As described above, the system of the present invention improves the efficiency of disaster reporting in emergencies and supports rapid and effective rescue operations by utilizing user emotional information.

[0410] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0411] Step 1:

[0412] When a user confirms a disaster, they access the web application from their device, such as a smartphone or PC. They log in by entering their authentication information (e.g., username and password). After logging in, they enter the following information into the reporting form:

[0413] Type of disaster (e.g. earthquake, fire)

[0414] Current location (automatically detected using the device's GPS function or manually entered)

[0415] Details of the situation (e.g., a building has collapsed and many people are injured)

[0416] Images and videos (optional attachments available)

[0417] The user enters all the required information and clicks the "Submit" button. At this time, the user's device serializes the entered data in JSON format and sends it to the web server using HTTPS. The input is the report content (text, image, location information), and the output is the data to be sent to the web server.

[0418] Step 2:

[0419] The server receives data sent from the user terminal as an HTTP POST request. First, the server checks the integrity of the received data and filters out incomplete or bad data. Data that has been confirmed to be consistent is temporarily stored in a database. The input is the JSON data sent by the user, and the output is the data whose integrity has been confirmed.

[0420] Step 3:

[0421] The server passes the received data to a generative artificial intelligence and natural language processing server. The generative AI model analyzes the received data and determines the reliability and authenticity of the report content. Natural language processing technology is used to extract important keywords from the report text and analyze its content. Data duplication checks and filtering are also performed. The input is data whose consistency has been confirmed, and the output is the analysis results and data with duplicates removed.

[0422] Step 4:

[0423] The server passes the analysis results to the emotion engine. The emotion engine receives the user's text data and voice data and uses an emotion analysis algorithm to recognize the user's emotions. It analyzes the user's language and sentence tone to evaluate stress levels and fear. The input is the analyzed data, and the output is data with emotional information added.

[0424] Step 5:

[0425] The server evaluates the importance of the message data to which emotional information has been added. Data that has been evaluated as having a high importance by the emotion engine is processed preferentially. The input is data to which emotional information has been added, and the output is data whose importance has been evaluated.

[0426] Step 6:

[0427] The server generates a notification message based on the evaluated data. Specifically, it may have a message such as "Emergency call: An earthquake has occurred at point A. Situation: Building collapsed, many injured. User stress level: High." The generated notification message is sent to the relevant rescue agencies (fire department, police, ambulance, etc.). The input is the data whose importance has been evaluated, and the output is the generated notification message.

[0428] Step 7:

[0429] Rescue agencies receive notifications and initiate actions to respond quickly based on the notification content. The input is a notification message sent from the server, and the output is the initiation of rescue operations.

[0430] (Application example 2)

[0431] 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."

[0432] Conventional disaster reporting systems have difficulty prioritizing reports, resulting in the inability to process reports of particularly high urgency quickly. Furthermore, because the report data is evaluated without taking into account the caller's emotions or stress level, the efficiency of rescue operations can be reduced. Therefore, there is a need for a system that can appropriately determine which reports are of high urgency and carry out prompt and effective rescue operations.

[0433] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing the message content and emotions, extracting and evaluating emotional data, means for analyzing the message content and determining its authenticity using generative artificial intelligence and natural language processing, and means for notifying a rescue organization based on the evaluated message information and emotional data. This makes it possible to accurately evaluate the urgency of the message content and prioritize calls of particularly high importance. Furthermore, utilizing the caller's emotional information improves the speed and effectiveness of rescue operations.

[0434] A "web application program" is software that can be accessed via the Internet and is a means by which users can report disaster information.

[0435] The "central processing unit" is a computer server that analyzes the received data and performs the necessary processing.

[0436] "Generative AI" is an AI technology that can analyze data patterns and generate new information.

[0437] "Natural language processing" is a technology for analyzing text and voice data entered by a user and understanding its content.

[0438] "Sentiment analysis" is the process of determining emotions and stress levels from user-entered text and voice data.

[0439] "Emotion data" is information that indicates the emotional state of the user extracted by emotion analysis.

[0440] "Report data" refers to information such as text, audio, images, and video that a user inputs when reporting disaster information.

[0441] "Rescue agency" refers to an organization or unit that responds when a disaster occurs.

[0442] "Duplicate check" is a process for identifying identical or similar notification data and preventing it from being sent again.

[0443] "Filtering" is the process of removing unnecessary data from received report data and extracting only the necessary information.

[0444] "Prioritization" is the process of determining the priority of rescue operations based on call data and sentiment data.

[0445] Overall system overview

[0446] The present invention is a disaster notification system consisting of a web application program, a central processing unit, generative artificial intelligence, natural language processing, emotion analysis, and a system for notifying rescue organizations. This system allows users to quickly and appropriately report disaster information, which is then analyzed and notified to the necessary rescue organizations.

[0447] System Configuration

[0448] The following are the main elements that make up the system:

[0449] Web Application Program

[0450] Users report disaster information through a web application program, which includes the type of disaster, current location, details of the situation, and the ability to attach images and videos. Once the user enters the content of the report and presses the send button, the information is sent to the central processing unit.

[0451] central processing unit

[0452] The central processing unit centrally manages the report data received from users. This unit uses generative artificial intelligence and natural language processing technology to analyze the report data and determine its authenticity. It also has the function of performing emotion analysis, extracting and evaluating emotional data.

[0453] Generative Artificial Intelligence and Natural Language Processing

[0454] Generative AI can analyze patterns in reports and generate new information. It uses natural language processing technology to understand the meaning of text and voice data entered by users and evaluate its reliability.

[0455] Emotion analysis

[0456] Sentiment analysis evaluates the user's emotional state from text and voice data entered by the user, and this emotional data is sent to the notification system along with the notification data.

[0457] Notification System

[0458] The notification system uses generative artificial intelligence and sentiment analysis to evaluate call data and then notify relevant rescue agencies. The notification includes the urgency of the call data and the user's emotional state.

[0459] Program operation explanation

[0460] This system uses the following hardware and software:

[0461] Hardware: Smartphones, computer servers

[0462] Software: Python, Flask (web framework), emotion recognition model, natural language processing (NLP) model

[0463] The central processing unit analyzes the data received from users and performs sentiment analysis. The generative AI evaluates the urgency of the call and stores the results in a database. The notification system uses this data to generate notification messages for rescue agencies, encouraging them to respond quickly.

[0464] Examples and prompts

[0465] For example, if a user reports that an earthquake has occurred, buildings have collapsed, and many people are injured, the system operates as follows:

[0466] 1. The user opens the web application program, inputs disaster information (including earthquake, current location, automatic detection, and situation details), and presses the send button.

[0467] 2. The central processing unit analyzes the received report data using generative artificial intelligence and natural language processing technology.

[0468] 3. Sentiment analysis obtains user emotion data using the following prompt sentence:

[0469] Prompt: "The user entered the following text: 'An earthquake occurred, buildings collapsed, and many people were injured.' Analyze the user's emotions (fear, stress) from this text."

[0470] 4. The generative AI evaluates the urgency of the report data using the following prompt:

[0471] Prompt: "Report data: {'disaster_type': 'Earthquake', 'location': 'Automatically detected location', 'details': 'A building has collapsed and many people are injured'} Rate the urgency of this data and calculate a priority."

[0472] 5. The notification system sends emergency notifications to rescue agencies based on the analysis results and emotion data.

[0473] This allows for more effective disaster response, since important report data, including the user's emotional information, can be promptly notified to the relevant rescue organizations.

[0474] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0475] Step 1:

[0476] The user launches the web application program, inputs the type of disaster, current location, details of the situation, and report information including images and videos, and presses the send button.

[0477] Input: User inputs disaster type, current location, situation details, and media files

[0478] Output: Serialized message data sent to the central processor

[0479] Step 2:

[0480] The user terminal sends the reported data to the central processing unit, which receives the data as an HTTP POST request.

[0481] Input: Report data sent from the user terminal

[0482] Output: Received data stored in the central processing unit

[0483] Step 3:

[0484] The central processing unit analyzes the received report data using generative artificial intelligence and natural language processing technology, particularly to determine the urgency and authenticity of the report content.

[0485] Input: Report data stored in the central processing unit

[0486] Output: Analyzed report data (including urgency rating and truth rating)

[0487] Specific operation: Generative AI uses natural language processing technology to analyze text data and determine the urgency and authenticity of the report.

[0488] Step 4:

[0489] The central processing unit performs sentiment analysis to extract emotional data, determines the emotional state from the text and voice data entered by the user, and performs sentiment analysis using specific prompt sentences.

[0490] Input: Text or voice data in the report data

[0491] Output: User's emotional data (e.g., stress level, fear level)

[0492] Specific behavior: The emotion engine uses the prompt "Text entered by the user: 'Specific content' Analyze the user's emotion (fear, stress) from this text."

[0493] Step 5:

[0494] The central processing unit generates a notification message based on the evaluated notification information and emotion data, and sends high-urgency notifications to relevant rescue organizations on a priority basis.

[0495] Input: Analyzed report data and emotion data

[0496] Output: Message to notify rescue agencies

[0497] Specific operation: The notification system evaluates the urgency of the notification using the prompt "Report data: {'disaster_type': 'Earthquake', 'location': 'Automatically detected location', 'details': 'Specific content'} Evaluate the urgency of this data and calculate the priority." and generates a notification message.

[0498] This allows important report data, including the user's emotional information, to be promptly notified to relevant rescue organizations, enabling effective disaster response.

[0499] 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.

[0500] 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.

[0501] 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.

[0502] [Second embodiment]

[0503] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0504] 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.

[0505] 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).

[0506] 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.

[0507] 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.

[0508] 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).

[0509] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0510] 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.

[0511] 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.

[0512] 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.

[0513] 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.

[0514] 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."

[0515] Overall overview

[0516] This invention is a system that realizes fast and accurate reporting during disasters by migrating the reporting system from telephone lines to a web system and utilizing generative artificial intelligence (AI) and natural language processing (NLP) technology. This is expected to result in efficient reporting during disasters, accelerating rescue operations and improving the effectiveness of lifesaving.

[0517] System Configuration

[0518] This system consists of the following main elements:

[0519] 1. User Device

[0520] 2. Web Server

[0521] 3. Generative AI and Natural Language Processing Server

[0522] 4. Notification system for rescue agencies

[0523] DETAILED DESCRIPTION OF THE EMBODIMENTS

[0524] 1. Reporting via user terminal

[0525] A user accesses a web application and logs in by entering their authentication information.

[0526] After logging in, the user fills in the necessary information in the form to make a report.

[0527] Type of disaster (e.g. earthquake, fire)

[0528] Current location (auto-detect or manual input)

[0529] Details of the situation (free description)

[0530] Images and videos (optional)

[0531] When the user enters the report content and clicks the "Send" button, the data is serialized and sent to the web server.

[0532] 2. Data reception by the web server

[0533] The web server receives the data as an HTTP POST request and passes it to a generative artificial intelligence and natural language processing server for analysis.

[0534] The server has mechanisms for securely receiving and storing data.

[0535] 3. Data analysis using generative artificial intelligence and natural language processing

[0536] The received data is analyzed using generative artificial intelligence and natural language processing technology to determine its authenticity.

[0537] The report content is analyzed in detail using natural language processing, and the reliability of the content is evaluated.

[0538] The data whose authenticity has been determined is stored in a database.

[0539] Duplicate checking and filtering of data also occurs at this stage.

[0540] 4. Notifying rescue agencies

[0541] Once the authenticity has been determined, the data is automatically communicated to the relevant rescue agencies.

[0542] Notifications are generated using messages based on the parsed data.

[0543] Example: "Emergency call: Earthquake occurred at point A. Situation: Building collapsed, injured."

[0544] Notifications are sent simultaneously to multiple rescue agencies, allowing for a rapid response.

[0545] Specific examples

[0546] As a concrete example, consider the occurrence of an earthquake.

[0547] When a user confirms that an earthquake has occurred, they open the web application and log in.

[0548] The user inputs "earthquake," "current location (automatically detected)," and "details of the situation (buildings have collapsed and many injured)," and presses the send button.

[0549] The user terminal transmits this data to the web server.

[0550] The server receives the data and uses generative artificial intelligence and natural language processing technology to analyze it, determine its authenticity, and perform duplicate checking and filtering.

[0551] The server sends notifications to relevant rescue agencies based on the analysis results.

[0552] Rescue agencies are notified and rush to the scene.

[0553] In this way, the system will streamline reporting during disasters and enable rapid rescue operations.

[0554] The processing flow will be explained below.

[0555] Step 1:

[0556] A user accesses the web application. The user opens a browser and logs in to the disaster notification system website. The user enters their authentication information (username and password) and presses the login button.

[0557] Step 2:

[0558] The user opens the report form. After logging in, the user clicks the "Report" button to open a form for entering disaster information. The user enters the following items:

[0559] Type of disaster (e.g. earthquake, fire)

[0560] Current location (auto-detect or manual input)

[0561] Details of the situation (free description)

[0562] Images and videos (optional)

[0563] Step 3:

[0564] The user submits the input data. The user enters the necessary information into the report form and clicks the "Submit" button. This causes the device to serialize the input data and send it to the server.

[0565] Step 4:

[0566] The device sends the serialized data to the web server as an HTTP POST request. The data includes the type of disaster, current location, details of the situation, and images and videos.

[0567] Step 5:

[0568] The server receives the data. The server parses the received HTTP POST request and extracts the data. The server prepares the received data to be passed to the generative artificial intelligence and natural language processing server.

[0569] Step 6:

[0570] The server analyzes the data. The received data is then analyzed using generative artificial intelligence and natural language processing technology. Natural language processing analyzes the report in detail and evaluates its reliability. The generative artificial intelligence determines whether the data is true or false, and the results are stored in a database.

[0571] Step 7:

[0572] The server checks for duplicate reports and filters them. The server checks against existing data in the database to ensure there are no duplicate reports with the same content. It also filters out false or unnecessary information.

[0573] Step 8:

[0574] The server sends a notification to the rescue organization. Based on the truth-checked and filtered data, the server generates a notification message to the relevant rescue organization. The notification message contains the parsed data.

[0575] Step 9:

[0576] The server sends a message to the rescue organization. The server then sends the generated notification message to multiple related rescue organizations, enabling a rapid response. The notification message includes the type of disaster, location, and details of the situation.

[0577] Step 10:

[0578] The user can later access the web application and view the history of the notifications they have sent, including the notification date, type of disaster, and details of the situation.

[0579] Example 1

[0580] 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."

[0581] Conventional disaster notification systems transmit information over telephone lines, making it difficult to transmit information quickly when communication lines are congested or multiple reports are made simultaneously, making them unsuitable for disasters that require immediate response. They are also prone to human error and delays in information transmission. Furthermore, they lack a mechanism for determining the authenticity of reports, which can sometimes prevent rescue agencies from responding appropriately. This can result in delays and reduced efficiency in rescue operations, hindering the ability to save lives. To address these issues, it is necessary to provide a system that can transmit disaster notifications more efficiently and quickly, and that can properly determine information and check for duplication.

[0582] 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.

[0583] In this invention, the server includes means for reporting disaster information using a user terminal, means for transmitting the reported information to the server via the Internet, means for analyzing the information received by the server in detail using generative artificial intelligence and natural language processing to determine the authenticity of the information, means for checking for duplication and filtering the determined information and storing highly reliable information in a database, and means for notifying rescue organizations of a notification message generated based on the determined information. This enables quick and accurate information transmission and analysis in the event of a disaster, thereby realizing efficient and rapid rescue operations.

[0584] A "user terminal" is an electronic device used by a user to report disaster information.

[0585] A "web application" is software that users access via the Internet to input and send disaster information.

[0586] The "server" is a central processing unit that analyzes received disaster information and notifies rescue organizations.

[0587] "Generative AI" is a type of AI technology used to analyze received information and determine its authenticity.

[0588] "Natural language processing" is a technology for analyzing text data and understanding its meaning and intent.

[0589] The "Internet" is a global network for communicating data between user terminals and servers.

[0590] "Duplicate check" is a process for detecting duplication when the same or similar information is reported multiple times.

[0591] "Filtering" is a process for removing unnecessary or inaccurate information and extracting reliable information.

[0592] A "database" is a data management system that stores analyzed information for later reference.

[0593] A "notification message" is a message that is generated based on the determined disaster information and sent to rescue organizations.

[0594] "Rescue organization" means an organization or agency that carries out rescue operations in the event of a disaster.

[0595] The present invention provides a notification system for use in disaster situations, which utilizes the Internet and the latest artificial intelligence technology to enable rapid and accurate information transmission. How this system is implemented will be explained below.

[0596] Reporting via user terminal

[0597] Users use a user device such as a smartphone, tablet, or PC to access the web application. After logging in by entering their authentication information, they can access a form for entering disaster information. The form includes fields for the type of disaster (e.g., earthquake, fire), current location (automatic detection or manual entry), details of the situation (free text), and the ability to upload images and videos. After the user enters the required information and clicks the "Submit" button, the data is serialized and sent to the web server.

[0598] Data reception by the web server

[0599] The server receives data sent from the user terminal as an HTTP POST request. The received data is then forwarded to the generative artificial intelligence and natural language processing server for analysis. The server is equipped with security functions to ensure the safety of the received data.

[0600] Data analysis using generative artificial intelligence and natural language processing

[0601] The server analyzes the received data using generative artificial intelligence (e.g., GPT-4) and natural language processing technology (e.g., SpaCy). Through this analysis, it evaluates the authenticity of disaster information and determines its reliability. It also checks for duplication and filters the data to remove duplicate or unreliable information. Through this process, highly reliable data is stored in the database.

[0602] Notifying rescue agencies

[0603] The server generates a notification message based on the determined truthfulness of the information. The generated notification message is then sent to the relevant rescue organizations. The notification is sent simultaneously to multiple rescue organizations via a messaging API (e.g., Twilio) to enable a rapid response. An example of a notification message is "Emergency call: Earthquake occurred at location A. Situation: Building collapsed, injured."

[0604] Specific examples

[0605] As a concrete example, consider the processing flow when an earthquake occurs. The user confirms the earthquake, accesses the web application, and logs in. Next, they enter "earthquake," "current location (automatically detected)," and "details of the situation (a building has collapsed and many injured people)" and press the send button. The user's device sends this data to the web server. The server receives the data and uses generative artificial intelligence and natural language processing technology to analyze it, determine its authenticity, and perform duplication checks and filtering. The server then sends a notification to the relevant rescue organizations based on the analysis results. The rescue organizations receive the notification and rush to the scene.

[0606] Prompt Sentence Examples

[0607] "An earthquake has occurred. Buildings have collapsed and many people are injured. Rescue is needed."

[0608] In this way, the present invention provides a system that makes reporting during disasters more efficient and supports rapid and accurate rescue operations.

[0609] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0610] Step 1:

[0611] A user accesses a web application and logs in by entering their credentials.

[0612] Specifically, a user opens a browser, enters a URL to access the login page of a web application, enters a username and password, and clicks the "Login" button.

[0613] Input details: Authentication information (user name, password)

[0614] Output: Authentication result, redirect to dashboard

[0615] Step 2:

[0616] After logging in, the user enters the necessary information into the report form.

[0617] Specifically, users access the form, select the type of disaster from a drop-down menu, press a button to automatically detect their "current location" or enter it manually, write details about the situation in the text box, and upload images and videos if necessary.

[0618] Input information: type of disaster, current location, details of the situation, images and videos

[0619] Output content: Input data confirmation screen

[0620] Step 3:

[0621] When the user clicks the "Submit" button, the input data is serialized and sent to the web server.

[0622] Specifically, when you click the "Submit" button, the form data is converted to JSON format and sent to the server as an HTTP POST request.

[0623] Input: Clicking the submit button, serialized data

[0624] Output: HTTP POST request to the server

[0625] Step 4:

[0626] The server receives the HTTP POST request sent from the user terminal, analyzes the received data, and forwards it to the generative artificial intelligence and natural language processing server.

[0627] Specifically, the server parses the JSON data in the request body and extracts the type of disaster, current location, details of the situation, and images and videos. This data is then transferred to the generative artificial intelligence and natural language processing server via a dedicated API.

[0628] Input: HTTP POST request, serialized data

[0629] Output contents: Analysis results, data transferred to generative artificial intelligence and natural language processing servers

[0630] Step 5:

[0631] Generative artificial intelligence and natural language processing servers analyze the received data and determine its authenticity.

[0632] Specifically, it uses generative artificial intelligence (e.g., GPT-4) and natural language processing (e.g., SpaCy) to analyze text content and evaluate the reliability and authenticity of information. It also checks for duplicates and filters out unreliable information.

[0633] Input information: type of disaster, current location, details of the situation, images and videos

[0634] Output contents: True / false judgment results, filtered data

[0635] Step 6:

[0636] The server stores reliable data based on the analysis results in a database.

[0637] Specifically, it uses a query to compare the data with existing records in the database, filters out duplicates, and then stores the newly parsed data in the database.

[0638] Input: Filtered data

[0639] Output contents: Results stored in the database

[0640] Step 7:

[0641] The server generates a notification message based on the information whose truth or falsity has been determined.

[0642] Specifically, the system inserts the analyzed data into an automatically generated message template, generating a message such as "Emergency call: Earthquake occurred at point A. Situation: Building collapsed, injured."

[0643] Input: Filtered data

[0644] Output content: Notification message

[0645] Step 8:

[0646] The server sends a notification message to the relevant rescue agency.

[0647] Specifically, notification messages are sent simultaneously to multiple rescue agency contacts via a message sending API (e.g., Twilio).

[0648] Input content: Notification message

[0649] Output content: Notification result to rescue agency

[0650] In this way, the system processes disaster reports quickly and accurately, and notifies relevant rescue organizations appropriately, enabling prompt rescue operations.

[0651] (Application example 1)

[0652] 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."

[0653] Conventional disaster response systems mainly rely on telephone lines for reporting, which often hinders the accuracy of reports and the speed of rescue operations. Specifically, it is difficult to properly convey detailed information about the situation when reporting, and auxiliary information such as location information and images and videos of the scene is often lacking. This makes it difficult for rescue agencies to respond quickly and appropriately, resulting in a decrease in the efficiency of lifesaving efforts.

[0654] 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.

[0655] In this invention, the server includes means for reporting disaster information using a web application, means for transmitting the reported information to the server, means for analyzing the information received by the server using generative artificial intelligence and natural language processing to determine its authenticity, means for automatically acquiring location information of the user device, means for attaching and transmitting images and videos related to the disaster situation, and means for notifying rescue organizations based on the determined information. This enables the transmission of detailed report content including location information and images / videos and the rapid determination of authenticity by generative AI, enabling rescue organizations to respond quickly and accurately.

[0656] A "web application" is software that can be used by users over the Internet.

[0657] "Means for reporting disaster information" refers to an interface that allows users to report the situation when a disaster occurs.

[0658] A "server" is a computer system that processes and stores data on a network.

[0659] "Generative artificial intelligence" refers to artificial intelligence technology that has the ability to generate new information based on input data.

[0660] "Natural language processing" is a technology that uses computers to understand, analyze, and generate human language.

[0661] "Means for determining authenticity" refers to the process of analyzing and evaluating whether the reported information is correct.

[0662] "User terminal" refers to any device used by a user, including smartphones and tablets.

[0663] "Means for automatically obtaining location information" refers to a function that automatically obtains the user's current location using technology such as GPS.

[0664] "Means for attaching and sending images and videos related to the disaster situation" refers to a function that allows users to attach images and videos they have taken to the report and send them.

[0665] "Means of notification" refers to the process of contacting rescue organizations based on the analyzed information.

[0666] System Program

[0667] The system of this invention begins with a user reporting disaster information using a web application and sending it to a server. The server then analyzes the reported information using generative artificial intelligence and natural language processing to determine its authenticity. Next, the user's device automatically acquires location information and sends it along with images and videos of the disaster situation. Finally, the server notifies rescue organizations based on the determined information.

[0668] Hardware and software used

[0669] Hardware: smartphones, tablets, servers

[0670] Software: GPS module, Python, Geopy library, Requests library, generative AI model, natural language processing technology (NLP)

[0671] Natural language processing explanation

[0672] 1. Data transmission by user terminal

[0673] Users use their smartphones or tablets to report disaster information through a web application. At this time, they input the necessary information, such as the type of disaster, detailed situation, and current location. Location information is automatically obtained using a GPS module. Users can also attach images and videos showing the current state of the disaster within the app. This information is serialized and sent to the server via a secure communication channel.

[0674] 2. Data analysis by the server

[0675] The server analyzes the received information using generative artificial intelligence and natural language processing technology. Natural language processing understands the text entered by the user, and generative AI evaluates the veracity of the content. For example, if a report is made that "a building has collapsed and many people are injured," the AI ​​analyzes the context and evaluates its reliability.

[0676] 3. Notifying rescue agencies

[0677] Once the information has been determined to be true or false, it is automatically sent to rescue agencies by the server. This notification includes a specific message generated by the generative AI. For example, it could read, "Emergency call: An earthquake has occurred at the specified location. Situation: A building has collapsed and many people are injured. Please respond quickly."

[0678] Specific examples

[0679] As a concrete example, consider the occurrence of an earthquake. A user opens a web application on their smartphone, selects "earthquake," and enters "buildings have collapsed and many injured." Location information is automatically acquired via GPS, and images and videos are attached. This information is sent to a server, where it is analyzed and evaluated using generative AI and natural language processing technology. As a result, a notification is sent to rescue agencies stating, "Emergency call: An earthquake has occurred at the specified location. Situation: buildings have collapsed and many injured. Please respond quickly."

[0680] Prompt Sentence Examples

[0681] input

[0682] Disaster type: Earthquake

[0683] Details: Buildings collapsed, many injured

[0684] Location information: Automatically acquired (latitude and longitude)

[0685] Attachment: Images and videos of the disaster site

[0686] output

[0687] "Emergency message: Earthquake occurred at specified location. Situation: Building collapsed, many injured. Please respond quickly."

[0688] This allows for accurate and prompt reporting and response.

[0689] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0690] Step 1:

[0691] Users access the web application using a smartphone or tablet, access the disaster information reporting form, and enter the necessary information, such as the type of disaster, current location (automatically obtained), details of the situation, and images and videos.

[0692] input:

[0693] Types of disasters

[0694] Current location (automatically obtained by GPS)

[0695] Details of the situation

[0696] Images and videos

[0697] output:

[0698] Serialized report data

[0699] Specific behavior:

[0700] Converts information entered into a web form into a serialized format such as JSON and prepares it for transmission to the server.

[0701] Step 2:

[0702] The user device sends the processed disaster information to the server, where the data is sent using a secure communication protocol (such as HTTPS).

[0703] input:

[0704] Serialized report data

[0705] output:

[0706] Report data received by the server

[0707] Specific behavior:

[0708] The serialized data is sent to the server as an HTTPS request.

[0709] Step 3:

[0710] The server analyzes the received report data using generative artificial intelligence and natural language processing technology to determine its authenticity.

[0711] input:

[0712] Report data received by the server

[0713] output:

[0714] Data that has been judged to be true or false

[0715] Specific behavior:

[0716] It uses a natural language processing engine to analyze text data and uses generative AI to evaluate the reliability of the information.

[0717] Step 4:

[0718] The server performs duplication checks and filtering on the parsed data, eliminating redundant and meaningless information.

[0719] input:

[0720] Data that has been judged to be true or false

[0721] output:

[0722] Duplicate checked and filtered data

[0723] Specific behavior:

[0724] Matching data with existing data in the database to remove duplicate information and filtering out incomplete or unnecessary data.

[0725] Step 5:

[0726] The server then notifies rescue agencies based on the filtered data, with the notification being an emergency message generated by generative AI.

[0727] input:

[0728] Duplicate checked and filtered data

[0729] output:

[0730] Emergency message sent to rescue agencies

[0731] Specific behavior:

[0732] Generative AI models are used to generate appropriate emergency messages based on the content of the call and send them to relevant rescue agencies.

[0733] Step 6:

[0734] Rescue agencies will receive notifications and respond quickly, specifically by dispatching the necessary rescue teams and resources to the scene based on the notification message.

[0735] input:

[0736] Emergency message sent to rescue agencies

[0737] output:

[0738] Rapid response from rescue agencies

[0739] Specific behavior:

[0740] Rescue agencies analyze the messages they receive, determine the appropriate response, and quickly begin action.

[0741] This overall system processing flow enables faster reporting and more accurate information transmission in the event of a disaster, improving the efficiency of rescue operations.

[0742] 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.

[0743] Overall overview

[0744] This invention is a system that recognizes user emotions and evaluates the importance and prioritization of report data by combining an emotion engine with a disaster reporting system, thereby enabling high-urgency reports to be processed quickly and enabling effective rescue operations.

[0745] System Configuration

[0746] This system consists of the following main elements:

[0747] 1. User Device

[0748] 2. Web Server

[0749] 3. Generative AI and Natural Language Processing Server

[0750] 4. Emotion Engine

[0751] 5. Notification system for rescue agencies

[0752] DETAILED DESCRIPTION OF THE EMBODIMENTS

[0753] 1. Reporting via user terminal

[0754] A user accesses a web application and logs in by entering their authentication information.

[0755] After logging in, the user fills in the necessary information in the form to make a report.

[0756] Type of disaster (e.g. earthquake, fire)

[0757] Current location (auto-detect or manual input)

[0758] Details of the situation (free description)

[0759] Images and videos (optional)

[0760] When the user enters the report content and clicks the "Send" button, the data is serialized and sent to the web server.

[0761] 2. Data reception by the web server

[0762] The web server receives the data as an HTTP POST request and passes it to a generative artificial intelligence and natural language processing server for analysis.

[0763] The server prepares to pass the received data to the emotion engine.

[0764] 3. Data analysis using generative artificial intelligence and natural language processing

[0765] The received data is analyzed using generative artificial intelligence and natural language processing techniques.

[0766] The report content is analyzed in detail using natural language processing, and the reliability of the content is evaluated.

[0767] Generative artificial intelligence determines the truth or falsity of the data and stores the results in a database.

[0768] Duplicate checking and filtering of data also occurs at this stage.

[0769] 4. Emotion Recognition by Emotion Engine

[0770] The emotion engine analyzes the text and voice data sent by the user and recognizes the user's emotions.

[0771] The recognized emotion information is added to the message data and used to evaluate the importance of the message data.

[0772] 5. Notifying rescue agencies

[0773] Data that is rated as highly important by the emotion engine is processed with priority.

[0774] When a notification is sent to rescue agencies, the emotion information is included along with the analyzed data.

[0775] Specifically, the following notification message is generated:

[0776] Example: "Emergency call: Earthquake occurred at location A. Situation: Building collapsed, people injured. User stress level: High."

[0777] Notifications are sent simultaneously to multiple rescue agencies, allowing for a rapid response.

[0778] Specific examples

[0779] As a concrete example, consider the occurrence of an earthquake.

[0780] When a user confirms that an earthquake has occurred, they open the web application and log in.

[0781] The user inputs "earthquake," "current location (automatically detected)," and "details of the situation (buildings have collapsed and many injured)," and presses the send button.

[0782] The user terminal transmits this data to the web server.

[0783] The server receives the data and analyzes it using generative artificial intelligence and natural language processing techniques.

[0784] The emotion engine analyzes user input and voice data to recognize the user's stress level and emotions.

[0785] The server sends a notification to the relevant rescue organization based on the analysis results and the emotion information. The notification message includes the type of disaster, location, details of the situation, and the user's emotion information.

[0786] Rescue agencies are notified and rush to the scene.

[0787] In this way, this system improves the efficiency of reporting during disasters and enables rapid rescue operations by utilizing users' emotional information.

[0788] The processing flow will be explained below.

[0789] Step 1:

[0790] A user accesses a web application.

[0791] The user opens a browser on their personal computer or smartphone, accesses the disaster notification system website, and logs in. The user enters their authentication information (username and password) and presses the login button.

[0792] Step 2:

[0793] The user opens the report form.

[0794] After logging in, users click the "Report" button from the main menu to open a form for reporting disaster information. Users must enter the following information:

[0795] Type of disaster (e.g. earthquake, fire)

[0796] Current location (auto-detect or manual input)

[0797] Details of the situation (free description)

[0798] Images and videos (optional)

[0799] Step 3:

[0800] The user sends the notification data.

[0801] The user enters disaster information and clicks the "Send" button, which causes the device to serialize all the entered data and prepare it to be sent to the web server.

[0802] Step 4:

[0803] The device sends the data to the server.

[0804] The device sends the serialized data to the web server as an HTTP POST request, which includes the type of disaster, current location, details of the situation, and images and videos.

[0805] Step 5:

[0806] The server receives the data.

[0807] The server analyzes the received HTTP POST request and extracts data from each field. The analyzed data is then passed to the generative artificial intelligence and natural language processing server.

[0808] Step 6:

[0809] The server analyzes the data.

[0810] The received data is analyzed using generative artificial intelligence and natural language processing technology. Natural language processing analyzes the contents of the report in detail and evaluates its reliability. The generative artificial intelligence determines whether the data is true or false, and the results are stored in a database.

[0811] Step 7:

[0812] The server performs duplicate checking and filtering.

[0813] The server checks existing data in the database to ensure there are no duplicate reports with the same content, and also filters out false or unnecessary information.

[0814] Step 8:

[0815] The server passes the data to the emotion engine.

[0816] The server passes the received text and voice data to the emotion engine for analysis, which analyzes the user's emotions.

[0817] Step 9:

[0818] The emotion engine recognizes the user's emotions.

[0819] The emotion engine analyzes the data sent by the user and evaluates the user's emotions, especially their stress level. The recognized emotion information is added to the report data.

[0820] Step 10:

[0821] The server sends a notification to the rescue agency.

[0822] Data that is evaluated as having high importance by the emotion engine is processed with priority.The server generates notification messages to relevant rescue organizations based on the analyzed data and emotion information.

[0823] Step 11:

[0824] The server sends a message to a rescue agency.

[0825] The server then sends the generated notification message to multiple related rescue organizations. The notification message includes the type of disaster, location, details of the situation, and the user's emotional state, allowing rescue organizations to respond to the scene quickly.

[0826] Step 12:

[0827] The user checks the report history.

[0828] Users can later revisit the web application and view the history of their submitted alerts, including the alert date, type of incident, situation details, and any attached emotional information.

[0829] Example 2

[0830] 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."

[0831] Conventional disaster reporting systems have difficulty in quickly determining the urgency of reports, and when many reports are received at the same time, important reports are buried. In addition, because they do not take into account the emotional information of the caller, it is difficult to accurately grasp situations with a high level of urgency.

[0832] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for analyzing received information using generative artificial intelligence and natural language processing to determine whether the information is true or false, a means for evaluating the importance of the report data based on the determined information and the user's emotional information, and a means for notifying a rescue organization based on the evaluated information. This makes it possible to evaluate the urgency of the report content with high accuracy and quickly notify an appropriate rescue organization.

[0833] A "web application" is software that runs on a web browser and can be accessed by users via the Internet.

[0834] "Disaster information" refers to detailed information about disasters such as earthquakes, fires, and floods reported by users.

[0835] "Reporting" is the act of a user providing disaster information through a web application.

[0836] A "server" is a computer system that receives, processes, and stores data from user terminals over a network.

[0837] "Generative artificial intelligence" is a technology that uses algorithms based on machine learning and deep learning to generate and analyze new data and patterns.

[0838] "Natural language processing" is the technology that enables computers to understand, interpret, and generate human language.

[0839] "Authenticity assessment" is the process of determining the accuracy and reliability of the information provided.

[0840] "Evaluating the importance of report data" is a process of determining how urgent the information is based on the disaster information provided and the user's emotional information.

[0841] "Notification" is the act of transmitting emergency information to relevant rescue organizations based on the evaluated information.

[0842] "Rescue agencies" are public institutions such as fire departments, police, and ambulance teams that respond to disasters.

[0843] "Emotional information" is data that indicates the emotional state (e.g., stress level or tension) that a user exhibits when making a report.

[0844] "Data duplication check" is a process to prevent multiple transmission of the same or similar report data.

[0845] "Filtering" is the process of eliminating irrelevant or erroneous information, leaving only the necessary data.

[0846] This invention is a system for realizing prompt and accurate reporting in the event of a disaster. This system analyzes disaster information and emotional information provided by users and evaluates the importance of the information, enabling prompt notification to rescue organizations.

[0847] System Configuration

[0848] This system consists of the following main elements:

[0849] 1. User Device

[0850] 2. Web Server

[0851] 3. Generative AI and Natural Language Processing Server

[0852] 4. Emotion Engine

[0853] 5. Notification system for rescue agencies

[0854] DETAILED DESCRIPTION OF THE EMBODIMENTS

[0855] 1. Report via user terminal:

[0856] Users access web applications using devices such as smartphones and personal computers.

[0857] Users log in by entering their authentication information (username and password), and then fill out a form with the type of disaster (e.g., earthquake, fire), their current location, details of the situation (such as the state of collapsed buildings), and images and videos (if necessary).

[0858] When the user presses the "Submit" button, the terminal serializes the entered data into JSON format and sends it to the web server using HTTPS.

[0859] 2. Data received by the web server:

[0860] The server receives the data sent from the user terminal as an HTTP POST request.

[0861] The server performs data integrity checks, filters out bad data, and temporarily stores the correct data in a database.

[0862] The received data is prepared to be passed to the generative artificial intelligence and natural language processing server for analysis, and also to the emotion engine.

[0863] 3. Data analysis using generative artificial intelligence and natural language processing:

[0864] The generative AI model analyzes the received data and determines the reliability and authenticity of the report.

[0865] Using natural language processing technology, key points from the report are extracted and the urgency of the disaster is assessed.

[0866] The AI ​​model stores the results in a database and performs duplicate checking and filtering of the data.

[0867] The server prepares to pass the analysis results to the emotion engine.

[0868] 4. Emotion Recognition with Emotion Engine:

[0869] The emotion engine receives the user's text data and voice data and uses emotion analysis algorithms to recognize the user's emotions.

[0870] The recognized emotion information is added to the message data and used to evaluate the importance of the message data.

[0871] 5. Notification to rescue agencies:

[0872] The server prioritizes processing of data that is evaluated as having high importance by the emotion engine.

[0873] The server generates a notification message containing the analysis results and emotion information and sends it to the relevant rescue organization. Specifically, a notification such as "Emergency call: Earthquake occurred at point A. Situation: Building collapse, many injured. User's stress level: High" is generated.

[0874] Rescue agencies are notified and rush to the scene.

[0875] Specific examples

[0876] As a concrete example, consider the occurrence of an earthquake.

[0877] The user sees the earthquake, opens the web application and logs in.

[0878] The user inputs "earthquake," "current location (automatically detected)," and "details of the situation (buildings have collapsed and many injured)," and then presses the send button.

[0879] The user terminal transmits this data to the web server.

[0880] A server receives the data and analyzes it using generative artificial intelligence and natural language processing.

[0881] The emotion engine analyzes the user's input data and voice data to recognize the user's stress level and emotions.

[0882] The server sends a notification to the relevant rescue organizations based on the analysis results and emotion information. The notification message includes the type of disaster, location, details of the situation, and the user's emotion information.

[0883] Rescue agencies are notified and rush to the scene.

[0884] Prompt Sentence Examples

[0885] Enter the following prompt into the generative AI model:

[0886] "Analyze the report data, recognize the user's emotions, and generate a notification message that includes the type of disaster, current location, details of the situation, and the user's stress level."

[0887] As described above, the system of the present invention improves the efficiency of disaster reporting in emergencies and supports rapid and effective rescue operations by utilizing user emotional information.

[0888] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0889] Step 1:

[0890] When a user confirms a disaster, they access the web application from their device, such as a smartphone or PC. They log in by entering their authentication information (e.g., username and password). After logging in, they enter the following information into the reporting form:

[0891] Type of disaster (e.g. earthquake, fire)

[0892] Current location (automatically detected using the device's GPS function or manually entered)

[0893] Details of the situation (e.g., a building has collapsed and many people are injured)

[0894] Images and videos (optional attachments available)

[0895] The user enters all the required information and clicks the "Submit" button. At this time, the user's device serializes the entered data in JSON format and sends it to the web server using HTTPS. The input is the report content (text, image, location information), and the output is the data to be sent to the web server.

[0896] Step 2:

[0897] The server receives data sent from the user terminal as an HTTP POST request. First, the server checks the integrity of the received data and filters out incomplete or bad data. Data that has been confirmed to be consistent is temporarily stored in a database. The input is the JSON data sent by the user, and the output is the data whose integrity has been confirmed.

[0898] Step 3:

[0899] The server passes the received data to a generative artificial intelligence and natural language processing server. The generative AI model analyzes the received data and determines the reliability and authenticity of the report content. Natural language processing technology is used to extract important keywords from the report text and analyze its content. Data duplication checks and filtering are also performed. The input is data whose consistency has been confirmed, and the output is the analysis results and data with duplicates removed.

[0900] Step 4:

[0901] The server passes the analysis results to the emotion engine. The emotion engine receives the user's text data and voice data and uses an emotion analysis algorithm to recognize the user's emotions. It analyzes the user's language and sentence tone to evaluate stress levels and fear. The input is the analyzed data, and the output is data with emotional information added.

[0902] Step 5:

[0903] The server evaluates the importance of the message data to which emotional information has been added. Data that has been evaluated as having a high importance by the emotion engine is processed preferentially. The input is data to which emotional information has been added, and the output is data whose importance has been evaluated.

[0904] Step 6:

[0905] The server generates a notification message based on the evaluated data. Specifically, it may have a message such as "Emergency call: An earthquake has occurred at point A. Situation: Building collapsed, many injured. User stress level: High." The generated notification message is sent to the relevant rescue agencies (fire department, police, ambulance, etc.). The input is the data whose importance has been evaluated, and the output is the generated notification message.

[0906] Step 7:

[0907] Rescue agencies receive notifications and initiate actions to respond quickly based on the notification content. The input is a notification message sent from the server, and the output is the initiation of rescue operations.

[0908] (Application example 2)

[0909] 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."

[0910] Conventional disaster reporting systems have difficulty prioritizing reports, resulting in the inability to process reports of particularly high urgency quickly. Furthermore, because the report data is evaluated without taking into account the caller's emotions or stress level, the efficiency of rescue operations can be reduced. Therefore, there is a need for a system that can appropriately determine which reports are of high urgency and carry out prompt and effective rescue operations.

[0911] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing the message content and emotions, extracting and evaluating emotional data, means for analyzing the message content and determining its authenticity using generative artificial intelligence and natural language processing, and means for notifying a rescue organization based on the evaluated message information and emotional data. This makes it possible to accurately evaluate the urgency of the message content and prioritize calls of particularly high importance. Furthermore, utilizing the caller's emotional information improves the speed and effectiveness of rescue operations.

[0912] A "web application program" is software that can be accessed via the Internet and is a means by which users can report disaster information.

[0913] The "central processing unit" is a computer server that analyzes the received data and performs the necessary processing.

[0914] "Generative AI" is an AI technology that can analyze data patterns and generate new information.

[0915] "Natural language processing" is a technology for analyzing text and voice data entered by a user and understanding its content.

[0916] "Sentiment analysis" is the process of determining emotions and stress levels from user-entered text and voice data.

[0917] "Emotion data" is information that indicates the emotional state of the user extracted by emotion analysis.

[0918] "Report data" refers to information such as text, audio, images, and video that a user inputs when reporting disaster information.

[0919] "Rescue agency" refers to an organization or unit that responds when a disaster occurs.

[0920] "Duplicate check" is a process for identifying identical or similar notification data and preventing it from being sent again.

[0921] "Filtering" is the process of removing unnecessary data from received report data and extracting only the necessary information.

[0922] "Prioritization" is the process of determining the priority of rescue operations based on call data and sentiment data.

[0923] Overall system overview

[0924] The present invention is a disaster notification system consisting of a web application program, a central processing unit, generative artificial intelligence, natural language processing, emotion analysis, and a system for notifying rescue organizations. This system allows users to quickly and appropriately report disaster information, which is then analyzed and notified to the necessary rescue organizations.

[0925] System Configuration

[0926] The following are the main elements that make up the system:

[0927] Web Application Program

[0928] Users report disaster information through a web application program, which includes the type of disaster, current location, details of the situation, and the ability to attach images and videos. Once the user enters the content of the report and presses the send button, the information is sent to the central processing unit.

[0929] central processing unit

[0930] The central processing unit centrally manages the report data received from users. This unit uses generative artificial intelligence and natural language processing technology to analyze the report data and determine its authenticity. It also has the function of performing emotion analysis, extracting and evaluating emotional data.

[0931] Generative Artificial Intelligence and Natural Language Processing

[0932] Generative AI can analyze patterns in reports and generate new information. It uses natural language processing technology to understand the meaning of text and voice data entered by users and evaluate its reliability.

[0933] Emotion analysis

[0934] Sentiment analysis evaluates the user's emotional state from text and voice data entered by the user, and this emotional data is sent to the notification system along with the notification data.

[0935] Notification System

[0936] The notification system uses generative artificial intelligence and sentiment analysis to evaluate call data and then notify relevant rescue agencies. The notification includes the urgency of the call data and the user's emotional state.

[0937] Program operation explanation

[0938] This system uses the following hardware and software:

[0939] Hardware: Smartphones, computer servers

[0940] Software: Python, Flask (web framework), emotion recognition model, natural language processing (NLP) model

[0941] The central processing unit analyzes the data received from users and performs sentiment analysis. The generative AI evaluates the urgency of the call and stores the results in a database. The notification system uses this data to generate notification messages for rescue agencies, encouraging them to respond quickly.

[0942] Examples and prompts

[0943] For example, if a user reports that an earthquake has occurred, buildings have collapsed, and many people are injured, the system operates as follows:

[0944] 1. The user opens the web application program, inputs disaster information (including earthquake, current location, automatic detection, and situation details), and presses the send button.

[0945] 2. The central processing unit analyzes the received report data using generative artificial intelligence and natural language processing technology.

[0946] 3. Sentiment analysis obtains user emotion data using the following prompt sentence:

[0947] Prompt: "The user entered the following text: 'An earthquake occurred, buildings collapsed, and many people were injured.' Analyze the user's emotions (fear, stress) from this text."

[0948] 4. The generative AI evaluates the urgency of the report data using the following prompt:

[0949] Prompt: "Report data: {'disaster_type': 'Earthquake', 'location': 'Automatically detected location', 'details': 'A building has collapsed and many people are injured'} Rate the urgency of this data and calculate a priority."

[0950] 5. The notification system sends emergency notifications to rescue agencies based on the analysis results and emotion data.

[0951] This allows for more effective disaster response, since important report data, including the user's emotional information, can be promptly notified to the relevant rescue organizations.

[0952] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0953] Step 1:

[0954] The user launches the web application program, inputs the type of disaster, current location, details of the situation, and report information including images and videos, and presses the send button.

[0955] Input: User inputs disaster type, current location, situation details, and media files

[0956] Output: Serialized message data sent to the central processor

[0957] Step 2:

[0958] The user terminal sends the reported data to the central processing unit, which receives the data as an HTTP POST request.

[0959] Input: Report data sent from the user terminal

[0960] Output: Received data stored in the central processing unit

[0961] Step 3:

[0962] The central processing unit analyzes the received report data using generative artificial intelligence and natural language processing technology, particularly to determine the urgency and authenticity of the report content.

[0963] Input: Report data stored in the central processing unit

[0964] Output: Analyzed report data (including urgency rating and truth rating)

[0965] Specific operation: Generative AI uses natural language processing technology to analyze text data and determine the urgency and authenticity of the report.

[0966] Step 4:

[0967] The central processing unit performs sentiment analysis to extract emotional data, determines the emotional state from the text and voice data entered by the user, and performs sentiment analysis using specific prompt sentences.

[0968] Input: Text or voice data in the report data

[0969] Output: User's emotional data (e.g., stress level, fear level)

[0970] Specific behavior: The emotion engine uses the prompt "Text entered by the user: 'Specific content' Analyze the user's emotion (fear, stress) from this text."

[0971] Step 5:

[0972] The central processing unit generates a notification message based on the evaluated notification information and emotion data, and sends high-urgency notifications to relevant rescue organizations on a priority basis.

[0973] Input: Analyzed report data and emotion data

[0974] Output: Message to notify rescue agencies

[0975] Specific operation: The notification system evaluates the urgency of the notification using the prompt "Report data: {'disaster_type': 'Earthquake', 'location': 'Automatically detected location', 'details': 'Specific content'} Evaluate the urgency of this data and calculate the priority." and generates a notification message.

[0976] This allows important report data, including the user's emotional information, to be promptly notified to relevant rescue organizations, enabling effective disaster response.

[0977] 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.

[0978] 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.

[0979] 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.

[0980] [Third embodiment]

[0981] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0982] 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.

[0983] 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).

[0984] 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.

[0985] 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.

[0986] 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).

[0987] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0988] 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.

[0989] 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.

[0990] 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.

[0991] 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.

[0992] 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."

[0993] Overall overview

[0994] This invention is a system that realizes fast and accurate reporting during disasters by migrating the reporting system from telephone lines to a web system and utilizing generative artificial intelligence (AI) and natural language processing (NLP) technology. This is expected to result in efficient reporting during disasters, accelerating rescue operations and improving the effectiveness of lifesaving.

[0995] System Configuration

[0996] This system consists of the following main elements:

[0997] 1. User Device

[0998] 2. Web Server

[0999] 3. Generative AI and Natural Language Processing Server

[1000] 4. Notification system for rescue agencies

[1001] DETAILED DESCRIPTION OF THE EMBODIMENTS

[1002] 1. Reporting via user terminal

[1003] A user accesses a web application and logs in by entering their authentication information.

[1004] After logging in, the user fills in the necessary information in the form to make a report.

[1005] Type of disaster (e.g. earthquake, fire)

[1006] Current location (auto-detect or manual input)

[1007] Details of the situation (free description)

[1008] Images and videos (optional)

[1009] When the user enters the report content and clicks the "Send" button, the data is serialized and sent to the web server.

[1010] 2. Data reception by the web server

[1011] The web server receives the data as an HTTP POST request and passes it to a generative artificial intelligence and natural language processing server for analysis.

[1012] The server has mechanisms for securely receiving and storing data.

[1013] 3. Data analysis using generative artificial intelligence and natural language processing

[1014] The received data is analyzed using generative artificial intelligence and natural language processing technology to determine its authenticity.

[1015] The report content is analyzed in detail using natural language processing, and the reliability of the content is evaluated.

[1016] The data whose authenticity has been determined is stored in a database.

[1017] Duplicate checking and filtering of data also occurs at this stage.

[1018] 4. Notifying rescue agencies

[1019] Once the authenticity has been determined, the data is automatically communicated to the relevant rescue agencies.

[1020] Notifications are generated using messages based on the parsed data.

[1021] Example: "Emergency call: Earthquake occurred at point A. Situation: Building collapsed, injured."

[1022] Notifications are sent simultaneously to multiple rescue agencies, allowing for a rapid response.

[1023] Specific examples

[1024] As a concrete example, consider the occurrence of an earthquake.

[1025] When a user confirms that an earthquake has occurred, they open the web application and log in.

[1026] The user inputs "earthquake," "current location (automatically detected)," and "details of the situation (buildings have collapsed and many injured)," and presses the send button.

[1027] The user terminal transmits this data to the web server.

[1028] The server receives the data and uses generative artificial intelligence and natural language processing technology to analyze it, determine its authenticity, and perform duplicate checking and filtering.

[1029] The server sends notifications to relevant rescue agencies based on the analysis results.

[1030] Rescue agencies are notified and rush to the scene.

[1031] In this way, the system will streamline reporting during disasters and enable rapid rescue operations.

[1032] The processing flow will be explained below.

[1033] Step 1:

[1034] A user accesses the web application. The user opens a browser and logs in to the disaster notification system website. The user enters their authentication information (username and password) and presses the login button.

[1035] Step 2:

[1036] The user opens the report form. After logging in, the user clicks the "Report" button to open a form for entering disaster information. The user enters the following items:

[1037] Type of disaster (e.g. earthquake, fire)

[1038] Current location (auto-detect or manual input)

[1039] Details of the situation (free description)

[1040] Images and videos (optional)

[1041] Step 3:

[1042] The user submits the input data. The user enters the necessary information into the report form and clicks the "Submit" button. This causes the device to serialize the input data and send it to the server.

[1043] Step 4:

[1044] The device sends the serialized data to the web server as an HTTP POST request. The data includes the type of disaster, current location, details of the situation, and images and videos.

[1045] Step 5:

[1046] The server receives the data. The server parses the received HTTP POST request and extracts the data. The server prepares the received data to be passed to the generative artificial intelligence and natural language processing server.

[1047] Step 6:

[1048] The server analyzes the data. The received data is then analyzed using generative artificial intelligence and natural language processing technology. Natural language processing analyzes the report in detail and evaluates its reliability. The generative artificial intelligence determines whether the data is true or false, and the results are stored in a database.

[1049] Step 7:

[1050] The server checks for duplicate reports and filters them. The server checks against existing data in the database to see if there are any duplicate reports with the same content. It also filters out false or unnecessary information.

[1051] Step 8:

[1052] The server sends a notification to the rescue organization. Based on the truth-checked and filtered data, the server generates a notification message to the relevant rescue organization. The notification message contains the parsed data.

[1053] Step 9:

[1054] The server sends a message to the rescue organization. The server then sends the generated notification message to multiple related rescue organizations, enabling a rapid response. The notification message includes the type of disaster, location, and details of the situation.

[1055] Step 10:

[1056] The user can view the call history. The user can later access the web application and view the call history they have sent. The history includes the call date, type of disaster, and details of the situation.

[1057] Example 1

[1058] 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."

[1059] Conventional disaster notification systems transmit information over telephone lines, making it difficult to transmit information quickly when communication lines are congested or multiple reports are made simultaneously, making them unsuitable for disasters that require immediate response. They are also prone to human error and delays in information transmission. Furthermore, they lack a mechanism for determining the authenticity of reports, which can sometimes prevent rescue agencies from responding appropriately. This can result in delays and reduced efficiency in rescue operations, hindering the ability to save lives. To address these issues, it is necessary to provide a system that can transmit disaster notifications more efficiently and quickly, and that can properly determine information and check for duplication.

[1060] 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.

[1061] In this invention, the server includes means for reporting disaster information using a user terminal, means for transmitting the reported information to the server via the Internet, means for analyzing the information received by the server in detail using generative artificial intelligence and natural language processing to determine the authenticity of the information, means for checking for duplication and filtering the determined information and storing highly reliable information in a database, and means for notifying rescue organizations of a notification message generated based on the determined information. This enables quick and accurate information transmission and analysis in the event of a disaster, thereby realizing efficient and rapid rescue operations.

[1062] A "user terminal" is an electronic device used by a user to report disaster information.

[1063] A "web application" is software that users access via the Internet to input and send disaster information.

[1064] The "server" is a central processing unit that analyzes received disaster information and notifies rescue organizations.

[1065] "Generative AI" is a type of AI technology used to analyze received information and determine its authenticity.

[1066] "Natural language processing" is a technology for analyzing text data and understanding its meaning and intent.

[1067] The "Internet" is a global network for communicating data between user terminals and servers.

[1068] "Duplicate check" is a process for detecting duplication when the same or similar information is reported multiple times.

[1069] "Filtering" is a process for removing unnecessary or inaccurate information and extracting reliable information.

[1070] A "database" is a data management system that stores analyzed information for later reference.

[1071] A "notification message" is a message that is generated based on the determined disaster information and sent to rescue organizations.

[1072] "Rescue organization" means an organization or agency that carries out rescue operations in the event of a disaster.

[1073] The present invention provides a notification system for use in disaster situations, which utilizes the Internet and the latest artificial intelligence technology to enable rapid and accurate information transmission. How this system is implemented will be explained below.

[1074] Reporting via user terminal

[1075] Users use a user device such as a smartphone, tablet, or PC to access the web application. After logging in by entering their authentication information, they can access a form for entering disaster information. The form includes fields for the type of disaster (e.g., earthquake, fire), current location (automatic detection or manual entry), details of the situation (free text), and the ability to upload images and videos. After the user enters the required information and clicks the "Submit" button, the data is serialized and sent to the web server.

[1076] Data reception by the web server

[1077] The server receives data sent from the user terminal as an HTTP POST request. The received data is then forwarded to the generative artificial intelligence and natural language processing server for analysis. The server is equipped with security functions to ensure the safety of the received data.

[1078] Data analysis using generative artificial intelligence and natural language processing

[1079] The server analyzes the received data using generative artificial intelligence (e.g., GPT-4) and natural language processing technology (e.g., SpaCy). Through this analysis, it evaluates the authenticity of disaster information and determines its reliability. It also checks for duplication and filters the data to remove duplicate or unreliable information. Through this process, highly reliable data is stored in the database.

[1080] Notifying rescue agencies

[1081] The server generates a notification message based on the determined truthfulness of the information. The generated notification message is then sent to the relevant rescue organizations. The notification is sent simultaneously to multiple rescue organizations via a messaging API (e.g., Twilio) to enable a rapid response. An example of a notification message is "Emergency call: Earthquake occurred at location A. Situation: Building collapsed, injured."

[1082] Specific examples

[1083] As a concrete example, consider the processing flow when an earthquake occurs. The user confirms the earthquake, accesses the web application, and logs in. Next, they enter "earthquake," "current location (automatically detected)," and "details of the situation (a building has collapsed and many injured people)" and press the send button. The user's device sends this data to the web server. The server receives the data and uses generative artificial intelligence and natural language processing technology to analyze it, determine its authenticity, and perform duplication checks and filtering. The server then sends a notification to the relevant rescue organizations based on the analysis results. The rescue organizations receive the notification and rush to the scene.

[1084] Prompt Sentence Examples

[1085] "An earthquake has occurred. Buildings have collapsed and many people are injured. Rescue is needed."

[1086] In this way, the present invention provides a system that makes reporting during disasters more efficient and supports rapid and accurate rescue operations.

[1087] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1088] Step 1:

[1089] A user accesses a web application and logs in by entering their credentials.

[1090] Specifically, a user opens a browser, enters a URL to access the login page of a web application, enters a username and password, and clicks the "Login" button.

[1091] Input details: Authentication information (user name, password)

[1092] Output: Authentication result, redirect to dashboard

[1093] Step 2:

[1094] After logging in, the user enters the necessary information into the report form.

[1095] Specifically, users access the form, select the type of disaster from a drop-down menu, press a button to automatically detect their "current location" or enter it manually, write details about the situation in the text box, and upload images and videos if necessary.

[1096] Input information: type of disaster, current location, details of the situation, images and videos

[1097] Output content: Input data confirmation screen

[1098] Step 3:

[1099] When the user clicks the "Submit" button, the input data is serialized and sent to the web server.

[1100] Specifically, when you click the "Submit" button, the form data is converted to JSON format and sent to the server as an HTTP POST request.

[1101] Input: Clicking the submit button, serialized data

[1102] Output: HTTP POST request to the server

[1103] Step 4:

[1104] The server receives the HTTP POST request sent from the user terminal, analyzes the received data, and forwards it to the generative artificial intelligence and natural language processing server.

[1105] Specifically, the server parses the JSON data in the request body and extracts the type of disaster, current location, details of the situation, and images and videos. This data is then transferred to the generative artificial intelligence and natural language processing server via a dedicated API.

[1106] Input: HTTP POST request, serialized data

[1107] Output contents: Analysis results, data transferred to generative artificial intelligence and natural language processing servers

[1108] Step 5:

[1109] Generative artificial intelligence and natural language processing servers analyze the received data and determine its authenticity.

[1110] Specifically, it uses generative artificial intelligence (e.g., GPT-4) and natural language processing (e.g., SpaCy) to analyze text content and evaluate the reliability and authenticity of information. It also checks for duplicates and filters out unreliable information.

[1111] Input information: type of disaster, current location, details of the situation, images and videos

[1112] Output contents: True / false judgment results, filtered data

[1113] Step 6:

[1114] The server stores reliable data based on the analysis results in a database.

[1115] Specifically, it uses a query to compare the data with existing records in the database, filters out duplicates, and then stores the newly parsed data in the database.

[1116] Input: Filtered data

[1117] Output contents: Results stored in the database

[1118] Step 7:

[1119] The server generates a notification message based on the information whose truth or falsity has been determined.

[1120] Specifically, the system inserts the analyzed data into an automatically generated message template, generating a message such as "Emergency call: Earthquake occurred at point A. Situation: Building collapsed, injured."

[1121] Input: Filtered data

[1122] Output content: Notification message

[1123] Step 8:

[1124] The server sends a notification message to the relevant rescue agency.

[1125] Specifically, notification messages are sent simultaneously to multiple rescue agency contacts via a message sending API (e.g., Twilio).

[1126] Input content: Notification message

[1127] Output content: Notification result to rescue agency

[1128] In this way, the system processes disaster reports quickly and accurately, and notifies relevant rescue organizations appropriately, enabling prompt rescue operations.

[1129] (Application example 1)

[1130] 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."

[1131] Conventional disaster response systems mainly rely on telephone lines for reporting, which often hinders the accuracy of reports and the speed of rescue operations. Specifically, it is difficult to properly convey detailed information about the situation when reporting, and auxiliary information such as location information and images and videos of the scene is often lacking. This makes it difficult for rescue agencies to respond quickly and appropriately, resulting in a decrease in the efficiency of lifesaving efforts.

[1132] 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.

[1133] In this invention, the server includes means for reporting disaster information using a web application, means for transmitting the reported information to the server, means for analyzing the information received by the server using generative artificial intelligence and natural language processing to determine its authenticity, means for automatically acquiring location information of the user device, means for attaching and transmitting images and videos related to the disaster situation, and means for notifying rescue organizations based on the determined information. This enables the transmission of detailed report content including location information and images / videos and the rapid determination of authenticity by generative AI, enabling rescue organizations to respond quickly and accurately.

[1134] A "web application" is software that can be used by users over the Internet.

[1135] "Means for reporting disaster information" refers to an interface that allows users to report the situation when a disaster occurs.

[1136] A "server" is a computer system that processes and stores data on a network.

[1137] "Generative artificial intelligence" refers to artificial intelligence technology that has the ability to generate new information based on input data.

[1138] "Natural language processing" is a technology that uses computers to understand, analyze, and generate human language.

[1139] "Means for determining authenticity" refers to the process of analyzing and evaluating whether the reported information is correct.

[1140] "User terminal" refers to any device used by a user, including smartphones and tablets.

[1141] "Means for automatically obtaining location information" refers to a function that automatically obtains the user's current location using technology such as GPS.

[1142] "Means for attaching and sending images and videos related to the disaster situation" refers to a function that allows users to attach images and videos they have taken to the report and send them.

[1143] "Means of notification" refers to the process of contacting rescue organizations based on the analyzed information.

[1144] System Program

[1145] The system of this invention begins with a user reporting disaster information using a web application and sending it to a server. The server then analyzes the reported information using generative artificial intelligence and natural language processing to determine its authenticity. Next, the user's device automatically acquires location information and sends it along with images and videos of the disaster situation. Finally, the server notifies rescue organizations based on the determined information.

[1146] Hardware and software used

[1147] Hardware: smartphones, tablets, servers

[1148] Software: GPS module, Python, Geopy library, Requests library, generative AI model, natural language processing technology (NLP)

[1149] Natural language processing explanation

[1150] 1. Data transmission by user terminal

[1151] Users use their smartphones or tablets to report disaster information through a web application. At this time, they input the necessary information, such as the type of disaster, detailed situation, and current location. Location information is automatically obtained using a GPS module. Users can also attach images and videos showing the current state of the disaster within the app. This information is serialized and sent to the server via a secure communication channel.

[1152] 2. Data analysis by the server

[1153] The server analyzes the received information using generative artificial intelligence and natural language processing technology. Natural language processing understands the text entered by the user, and generative AI evaluates the veracity of the content. For example, if a report is made that "a building has collapsed and many people are injured," the AI ​​analyzes the context and evaluates its reliability.

[1154] 3. Notifying rescue agencies

[1155] Once the information has been determined to be true or false, it is automatically sent to rescue agencies by the server. This notification includes a specific message generated by the generative AI. For example, it could read, "Emergency call: An earthquake has occurred at the specified location. Situation: A building has collapsed and many people are injured. Please respond quickly."

[1156] Specific examples

[1157] As a concrete example, consider the occurrence of an earthquake. A user opens a web application on their smartphone, selects "earthquake," and enters "buildings have collapsed and many injured." Location information is automatically acquired via GPS, and images and videos are attached. This information is sent to a server, where it is analyzed and evaluated using generative AI and natural language processing technology. As a result, a notification is sent to rescue agencies stating, "Emergency call: An earthquake has occurred at the specified location. Situation: buildings have collapsed and many injured. Please respond quickly."

[1158] Prompt Sentence Examples

[1159] input

[1160] Disaster type: Earthquake

[1161] Details: Buildings collapsed, many injured

[1162] Location information: Automatically acquired (latitude and longitude)

[1163] Attachment: Images and videos of the disaster site

[1164] output

[1165] "Emergency message: Earthquake occurred at specified location. Situation: Building collapsed, many injured. Please respond quickly."

[1166] This allows for accurate and prompt reporting and response.

[1167] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1168] Step 1:

[1169] Users access the web application using a smartphone or tablet, access the disaster information reporting form, and enter the necessary information, such as the type of disaster, current location (automatically obtained), details of the situation, and images and videos.

[1170] input:

[1171] Types of disasters

[1172] Current location (automatically obtained by GPS)

[1173] Details of the situation

[1174] Images and videos

[1175] output:

[1176] Serialized report data

[1177] Specific behavior:

[1178] Converts information entered into a web form into a serialized format such as JSON and prepares it for transmission to the server.

[1179] Step 2:

[1180] The user device sends the processed disaster information to the server, where the data is sent using a secure communication protocol (such as HTTPS).

[1181] input:

[1182] Serialized report data

[1183] output:

[1184] Report data received by the server

[1185] Specific behavior:

[1186] The serialized data is sent to the server as an HTTPS request.

[1187] Step 3:

[1188] The server analyzes the received report data using generative artificial intelligence and natural language processing technology to determine its authenticity.

[1189] input:

[1190] Report data received by the server

[1191] output:

[1192] Data that has been judged to be true or false

[1193] Specific behavior:

[1194] It uses a natural language processing engine to analyze text data and uses generative AI to evaluate the reliability of the information.

[1195] Step 4:

[1196] The server performs duplication checks and filtering on the parsed data, eliminating redundant and meaningless information.

[1197] input:

[1198] Data that has been judged to be true or false

[1199] output:

[1200] Duplicate checked and filtered data

[1201] Specific behavior:

[1202] Matching data with existing data in the database to remove duplicate information and filtering out incomplete or unnecessary data.

[1203] Step 5:

[1204] The server then notifies rescue agencies based on the filtered data, with the notification being an emergency message generated by generative AI.

[1205] input:

[1206] Duplicate checked and filtered data

[1207] output:

[1208] Emergency message sent to rescue agencies

[1209] Specific behavior:

[1210] Generative AI models are used to generate appropriate emergency messages based on the content of the call and send them to relevant rescue agencies.

[1211] Step 6:

[1212] Rescue agencies will receive notifications and respond quickly, specifically by dispatching the necessary rescue teams and resources to the scene based on the notification message.

[1213] input:

[1214] Emergency message sent to rescue agencies

[1215] output:

[1216] Rapid response from rescue agencies

[1217] Specific behavior:

[1218] Rescue agencies analyze the messages they receive, determine the appropriate response, and quickly begin action.

[1219] This overall system processing flow enables faster reporting and more accurate information transmission in the event of a disaster, improving the efficiency of rescue operations.

[1220] 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.

[1221] Overall overview

[1222] This invention is a system that recognizes user emotions and evaluates the importance and prioritization of report data by combining an emotion engine with a disaster reporting system, thereby enabling high-urgency reports to be processed quickly and enabling effective rescue operations.

[1223] System Configuration

[1224] This system consists of the following main elements:

[1225] 1. User Device

[1226] 2. Web Server

[1227] 3. Generative AI and Natural Language Processing Server

[1228] 4. Emotion Engine

[1229] 5. Notification system for rescue agencies

[1230] DETAILED DESCRIPTION OF THE EMBODIMENTS

[1231] 1. Reporting via user terminal

[1232] A user accesses a web application and logs in by entering their authentication information.

[1233] After logging in, the user fills in the necessary information in the form to make a report.

[1234] Type of disaster (e.g. earthquake, fire)

[1235] Current location (auto-detect or manual input)

[1236] Details of the situation (free description)

[1237] Images and videos (optional)

[1238] When the user enters the report content and clicks the "Send" button, the data is serialized and sent to the web server.

[1239] 2. Data reception by the web server

[1240] The web server receives the data as an HTTP POST request and passes it to a generative artificial intelligence and natural language processing server for analysis.

[1241] The server prepares to pass the received data to the emotion engine.

[1242] 3. Data analysis using generative artificial intelligence and natural language processing

[1243] The received data is analyzed using generative artificial intelligence and natural language processing techniques.

[1244] The report content is analyzed in detail using natural language processing, and the reliability of the content is evaluated.

[1245] Generative artificial intelligence determines the truth or falsity of the data and stores the results in a database.

[1246] Duplicate checking and filtering of data also occurs at this stage.

[1247] 4. Emotion Recognition by Emotion Engine

[1248] The emotion engine analyzes the text and voice data sent by the user and recognizes the user's emotions.

[1249] The recognized emotion information is added to the message data and used to evaluate the importance of the message data.

[1250] 5. Notifying rescue agencies

[1251] Data that is rated as highly important by the emotion engine is processed with priority.

[1252] When a notification is sent to rescue agencies, the emotion information is included along with the analyzed data.

[1253] Specifically, the following notification message is generated:

[1254] Example: "Emergency call: Earthquake occurred at location A. Situation: Building collapsed, people injured. User stress level: High."

[1255] Notifications are sent simultaneously to multiple rescue agencies, allowing for a rapid response.

[1256] Specific examples

[1257] As a concrete example, consider the occurrence of an earthquake.

[1258] When a user confirms that an earthquake has occurred, they open the web application and log in.

[1259] The user inputs "earthquake," "current location (automatically detected)," and "details of the situation (buildings have collapsed and many injured)," and presses the send button.

[1260] The user terminal transmits this data to the web server.

[1261] The server receives the data and analyzes it using generative artificial intelligence and natural language processing techniques.

[1262] The emotion engine analyzes user input and voice data to recognize the user's stress level and emotions.

[1263] The server sends a notification to the relevant rescue organization based on the analysis results and the emotion information. The notification message includes the type of disaster, location, details of the situation, and the user's emotion information.

[1264] Rescue agencies are notified and rush to the scene.

[1265] In this way, this system improves the efficiency of reporting during disasters and enables rapid rescue operations by utilizing users' emotional information.

[1266] The processing flow will be explained below.

[1267] Step 1:

[1268] A user accesses a web application.

[1269] The user opens a browser on their personal computer or smartphone, accesses the disaster notification system website, and logs in. The user enters their authentication information (username and password) and presses the login button.

[1270] Step 2:

[1271] The user opens the report form.

[1272] After logging in, users click the "Report" button from the main menu to open a form for reporting disaster information. Users must enter the following information:

[1273] Type of disaster (e.g. earthquake, fire)

[1274] Current location (auto-detect or manual input)

[1275] Details of the situation (free description)

[1276] Images and videos (optional)

[1277] Step 3:

[1278] The user sends the notification data.

[1279] The user enters disaster information and clicks the "Send" button, which causes the device to serialize all the entered data and prepare it to be sent to the web server.

[1280] Step 4:

[1281] The device sends the data to the server.

[1282] The device sends the serialized data to the web server as an HTTP POST request, which includes the type of disaster, current location, details of the situation, and images and videos.

[1283] Step 5:

[1284] The server receives the data.

[1285] The server analyzes the received HTTP POST request and extracts data from each field. The analyzed data is then passed to the generative artificial intelligence and natural language processing server.

[1286] Step 6:

[1287] The server analyzes the data.

[1288] The received data is analyzed using generative artificial intelligence and natural language processing technology. Natural language processing analyzes the contents of the report in detail and evaluates its reliability. The generative artificial intelligence determines whether the data is true or false, and the results are stored in a database.

[1289] Step 7:

[1290] The server performs duplicate checking and filtering.

[1291] The server checks existing data in the database to ensure there are no duplicate reports with the same content, and also filters out false or unnecessary information.

[1292] Step 8:

[1293] The server passes the data to the emotion engine.

[1294] The server passes the received text and voice data to the emotion engine for analysis, which analyzes the user's emotions.

[1295] Step 9:

[1296] The emotion engine recognizes the user's emotions.

[1297] The emotion engine analyzes the data sent by the user and evaluates the user's emotions, especially their stress level. The recognized emotion information is added to the report data.

[1298] Step 10:

[1299] The server sends a notification to the rescue agency.

[1300] Data that is evaluated as having high importance by the emotion engine is processed with priority.The server generates notification messages to relevant rescue organizations based on the analyzed data and emotion information.

[1301] Step 11:

[1302] The server sends a message to a rescue agency.

[1303] The server then sends the generated notification message to multiple related rescue organizations. The notification message includes the type of disaster, location, details of the situation, and the user's emotional state, allowing rescue organizations to respond to the scene quickly.

[1304] Step 12:

[1305] The user checks the report history.

[1306] Users can later revisit the web application and view the history of their submitted alerts, including the alert date, type of incident, situation details, and any attached emotional information.

[1307] Example 2

[1308] 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."

[1309] Conventional disaster reporting systems have difficulty in quickly determining the urgency of reports, and when many reports are received at the same time, important reports are buried. In addition, because they do not take into account the emotional information of the caller, it is difficult to accurately grasp situations with a high level of urgency.

[1310] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for analyzing received information using generative artificial intelligence and natural language processing to determine whether the information is true or false, a means for evaluating the importance of the report data based on the determined information and the user's emotional information, and a means for notifying a rescue organization based on the evaluated information. This makes it possible to evaluate the urgency of the report content with high accuracy and quickly notify an appropriate rescue organization.

[1311] A "web application" is software that runs on a web browser and can be accessed by users via the Internet.

[1312] "Disaster information" refers to detailed information about disasters such as earthquakes, fires, and floods reported by users.

[1313] "Reporting" is the act of a user providing disaster information through a web application.

[1314] A "server" is a computer system that receives, processes, and stores data from user terminals over a network.

[1315] "Generative artificial intelligence" is a technology that uses algorithms based on machine learning and deep learning to generate and analyze new data and patterns.

[1316] "Natural language processing" is the technology that enables computers to understand, interpret, and generate human language.

[1317] "Authenticity assessment" is the process of determining the accuracy and reliability of the information provided.

[1318] "Evaluating the importance of report data" is a process of determining how urgent the information is based on the disaster information provided and the user's emotional information.

[1319] "Notification" is the act of transmitting emergency information to relevant rescue organizations based on the evaluated information.

[1320] "Rescue agencies" are public institutions such as fire departments, police, and ambulance teams that respond to disasters.

[1321] "Emotional information" is data that indicates the emotional state (e.g., stress level or tension) that a user exhibits when making a report.

[1322] "Data duplication check" is a process to prevent multiple transmission of the same or similar report data.

[1323] "Filtering" is the process of eliminating irrelevant or erroneous information, leaving only the necessary data.

[1324] This invention is a system for realizing prompt and accurate reporting in the event of a disaster. This system analyzes disaster information and emotional information provided by users and evaluates the importance of the information, enabling prompt notification to rescue organizations.

[1325] System Configuration

[1326] This system consists of the following main elements:

[1327] 1. User Device

[1328] 2. Web Server

[1329] 3. Generative AI and Natural Language Processing Server

[1330] 4. Emotion Engine

[1331] 5. Notification system for rescue agencies

[1332] DETAILED DESCRIPTION OF THE EMBODIMENTS

[1333] 1. Report via user terminal:

[1334] Users access web applications using devices such as smartphones and personal computers.

[1335] Users log in by entering their authentication information (username and password), and then fill out a form with the type of disaster (e.g., earthquake, fire), their current location, details of the situation (such as the state of collapsed buildings), and images and videos (if necessary).

[1336] When the user presses the "Submit" button, the terminal serializes the entered data into JSON format and sends it to the web server using HTTPS.

[1337] 2. Data received by the web server:

[1338] The server receives the data sent from the user terminal as an HTTP POST request.

[1339] The server performs data integrity checks, filters out bad data, and temporarily stores the correct data in a database.

[1340] The received data is prepared to be passed to the generative artificial intelligence and natural language processing server for analysis, and also to the emotion engine.

[1341] 3. Data analysis using generative artificial intelligence and natural language processing:

[1342] The generative AI model analyzes the received data and determines the reliability and authenticity of the report.

[1343] Using natural language processing technology, key points from the report are extracted and the urgency of the disaster is assessed.

[1344] The AI ​​model stores the results in a database and performs duplicate checking and filtering of the data.

[1345] The server prepares to pass the analysis results to the emotion engine.

[1346] 4. Emotion Recognition with Emotion Engine:

[1347] The emotion engine receives the user's text data and voice data and uses emotion analysis algorithms to recognize the user's emotions.

[1348] The recognized emotion information is added to the message data and used to evaluate the importance of the message data.

[1349] 5. Notification to rescue agencies:

[1350] The server prioritizes processing of data that is evaluated as having high importance by the emotion engine.

[1351] The server generates a notification message containing the analysis results and emotion information and sends it to the relevant rescue organization. Specifically, a notification such as "Emergency call: Earthquake occurred at point A. Situation: Building collapse, many injured. User's stress level: High" is generated.

[1352] Rescue agencies are notified and rush to the scene.

[1353] Specific examples

[1354] As a concrete example, consider the occurrence of an earthquake.

[1355] The user sees the earthquake, opens the web application and logs in.

[1356] The user inputs "earthquake," "current location (automatically detected)," and "details of the situation (buildings have collapsed and many injured)," and then presses the send button.

[1357] The user terminal transmits this data to the web server.

[1358] A server receives the data and analyzes it using generative artificial intelligence and natural language processing.

[1359] The emotion engine analyzes the user's input data and voice data to recognize the user's stress level and emotions.

[1360] The server sends a notification to the relevant rescue organizations based on the analysis results and emotion information. The notification message includes the type of disaster, location, details of the situation, and the user's emotion information.

[1361] Rescue agencies are notified and rush to the scene.

[1362] Prompt Sentence Examples

[1363] Enter the following prompt into the generative AI model:

[1364] "Analyze the report data, recognize the user's emotions, and generate a notification message that includes the type of disaster, current location, details of the situation, and the user's stress level."

[1365] As described above, the system of the present invention improves the efficiency of disaster reporting in emergencies and supports rapid and effective rescue operations by utilizing user emotional information.

[1366] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1367] Step 1:

[1368] When a user confirms a disaster, they access the web application from their device, such as a smartphone or PC. They log in by entering their authentication information (e.g., username and password). After logging in, they enter the following information into the reporting form:

[1369] Type of disaster (e.g. earthquake, fire)

[1370] Current location (automatically detected using the device's GPS function or manually entered)

[1371] Details of the situation (e.g., a building has collapsed and many people are injured)

[1372] Images and videos (optional attachments available)

[1373] The user enters all the required information and clicks the "Submit" button. At this time, the user's device serializes the entered data in JSON format and sends it to the web server using HTTPS. The input is the report content (text, image, location information), and the output is the data to be sent to the web server.

[1374] Step 2:

[1375] The server receives data sent from the user terminal as an HTTP POST request. First, the server checks the integrity of the received data and filters out incomplete or bad data. Data that has been confirmed to be consistent is temporarily stored in a database. The input is the JSON data sent by the user, and the output is the data whose integrity has been confirmed.

[1376] Step 3:

[1377] The server passes the received data to a generative artificial intelligence and natural language processing server. The generative AI model analyzes the received data and determines the reliability and authenticity of the report content. Natural language processing technology is used to extract important keywords from the report text and analyze its content. Data duplication checks and filtering are also performed. The input is data whose consistency has been confirmed, and the output is the analysis results and data with duplicates removed.

[1378] Step 4:

[1379] The server passes the analysis results to the emotion engine. The emotion engine receives the user's text data and voice data and uses an emotion analysis algorithm to recognize the user's emotions. It analyzes the user's language and sentence tone to evaluate stress levels and fear. The input is the analyzed data, and the output is data with emotional information added.

[1380] Step 5:

[1381] The server evaluates the importance of the message data to which emotional information has been added. Data that has been evaluated as having a high importance by the emotion engine is processed preferentially. The input is data to which emotional information has been added, and the output is data whose importance has been evaluated.

[1382] Step 6:

[1383] The server generates a notification message based on the evaluated data. Specifically, it may have a message such as "Emergency call: An earthquake has occurred at point A. Situation: Building collapsed, many injured. User stress level: High." The generated notification message is sent to the relevant rescue agencies (fire department, police, ambulance, etc.). The input is the data whose importance has been evaluated, and the output is the generated notification message.

[1384] Step 7:

[1385] Rescue agencies receive notifications and initiate actions to respond quickly based on the notification content. The input is a notification message sent from the server, and the output is the initiation of rescue operations.

[1386] (Application example 2)

[1387] 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."

[1388] Conventional disaster reporting systems have difficulty prioritizing reports, resulting in the inability to process reports of particularly high urgency quickly. Furthermore, because the report data is evaluated without taking into account the caller's emotions or stress level, the efficiency of rescue operations can be reduced. Therefore, there is a need for a system that can appropriately determine which reports are of high urgency and carry out prompt and effective rescue operations.

[1389] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing the message content and emotions, extracting and evaluating emotional data, means for analyzing the message content and determining its authenticity using generative artificial intelligence and natural language processing, and means for notifying a rescue organization based on the evaluated message information and emotional data. This makes it possible to accurately evaluate the urgency of the message content and prioritize calls of particularly high importance. Furthermore, utilizing the caller's emotional information improves the speed and effectiveness of rescue operations.

[1390] A "web application program" is software that can be accessed via the Internet and is a means by which users can report disaster information.

[1391] The "central processing unit" is a computer server that analyzes the received data and performs the necessary processing.

[1392] "Generative AI" is an AI technology that can analyze data patterns and generate new information.

[1393] "Natural language processing" is a technology for analyzing text and voice data entered by a user and understanding its content.

[1394] "Sentiment analysis" is the process of determining emotions and stress levels from user-entered text and voice data.

[1395] "Emotion data" is information that indicates the emotional state of the user extracted by emotion analysis.

[1396] "Report data" refers to information such as text, audio, images, and video that a user inputs when reporting disaster information.

[1397] "Rescue agency" refers to an organization or unit that responds when a disaster occurs.

[1398] "Duplicate check" is a process for identifying identical or similar notification data and preventing it from being sent again.

[1399] "Filtering" is the process of removing unnecessary data from received report data and extracting only the necessary information.

[1400] "Prioritization" is the process of determining the priority of rescue operations based on call data and sentiment data.

[1401] Overall system overview

[1402] The present invention is a disaster notification system consisting of a web application program, a central processing unit, generative artificial intelligence, natural language processing, emotion analysis, and a system for notifying rescue organizations. This system allows users to quickly and appropriately report disaster information, which is then analyzed and notified to the necessary rescue organizations.

[1403] System Configuration

[1404] The following are the main elements that make up the system:

[1405] Web Application Program

[1406] Users report disaster information through a web application program, which includes the type of disaster, current location, details of the situation, and the ability to attach images and videos. Once the user enters the content of the report and presses the send button, the information is sent to the central processing unit.

[1407] central processing unit

[1408] The central processing unit centrally manages the report data received from users. This unit uses generative artificial intelligence and natural language processing technology to analyze the report data and determine its authenticity. It also has the function of performing emotion analysis, extracting and evaluating emotional data.

[1409] Generative Artificial Intelligence and Natural Language Processing

[1410] Generative AI can analyze patterns in reports and generate new information. It uses natural language processing technology to understand the meaning of text and voice data entered by users and evaluate its reliability.

[1411] Emotion analysis

[1412] Sentiment analysis evaluates the user's emotional state from text and voice data entered by the user, and this emotional data is sent to the notification system along with the notification data.

[1413] Notification System

[1414] The notification system uses generative artificial intelligence and sentiment analysis to evaluate call data and then notify relevant rescue agencies. The notification includes the urgency of the call data and the user's emotional state.

[1415] Program operation explanation

[1416] This system uses the following hardware and software:

[1417] Hardware: Smartphones, computer servers

[1418] Software: Python, Flask (web framework), emotion recognition model, natural language processing (NLP) model

[1419] The central processing unit analyzes the data received from users and performs sentiment analysis. The generative AI evaluates the urgency of the call and stores the results in a database. The notification system uses this data to generate notification messages for rescue agencies, encouraging them to respond quickly.

[1420] Examples and prompts

[1421] For example, if a user reports that an earthquake has occurred, buildings have collapsed, and many people are injured, the system operates as follows:

[1422] 1. The user opens the web application program, inputs disaster information (including earthquake, current location, automatic detection, and situation details), and presses the send button.

[1423] 2. The central processing unit analyzes the received report data using generative artificial intelligence and natural language processing technology.

[1424] 3. Sentiment analysis obtains user emotion data using the following prompt sentence:

[1425] Prompt: "The user entered the following text: 'An earthquake occurred, buildings collapsed, and many people were injured.' Analyze the user's emotions (fear, stress) from this text."

[1426] 4. The generative AI evaluates the urgency of the report data using the following prompt:

[1427] Prompt: "Report data: {'disaster_type': 'Earthquake', 'location': 'Automatically detected location', 'details': 'A building has collapsed and many people are injured'} Rate the urgency of this data and calculate a priority."

[1428] 5. The notification system sends emergency notifications to rescue agencies based on the analysis results and emotion data.

[1429] This allows for more effective disaster response, since important report data, including the user's emotional information, can be promptly notified to the relevant rescue organizations.

[1430] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1431] Step 1:

[1432] The user launches the web application program, inputs the type of disaster, current location, details of the situation, and report information including images and videos, and presses the send button.

[1433] Input: User inputs disaster type, current location, situation details, and media files

[1434] Output: Serialized message data sent to the central processor

[1435] Step 2:

[1436] The user terminal sends the reported data to the central processing unit, which receives the data as an HTTP POST request.

[1437] Input: Report data sent from the user terminal

[1438] Output: Received data stored in the central processing unit

[1439] Step 3:

[1440] The central processing unit analyzes the received report data using generative artificial intelligence and natural language processing technology, particularly to determine the urgency and authenticity of the report content.

[1441] Input: Report data stored in the central processing unit

[1442] Output: Analyzed report data (including urgency rating and truth rating)

[1443] Specific operation: Generative AI uses natural language processing technology to analyze text data and determine the urgency and authenticity of the report.

[1444] Step 4:

[1445] The central processing unit performs sentiment analysis to extract emotional data, determines the emotional state from the text and voice data entered by the user, and performs sentiment analysis using specific prompt sentences.

[1446] Input: Text or voice data in the report data

[1447] Output: User's emotional data (e.g., stress level, fear level)

[1448] Specific behavior: The emotion engine uses the prompt "Text entered by the user: 'Specific content' Analyze the user's emotion (fear, stress) from this text."

[1449] Step 5:

[1450] The central processing unit generates a notification message based on the evaluated notification information and emotion data, and sends high-urgency notifications to relevant rescue organizations on a priority basis.

[1451] Input: Analyzed report data and emotion data

[1452] Output: Message to notify rescue agencies

[1453] Specific operation: The notification system evaluates the urgency of the notification using the prompt "Report data: {'disaster_type': 'Earthquake', 'location': 'Automatically detected location', 'details': 'Specific content'} Evaluate the urgency of this data and calculate the priority." and generates a notification message.

[1454] This allows important report data, including the user's emotional information, to be promptly notified to relevant rescue organizations, enabling effective disaster response.

[1455] 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.

[1456] 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.

[1457] 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.

[1458] [Fourth embodiment]

[1459] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1460] 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.

[1461] 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).

[1462] 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.

[1463] 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.

[1464] 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).

[1465] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1466] 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.

[1467] 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.

[1468] 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.

[1469] 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.

[1470] 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.

[1471] 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."

[1472] Overall overview

[1473] This invention is a system that realizes fast and accurate reporting during disasters by migrating the reporting system from telephone lines to a web system and utilizing generative artificial intelligence (AI) and natural language processing (NLP) technology. This is expected to result in efficient reporting during disasters, accelerating rescue operations and improving the effectiveness of lifesaving.

[1474] System Configuration

[1475] This system consists of the following main elements:

[1476] 1. User Device

[1477] 2. Web Server

[1478] 3. Generative AI and Natural Language Processing Server

[1479] 4. Notification system for rescue agencies

[1480] DETAILED DESCRIPTION OF THE EMBODIMENTS

[1481] 1. Reporting via user terminal

[1482] A user accesses a web application and logs in by entering their authentication information.

[1483] After logging in, the user fills in the necessary information in the form to make a report.

[1484] Type of disaster (e.g. earthquake, fire)

[1485] Current location (auto-detect or manual input)

[1486] Details of the situation (free description)

[1487] Images and videos (optional)

[1488] When the user enters the report content and clicks the "Send" button, the data is serialized and sent to the web server.

[1489] 2. Data reception by the web server

[1490] The web server receives the data as an HTTP POST request and passes it to a generative artificial intelligence and natural language processing server for analysis.

[1491] The server has mechanisms for securely receiving and storing data.

[1492] 3. Data analysis using generative artificial intelligence and natural language processing

[1493] The received data is analyzed using generative artificial intelligence and natural language processing technology to determine its authenticity.

[1494] The report content is analyzed in detail using natural language processing, and the reliability of the content is evaluated.

[1495] The data whose authenticity has been determined is stored in a database.

[1496] Duplicate checking and filtering of data also occurs at this stage.

[1497] 4. Notifying rescue agencies

[1498] Once the authenticity has been determined, the data is automatically communicated to the relevant rescue agencies.

[1499] Notifications are generated using messages based on the parsed data.

[1500] Example: "Emergency call: Earthquake occurred at point A. Situation: Building collapsed, injured."

[1501] Notifications are sent simultaneously to multiple rescue agencies, allowing for a rapid response.

[1502] Specific examples

[1503] As a concrete example, consider the occurrence of an earthquake.

[1504] When a user confirms that an earthquake has occurred, they open the web application and log in.

[1505] The user inputs "earthquake," "current location (automatically detected)," and "details of the situation (buildings have collapsed and many injured)," and presses the send button.

[1506] The user terminal transmits this data to the web server.

[1507] The server receives the data and uses generative artificial intelligence and natural language processing technology to analyze it, determine its authenticity, and perform duplicate checking and filtering.

[1508] The server sends notifications to relevant rescue agencies based on the analysis results.

[1509] Rescue agencies are notified and rush to the scene.

[1510] In this way, the system will streamline reporting during disasters and enable rapid rescue operations.

[1511] The processing flow will be explained below.

[1512] Step 1:

[1513] A user accesses the web application. The user opens a browser and logs in to the disaster notification system website. The user enters their authentication information (username and password) and presses the login button.

[1514] Step 2:

[1515] The user opens the report form. After logging in, the user clicks the "Report" button to open a form for entering disaster information. The user enters the following items:

[1516] Type of disaster (e.g. earthquake, fire)

[1517] Current location (auto-detect or manual input)

[1518] Details of the situation (free description)

[1519] Images and videos (optional)

[1520] Step 3:

[1521] The user submits the input data. The user enters the necessary information into the report form and clicks the "Submit" button. This causes the device to serialize the input data and send it to the server.

[1522] Step 4:

[1523] The device sends the serialized data to the web server as an HTTP POST request. The data includes the type of disaster, current location, details of the situation, and images and videos.

[1524] Step 5:

[1525] The server receives the data. The server parses the received HTTP POST request and extracts the data. The server prepares the received data to be passed to the generative artificial intelligence and natural language processing server.

[1526] Step 6:

[1527] The server analyzes the data. The received data is then analyzed using generative artificial intelligence and natural language processing technology. Natural language processing analyzes the report in detail and evaluates its reliability. The generative artificial intelligence determines whether the data is true or false, and the results are stored in a database.

[1528] Step 7:

[1529] The server checks for duplicate reports and filters them. The server checks against existing data in the database to see if there are any duplicate reports with the same content. It also filters out false or unnecessary information.

[1530] Step 8:

[1531] The server sends a notification to the rescue organization. Based on the truth-checked and filtered data, the server generates a notification message to the relevant rescue organization. The notification message contains the parsed data.

[1532] Step 9:

[1533] The server sends a message to the rescue organization. The server then sends the generated notification message to multiple related rescue organizations, enabling a rapid response. The notification message includes the type of disaster, location, and details of the situation.

[1534] Step 10:

[1535] The user can view the call history. The user can later access the web application and view the call history they have sent. The history includes the call date, type of disaster, and details of the situation.

[1536] Example 1

[1537] 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."

[1538] Conventional disaster notification systems transmit information over telephone lines, making it difficult to transmit information quickly when communication lines are congested or multiple reports are made simultaneously, making them unsuitable for disasters that require immediate response. They are also prone to human error and delays in information transmission. Furthermore, they lack a mechanism for determining the authenticity of reports, which can sometimes prevent rescue agencies from responding appropriately. This can result in delays and reduced efficiency in rescue operations, hindering the ability to save lives. To address these issues, it is necessary to provide a system that can transmit disaster notifications more efficiently and quickly, and that can properly determine information and check for duplication.

[1539] 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.

[1540] In this invention, the server includes means for reporting disaster information using a user terminal, means for transmitting the reported information to the server via the Internet, means for analyzing the information received by the server in detail using generative artificial intelligence and natural language processing to determine the authenticity of the information, means for checking for duplication and filtering the determined information and storing highly reliable information in a database, and means for notifying rescue organizations of a notification message generated based on the determined information. This enables quick and accurate information transmission and analysis in the event of a disaster, thereby realizing efficient and rapid rescue operations.

[1541] A "user terminal" is an electronic device used by a user to report disaster information.

[1542] A "web application" is software that users access via the Internet to input and send disaster information.

[1543] The "server" is a central processing unit that analyzes received disaster information and notifies rescue organizations.

[1544] "Generative AI" is a type of AI technology used to analyze received information and determine its authenticity.

[1545] "Natural language processing" is a technology for analyzing text data and understanding its meaning and intent.

[1546] The "Internet" is a global network for communicating data between user terminals and servers.

[1547] "Duplicate check" is a process for detecting duplication when the same or similar information is reported multiple times.

[1548] "Filtering" is a process for removing unnecessary or inaccurate information and extracting reliable information.

[1549] A "database" is a data management system that stores analyzed information for later reference.

[1550] A "notification message" is a message that is generated based on the determined disaster information and sent to rescue organizations.

[1551] "Rescue organization" means an organization or agency that carries out rescue operations in the event of a disaster.

[1552] The present invention provides a notification system for use in disaster situations, which utilizes the Internet and the latest artificial intelligence technology to enable rapid and accurate information transmission. How this system is implemented will be explained below.

[1553] Reporting via user terminal

[1554] Users use a user device such as a smartphone, tablet, or PC to access the web application. After logging in by entering their authentication information, they can access a form for entering disaster information. The form includes fields for the type of disaster (e.g., earthquake, fire), current location (automatic detection or manual entry), details of the situation (free text), and the ability to upload images and videos. After the user enters the required information and clicks the "Submit" button, the data is serialized and sent to the web server.

[1555] Data reception by the web server

[1556] The server receives data sent from the user terminal as an HTTP POST request. The received data is then forwarded to the generative artificial intelligence and natural language processing server for analysis. The server is equipped with security functions to ensure the safety of the received data.

[1557] Data analysis using generative artificial intelligence and natural language processing

[1558] The server analyzes the received data using generative artificial intelligence (e.g., GPT-4) and natural language processing technology (e.g., SpaCy). Through this analysis, it evaluates the authenticity of disaster information and determines its reliability. It also checks for duplication and filters the data to remove duplicate or unreliable information. Through this process, highly reliable data is stored in the database.

[1559] Notifying rescue agencies

[1560] The server generates a notification message based on the determined truthfulness of the information. The generated notification message is then sent to the relevant rescue organizations. The notification is sent simultaneously to multiple rescue organizations via a messaging API (e.g., Twilio) to enable a rapid response. An example of a notification message is "Emergency call: Earthquake occurred at location A. Situation: Building collapsed, injured."

[1561] Specific examples

[1562] As a concrete example, consider the processing flow when an earthquake occurs. The user confirms the earthquake, accesses the web application, and logs in. Next, they enter "earthquake," "current location (automatically detected)," and "details of the situation (a building has collapsed and many injured people)" and press the send button. The user's device sends this data to the web server. The server receives the data and uses generative artificial intelligence and natural language processing technology to analyze it, determine its authenticity, and perform duplication checks and filtering. The server then sends a notification to the relevant rescue organizations based on the analysis results. The rescue organizations receive the notification and rush to the scene.

[1563] Prompt Sentence Examples

[1564] "An earthquake has occurred. Buildings have collapsed and many people are injured. Rescue is needed."

[1565] In this way, the present invention provides a system that makes reporting during disasters more efficient and supports rapid and accurate rescue operations.

[1566] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1567] Step 1:

[1568] A user accesses a web application and logs in by entering their credentials.

[1569] Specifically, a user opens a browser, enters a URL to access the login page of a web application, enters a username and password, and clicks the "Login" button.

[1570] Input details: Authentication information (user name, password)

[1571] Output: Authentication result, redirect to dashboard

[1572] Step 2:

[1573] After logging in, the user enters the necessary information into the report form.

[1574] Specifically, users access the form, select the type of disaster from a drop-down menu, press a button to automatically detect their "current location" or enter it manually, write details about the situation in the text box, and upload images and videos if necessary.

[1575] Input information: type of disaster, current location, details of the situation, images and videos

[1576] Output content: Input data confirmation screen

[1577] Step 3:

[1578] When the user clicks the "Submit" button, the input data is serialized and sent to the web server.

[1579] Specifically, when you click the "Submit" button, the form data is converted to JSON format and sent to the server as an HTTP POST request.

[1580] Input: Clicking the submit button, serialized data

[1581] Output: HTTP POST request to the server

[1582] Step 4:

[1583] The server receives the HTTP POST request sent from the user terminal, analyzes the received data, and forwards it to the generative artificial intelligence and natural language processing server.

[1584] Specifically, the server parses the JSON data in the request body and extracts the type of disaster, current location, details of the situation, and images and videos. This data is then transferred to the generative artificial intelligence and natural language processing server via a dedicated API.

[1585] Input: HTTP POST request, serialized data

[1586] Output contents: Analysis results, data transferred to generative artificial intelligence and natural language processing servers

[1587] Step 5:

[1588] Generative artificial intelligence and natural language processing servers analyze the received data and determine its authenticity.

[1589] Specifically, it uses generative artificial intelligence (e.g., GPT-4) and natural language processing (e.g., SpaCy) to analyze text content and evaluate the reliability and authenticity of information. It also checks for duplicates and filters out unreliable information.

[1590] Input information: type of disaster, current location, details of the situation, images and videos

[1591] Output contents: True / false judgment results, filtered data

[1592] Step 6:

[1593] The server stores reliable data based on the analysis results in a database.

[1594] Specifically, it uses a query to compare the data with existing records in the database, filters out duplicates, and then stores the newly parsed data in the database.

[1595] Input: Filtered data

[1596] Output contents: Results stored in the database

[1597] Step 7:

[1598] The server generates a notification message based on the information whose truth or falsity has been determined.

[1599] Specifically, the system inserts the analyzed data into an automatically generated message template, generating a message such as "Emergency call: Earthquake occurred at point A. Situation: Building collapsed, injured."

[1600] Input: Filtered data

[1601] Output content: Notification message

[1602] Step 8:

[1603] The server sends a notification message to the relevant rescue agency.

[1604] Specifically, notification messages are sent simultaneously to multiple rescue agency contacts via a message sending API (e.g., Twilio).

[1605] Input content: Notification message

[1606] Output content: Notification result to rescue agency

[1607] In this way, the system processes disaster reports quickly and accurately, and notifies relevant rescue organizations appropriately, enabling prompt rescue operations.

[1608] (Application example 1)

[1609] 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."

[1610] Conventional disaster response systems mainly rely on telephone lines for reporting, which often hinders the accuracy of reports and the speed of rescue operations. Specifically, it is difficult to properly convey detailed information about the situation when reporting, and auxiliary information such as location information and images and videos of the scene is often lacking. This makes it difficult for rescue agencies to respond quickly and appropriately, resulting in a decrease in the efficiency of lifesaving efforts.

[1611] 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.

[1612] In this invention, the server includes means for reporting disaster information using a web application, means for transmitting the reported information to the server, means for analyzing the information received by the server using generative artificial intelligence and natural language processing to determine its authenticity, means for automatically acquiring location information of the user device, means for attaching and transmitting images and videos related to the disaster situation, and means for notifying rescue organizations based on the determined information. This enables the transmission of detailed report content including location information and images / videos and the rapid determination of authenticity by generative AI, enabling rescue organizations to respond quickly and accurately.

[1613] A "web application" is software that can be used by users over the Internet.

[1614] "Means for reporting disaster information" refers to an interface that allows users to report the situation when a disaster occurs.

[1615] A "server" is a computer system that processes and stores data on a network.

[1616] "Generative artificial intelligence" refers to artificial intelligence technology that has the ability to generate new information based on input data.

[1617] "Natural language processing" is a technology that uses computers to understand, analyze, and generate human language.

[1618] "Means for determining authenticity" refers to the process of analyzing and evaluating whether the reported information is correct.

[1619] "User terminal" refers to any device used by a user, including smartphones and tablets.

[1620] "Means for automatically obtaining location information" refers to a function that automatically obtains the user's current location using technology such as GPS.

[1621] "Means for attaching and sending images and videos related to the disaster situation" refers to a function that allows users to attach images and videos they have taken to the report and send them.

[1622] "Means of notification" refers to the process of contacting rescue organizations based on the analyzed information.

[1623] System Program

[1624] The system of this invention begins with a user reporting disaster information using a web application and sending it to a server. The server then analyzes the reported information using generative artificial intelligence and natural language processing to determine its authenticity. Next, the user's device automatically acquires location information and sends it along with images and videos of the disaster situation. Finally, the server notifies rescue organizations based on the determined information.

[1625] Hardware and software used

[1626] Hardware: smartphones, tablets, servers

[1627] Software: GPS module, Python, Geopy library, Requests library, generative AI model, natural language processing technology (NLP)

[1628] Natural language processing explanation

[1629] 1. Data transmission by user terminal

[1630] Users use their smartphones or tablets to report disaster information through a web application. At this time, they input the necessary information, such as the type of disaster, detailed situation, and current location. Location information is automatically obtained using a GPS module. Users can also attach images and videos showing the current state of the disaster within the app. This information is serialized and sent to the server via a secure communication channel.

[1631] 2. Data analysis by the server

[1632] The server analyzes the received information using generative artificial intelligence and natural language processing technology. Natural language processing understands the text entered by the user, and generative AI evaluates the veracity of the content. For example, if a report is made that "a building has collapsed and many people are injured," the AI ​​analyzes the context and evaluates its reliability.

[1633] 3. Notifying rescue agencies

[1634] Once the information has been determined to be true or false, it is automatically sent to rescue agencies by the server. This notification includes a specific message generated by the generative AI. For example, it could read, "Emergency call: An earthquake has occurred at the specified location. Situation: A building has collapsed and many people are injured. Please respond quickly."

[1635] Specific examples

[1636] As a concrete example, consider the occurrence of an earthquake. A user opens a web application on their smartphone, selects "earthquake," and enters "buildings have collapsed and many injured." Location information is automatically acquired via GPS, and images and videos are attached. This information is sent to a server, where it is analyzed and evaluated using generative AI and natural language processing technology. As a result, a notification is sent to rescue agencies stating, "Emergency call: An earthquake has occurred at the specified location. Situation: buildings have collapsed and many injured. Please respond quickly."

[1637] Prompt Sentence Examples

[1638] input

[1639] Disaster type: Earthquake

[1640] Details: Buildings collapsed, many injured

[1641] Location information: Automatically acquired (latitude and longitude)

[1642] Attachment: Images and videos of the disaster site

[1643] output

[1644] "Emergency message: Earthquake occurred at specified location. Situation: Building collapsed, many injured. Please respond quickly."

[1645] This allows for accurate and prompt reporting and response.

[1646] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1647] Step 1:

[1648] Users access the web application using a smartphone or tablet, access the disaster information reporting form, and enter the necessary information, such as the type of disaster, current location (automatically obtained), details of the situation, and images and videos.

[1649] input:

[1650] Types of disasters

[1651] Current location (automatically obtained by GPS)

[1652] Details of the situation

[1653] Images and videos

[1654] output:

[1655] Serialized report data

[1656] Specific behavior:

[1657] Converts information entered into a web form into a serialized format such as JSON and prepares it for transmission to the server.

[1658] Step 2:

[1659] The user device sends the processed disaster information to the server, where the data is sent using a secure communication protocol (such as HTTPS).

[1660] input:

[1661] Serialized report data

[1662] output:

[1663] Report data received by the server

[1664] Specific behavior:

[1665] The serialized data is sent to the server as an HTTPS request.

[1666] Step 3:

[1667] The server analyzes the received report data using generative artificial intelligence and natural language processing technology to determine its authenticity.

[1668] input:

[1669] Report data received by the server

[1670] output:

[1671] Data that has been judged to be true or false

[1672] Specific behavior:

[1673] It uses a natural language processing engine to analyze text data and uses generative AI to evaluate the reliability of the information.

[1674] Step 4:

[1675] The server performs duplication checks and filtering on the parsed data, eliminating redundant and meaningless information.

[1676] input:

[1677] Data that has been judged to be true or false

[1678] output:

[1679] Duplicate checked and filtered data

[1680] Specific behavior:

[1681] Matching data with existing data in the database to remove duplicate information and filtering out incomplete or unnecessary data.

[1682] Step 5:

[1683] The server then notifies rescue agencies based on the filtered data, with the notification being an emergency message generated by generative AI.

[1684] input:

[1685] Duplicate checked and filtered data

[1686] output:

[1687] Emergency message sent to rescue agencies

[1688] Specific behavior:

[1689] Generative AI models are used to generate appropriate emergency messages based on the content of the call and send them to relevant rescue agencies.

[1690] Step 6:

[1691] Rescue agencies will receive notifications and respond quickly, specifically by dispatching the necessary rescue teams and resources to the scene based on the notification message.

[1692] input:

[1693] Emergency message sent to rescue agencies

[1694] output:

[1695] Rapid response from rescue agencies

[1696] Specific behavior:

[1697] Rescue agencies analyze the messages they receive, determine the appropriate response, and quickly begin action.

[1698] This overall system processing flow enables faster reporting and more accurate information transmission in the event of a disaster, improving the efficiency of rescue operations.

[1699] 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.

[1700] Overall overview

[1701] This invention is a system that recognizes user emotions and evaluates the importance and prioritization of report data by combining an emotion engine with a disaster reporting system, thereby enabling high-urgency reports to be processed quickly and enabling effective rescue operations.

[1702] System Configuration

[1703] This system consists of the following main elements:

[1704] 1. User Device

[1705] 2. Web Server

[1706] 3. Generative AI and Natural Language Processing Server

[1707] 4. Emotion Engine

[1708] 5. Notification system for rescue agencies

[1709] DETAILED DESCRIPTION OF THE EMBODIMENTS

[1710] 1. Reporting via user terminal

[1711] A user accesses a web application and logs in by entering their authentication information.

[1712] After logging in, the user fills in the necessary information in the form to make a report.

[1713] Type of disaster (e.g. earthquake, fire)

[1714] Current location (auto-detect or manual input)

[1715] Details of the situation (free description)

[1716] Images and videos (optional)

[1717] When the user enters the report content and clicks the "Send" button, the data is serialized and sent to the web server.

[1718] 2. Data reception by the web server

[1719] The web server receives the data as an HTTP POST request and passes it to a generative artificial intelligence and natural language processing server for analysis.

[1720] The server prepares to pass the received data to the emotion engine.

[1721] 3. Data analysis using generative artificial intelligence and natural language processing

[1722] The received data is analyzed using generative artificial intelligence and natural language processing techniques.

[1723] The report content is analyzed in detail using natural language processing, and the reliability of the content is evaluated.

[1724] Generative artificial intelligence determines the truth or falsity of the data and stores the results in a database.

[1725] Duplicate checking and filtering of data also occurs at this stage.

[1726] 4. Emotion Recognition by Emotion Engine

[1727] The emotion engine analyzes the text and voice data sent by the user and recognizes the user's emotions.

[1728] The recognized emotion information is added to the message data and used to evaluate the importance of the message data.

[1729] 5. Notifying rescue agencies

[1730] Data that is rated as highly important by the emotion engine is processed with priority.

[1731] When a notification is sent to rescue agencies, the emotion information is included along with the analyzed data.

[1732] Specifically, the following notification message is generated:

[1733] Example: "Emergency call: Earthquake occurred at location A. Situation: Building collapsed, people injured. User stress level: High."

[1734] Notifications are sent simultaneously to multiple rescue agencies, allowing for a rapid response.

[1735] Specific examples

[1736] As a concrete example, consider the occurrence of an earthquake.

[1737] When a user confirms that an earthquake has occurred, they open the web application and log in.

[1738] The user inputs "earthquake," "current location (automatically detected)," and "details of the situation (buildings have collapsed and many injured)," and presses the send button.

[1739] The user terminal transmits this data to the web server.

[1740] The server receives the data and analyzes it using generative artificial intelligence and natural language processing techniques.

[1741] The emotion engine analyzes user input and voice data to recognize the user's stress level and emotions.

[1742] The server sends a notification to the relevant rescue organization based on the analysis results and the emotion information. The notification message includes the type of disaster, location, details of the situation, and the user's emotion information.

[1743] Rescue agencies are notified and rush to the scene.

[1744] In this way, this system improves the efficiency of reporting during disasters and enables rapid rescue operations by utilizing users' emotional information.

[1745] The processing flow will be explained below.

[1746] Step 1:

[1747] A user accesses a web application.

[1748] The user opens a browser on their personal computer or smartphone, accesses the disaster notification system website, and logs in. The user enters their authentication information (username and password) and presses the login button.

[1749] Step 2:

[1750] The user opens the report form.

[1751] After logging in, users click the "Report" button from the main menu to open a form for reporting disaster information. Users must enter the following information:

[1752] Type of disaster (e.g. earthquake, fire)

[1753] Current location (auto-detect or manual input)

[1754] Details of the situation (free description)

[1755] Images and videos (optional)

[1756] Step 3:

[1757] The user sends the notification data.

[1758] The user enters disaster information and clicks the "Send" button, which causes the device to serialize all the entered data and prepare it to be sent to the web server.

[1759] Step 4:

[1760] The device sends the data to the server.

[1761] The device sends the serialized data as an HTTP POST request to a web server, which includes the type of disaster, current location, details of the situation, and images and videos.

[1762] Step 5:

[1763] The server receives the data.

[1764] The server analyzes the received HTTP POST request and extracts data from each field. The analyzed data is then passed to the generative artificial intelligence and natural language processing server.

[1765] Step 6:

[1766] The server analyzes the data.

[1767] The received data is analyzed using generative artificial intelligence and natural language processing technology. Natural language processing analyzes the contents of the report in detail and evaluates its reliability. The generative artificial intelligence determines whether the data is true or false, and the results are stored in a database.

[1768] Step 7:

[1769] The server performs duplicate checking and filtering.

[1770] The server checks existing data in the database to ensure there are no duplicate reports with the same content, and also filters out false or unnecessary information.

[1771] Step 8:

[1772] The server passes the data to the emotion engine.

[1773] The server passes the received text and voice data to the emotion engine for analysis, which analyzes the user's emotions.

[1774] Step 9:

[1775] The emotion engine recognizes the user's emotions.

[1776] The emotion engine analyzes the data sent by the user and evaluates the user's emotions, especially their stress level. The recognized emotion information is added to the report data.

[1777] Step 10:

[1778] The server sends a notification to the rescue agency.

[1779] Data that is evaluated as having high importance by the emotion engine is processed with priority.The server generates notification messages to relevant rescue organizations based on the analyzed data and emotion information.

[1780] Step 11:

[1781] The server sends a message to a rescue agency.

[1782] The server then sends the generated notification message to multiple related rescue organizations. The notification message includes the type of disaster, location, details of the situation, and the user's emotional state, allowing rescue organizations to respond to the scene quickly.

[1783] Step 12:

[1784] The user checks the report history.

[1785] Users can later revisit the web application and view the history of their submitted alerts, including the alert date, type of incident, situation details, and any attached emotional information.

[1786] Example 2

[1787] 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."

[1788] Conventional disaster reporting systems have difficulty in quickly determining the urgency of reports, and when many reports are received at the same time, important reports are buried. In addition, because they do not take into account the emotional information of the caller, it is difficult to accurately grasp situations with a high level of urgency.

[1789] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for analyzing received information using generative artificial intelligence and natural language processing to determine whether the information is true or false, a means for evaluating the importance of the report data based on the determined information and the user's emotional information, and a means for notifying a rescue organization based on the evaluated information. This makes it possible to evaluate the urgency of the report content with high accuracy and quickly notify an appropriate rescue organization.

[1790] A "web application" is software that runs on a web browser and can be accessed by users via the Internet.

[1791] "Disaster information" refers to detailed information about disasters such as earthquakes, fires, and floods reported by users.

[1792] "Reporting" is the act of a user providing disaster information through a web application.

[1793] A "server" is a computer system that receives, processes, and stores data from user terminals over a network.

[1794] "Generative artificial intelligence" is a technology that uses algorithms based on machine learning and deep learning to generate and analyze new data and patterns.

[1795] "Natural language processing" is the technology that enables computers to understand, interpret, and generate human language.

[1796] "Authenticity assessment" is the process of determining the accuracy and reliability of the information provided.

[1797] "Evaluating the importance of report data" is a process of determining how urgent the information is based on the disaster information provided and the user's emotional information.

[1798] "Notification" is the act of transmitting emergency information to relevant rescue organizations based on the evaluated information.

[1799] "Rescue agencies" are public institutions such as fire departments, police, and ambulance teams that respond to disasters.

[1800] "Emotional information" is data that indicates the emotional state (e.g., stress level or tension) that a user exhibits when making a report.

[1801] "Data duplication check" is a process to prevent multiple transmission of the same or similar report data.

[1802] "Filtering" is the process of eliminating irrelevant or erroneous information, leaving only the necessary data.

[1803] This invention is a system for realizing prompt and accurate reporting in the event of a disaster. This system analyzes disaster information and emotional information provided by users and evaluates the importance of the information, enabling prompt notification to rescue organizations.

[1804] System Configuration

[1805] This system consists of the following main elements:

[1806] 1. User Device

[1807] 2. Web Server

[1808] 3. Generative AI and Natural Language Processing Server

[1809] 4. Emotion Engine

[1810] 5. Notification system for rescue agencies

[1811] DETAILED DESCRIPTION OF THE EMBODIMENTS

[1812] 1. Reporting via user terminal:

[1813] Users access web applications using devices such as smartphones and personal computers.

[1814] Users log in by entering their authentication information (username and password), and then fill out a form with the type of disaster (e.g., earthquake, fire), their current location, details of the situation (such as the state of building collapse), and images and videos (if necessary).

[1815] When the user presses the "Submit" button, the terminal serializes the entered data into JSON format and sends it to the web server using HTTPS.

[1816] 2. Data received by the web server:

[1817] The server receives the data sent from the user terminal as an HTTP POST request.

[1818] The server performs data integrity checks, filters out bad data, and temporarily stores the correct data in a database.

[1819] The received data is prepared to be passed to the generative artificial intelligence and natural language processing server for analysis, and also to the emotion engine.

[1820] 3. Data analysis using generative artificial intelligence and natural language processing:

[1821] The generative AI model analyzes the received data and determines the reliability and authenticity of the report.

[1822] Using natural language processing technology, key points from the report are extracted and the urgency of the disaster is assessed.

[1823] The AI ​​model stores the results in a database and performs duplicate checking and filtering of the data.

[1824] The server prepares to pass the analysis results to the emotion engine.

[1825] 4. Emotion Recognition with Emotion Engine:

[1826] The emotion engine receives the user's text data and voice data and uses emotion analysis algorithms to recognize the user's emotions.

[1827] The recognized emotion information is added to the message data and used to evaluate the importance of the message data.

[1828] 5. Notification to rescue agencies:

[1829] The server prioritizes processing of data that is evaluated as having high importance by the emotion engine.

[1830] The server generates a notification message containing the analysis results and emotion information and sends it to the relevant rescue organization. Specifically, a notification such as "Emergency call: Earthquake occurred at point A. Situation: Building collapse, many injured. User's stress level: High" is generated.

[1831] Rescue agencies are notified and rush to the scene.

[1832] Specific examples

[1833] As a concrete example, consider the occurrence of an earthquake.

[1834] The user sees the earthquake, opens the web application and logs in.

[1835] The user inputs "earthquake," "current location (automatically detected)," and "details of the situation (buildings have collapsed and many injured)," and then presses the send button.

[1836] The user terminal transmits this data to the web server.

[1837] A server receives the data and analyzes it using generative artificial intelligence and natural language processing.

[1838] The emotion engine analyzes the user's input data and voice data to recognize the user's stress level and emotions.

[1839] The server sends a notification to the relevant rescue organizations based on the analysis results and emotion information. The notification message includes the type of disaster, location, details of the situation, and the user's emotion information.

[1840] Rescue agencies are notified and rush to the scene.

[1841] Prompt Sentence Examples

[1842] Enter the following prompt into the generative AI model:

[1843] "Analyze the report data, recognize the user's emotions, and generate a notification message that includes the type of disaster, current location, details of the situation, and the user's stress level."

[1844] As described above, the system of the present invention improves the efficiency of disaster reporting in emergencies and supports rapid and effective rescue operations by utilizing user emotional information.

[1845] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1846] Step 1:

[1847] When a user confirms a disaster, they access the web application from their device, such as a smartphone or PC. They log in by entering their authentication information (e.g., username and password). After logging in, they enter the following information into the reporting form:

[1848] Type of disaster (e.g. earthquake, fire)

[1849] Current location (automatically detected using the device's GPS function or manually entered)

[1850] Details of the situation (e.g., a building has collapsed and many people are injured)

[1851] Images and videos (optional attachments available)

[1852] The user enters all the required information and clicks the "Submit" button. At this time, the user's device serializes the entered data in JSON format and sends it to the web server using HTTPS. The input is the report content (text, image, location information), and the output is the data to be sent to the web server.

[1853] Step 2:

[1854] The server receives data sent from the user terminal as an HTTP POST request. First, the server checks the integrity of the received data and filters out incomplete or bad data. Data that has been confirmed to be consistent is temporarily stored in a database. The input is the JSON data sent by the user, and the output is the data whose integrity has been confirmed.

[1855] Step 3:

[1856] The server passes the received data to a generative artificial intelligence and natural language processing server. The generative AI model analyzes the received data and determines the reliability and authenticity of the report content. Natural language processing technology is used to extract important keywords from the report text and analyze its content. Data duplication checks and filtering are also performed. The input is data whose consistency has been confirmed, and the output is the analysis results and data with duplicates removed.

[1857] Step 4:

[1858] The server passes the analysis results to the emotion engine. The emotion engine receives the user's text data and voice data and uses an emotion analysis algorithm to recognize the user's emotions. It analyzes the user's language and sentence tone to evaluate stress levels and fear. The input is the analyzed data, and the output is data with emotional information added.

[1859] Step 5:

[1860] The server evaluates the importance of the message data to which emotional information has been added. Data that has been evaluated as having a high importance by the emotion engine is processed preferentially. The input is data to which emotional information has been added, and the output is data whose importance has been evaluated.

[1861] Step 6:

[1862] The server generates a notification message based on the evaluated data. Specifically, it may have a message such as "Emergency call: An earthquake has occurred at point A. Situation: Building collapsed, many injured. User stress level: High." The generated notification message is sent to the relevant rescue agencies (fire department, police, ambulance, etc.). The input is the data whose importance has been evaluated, and the output is the generated notification message.

[1863] Step 7:

[1864] Rescue agencies receive notifications and initiate actions to respond quickly based on the notification content. The input is a notification message sent from the server, and the output is the initiation of rescue operations.

[1865] (Application example 2)

[1866] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1867] Conventional disaster reporting systems have difficulty prioritizing reports, resulting in the inability to process reports of particularly high urgency quickly. Furthermore, because the report data is evaluated without taking into account the caller's emotions or stress level, the efficiency of rescue operations can be reduced. Therefore, there is a need for a system that can appropriately determine which reports are of high urgency and carry out prompt and effective rescue operations.

[1868] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing the message content and emotions, extracting and evaluating emotional data, means for analyzing the message content and determining its authenticity using generative artificial intelligence and natural language processing, and means for notifying a rescue organization based on the evaluated message information and emotional data. This makes it possible to accurately evaluate the urgency of the message content and prioritize calls of particularly high importance. Furthermore, utilizing the caller's emotional information improves the speed and effectiveness of rescue operations.

[1869] A "web application program" is software that can be accessed via the Internet and is a means by which users can report disaster information.

[1870] The "central processing unit" is a computer server that analyzes the received data and performs the necessary processing.

[1871] "Generative AI" is an AI technology that can analyze data patterns and generate new information.

[1872] "Natural language processing" is a technology for analyzing text and voice data entered by a user and understanding its content.

[1873] "Sentiment analysis" is the process of determining emotions and stress levels from user-entered text and voice data.

[1874] "Emotion data" is information that indicates the emotional state of the user extracted by emotion analysis.

[1875] "Report data" refers to information such as text, audio, images, and video that a user inputs when reporting disaster information.

[1876] "Rescue agency" refers to an organization or unit that responds when a disaster occurs.

[1877] "Duplicate check" is a process for identifying identical or similar notification data and preventing it from being sent again.

[1878] "Filtering" is the process of removing unnecessary data from received report data and extracting only the necessary information.

[1879] "Prioritization" is the process of determining the priority of rescue operations based on call data and sentiment data.

[1880] Overall system overview

[1881] The present invention is a disaster notification system consisting of a web application program, a central processing unit, generative artificial intelligence, natural language processing, emotion analysis, and a system for notifying rescue organizations. This system allows users to quickly and appropriately report disaster information, which is then analyzed and notified to the necessary rescue organizations.

[1882] System Configuration

[1883] The following are the main elements that make up the system:

[1884] Web Application Program

[1885] Users report disaster information through a web application program, which includes the type of disaster, current location, details of the situation, and the ability to attach images and videos. Once the user enters the content of the report and presses the send button, the information is sent to the central processing unit.

[1886] central processing unit

[1887] The central processing unit centrally manages the report data received from users. This unit uses generative artificial intelligence and natural language processing technology to analyze the report data and determine its authenticity. It also has the function of performing emotion analysis, extracting and evaluating emotional data.

[1888] Generative Artificial Intelligence and Natural Language Processing

[1889] Generative AI can analyze patterns in reports and generate new information. It uses natural language processing technology to understand the meaning of text and voice data entered by users and evaluate its reliability.

[1890] Emotion analysis

[1891] Sentiment analysis evaluates the user's emotional state from text and voice data entered by the user, and this emotional data is sent to the notification system along with the notification data.

[1892] Notification System

[1893] The notification system uses generative artificial intelligence and sentiment analysis to evaluate call data and then notify relevant rescue agencies. The notification includes the urgency of the call data and the user's emotional state.

[1894] Program operation explanation

[1895] This system uses the following hardware and software:

[1896] Hardware: Smartphones, computer servers

[1897] Software: Python, Flask (web framework), emotion recognition model, natural language processing (NLP) model

[1898] The central processing unit analyzes the data received from users and performs sentiment analysis. The generative AI evaluates the urgency of the call and stores the results in a database. The notification system uses this data to generate notification messages for rescue agencies, encouraging them to respond quickly.

[1899] Examples and prompts

[1900] For example, if a user reports that an earthquake has occurred, buildings have collapsed, and many people are injured, the system operates as follows:

[1901] 1. The user opens the web application program, inputs disaster information (including earthquake, current location, automatic detection, and situation details), and presses the send button.

[1902] 2. The central processing unit analyzes the received report data using generative artificial intelligence and natural language processing technology.

[1903] 3. Sentiment analysis obtains user emotion data using the following prompt sentence:

[1904] Prompt: "The user entered the following text: 'An earthquake occurred, buildings collapsed, and many people were injured.' Analyze the user's emotions (fear, stress) from this text."

[1905] 4. The generative AI evaluates the urgency of the report data using the following prompt:

[1906] Prompt: "Report data: {'disaster_type': 'Earthquake', 'location': 'Automatically detected location', 'details': 'A building has collapsed and many people are injured'} Rate the urgency of this data and calculate a priority."

[1907] 5. The notification system sends emergency notifications to rescue agencies based on the analysis results and emotion data.

[1908] This allows for more effective disaster response, since important report data, including the user's emotional information, can be promptly notified to the relevant rescue organizations.

[1909] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1910] Step 1:

[1911] The user launches the web application program, inputs the type of disaster, current location, details of the situation, and report information including images and videos, and presses the send button.

[1912] Input: User inputs disaster type, current location, situation details, and media files

[1913] Output: Serialized message data sent to the central processor

[1914] Step 2:

[1915] The user terminal sends the reported data to the central processing unit, which receives the data as an HTTP POST request.

[1916] Input: Report data sent from the user terminal

[1917] Output: Received data stored in the central processing unit

[1918] Step 3:

[1919] The central processing unit analyzes the received report data using generative artificial intelligence and natural language processing technology, particularly to determine the urgency and authenticity of the report content.

[1920] Input: Report data stored in the central processing unit

[1921] Output: Analyzed report data (including urgency rating and truth rating)

[1922] Specific operation: Generative AI uses natural language processing technology to analyze text data and determine the urgency and authenticity of the report.

[1923] Step 4:

[1924] The central processing unit performs sentiment analysis to extract emotional data, determines the emotional state from the text and voice data entered by the user, and performs sentiment analysis using specific prompt sentences.

[1925] Input: Text or voice data in the report data

[1926] Output: User's emotional data (e.g., stress level, fear level)

[1927] Specific behavior: The emotion engine uses the prompt "Text entered by the user: 'Specific content' Analyze the user's emotion (fear, stress) from this text."

[1928] Step 5:

[1929] The central processing unit generates a notification message based on the evaluated notification information and emotion data, and sends high-urgency notifications to relevant rescue organizations on a priority basis.

[1930] Input: Analyzed report data and emotion data

[1931] Output: Message to notify rescue agencies

[1932] Specific operation: The notification system evaluates the urgency of the notification using the prompt "Report data: {'disaster_type': 'Earthquake', 'location': 'Automatically detected location', 'details': 'Specific content'} Evaluate the urgency of this data and calculate the priority." and generates a notification message.

[1933] This allows important report data, including the user's emotional information, to be promptly notified to relevant rescue organizations, enabling effective disaster response.

[1934] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1935] 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.

[1936] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1937] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1938] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1939] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1940] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1941] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1942] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1943] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1944] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1945] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1946] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1947] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1948] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1949] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1950] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1951] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1952] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1953] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1954] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1955] The following is further disclosed regarding the above embodiment.

[1956] (Claim 1)

[1957] A means for reporting disaster information using a web application;

[1958] means for transmitting the reported information to a server;

[1959] A means for analyzing the received information in the server using generative artificial intelligence and natural language processing to determine its authenticity;

[1960] a means for notifying a rescue agency based on the determined information;

[1961] A system including:

[1962] (Claim 2)

[1963] 10. The system of claim 1, further comprising means for performing duplicate checking and filtering of received information.

[1964] (Claim 3)

[1965] 10. The system of claim 1, further comprising means for transmitting the generated notification message to a plurality of associated rescue organizations.

[1966] "Example 1"

[1967] (Claim 1)

[1968] a means for reporting disaster information using a user terminal;

[1969] means for transmitting the reported information to a server via the Internet;

[1970] A means for analyzing the received information in detail using generative artificial intelligence and natural language processing in the server and determining the authenticity of the information;

[1971] A means for checking for duplication and filtering the determined information and storing highly reliable information in a database;

[1972] The system includes means for transmitting a notification message to a rescue agency that is generated based on the determined information.

[1973] (Claim 2)

[1974] The system according to claim 1, further comprising means for inputting the type of disaster, current location, details of the situation, and images and videos into the reporting form.

[1975] (Claim 3)

[1976] 10. The system of claim 1, further comprising means for simultaneously transmitting the generated notification message to a plurality of associated rescue organizations.

[1977] "Application Example 1"

[1978] (Claim 1)

[1979] A means for reporting disaster information using a web application;

[1980] means for transmitting the reported information to a server;

[1981] A means for analyzing the received information in the server using generative artificial intelligence and natural language processing to determine its authenticity;

[1982] A means of automatically obtaining location information from the user's device,

[1983] A means to attach and send images and videos related to the disaster situation,

[1984] a means for notifying a rescue agency based on the determined information;

[1985] A system including:

[1986] (Claim 2)

[1987] 10. The system of claim 1, further comprising means for performing duplicate checking and filtering of received information.

[1988] (Claim 3)

[1989] 10. The system of claim 1, further comprising means for transmitting the generated notification message to a plurality of associated rescue organizations.

[1990] "Example 2: Combining Emotion Engines"

[1991] (Claim 1)

[1992] A means for reporting disaster information using a web application;

[1993] means for transmitting the reported information to a server;

[1994] A means for analyzing the received information in the server using generative artificial intelligence and natural language processing to determine its authenticity;

[1995] a means for evaluating the importance of the report data based on the determined information and the user's emotional information;

[1996] a means for notifying rescue agencies based on the assessed information;

[1997] A system including:

[1998] (Claim 2)

[1999] 10. The system of claim 1, further comprising means for performing duplicate checking and filtering of received information.

[2000] (Claim 3)

[2001] 10. The system of claim 1, further comprising means for transmitting the generated notification message to a plurality of associated rescue organizations.

[2002] "Application example 2 when combining emotion engines"

[2003] (Claim 1)

[2004] a means for reporting disaster information using a web application program;

[2005] means for transmitting the reported information to a central processing unit;

[2006] means for analyzing the received information in the central processing unit using generative artificial intelligence and natural language processing to determine whether the information is true or false;

[2007] A means for analyzing the contents and emotions of reports and extracting and evaluating emotion data;

[2008] a means for notifying a rescue agency based on the evaluated call information and emotion data;

[2009] A system including:

[2010] (Claim 2)

[2011] 10. The system of claim 1, further comprising means for performing duplicate checking and filtering of received information.

[2012] (Claim 3)

[2013] 10. The system of claim 1, further comprising means for transmitting the generated notification message to a plurality of associated rescue organizations. [Explanation of symbols]

[2014] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for reporting disaster information using a web application; means for transmitting the reported information to a server; A means for analyzing the received information in the server using generative artificial intelligence and natural language processing to determine its authenticity; a means for notifying a rescue agency based on the determined information; A system including:

2. 10. The system of claim 1, further comprising means for performing duplicate checking and filtering of received information.

3. The system of claim 1 further comprising means for transmitting the generated notification message to a plurality of associated rescue organizations.

Images