system

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting posts related to urgency using an SNSAPI; means for transmitting contents of an inquiry to a server of a company; means for analyzing the collected posts and the contents of the inquiry and extracting an IP address and an area name; means for specifying the area and the urgency based on the analyzed contents; and means for notifying a relevant organization of the specified 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] Communications systems often go down in disaster-stricken areas, resulting in problems with the inability to quickly share important information both within and outside the affected area. This delays relief efforts and the delivery of relief supplies, posing a significant risk to the safety and livelihoods of disaster victims. Furthermore, there is a lack of means to accurately determine what is needed in each area, making it difficult to prioritize aid. A system that can solve these issues, quickly and accurately collect and analyze information from disaster-stricken areas, and connect with relevant organizations is needed. [Means for solving the problem]

[0005] The present invention solves the above problem by providing a system that includes a means for collecting posts related to urgency using a SNS API, a means for sending the content of inquiries to a company server, a means for analyzing the collected posts and inquiry content and extracting IP addresses and area names, a means for identifying the area and urgency based on the analyzed content, and a means for notifying relevant organizations of the identified information.

[0006] By using SNS APIs to collect posts from disaster-stricken areas in real time and sending them to a server along with inquiry data, it is possible to quickly gather information. The collected text data is then analyzed to extract IP addresses, area names, and keywords. Natural Language Processing (NLP) is then used to categorize the posts, and the GeoIP library is used to obtain area information from IP addresses, effectively identifying the area and the problem. The system then determines the level of urgency based on the identified information and notifies the necessary relevant organizations in real time. This enables a quick and appropriate response according to the situation in the disaster-stricken area.

[0007] "SNS API" is an application programming interface for retrieving and manipulating posts and data from social networking services through programs.

[0008] "Urgent posts" are messages or comments on social media that contain important information that requires a rapid response, such as information about communication outages, infrastructure problems, rescue operations, etc. in the disaster-stricken areas.

[0009] "Content of inquiries" refers to questions and requests regarding communication disruptions and infrastructure problems sent to the company by disaster victims and users.

[0010] A "server" is a computer system that stores and processes data on a network and provides information in response to requests from clients.

[0011] An "IP address" is a unique number that identifies a device connected to the Internet.

[0012] A "region name" is a name that indicates a specific geographical area, such as an administrative division or place name.

[0013] "Natural Language Processing (NLP)" is a general term for technology that processes, understands, and generates human language using computers.

[0014] The "GeoIP Library" is a software component for obtaining geographical location information from an IP address.

[0015] A "category" is a criterion for classifying information with similar properties or attributes into a group.

[0016] "Related organizations" are organizations such as the national government, local governments, and medical institutions that play an important role in support activities in the disaster-stricken areas. [Brief explanation of the drawings]

[0017] [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

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] 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).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] This invention relates to a system for understanding the situation in disaster-stricken areas and taking prompt and appropriate action. This system collects social media posts and inquiries to companies, analyzes them, identifies the level of urgency and the area, and notifies relevant organizations.

[0039] Overall system configuration

[0040] The system mainly consists of the following components:

[0041] 1. Terminal

[0042] 2. Server

[0043] 3. Social Media API

[0044] 4. GeoIP Library

[0045] 5. Natural Language Processing (NLP) Module

[0046] Terminal

[0047] The device collects inquiries from users and companies and sends them to a server. Specifically, the device uses SNS APIs to periodically check for posts containing specific hashtags such as "disaster" or "rescue" and temporarily stores them. It also collects data on inquiries to the company and sends this data to a server.

[0048] server

[0049] The server receives the information sent from the device and stores it in a database. Next, it analyzes the received text data and extracts the IP address and area name. At this time, it uses the GeoIP library to obtain area information from the IP address. It then analyzes the text using NLP technology and classifies the post content into categories. For example, if the post content contains the keyword "no water," the information will be classified into the category "infrastructure problems."

[0050] Urgency judgment

[0051] The server identifies the region and urgency level based on the analyzed content. Specifically, it analyzes keywords and phrases in the text, and if they are of high urgency, it classifies them as "high urgency." For example, keywords such as "help" and "fire" are treated as high urgency.

[0052] notification

[0053] The server then notifies the relevant organizations based on the identified information. For example, if high-urgency information such as "water is not coming out in ward X" is extracted, the information is immediately sent to the waterworks bureau. This is done using real-time notification methods via APIs and webhooks.

[0054] Specific examples

[0055] Below are a series of examples of this system in action:

[0056] 1. Users

[0057] A user posts on Twitter, "There is no water in XX ward."

[0058] 2. Terminal

[0059] The device periodically retrieves these posts using the SNS API and temporarily stores them.

[0060] It then sends the saved post to the server.

[0061] 3. Server

[0062] The server stores the posts received from the terminals in a database.

[0063] Analyze the text data and extract IP addresses and area names.

[0064] Posts containing the keyword "no water" are categorized as "infrastructure problems."

[0065] 4. Urgency determination

[0066] Text analysis determines that this post is of "high urgency."

[0067] 5. Notification

[0068] The server immediately notifies the waterworks bureau of the information that "there is no water in XX ward."

[0069] In this way, this system can quickly and accurately grasp the situation in the disaster-stricken areas and prompt the appropriate relevant organizations to take prompt action, thereby enabling effective support to be provided to the disaster-stricken areas.

[0070] The processing flow will be explained below.

[0071] Step 1:

[0072] User

[0073] A user posts on social media, such as "There is no water in ward XX." The information posted by the user is stored on the social media platform.

[0074] Step 2:

[0075] Terminal

[0076] The device periodically connects to the SNS API to check for new posts containing specific hashtags or keywords such as "disaster" or "rescue." The new posts retrieved from the API are temporarily stored in the device's storage.

[0077] Step 3:

[0078] Terminal

[0079] The device analyzes the collected posting data, extracts metadata such as the user's IP address and the content of the post, and formats this data for transmission to the server.

[0080] Step 4:

[0081] Terminal

[0082] The formatted data is sent to the server via an API endpoint that is designed to ensure it reaches the server.

[0083] Step 5:

[0084] server

[0085] The server stores the data received from the device in a database, which is then used for subsequent analysis.

[0086] Step 6:

[0087] server

[0088] The server then analyzes the received text data using natural language processing (NLP), which involves extracting IP addresses, location names, and specific keywords and phrases from the text.

[0089] Step 7:

[0090] server

[0091] Based on the parsed data, we use the GeoIP library to extract location information from IP addresses, which allows us to determine which region a post originates from.

[0092] Step 8:

[0093] server

[0094] The posts are then categorized based on the extracted keywords and phrases. For example, a post about "no water" would be classified as "infrastructure problems."

[0095] Step 9:

[0096] server

[0097] An urgency assessment algorithm is applied to assess the urgency of the analyzed data. Posts that are deemed to be of high urgency require immediate and appropriate action.

[0098] Step 10:

[0099] server

[0100] Once the urgency assessment is complete, appropriate relevant organizations (national government, local government, medical organizations, etc.) will be notified. Notifications will be sent in real time via API or webhook.

[0101] Step 11:

[0102] server

[0103] The system confirms that notifications have been sent successfully and records the history in a database, making it possible to track which information was sent to which institution and when.

[0104] Through the above processing steps, the system quickly collects and analyzes information of high urgency in the affected area and notifies the appropriate relevant agencies, thereby facilitating a rapid response.

[0105] Example 1

[0106] 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."

[0107] During natural disasters and emergencies, many people use social media and email to seek help, but there is a problem of difficulty in collecting and analyzing this information appropriately and quickly and notifying the relevant authorities. In particular, if geographic information is not accurately identified and the level of urgency is not accurately assessed, appropriate responses may be delayed. In conventional systems, these tasks are often performed manually, requiring a great deal of time and effort. Furthermore, response delays are likely to occur due to delayed recognition and overlooked information.

[0108] 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.

[0109] In this invention, the server includes a means for automatically collecting information about the level of urgency from SNS, a means for storing data sent directly from users in a central database, and a means for extracting meaning from the collected text data using text analysis technology. This makes it possible to automatically collect emergency information, appropriately analyze it, and promptly notify relevant organizations.

[0110] "SNS" stands for Social Networking Service, a platform for people to interact and share information online.

[0111] "Text analytics" is the process of extracting meaning and information from text data using natural language processing techniques.

[0112] "Urgency" is an index that evaluates how quickly the information requires a response.

[0113] "Categorization" is the process of grouping text data based on specific themes or content.

[0114] "Text data" is a collection of textual information written in a human-readable format.

[0115] "Relevant organizations" is a general term for organizations and groups that are responsible for receiving and responding to emergency information.

[0116] "Geographic identification technology" is a technology that identifies geographical locations and regions from information such as IP addresses.

[0117] MODE FOR CARRYING OUT THE INVENTION

[0118] This invention is a system for quickly grasping the situation in disaster-stricken areas and taking appropriate measures. This system comprises a series of processes that collect and analyze social media posts and inquiries, and notify relevant organizations of the results. The detailed components and processing procedures of the system are described below.

[0119] System Configuration

[0120] The system consists of the following main components:

[0121] 1. Terminal

[0122] 2. Server

[0123] 3. Social Media API

[0124] 4. GeoIP Library

[0125] 5. Natural Language Processing (NLP) Module

[0126] Hardware and Software Use

[0127] Terminal

[0128] The device is responsible for collecting inquiries from users and businesses and sending them to a server. Specifically, the device uses SNS APIs (e.g., Twitter API, Facebook Graph API) to periodically check for posts containing specific hashtags (e.g., "disaster" or "rescue") and temporarily store them. It also collects data on inquiries to businesses in a similar manner and periodically sends this data to the server. For example, the device can make a request to the SNS API every 15 minutes to retrieve new posts and store them in local storage.

[0129] server

[0130] The server receives the information sent from the device and stores it in a database. Next, it uses NLP technology to analyze the received text data and uses the GeoIP library to extract IP addresses and area names. For example, the server uses an NLP module (e.g., spaCy, BERT) to analyze the text, extract specific keywords, and understand the content. It also uses a GeoIP library (e.g., GeoIP2) to obtain geographical information from the IP address. This series of processes allows it to extract specific phrases such as "no water" or "need help" and identify area information based on them.

[0131] Urgency assessment and notification

[0132] The server evaluates the urgency level based on the analyzed data and identifies those with high urgency. It calculates an urgency score for each category, and if the score exceeds a predetermined threshold, it marks it as "high urgency." For example, the server recognizes posts containing keywords such as "help" or "fire" as high urgency. The server then notifies relevant authorities of high urgency information. This can be done in real time using APIs or webhooks. For example, it can send a request to the API endpoint of a waterworks or fire department to convey emergency information.

[0133] Specific examples

[0134] Below is an example of how this system works:

[0135] 1. Users

[0136] A user posts on Twitter, "There is no water in XX ward."

[0137] 2. Terminal

[0138] The device periodically retrieves these posts using the SNS API, temporarily stores them, and then sends them to the server.

[0139] 3. Server

[0140] The server stores the posts received from the devices in a database. It then analyzes the text data to extract IP addresses and area names. Posts containing the keyword "no water" are categorized as "infrastructure problems."

[0141] 4. Urgency determination

[0142] Text analysis determines that this post is of "high urgency."

[0143] 5. Notification

[0144] The server immediately notifies the waterworks bureau of the information that "there is no water in XX ward."

[0145] In this way, the system can quickly and accurately grasp the situation in the disaster-stricken areas and prompt the appropriate relevant organizations to take prompt action.

[0146] Prompt Sentence Examples

[0147] Below are some example prompts to input to a generative AI model:

[0148] Please explain the system that efficiently collects and analyzes information about disaster areas posted on social media such as Twitter and Instagram to identify the level of urgency and area, and promptly notifies relevant organizations.

[0149] Components of this system

[0150] How we collect information

[0151] Analysis and classification methods

[0152] Urgency assessment criteria

[0153] Notification method description

[0154] Actual operation example

[0155] This enables the system to automatically collect emergency information, analyze it appropriately, and quickly notify relevant agencies.

[0156] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0157] Step 1:

[0158] The device uses the SNS API to collect posts containing specific hashtags (e.g., "disaster," "rescue"). The input is the post data obtained from the SNS API, and this data is temporarily stored in the device's local storage. The collected and stored data is output. Specifically, the device sends a request to the Twitter API every 15 minutes to obtain the latest posts.

[0159] Step 2:

[0160] The device collects inquiries from users to the company. The input is emails and chat messages from the customer support system, which are temporarily stored in the device's local storage. The collected inquiry data is output. Specifically, the device connects to the email server, retrieves unread emails from a specific folder, and saves them.

[0161] Step 3:

[0162] The device sends the collected SNS posts and inquiries to the server. The input is data stored in the device's local storage and is sent to the server using the HTTPS protocol. The sent data is received by the server. Specifically, the device periodically compiles the collected data in batch format and sends a POST request to the server's API endpoint.

[0163] Step 4:

[0164] The server analyzes the received text data using NLP technology. The input is text data from social media posts and inquiries, and meaning is extracted using an NLP module (e.g., spaCy, BERT). The extracted semantic information is output. Specifically, the server uses an NLP library to perform morphological analysis of the text and identify important keywords and phrases.

[0165] Step 5:

[0166] The server uses a GeoIP library to extract region information from IP addresses. The input is the IP address contained in a post or query, and a GeoIP library (e.g., GeoIP2) is used to obtain the geographic coordinates and region name. The extracted region information is output. Specifically, the server queries the GeoIP database for the IP address and obtains the corresponding region information.

[0167] Step 6:

[0168] The server classifies the posts into categories based on the results of text analysis. The input is the extraction results from NLP, and the data is grouped using a categorization algorithm. The classified category information is output. Specifically, the server classifies posts into categories such as "infrastructure issues" and "lifesaving" based on specific keywords.

[0169] Step 7:

[0170] The server evaluates the urgency level based on the classified data. The input is categorized data, and the urgency level is determined using an algorithm that calculates an urgency score. Data with a high urgency level is output as "high urgency." Specifically, the server calculates the urgency score based on the presence or absence of keywords such as "help" or "fire," and marks anything that exceeds a threshold as high urgency.

[0171] Step 8:

[0172] The server notifies the relevant authorities of any identified high-urgency information. The input is data determined to be of high urgency, and notifications are sent in real time using APIs and web hooks. The notified information is then output. Specifically, the server sends requests to APIs of waterworks departments, fire departments, etc., to convey the necessary emergency information. Notifications are also sent via email and SMS.

[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 information gathering and emergency response systems in disaster areas have the problem of taking time to gather and analyze information, making it difficult to respond quickly. In particular, in the event of trouble or an emergency at a factory, a fast and effective response is required. Against this background, there is a growing need for a system that can collect and analyze information in real time and immediately notify relevant organizations and employees.

[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 collecting posts related to urgency using an SNS API, means for sending the content of inquiries to an information processing device, and means for analyzing the collected posts and inquiry content and extracting communication point information and location names. This makes it possible to display notification content on the smart glasses in real time.

[0178] "SNS API" refers to an application programming interface published by a social network service (SNS) provider, through which data on the SNS can be obtained and manipulated.

[0179] "Content of inquiry" refers to the content of communication including information provided, questions, reports, etc. from users and related parties, and the system uses this as data to be analyzed.

[0180] An "information processing device" is part of a computer system that collects, analyzes, stores, and notifies data, and includes servers and cloud services.

[0181] "Communication location information" refers to data obtained as location information of communication devices, and geographical information is identified based on this data.

[0182] "Place name" refers to a geographical name or area name, and is used to extract location information.

[0183] "Smart glasses" are a type of wearable device, a pair of eyeglass-type electronic devices that provide information to users by displaying visual information on a display.

[0184] "Real-time" means being able to process an event the moment it occurs, and being able to provide and process information without delay.

[0185] "NLP" stands for natural language processing, and is a technology that analyzes, understands, and interprets information contained in text data and spoken language.

[0186] "GeoIP Library" means a software library for obtaining geographic location information from an IP address, which is used in conjunction with an IP address to determine location.

[0187] The present invention is a system that uses a social networking service (SNS) API to collect posts related to urgency, transmits the contents of inquiries to an information processing device, analyzes the collected posts and inquiry contents, extracts communication point information and location names, identifies the location and urgency based on the analyzed contents, notifies related devices of the identified information, and displays the notification contents on smart glasses in real time.

[0188] Overall system configuration

[0189] The system mainly consists of the following components:

[0190] 1. Terminal

[0191] 2. Server

[0192] 3. Social Media API

[0193] 4. GeoIP Library

[0194] 5. Natural Language Processing (NLP) Module

[0195] 6. Smart Glasses

[0196] Terminal

[0197] The device collects posts from users and related parties related to inquiries and their urgency, and sends them to the server. Specifically, the device uses SNS APIs to periodically check for posts containing specific hashtags such as "factory trouble" and temporarily saves them. It also collects inquiry data and sends it to the server.

[0198] server

[0199] The server receives the information sent from the device and stores it in a database. Next, it analyzes the received text data and extracts communication point information and location names. At this time, it uses the GeoIP library to obtain region information from IP addresses. It then uses NLP technology to analyze the text and classify the post content into categories. For example, if the post content contains the keyword "fire broke out," the information will be classified into the category "fire accident."

[0200] Urgency judgment

[0201] The server identifies the location and urgency based on the analyzed content. Specifically, it analyzes keywords and phrases in the text, and if they are of high urgency, it classifies them as "high urgency." For example, keywords such as "fire" and "explosion" are treated as high urgency.

[0202] Notifications and Displays

[0203] The server then sends notifications to relevant devices based on the identified information. For example, if high-urgency information such as "A fire has broken out at Factory A" is extracted, the information is immediately sent to the fire department and relevant parties. Furthermore, the notification content is displayed in real time on the smart glasses, accelerating response.

[0204] Specific examples

[0205] A series of examples of how the system can be implemented include the following:

[0206] 1. Users

[0207] A user posts on Twitter, "There's a fire at Factory A."

[0208] 2. Terminal

[0209] The device periodically retrieves these posts using the SNS API, temporarily stores them, and then sends them to the server.

[0210] 3. Server

[0211] The server stores the posts received from the devices in a database, analyzes the text data, and extracts communication point information and location names. Posts containing the keyword "fire breaks out" are categorized as "fire accidents."

[0212] 4. Urgency determination

[0213] Text analysis determines that this post is of "high urgency."

[0214] 5. Notices and Displays

[0215] The server immediately notifies the fire department that "a fire has broken out at Factory A," and the smart glasses display a message saying "Fire has broken out. Please take emergency action."

[0216] Prompt Sentence Examples

[0217] "Please build an emergency assessment system to detect and respond to factory troubles. This system will assess the emergency level and respond appropriately by collecting and analyzing social media posts containing the following specific hashtags."

[0218] This will enable quick and appropriate responses to troubles and emergencies within the factory.

[0219] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0220] Step 1:

[0221] The device uses SNS APIs to collect posts related to urgency. During this process, the device periodically checks for posts containing specific hashtags (e.g., "factory trouble") and temporarily stores their contents. The input is the raw data of SNS posts, and the output is the temporarily stored post data related to urgency. Data processing involves filtering and storing the raw data obtained through the SNS API.

[0222] Step 2:

[0223] The terminal sends the collected posts and inquiry contents to the information processing device. The saved post data related to urgency is sent to the server. The input is the post data saved in step 1, and the output is the post data sent to the server. Data processing includes sending the saved data on the terminal to the server via network communication.

[0224] Step 3:

[0225] The server stores the received post data in a database and uses an NLP module to analyze the text data. The input is the post data sent to the server, and the output is the analysis results. Specifically, NLP technology is used to classify the post content into categories and extract important keywords and phrases.

[0226] Step 4:

[0227] The server uses the GeoIP library to obtain communication point information from the poster's IP address and identify the location name. The input is the IP address and analysis results contained in the posted data, and the output is communication point information and the location name. Specifically, the GeoIP library analyzes the IP address to extract geographical location information.

[0228] Step 5:

[0229] The server identifies the location and urgency based on the analyzed content. Information with a high urgency level is classified as "high urgency" based on keywords and phrases in the text. The input is the NLP analysis results and communication point information, and the output is the urgency classification result. For data calculation, an urgency determination algorithm is used to evaluate and classify the text analysis results.

[0230] Step 6:

[0231] The server notifies the relevant devices of the identified information. For example, if there is information that "a fire has broken out at Factory A," it will immediately notify the fire department and relevant parties. The input is the urgency classification result and specific location information, and the output is a notification message. Specifically, it uses a notification API or web hook to send information to relevant devices in real time.

[0232] Step 7:

[0233] The server displays the notification content on the smart glasses in real time. The input is the notification message, and the output is the information displayed on the smart glasses' display. The server sends the same notification as the information sent to the related devices to the smart glasses, providing the user with information in real time. Specifically, the message is displayed through an API dedicated to the smart glasses.

[0234] 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.

[0235] This invention relates to a system for grasping the situation in disaster-stricken areas and taking prompt and appropriate action. This system collects and analyzes social media posts and company inquiries to identify the level of urgency and the area, and notifies relevant organizations. Furthermore, it combines an emotion engine that recognizes user emotions to analyze the emotions in the posts and help identify the level of urgency.

[0236] Overall system configuration

[0237] The system mainly consists of the following components:

[0238] 1. Terminal

[0239] 2. Server

[0240] 3. Social Media API

[0241] 4. GeoIP Library

[0242] 5. Natural Language Processing (NLP) Module

[0243] 6. Emotion Engine

[0244] Terminal

[0245] The device collects inquiries from users and companies and sends them to a server. Specifically, the device uses SNS APIs to periodically check for posts containing specific hashtags such as "disaster" or "rescue" and temporarily stores them. It also collects data on inquiries to the company and sends this data to a server.

[0246] server

[0247] The server receives the information sent from the device and stores it in a database. The received text data is then analyzed using natural language processing (NLP). NLP analysis extracts IP addresses, local area names, and specific keywords and phrases from the text, and classifies the post content into categories. For example, if a post contains the keyword "no water," the information will be classified into the category "infrastructure problems."

[0248] Emotion Engine

[0249] The analysis on the server also uses an emotion engine. The emotion engine analyzes the emotions in the posted content and can identify emotions such as "sadness," "fear," and "anger." The emotion data obtained by the emotion engine is used to assist in determining the level of urgency.

[0250] Urgency judgment

[0251] The server uses NLP and an emotion engine to analyze the data and identify the region and level of urgency. Specifically, it analyzes keywords and phrases in the text, as well as the extracted emotion data, and classifies any that indicate a high level of urgency as "high urgency." For example, keywords such as "help" and "fire" are treated as high urgency, and if the emotion engine detects "fear," it is treated as an even higher level of urgency.

[0252] notification

[0253] The server then notifies the relevant organizations based on the identified information. For example, if high-urgency information such as "water is not coming out in ward X" is extracted, the information is immediately sent to the waterworks bureau. This is done using real-time notification methods via APIs and webhooks.

[0254] Specific examples

[0255] Below are a series of examples of this system in action:

[0256] 1. Users

[0257] A user posts on Twitter, "There is no water in XX ward." This post conveys the emotion of "I am in great trouble."

[0258] 2. Terminal

[0259] The device periodically retrieves these posts using the SNS API, temporarily stores them, and then sends them to the server.

[0260] 3. Server

[0261] The server stores the posts received from the devices in a database. It analyzes the text data and extracts IP addresses and area names. Posts containing the keyword "no water" are classified into the category "infrastructure problems."

[0262] 4. Emotion Engine

[0263] The emotion engine recognizes the emotion "very troubled" from the content of the post.

[0264] 5. Urgency determination

[0265] Based on text analysis and sentiment data, this post is determined to be of "high urgency."

[0266] 6. Notification

[0267] The server immediately notifies the waterworks bureau of the information that "there is no water in XX ward."

[0268] In this way, the system can quickly and accurately grasp the situation in the disaster area and prompt the appropriate relevant organizations to take prompt action. By adding an emotion engine, it becomes possible to make more accurate urgency judgments and gain a deeper understanding of the condition of the victims.

[0269] The processing flow will be explained below.

[0270] Step 1:

[0271] User

[0272] A user posts on social media, such as "There is no water in ward XX." The information posted by the user is stored on the social media platform.

[0273] Step 2:

[0274] Terminal

[0275] The device periodically connects to the SNS API to check for new posts containing specific hashtags or keywords such as "disaster" or "rescue." The new posts retrieved from the API are temporarily stored in the device's storage.

[0276] Step 3:

[0277] Terminal

[0278] The device analyzes the collected posting data, extracts metadata such as the user's IP address and the content of the post, and formats this data for transmission to the server.

[0279] Step 4:

[0280] Terminal

[0281] The formatted data is sent to the server via an API endpoint that is designed to ensure it reaches the server.

[0282] Step 5:

[0283] server

[0284] The server stores the data received from the device in a database, which is used for subsequent analysis.

[0285] Step 6:

[0286] server

[0287] The server then analyzes the received text data using natural language processing (NLP), which involves extracting IP addresses, location names, and specific keywords and phrases from the text.

[0288] Step 7:

[0289] server

[0290] Using data obtained from NLP analysis, we use the GeoIP library to extract geographic information from IP addresses, thereby identifying the region from which a post originates.

[0291] Step 8:

[0292] server

[0293] The NLP module classifies posts into categories based on keywords and phrases extracted. For example, a post about "no water" would be classified as "infrastructure problems."

[0294] Step 9:

[0295] server

[0296] The server uses an emotion engine to analyze the sentiment of the posts, using an emotion-identifying algorithm to identify emotions such as "sadness," "fear," and "anger."

[0297] Step 10:

[0298] server

[0299] Based on data obtained from NLP analysis and sentiment analysis, an urgency assessment algorithm is applied to assess the urgency of posts. Posts that are deemed to be of high urgency are immediately classified as "high urgency."

[0300] Step 11:

[0301] server

[0302] Based on information deemed to be of high urgency, relevant organizations (national government, local government, medical organizations, etc.) are notified. Notifications are sent in real time via API or webhook.

[0303] Step 12:

[0304] server

[0305] The system confirms that notifications have been sent successfully and records the history in a database, making it possible to track which information was sent to which institution and when.

[0306] Specific examples

[0307] Below are the steps by which the system actually works in a concrete example:

[0308] 1. Users

[0309] A user posts on Twitter, "There is no water in XX ward." This post conveys the emotion of "I am in great trouble."

[0310] 2. Terminal

[0311] The device uses the Twitter API to check posts with the hashtag "disaster," retrieves these posts, stores them temporarily, and then sends the data to the server.

[0312] 3. Server

[0313] The server receives the posted data obtained from the terminal and stores it in a database.

[0314] 4. Server

[0315] It uses an NLP module to parse the text and extract keywords like "no water," while also using the GeoIP library to determine the region of the post from its IP address.

[0316] 5. Server

[0317] Using a sentiment engine, the sentiment of the post is identified as "very distressed."

[0318] 6. Server

[0319] Using an urgency assessment algorithm, messages are classified as "high urgency" based on information obtained from text analysis and sentiment analysis.

[0320] 7. Server

[0321] Based on highly urgent information such as "water is not coming out in ward XX," the waterworks bureau is notified immediately.

[0322] 8. Server

[0323] Records that the notification was successful and stores the history in a database.

[0324] In this way, the system can quickly and accurately grasp the situation in the disaster area and prompt the appropriate relevant organizations to take prompt action. By adding an emotion engine, it becomes possible to make more accurate urgency judgments and gain a deeper understanding of the condition of the victims.

[0325] Example 2

[0326] 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."

[0327] The problem is that it is difficult to gather and analyze information to quickly and accurately grasp the situation in disaster-stricken areas and take appropriate measures. In particular, the technical challenge is extracting useful information from the vast amount of data on social media and inquiries, and determining the level of urgency. Furthermore, by adding emotion analysis, more accurate urgency determination is required.

[0328] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0329] In this invention, the server includes: [means for collecting posts related to urgency using an SNS API;] [means for sending the content of inquiries to the organization's server;] [means for analyzing the collected posts and inquiry content and extracting IP addresses and regional information;] [means for analyzing the content of posts using a Natural Language Processing (NLP) module and extracting keywords and phrases;] ​​[means for analyzing the emotions of the content of posts using an emotion engine;] [means for identifying the region and urgency based on the analyzed content; and [means for notifying relevant organizations of the identified information.] This makes it possible to quickly and accurately grasp the situation in the disaster-stricken areas and to promptly notify appropriate relevant organizations.

[0330] "SNS API" is an application programming interface that allows programs to use posted data from social networking services.

[0331] "Inquiries" refer to the content of communication such as questions, consultations, and requests made by users and related parties to an organization.

[0332] A "server" is a computer system that receives, stores, analyzes, and transmits data over a network.

[0333] "IP address" refers to a unique numeric code used when sending and receiving data on the Internet.

[0334] "Region information" refers to information about a particular geographic area, including city, ward, town, village name, postal code, etc.

[0335] A "Natural Language Processing (NLP) module" is a software component that allows a computer to analyze human natural language and understand its meaning and structure.

[0336] "Keywords" refer to words or phrases that are particularly important within text data.

[0337] An "emotion engine" is a software component that analyzes emotions from text data and classifies them into specific emotion categories (e.g., joy, sadness, fear, etc.).

[0338] "Analyzed content" refers to the information obtained as a result of analyzing collected data using an NLP module or emotion engine.

[0339] "Urgency" is a measure that indicates the level of urgency of data or an event, and is used to determine the priority of responses.

[0340] "Relevant organizations" refer to government agencies, private companies, non-governmental organizations (NGOs), etc. that need to respond based on specific information.

[0341] This invention relates to a system for quickly and accurately grasping the situation in disaster-stricken areas and taking appropriate measures. This system collects social media posts and inquiries to companies, analyzes them, identifies the level of urgency and the area, and notifies the relevant organizations.

[0342] Overall system configuration

[0343] The system mainly consists of the following components:

[0344] 1. Terminal

[0345] 2. Server

[0346] 3. Social Media API

[0347] 4. GeoIP Library

[0348] 5. Natural Language Processing (NLP) Module

[0349] 6. Emotion Engine

[0350] Terminal

[0351] The device collects inquiries from users and companies and sends them to a server. Specifically, the device uses SNS APIs to periodically check for posts containing specific hashtags such as "disaster" or "rescue" and temporarily stores them. It also collects data on inquiries to the company and sends this data to a server.

[0352] server

[0353] The server receives the information sent from the device and stores it in a database. Next, it analyzes the received text data using a natural language processing (NLP) module. NLP analysis extracts IP addresses, local area names, and specific keywords and phrases from the text, and classifies the post content into categories. For example, if the post content contains the keyword "no water," the information will be classified into the category "infrastructure problems."

[0354] Emotion Engine

[0355] The analysis on the server also uses an emotion engine. The emotion engine analyzes the emotions in the posted content and can identify emotions such as "sadness," "fear," and "anger." The emotion data obtained by the emotion engine is used to assist in determining the level of urgency.

[0356] Urgency judgment

[0357] The server uses NLP and an emotion engine to analyze the data and identify the region and level of urgency. Specifically, it analyzes keywords and phrases in the text, as well as the extracted emotion data, and classifies any that indicate a high level of urgency as "high urgency." For example, keywords such as "help" and "fire" are treated as high urgency, and if the emotion engine detects "fear," it is treated as an even higher level of urgency.

[0358] notification

[0359] The server then notifies the relevant organizations based on the identified information. For example, if high-urgency information such as "water is not coming out in ward X" is extracted, the information is immediately sent to the waterworks bureau. This is done using real-time notification methods via APIs and webhooks.

[0360] Specific examples

[0361] Below are a series of examples of this system in action:

[0362] 1. Users

[0363] A user posts on Twitter, "There is no water in XX ward." This post conveys the emotion of "I am in great trouble."

[0364] 2. Terminal

[0365] The device periodically retrieves these posts using the SNS API, temporarily stores them, and then sends them to the server.

[0366] 3. Server

[0367] The server stores the posts received from the devices in a database. It analyzes the text data and extracts IP addresses and area names. Posts containing the keyword "no water" are classified into the category "infrastructure problems."

[0368] 4. Emotion Engine

[0369] The emotion engine recognizes the emotion "very troubled" from the content of the post.

[0370] 5. Urgency determination

[0371] Based on text analysis and sentiment data, this post is determined to be of "high urgency."

[0372] 6. Notification

[0373] The server immediately notifies the waterworks bureau of the information that "there is no water in XX ward."

[0374] In this way, the system can quickly and accurately grasp the situation in the disaster area and prompt the appropriate relevant organizations to take prompt action.In addition, by using the emotion engine, the accuracy of urgency determination can be improved, enabling a deeper understanding of the condition of the victims.

[0375] Prompt Sentence Examples

[0376] Please explain how the system works: collects posts on Twitter that contain the hashtags "disaster" and "rescue," determines the area and urgency based on the content, and notifies the relevant organizations.

[0377] Using this prompt, the generative AI model can generate sentences like the one above that detail the process of the system.

[0378] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0379] Step 1:

[0380] User posts to SNS

[0381] Users post on Twitter or other SNSs using hashtags such as "disaster" or "rescue." For example, they might post something like, "There's no water in XX ward. We're in a lot of trouble." The input is the user's SNS post, and the output is the post itself. The specific actions a user takes are logging in to the SNS using a smartphone or PC and posting.

[0382] Step 2:

[0383] The device collects posts

[0384] The device periodically checks for posts containing these hashtags using the SNS API. The device collects the posts, temporarily stores them in local storage, and then sends them to the server. The input is the user's SNS posts, and the output is the collected post data. Specifically, the device searches for posts using the SNS API, retrieves and saves the relevant posts, and sends them to the server.

[0385] Step 3:

[0386] The server receives the data

[0387] The server receives the posted data sent from the device and stores it in a database. The input is the posted data sent from the device, and the output is the data stored in the database. Specifically, the server analyzes the received data, formats it, and then inserts it into the database.

[0388] Step 4:

[0389] The server uses the NLP module to analyze the text.

[0390] The server uses an NLP module to analyze the received text data. It extracts IP addresses, local area names, and specific keywords and phrases from the text and categorizes the posts. The input is the received text data, and the output is data such as analyzed keywords, local area names, and IP addresses. Specifically, it runs the NLP module to analyze and extract each element of the text.

[0391] Step 5:

[0392] The server performs emotion analysis using the emotion engine.

[0393] The server uses an emotion engine to analyze the emotions in the posted content. For example, emotions such as "fear" or "confusion" can be identified from the text data. The input is the text data, and the output is the detected emotion information. Specifically, the emotion engine is executed to extract emotion data from the text and identify which emotions are contained.

[0394] Step 6:

[0395] The server determines the urgency

[0396] The server determines the urgency of a post based on the results of the NLP and emotion engine. It analyzes keywords, phrases, and emotional data in the text and determines the urgency level from high to low. The input is the analyzed keywords and emotional information, and the output is the urgency level determination result. Specifically, it evaluates the extracted data and sets the urgency level.

[0397] Step 7:

[0398] The server notifies the relevant parties

[0399] The server notifies relevant organizations of specific information based on the results of the assessment. For example, if there is high-urgency information such as "water is not coming out in ward XX," it will notify the waterworks bureau. The input is the urgency assessment result, and the output is the sent notification. Specific operations include sending real-time notifications using APIs and webhooks.

[0400] This will enable the entire system to operate efficiently and to quickly and appropriately communicate the situation in the disaster-stricken areas to relevant organizations.

[0401] (Application example 2)

[0402] 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."

[0403] Conventional emergency response systems have difficulty in quickly and accurately grasping the situation in disaster-stricken areas, resulting in delayed appropriate responses. Furthermore, they often failed to properly assess the emotions and urgency contained in posts on social media, resulting in a failure to respond immediately to highly urgent situations. Furthermore, delays in notification to relevant organizations have also led to delays in rescue efforts for victims.

[0404] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0405] In this invention, the server includes: means for collecting posts related to urgency using a social networking service (SNS) API; means for sending inquiry content to a database server; means for analyzing the collected posts and inquiry content and extracting IP addresses and local area names; emotion engine means for analyzing the emotional state of the posts; means for identifying the local area and urgency level based on the analyzed content and emotional state; and means for notifying relevant organizations and security services of the identified information. This allows for rapid identification of the local area and urgency level of the collected posts, enabling immediate notification to relevant organizations. Furthermore, the emotion engine also performs emotion analysis of the posts, allowing for accurate identification of high-urgency situations, enabling rapid and appropriate responses. Furthermore, natural language processing and emotion analysis using a generative AI model enables more advanced information analysis and improved decision accuracy.

[0406] "SNS API" is an application programming interface for accessing data from social networking services (SNS).

[0407] A "database server" is a server that manages a database and performs operations such as storing, searching, updating, and deleting data.

[0408] "Posted content" refers to text and media information that users make public on social media and other communication platforms.

[0409] "Inquiry content" is text information of questions or opinions that users have made to companies or organizations.

[0410] An "IP address" is a unique number that identifies a device on the Internet.

[0411] A "region name" is a name that indicates a specific geographical area.

[0412] An "emotion engine" is a software module that analyzes emotions in text data and identifies the emotional state.

[0413] "Urgency" is an indicator of the level of urgency of a particular event or situation.

[0414] "Relevant organizations" refers to organizations or organisations directly involved in emergency and disaster response.

[0415] "Security services" is a general term for services that protect people and assets, prevent crime, and deal with disasters.

[0416] A "generative AI model" is an artificial intelligence model built using machine learning and deep learning, which learns from specific tasks and makes predictions and analyses.

[0417] A "prompt" is text that provides instructions or example input given to a generative AI model to perform a specific task.

[0418] The present invention is a system for quickly and accurately grasping the situation in a disaster area and prompting appropriate organizations to respond. Specific embodiments for carrying out the present invention are described below.

[0419] Overall system configuration

[0420] The system mainly consists of the following components:

[0421] 1. Terminal

[0422] 2. Server

[0423] 3. Social Media API

[0424] 4. Database Server

[0425] 5. Natural Language Processing (NLP) Module

[0426] 6. Emotion Engine

[0427] 7. Generative AI Models

[0428] Terminal

[0429] The device is responsible for collecting inquiries from users and businesses and sending this data to a server. Specifically, the device uses SNS APIs to periodically check for posts containing specific hashtags such as "disaster" or "rescue" and temporarily stores them. Inquiries to businesses are also collected in the same way and sent to the server.

[0430] server

[0431] The server receives the information sent from the device and stores it in a database server. The received text data is then analyzed using an NLP module. NLP analysis extracts IP addresses, local area names, and specific keywords and phrases from the text, and classifies the posted content into categories.

[0432] Emotion Engine

[0433] The server also uses an emotion engine to analyze the emotions in the posts and identify emotions such as "fear," "sadness," and "confusion."

[0434] Urgency judgment

[0435] The server identifies the region and urgency based on the data analyzed using the NLP module and emotion engine. Specifically, it analyzes keywords and phrases in the text as well as the extracted emotion data, and if it indicates a high level of urgency, it classifies it as "high urgency." For example, keywords such as "help" and "fire" are treated as high urgency, and if the emotion engine detects "fear," it is treated as an even higher level of urgency.

[0436] notification

[0437] The server then notifies relevant authorities and security services based on the identified information, using APIs and webhooks to prompt immediate action in real time.

[0438] Specific examples

[0439] Here's an example of this system in action:

[0440] Example 1: Collecting and analyzing social media posts

[0441] 1. Users

[0442] A user posts on Twitter, "Disaster Fire There's a fire in XX ward. It's very dangerous, please help."

[0443] 2. Terminal

[0444] The device periodically retrieves these posts using the SNS API, temporarily stores them, and then sends them to the server.

[0445] 3. Server

[0446] The server stores the posts received from the devices in a database server. The text data is analyzed to extract IP addresses and area names. Posts containing the keyword "fire" are classified as "high urgency."

[0447] 4. Emotion Engine

[0448] The emotion engine recognizes the emotion "It's very dangerous, please help" from the content of the post.

[0449] 5. Urgency determination

[0450] Based on text analysis and sentiment data, this post is determined to be of "high urgency."

[0451] 6. Notification

[0452] The server immediately notifies the fire department and security services of the information "There is a fire in ward XX."

[0453] Prompt Sentence Examples

[0454] Here are some example prompts to apply to generative AI models:

[0455] Prompt: "Create a program that analyzes the sentiment of posts collected from social media, extracts local information, and determines the level of urgency. If the level of urgency is high, include a function to notify the relevant authorities."

[0456] The above is the details of the "Mode for Carrying Out the Invention." By using this system, it is possible to quickly and accurately grasp the situation in the disaster area and respond appropriately.

[0457] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0458] Step 1:

[0459] A user posts an emergency situation on a social networking service (SNS). This post includes a hashtag (e.g., "disaster" or "fire") and a specific description of the situation (e.g., "There's a fire in ____ ward. It's very dangerous. Please help.").

[0460] Step 2:

[0461] The device periodically calls the SNS API to search and collect posts containing specific hashtags. This temporarily stores newly posted emergency information. The input is data from the SNS API, and the output is the temporarily stored post data.

[0462] Step 3:

[0463] The terminal transmits the temporarily saved posted data to the server. Here, the input is the temporarily saved posted data, and the output is the data sent to the server. This data includes the text of the post, the poster's IP address, and the posting date and time.

[0464] Step 4:

[0465] The server stores the received submission data in a database server. This ensures that the data required for subsequent analysis steps is stored persistently. The input is the data sent from the device, and the output is the data stored in the database.

[0466] Step 5:

[0467] The server analyzes the saved posting data using an NLP (Natural Language Processing) module, which extracts location-related information (place names and IP addresses) and specific keywords and phrases from the posting content. The input is the posting data retrieved from the database, and the output is the analyzed text data and extracted location information.

[0468] Step 6:

[0469] The server uses an emotion engine to analyze the emotional state of the post. Emotions such as "fear," "sadness," and "confusion" are identified. The input is the analyzed text data, and the output is the extracted emotional data.

[0470] Step 7:

[0471] The server determines the urgency level based on data analyzed by the NLP module and emotion engine. If the keyword "fire" or the emotion "fear" is identified, it is classified as high urgency. The input is the analyzed text data and emotion data, and the output is the determined urgency information.

[0472] Step 8:

[0473] The server notifies relevant organizations and security services based on the determined urgency information. Notifications are sent via API or web hooks, and if the urgency is high, notifications are sent immediately. The input is urgency information, and the output is notification data sent to relevant organizations.

[0474] Step 9:

[0475] The relevant authorities receive the notification from the server and take immediate action. Specifically, the fire department may be dispatched to the scene. The input is the notification data from the server, and the output is the actual response action.

[0476] The above is the specific flow of the processing of the present invention. Through these steps, it becomes possible to quickly and accurately grasp the situation in the disaster area and respond appropriately.

[0477] 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.

[0478] 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.

[0479] 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.

[0480] [Second embodiment]

[0481] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0482] 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.

[0483] 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).

[0484] 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.

[0485] 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.

[0486] 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).

[0487] 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.

[0488] 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.

[0489] 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.

[0490] 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.

[0491] 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.

[0492] 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."

[0493] This invention relates to a system for understanding the situation in disaster-stricken areas and taking prompt and appropriate action. This system collects social media posts and inquiries to companies, analyzes them, identifies the level of urgency and the area, and notifies relevant organizations.

[0494] Overall system configuration

[0495] The system mainly consists of the following components:

[0496] 1. Terminal

[0497] 2. Server

[0498] 3. Social Media API

[0499] 4. GeoIP Library

[0500] 5. Natural Language Processing (NLP) Module

[0501] Terminal

[0502] The device collects inquiries from users and companies and sends them to a server. Specifically, the device uses SNS APIs to periodically check for posts containing specific hashtags such as "disaster" or "rescue" and temporarily stores them. It also collects data on inquiries to the company and sends this data to a server.

[0503] server

[0504] The server receives the information sent from the device and stores it in a database. Next, it analyzes the received text data and extracts the IP address and area name. At this time, it uses the GeoIP library to obtain area information from the IP address. It then analyzes the text using NLP technology and classifies the post content into categories. For example, if the post content contains the keyword "no water," the information will be classified into the category "infrastructure problems."

[0505] Urgency judgment

[0506] The server identifies the region and urgency level based on the analyzed content. Specifically, it analyzes keywords and phrases in the text, and if they are of high urgency, it classifies them as "high urgency." For example, keywords such as "help" and "fire" are treated as high urgency.

[0507] notification

[0508] The server then notifies the relevant organizations based on the identified information. For example, if high-urgency information such as "water is not coming out in ward X" is extracted, the information is immediately sent to the waterworks bureau. This is done using real-time notification methods via APIs and webhooks.

[0509] Specific examples

[0510] Below are a series of examples of this system in action:

[0511] 1. Users

[0512] A user posts on Twitter, "There is no water in XX ward."

[0513] 2. Terminal

[0514] The device periodically retrieves these posts using the SNS API and temporarily stores them.

[0515] It then sends the saved post to the server.

[0516] 3. Server

[0517] The server stores the posts received from the terminals in a database.

[0518] Analyze the text data and extract IP addresses and area names.

[0519] Posts containing the keyword "no water" are categorized as "infrastructure problems."

[0520] 4. Urgency determination

[0521] Text analysis determines that this post is of "high urgency."

[0522] 5. Notification

[0523] The server immediately notifies the waterworks bureau of the information that "there is no water in XX ward."

[0524] In this way, this system can quickly and accurately grasp the situation in the disaster-stricken areas and prompt the appropriate relevant organizations to take prompt action, thereby enabling effective support to be provided to the disaster-stricken areas.

[0525] The processing flow will be explained below.

[0526] Step 1:

[0527] User

[0528] A user posts on social media, such as "There is no water in ward XX." The information posted by the user is stored on the social media platform.

[0529] Step 2:

[0530] Terminal

[0531] The device periodically connects to the SNS API to check for new posts containing specific hashtags or keywords such as "disaster" or "rescue." The new posts retrieved from the API are temporarily stored in the device's storage.

[0532] Step 3:

[0533] Terminal

[0534] The device analyzes the collected posting data, extracts metadata such as the user's IP address and the content of the post, and formats this data for transmission to the server.

[0535] Step 4:

[0536] Terminal

[0537] The formatted data is sent to the server via an API endpoint that is designed to ensure it reaches the server.

[0538] Step 5:

[0539] server

[0540] The server stores the data received from the device in a database, which is then used for subsequent analysis.

[0541] Step 6:

[0542] server

[0543] The server then analyzes the received text data using natural language processing (NLP), which involves extracting IP addresses, location names, and specific keywords and phrases from the text.

[0544] Step 7:

[0545] server

[0546] Based on the parsed data, we use the GeoIP library to extract location information from IP addresses, which allows us to determine which region a post originates from.

[0547] Step 8:

[0548] server

[0549] The posts are then categorized based on the extracted keywords and phrases. For example, a post about "no water" would be classified as "infrastructure problems."

[0550] Step 9:

[0551] server

[0552] An urgency assessment algorithm is applied to assess the urgency of the analyzed data. Posts that are deemed to be of high urgency require immediate and appropriate action.

[0553] Step 10:

[0554] server

[0555] Once the urgency assessment is complete, appropriate relevant organizations (national government, local government, medical organizations, etc.) will be notified. Notifications will be sent in real time via API or webhook.

[0556] Step 11:

[0557] server

[0558] The system confirms that notifications have been sent successfully and records the history in a database, making it possible to track which information was sent to which institution and when.

[0559] Through the above processing steps, the system quickly collects and analyzes information of high urgency in the affected area and notifies the appropriate relevant agencies, thereby facilitating a rapid response.

[0560] Example 1

[0561] 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."

[0562] During natural disasters and emergencies, many people use social media and email to seek help, but there is a problem of difficulty in collecting and analyzing this information appropriately and quickly and notifying the relevant authorities. In particular, if geographic information is not accurately identified and the level of urgency is not accurately assessed, appropriate responses may be delayed. In conventional systems, these tasks are often performed manually, requiring a great deal of time and effort. Furthermore, response delays are likely to occur due to delayed recognition and overlooked information.

[0563] 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.

[0564] In this invention, the server includes a means for automatically collecting information about the level of urgency from SNS, a means for storing data sent directly from users in a central database, and a means for extracting meaning from the collected text data using text analysis technology. This makes it possible to automatically collect emergency information, appropriately analyze it, and promptly notify relevant organizations.

[0565] "SNS" stands for Social Networking Service, a platform for people to interact and share information online.

[0566] "Text analytics" is the process of extracting meaning and information from text data using natural language processing techniques.

[0567] "Urgency" is an index that evaluates how quickly the information requires a response.

[0568] "Categorization" is the process of grouping text data based on specific themes or content.

[0569] "Text data" is a collection of textual information written in a human-readable format.

[0570] "Relevant organizations" is a general term for organizations and groups that are responsible for receiving and responding to emergency information.

[0571] "Geographic identification technology" is a technology that identifies geographical locations and regions from information such as IP addresses.

[0572] MODE FOR CARRYING OUT THE INVENTION

[0573] This invention is a system for quickly grasping the situation in disaster-stricken areas and taking appropriate measures. This system comprises a series of processes that collect and analyze social media posts and inquiries, and notify relevant organizations of the results. The detailed components and processing procedures of the system are described below.

[0574] System Configuration

[0575] The system consists of the following main components:

[0576] 1. Terminal

[0577] 2. Server

[0578] 3. Social Media API

[0579] 4. GeoIP Library

[0580] 5. Natural Language Processing (NLP) Module

[0581] Hardware and Software Use

[0582] Terminal

[0583] The device is responsible for collecting inquiries from users and businesses and sending them to a server. Specifically, the device uses SNS APIs (e.g., Twitter API, Facebook Graph API) to periodically check for posts containing specific hashtags (e.g., "disaster" or "rescue") and temporarily store them. It also collects data on inquiries to businesses in a similar manner and periodically sends this data to the server. For example, the device can make a request to the SNS API every 15 minutes to retrieve new posts and store them in local storage.

[0584] server

[0585] The server receives the information sent from the device and stores it in a database. Next, it uses NLP technology to analyze the received text data and uses the GeoIP library to extract IP addresses and area names. For example, the server uses an NLP module (e.g., spaCy, BERT) to analyze the text, extract specific keywords, and understand the content. It also uses a GeoIP library (e.g., GeoIP2) to obtain geographical information from the IP address. This series of processes allows it to extract specific phrases such as "no water" or "need help" and identify area information based on them.

[0586] Urgency assessment and notification

[0587] The server evaluates the urgency level based on the analyzed data and identifies those with high urgency. It calculates an urgency score for each category, and if the score exceeds a predetermined threshold, it marks it as "high urgency." For example, the server recognizes posts containing keywords such as "help" or "fire" as high urgency. The server then notifies relevant authorities of high urgency information. This can be done in real time using APIs or webhooks. For example, it can send a request to the API endpoint of a waterworks or fire department to convey emergency information.

[0588] Specific examples

[0589] Below is an example of how this system works:

[0590] 1. Users

[0591] A user posts on Twitter, "There is no water in XX ward."

[0592] 2. Terminal

[0593] The device periodically retrieves these posts using the SNS API, temporarily stores them, and then sends them to the server.

[0594] 3. Server

[0595] The server stores the posts received from the devices in a database. It then analyzes the text data to extract IP addresses and area names. Posts containing the keyword "no water" are categorized as "infrastructure problems."

[0596] 4. Urgency determination

[0597] Text analysis determines that this post is of "high urgency."

[0598] 5. Notification

[0599] The server immediately notifies the waterworks bureau of the information that "there is no water in XX ward."

[0600] In this way, the system can quickly and accurately grasp the situation in the disaster-stricken areas and prompt the appropriate relevant organizations to take prompt action.

[0601] Prompt Sentence Examples

[0602] Below are some example prompts to input to a generative AI model:

[0603] Please explain the system that efficiently collects and analyzes information about disaster areas posted on social media such as Twitter and Instagram to identify the level of urgency and area, and promptly notifies relevant organizations.

[0604] Components of this system

[0605] How we collect information

[0606] Analysis and classification methods

[0607] Urgency assessment criteria

[0608] Notification method description

[0609] Actual operation example

[0610] This enables the system to automatically collect emergency information, analyze it appropriately, and quickly notify relevant agencies.

[0611] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0612] Step 1:

[0613] The device uses the SNS API to collect posts containing specific hashtags (e.g., "disaster," "rescue"). The input is the post data obtained from the SNS API, and this data is temporarily stored in the device's local storage. The collected and stored data is output. Specifically, the device sends a request to the Twitter API every 15 minutes to obtain the latest posts.

[0614] Step 2:

[0615] The device collects inquiries from users to the company. The input is emails and chat messages from the customer support system, which are temporarily stored in the device's local storage. The collected inquiry data is output. Specifically, the device connects to the email server, retrieves unread emails from a specific folder, and saves them.

[0616] Step 3:

[0617] The device sends the collected SNS posts and inquiries to the server. The input is data stored in the device's local storage and is sent to the server using the HTTPS protocol. The sent data is received by the server. Specifically, the device periodically compiles the collected data in batch format and sends a POST request to the server's API endpoint.

[0618] Step 4:

[0619] The server analyzes the received text data using NLP technology. The input is text data from social media posts and inquiries, and meaning is extracted using an NLP module (e.g., spaCy, BERT). The extracted semantic information is output. Specifically, the server uses an NLP library to perform morphological analysis of the text and identify important keywords and phrases.

[0620] Step 5:

[0621] The server uses a GeoIP library to extract region information from IP addresses. The input is the IP address contained in a post or query, and a GeoIP library (e.g., GeoIP2) is used to obtain the geographic coordinates and region name. The extracted region information is output. Specifically, the server queries the GeoIP database for the IP address and obtains the corresponding region information.

[0622] Step 6:

[0623] The server classifies the posts into categories based on the results of text analysis. The input is the extraction results from NLP, and the data is grouped using a categorization algorithm. The classified category information is output. Specifically, the server classifies posts into categories such as "infrastructure issues" and "lifesaving" based on specific keywords.

[0624] Step 7:

[0625] The server evaluates the urgency level based on the classified data. The input is categorized data, and the urgency level is determined using an algorithm that calculates an urgency score. Data with a high urgency level is output as "high urgency." Specifically, the server calculates the urgency score based on the presence or absence of keywords such as "help" or "fire," and marks anything that exceeds a threshold as high urgency.

[0626] Step 8:

[0627] The server notifies the relevant authorities of any identified high-urgency information. The input is data determined to be of high urgency, and notifications are sent in real time using APIs and web hooks. The notified information is then output. Specifically, the server sends requests to APIs of waterworks departments, fire departments, etc., to convey the necessary emergency information. Notifications are also sent via email and SMS.

[0628] (Application example 1)

[0629] 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."

[0630] Conventional information gathering and emergency response systems in disaster areas have the problem of taking time to gather and analyze information, making it difficult to respond quickly. In particular, in the event of trouble or an emergency at a factory, a fast and effective response is required. Against this background, there is a growing need for a system that can collect and analyze information in real time and immediately notify relevant organizations and employees.

[0631] 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.

[0632] In this invention, the server includes means for collecting posts related to urgency using an SNS API, means for sending the content of inquiries to an information processing device, and means for analyzing the collected posts and inquiry content and extracting communication point information and location names. This makes it possible to display notification content on the smart glasses in real time.

[0633] "SNS API" refers to an application programming interface published by a social network service (SNS) provider, through which data on the SNS can be obtained and manipulated.

[0634] "Content of inquiry" refers to the content of communication including information provided, questions, reports, etc. from users and related parties, and the system uses this as data to be analyzed.

[0635] An "information processing device" is part of a computer system that collects, analyzes, stores, and notifies data, and includes servers and cloud services.

[0636] "Communication location information" refers to data obtained as location information of communication devices, and geographical information is identified based on this data.

[0637] "Place name" refers to a geographical name or area name, and is used to extract location information.

[0638] "Smart glasses" are a type of wearable device, a pair of eyeglass-type electronic devices that provide information to users by displaying visual information on a display.

[0639] "Real-time" means being able to process an event the moment it occurs, and being able to provide and process information without delay.

[0640] "NLP" stands for natural language processing, and is a technology that analyzes, understands, and interprets information contained in text data and spoken language.

[0641] "GeoIP Library" means a software library for obtaining geographic location information from an IP address, which is used in conjunction with an IP address to determine location.

[0642] The present invention is a system that uses a social networking service (SNS) API to collect posts related to urgency, transmits the contents of inquiries to an information processing device, analyzes the collected posts and inquiry contents, extracts communication point information and location names, identifies the location and urgency based on the analyzed contents, notifies related devices of the identified information, and displays the notification contents on smart glasses in real time.

[0643] Overall system configuration

[0644] The system mainly consists of the following components:

[0645] 1. Terminal

[0646] 2. Server

[0647] 3. Social Media API

[0648] 4. GeoIP Library

[0649] 5. Natural Language Processing (NLP) Module

[0650] 6. Smart Glasses

[0651] Terminal

[0652] The device collects posts from users and related parties related to inquiries and their urgency, and sends them to the server. Specifically, the device uses SNS APIs to periodically check for posts containing specific hashtags such as "factory trouble" and temporarily saves them. It also collects inquiry data and sends it to the server.

[0653] server

[0654] The server receives the information sent from the device and stores it in a database. Next, it analyzes the received text data and extracts communication point information and location names. At this time, it uses the GeoIP library to obtain region information from IP addresses. It then uses NLP technology to analyze the text and classify the post content into categories. For example, if the post content contains the keyword "fire broke out," the information will be classified into the category "fire accident."

[0655] Urgency judgment

[0656] The server identifies the location and urgency based on the analyzed content. Specifically, it analyzes keywords and phrases in the text, and if they are of high urgency, it classifies them as "high urgency." For example, keywords such as "fire" and "explosion" are treated as high urgency.

[0657] Notifications and Displays

[0658] The server then sends notifications to relevant devices based on the identified information. For example, if high-urgency information such as "A fire has broken out at Factory A" is extracted, the information is immediately sent to the fire department and relevant parties. Furthermore, the notification content is displayed in real time on the smart glasses, accelerating response.

[0659] Specific examples

[0660] A series of examples of how the system can be implemented include the following:

[0661] 1. Users

[0662] A user posts on Twitter, "There's a fire at Factory A."

[0663] 2. Terminal

[0664] The device periodically retrieves these posts using the SNS API, temporarily stores them, and then sends them to the server.

[0665] 3. Server

[0666] The server stores the posts received from the devices in a database, analyzes the text data, and extracts communication point information and location names. Posts containing the keyword "fire breaks out" are categorized as "fire accidents."

[0667] 4. Urgency determination

[0668] Text analysis determines that this post is of "high urgency."

[0669] 5. Notices and Displays

[0670] The server immediately notifies the fire department that "a fire has broken out at Factory A," and the smart glasses display a message saying "Fire has broken out. Please take emergency action."

[0671] Prompt Sentence Examples

[0672] "Please build an emergency assessment system to detect and respond to factory troubles. This system will assess the emergency level and respond appropriately by collecting and analyzing social media posts containing the following specific hashtags."

[0673] This will enable quick and appropriate responses to troubles and emergencies within the factory.

[0674] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0675] Step 1:

[0676] The device uses SNS APIs to collect posts related to urgency. During this process, the device periodically checks for posts containing specific hashtags (e.g., "factory trouble") and temporarily stores their contents. The input is the raw data of SNS posts, and the output is the temporarily stored post data related to urgency. Data processing involves filtering and storing the raw data obtained through the SNS API.

[0677] Step 2:

[0678] The terminal sends the collected posts and inquiry contents to the information processing device. The saved post data related to urgency is sent to the server. The input is the post data saved in step 1, and the output is the post data sent to the server. Data processing includes sending the saved data on the terminal to the server via network communication.

[0679] Step 3:

[0680] The server stores the received post data in a database and uses an NLP module to analyze the text data. The input is the post data sent to the server, and the output is the analysis results. Specifically, NLP technology is used to classify the post content into categories and extract important keywords and phrases.

[0681] Step 4:

[0682] The server uses the GeoIP library to obtain communication point information from the poster's IP address and identify the location name. The input is the IP address and analysis results contained in the posted data, and the output is communication point information and the location name. Specifically, the GeoIP library analyzes the IP address to extract geographical location information.

[0683] Step 5:

[0684] The server identifies the location and urgency based on the analyzed content. Information with a high urgency level is classified as "high urgency" based on keywords and phrases in the text. The input is the NLP analysis results and communication point information, and the output is the urgency classification result. For data calculation, an urgency determination algorithm is used to evaluate and classify the text analysis results.

[0685] Step 6:

[0686] The server notifies the relevant devices of the identified information. For example, if there is information that "a fire has broken out at Factory A," it will immediately notify the fire department and relevant parties. The input is the urgency classification result and specific location information, and the output is a notification message. Specifically, it uses a notification API or web hook to send information to relevant devices in real time.

[0687] Step 7:

[0688] The server displays the notification content on the smart glasses in real time. The input is the notification message, and the output is the information displayed on the smart glasses' display. The server sends the same notification as the information sent to the related devices to the smart glasses, providing the user with information in real time. Specifically, the message is displayed through an API dedicated to the smart glasses.

[0689] 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.

[0690] This invention relates to a system for grasping the situation in disaster-stricken areas and taking prompt and appropriate action. This system collects and analyzes social media posts and company inquiries to identify the level of urgency and the area, and notifies relevant organizations. Furthermore, it combines an emotion engine that recognizes user emotions to analyze the emotions in the posts and help identify the level of urgency.

[0691] Overall system configuration

[0692] The system mainly consists of the following components:

[0693] 1. Terminal

[0694] 2. Server

[0695] 3. Social Media API

[0696] 4. GeoIP Library

[0697] 5. Natural Language Processing (NLP) Module

[0698] 6. Emotion Engine

[0699] Terminal

[0700] The device collects inquiries from users and companies and sends them to a server. Specifically, the device uses SNS APIs to periodically check for posts containing specific hashtags such as "disaster" or "rescue" and temporarily stores them. It also collects data on inquiries to the company and sends this data to a server.

[0701] server

[0702] The server receives the information sent from the device and stores it in a database. The received text data is then analyzed using natural language processing (NLP). NLP analysis extracts IP addresses, local area names, and specific keywords and phrases from the text, and classifies the post content into categories. For example, if a post contains the keyword "no water," the information will be classified into the category "infrastructure problems."

[0703] Emotion Engine

[0704] The analysis on the server also uses an emotion engine. The emotion engine analyzes the emotions in the posted content and can identify emotions such as "sadness," "fear," and "anger." The emotion data obtained by the emotion engine is used to assist in determining the level of urgency.

[0705] Urgency judgment

[0706] The server uses NLP and an emotion engine to analyze the data and identify the region and level of urgency. Specifically, it analyzes keywords and phrases in the text, as well as the extracted emotion data, and classifies any that indicate a high level of urgency as "high urgency." For example, keywords such as "help" and "fire" are treated as high urgency, and if the emotion engine detects "fear," it is treated as an even higher level of urgency.

[0707] notification

[0708] The server then notifies the relevant organizations based on the identified information. For example, if high-urgency information such as "water is not coming out in ward X" is extracted, the information is immediately sent to the waterworks bureau. This is done using real-time notification methods via APIs and webhooks.

[0709] Specific examples

[0710] Below are a series of examples of this system in action:

[0711] 1. Users

[0712] A user posts on Twitter, "There is no water in XX ward." This post conveys the emotion of "I am in great trouble."

[0713] 2. Terminal

[0714] The device periodically retrieves these posts using the SNS API, temporarily stores them, and then sends them to the server.

[0715] 3. Server

[0716] The server stores the posts received from the devices in a database. It analyzes the text data and extracts IP addresses and area names. Posts containing the keyword "no water" are classified into the category "infrastructure problems."

[0717] 4. Emotion Engine

[0718] The emotion engine recognizes the emotion "very troubled" from the content of the post.

[0719] 5. Urgency determination

[0720] Based on text analysis and sentiment data, this post is determined to be of "high urgency."

[0721] 6. Notification

[0722] The server immediately notifies the waterworks bureau of the information that "there is no water in XX ward."

[0723] In this way, the system can quickly and accurately grasp the situation in the disaster area and prompt the appropriate relevant organizations to take prompt action. By adding an emotion engine, it becomes possible to make more accurate urgency judgments and gain a deeper understanding of the condition of the victims.

[0724] The processing flow will be explained below.

[0725] Step 1:

[0726] User

[0727] A user posts on social media, such as "There is no water in ward XX." The information posted by the user is stored on the social media platform.

[0728] Step 2:

[0729] Terminal

[0730] The device periodically connects to the SNS API to check for new posts containing specific hashtags or keywords such as "disaster" or "rescue." The new posts retrieved from the API are temporarily stored in the device's storage.

[0731] Step 3:

[0732] Terminal

[0733] The device analyzes the collected posting data, extracts metadata such as the user's IP address and the content of the post, and formats this data for transmission to the server.

[0734] Step 4:

[0735] Terminal

[0736] The formatted data is sent to the server via an API endpoint that is designed to ensure it reaches the server.

[0737] Step 5:

[0738] server

[0739] The server stores the data received from the device in a database, which is used for subsequent analysis.

[0740] Step 6:

[0741] server

[0742] The server then analyzes the received text data using natural language processing (NLP), which involves extracting IP addresses, location names, and specific keywords and phrases from the text.

[0743] Step 7:

[0744] server

[0745] Using data obtained from NLP analysis, we use the GeoIP library to extract geographic information from IP addresses, thereby identifying the region from which a post originates.

[0746] Step 8:

[0747] server

[0748] The NLP module classifies posts into categories based on keywords and phrases extracted. For example, a post about "no water" would be classified as "infrastructure problems."

[0749] Step 9:

[0750] server

[0751] The server uses an emotion engine to analyze the sentiment of the posts, using an emotion-identifying algorithm to identify emotions such as "sadness," "fear," and "anger."

[0752] Step 10:

[0753] server

[0754] Based on data obtained from NLP analysis and sentiment analysis, an urgency assessment algorithm is applied to assess the urgency of posts. Posts that are deemed to be of high urgency are immediately classified as "high urgency."

[0755] Step 11:

[0756] server

[0757] Based on information deemed to be of high urgency, relevant organizations (national government, local government, medical organizations, etc.) are notified. Notifications are sent in real time via API or webhook.

[0758] Step 12:

[0759] server

[0760] The system confirms that notifications have been sent successfully and records the history in a database, making it possible to track which information was sent to which institution and when.

[0761] Specific examples

[0762] Below are the steps by which the system actually works in a concrete example:

[0763] 1. Users

[0764] A user posts on Twitter, "There is no water in XX ward." This post conveys the emotion of "I am in great trouble."

[0765] 2. Terminal

[0766] The device uses the Twitter API to check posts with the hashtag "disaster," retrieves these posts, stores them temporarily, and then sends the data to the server.

[0767] 3. Server

[0768] The server receives the posted data obtained from the terminal and stores it in a database.

[0769] 4. Server

[0770] It uses an NLP module to parse the text and extract keywords like "no water," while also using the GeoIP library to determine the region of the post from its IP address.

[0771] 5. Server

[0772] Using a sentiment engine, the sentiment of the post is identified as "very distressed."

[0773] 6. Server

[0774] Using an urgency assessment algorithm, messages are classified as "high urgency" based on information obtained from text analysis and sentiment analysis.

[0775] 7. Server

[0776] Based on highly urgent information such as "water is not coming out in ward XX," the waterworks bureau is notified immediately.

[0777] 8. Server

[0778] Records that the notification was successful and stores the history in a database.

[0779] In this way, the system can quickly and accurately grasp the situation in the disaster area and prompt the appropriate relevant organizations to take prompt action. By adding an emotion engine, it becomes possible to make more accurate urgency judgments and gain a deeper understanding of the condition of the victims.

[0780] Example 2

[0781] 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."

[0782] The problem is that it is difficult to gather and analyze information to quickly and accurately grasp the situation in disaster-stricken areas and take appropriate measures. In particular, the technical challenge is extracting useful information from the vast amount of data on social media and inquiries, and determining the level of urgency. Furthermore, by adding emotion analysis, more accurate urgency determination is required.

[0783] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0784] In this invention, the server includes: [means for collecting posts related to urgency using an SNS API;] [means for sending the content of inquiries to the organization's server;] [means for analyzing the collected posts and inquiry content and extracting IP addresses and regional information;] [means for analyzing the content of posts using a Natural Language Processing (NLP) module and extracting keywords and phrases;] ​​[means for analyzing the emotions of the content of posts using an emotion engine;] [means for identifying the region and urgency based on the analyzed content; and [means for notifying relevant organizations of the identified information.] This makes it possible to quickly and accurately grasp the situation in the disaster-stricken areas and to promptly notify appropriate relevant organizations.

[0785] "SNS API" is an application programming interface that allows programs to use posted data from social networking services.

[0786] "Inquiries" refer to the content of communication such as questions, consultations, and requests made by users and related parties to an organization.

[0787] A "server" is a computer system that receives, stores, analyzes, and transmits data over a network.

[0788] "IP address" refers to a unique numeric code used when sending and receiving data on the Internet.

[0789] "Region information" refers to information about a particular geographic area, including city, ward, town, village name, postal code, etc.

[0790] A "Natural Language Processing (NLP) module" is a software component that allows a computer to analyze human natural language and understand its meaning and structure.

[0791] "Keywords" refer to words or phrases that are particularly important within text data.

[0792] An "emotion engine" is a software component that analyzes emotions from text data and classifies them into specific emotion categories (e.g., joy, sadness, fear, etc.).

[0793] "Analyzed content" refers to the information obtained as a result of analyzing collected data using an NLP module or emotion engine.

[0794] "Urgency" is a measure that indicates the level of urgency of data or an event, and is used to determine the priority of responses.

[0795] "Relevant organizations" refer to government agencies, private companies, non-governmental organizations (NGOs), etc. that need to respond based on specific information.

[0796] This invention relates to a system for quickly and accurately grasping the situation in disaster-stricken areas and taking appropriate measures. This system collects social media posts and inquiries to companies, analyzes them, identifies the level of urgency and the area, and notifies the relevant organizations.

[0797] Overall system configuration

[0798] The system mainly consists of the following components:

[0799] 1. Terminal

[0800] 2. Server

[0801] 3. Social Media API

[0802] 4. GeoIP Library

[0803] 5. Natural Language Processing (NLP) Module

[0804] 6. Emotion Engine

[0805] Terminal

[0806] The device collects inquiries from users and companies and sends them to a server. Specifically, the device uses SNS APIs to periodically check for posts containing specific hashtags such as "disaster" or "rescue" and temporarily stores them. It also collects data on inquiries to the company and sends this data to a server.

[0807] server

[0808] The server receives the information sent from the device and stores it in a database. Next, it analyzes the received text data using a natural language processing (NLP) module. NLP analysis extracts IP addresses, local area names, and specific keywords and phrases from the text, and classifies the post content into categories. For example, if the post content contains the keyword "no water," the information will be classified into the category "infrastructure problems."

[0809] Emotion Engine

[0810] The analysis on the server also uses an emotion engine. The emotion engine analyzes the emotions in the posted content and can identify emotions such as "sadness," "fear," and "anger." The emotion data obtained by the emotion engine is used to assist in determining the level of urgency.

[0811] Urgency judgment

[0812] The server uses NLP and an emotion engine to analyze the data and identify the region and level of urgency. Specifically, it analyzes keywords and phrases in the text, as well as the extracted emotion data, and classifies any that indicate a high level of urgency as "high urgency." For example, keywords such as "help" and "fire" are treated as high urgency, and if the emotion engine detects "fear," it is treated as an even higher level of urgency.

[0813] notification

[0814] The server then notifies the relevant organizations based on the identified information. For example, if high-urgency information such as "water is not coming out in ward X" is extracted, the information is immediately sent to the waterworks bureau. This is done using real-time notification methods via APIs and webhooks.

[0815] Specific examples

[0816] Below are a series of examples of this system in action:

[0817] 1. Users

[0818] A user posts on Twitter, "There is no water in XX ward." This post conveys the emotion of "I am in great trouble."

[0819] 2. Terminal

[0820] The device periodically retrieves these posts using the SNS API, temporarily stores them, and then sends them to the server.

[0821] 3. Server

[0822] The server stores the posts received from the devices in a database. It analyzes the text data and extracts IP addresses and area names. Posts containing the keyword "no water" are classified into the category "infrastructure problems."

[0823] 4. Emotion Engine

[0824] The emotion engine recognizes the emotion "very troubled" from the content of the post.

[0825] 5. Urgency determination

[0826] Based on text analysis and sentiment data, this post is determined to be of "high urgency."

[0827] 6. Notification

[0828] The server immediately notifies the waterworks bureau of the information that "there is no water in XX ward."

[0829] In this way, the system can quickly and accurately grasp the situation in the disaster area and prompt the appropriate relevant organizations to take prompt action.In addition, by using the emotion engine, the accuracy of urgency determination can be improved, enabling a deeper understanding of the condition of the victims.

[0830] Prompt Sentence Examples

[0831] Please explain how the system works: collects posts on Twitter that contain the hashtags "disaster" and "rescue," determines the area and urgency based on the content, and notifies the relevant organizations.

[0832] Using this prompt, the generative AI model can generate sentences like the one above that detail the process of the system.

[0833] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0834] Step 1:

[0835] User posts to SNS

[0836] Users post on Twitter or other SNSs using hashtags such as "disaster" or "rescue." For example, they might post something like, "There's no water in XX ward. We're in a lot of trouble." The input is the user's SNS post, and the output is the post itself. The specific actions a user takes are logging in to the SNS using a smartphone or PC and posting.

[0837] Step 2:

[0838] The device collects posts

[0839] The device periodically checks for posts containing these hashtags using the SNS API. The device collects the posts, temporarily stores them in local storage, and then sends them to the server. The input is the user's SNS posts, and the output is the collected post data. Specifically, the device searches for posts using the SNS API, retrieves and saves the relevant posts, and sends them to the server.

[0840] Step 3:

[0841] The server receives the data

[0842] The server receives the posted data sent from the device and stores it in a database. The input is the posted data sent from the device, and the output is the data stored in the database. Specifically, the server analyzes the received data, formats it, and then inserts it into the database.

[0843] Step 4:

[0844] The server uses the NLP module to analyze the text.

[0845] The server uses an NLP module to analyze the received text data. It extracts IP addresses, local area names, and specific keywords and phrases from the text and categorizes the posts. The input is the received text data, and the output is data such as analyzed keywords, local area names, and IP addresses. Specifically, it runs the NLP module to analyze and extract each element of the text.

[0846] Step 5:

[0847] The server performs emotion analysis using the emotion engine.

[0848] The server uses an emotion engine to analyze the emotions in the posted content. For example, emotions such as "fear" or "confusion" can be identified from the text data. The input is the text data, and the output is the detected emotion information. Specifically, the emotion engine is executed to extract emotion data from the text and identify which emotions are contained.

[0849] Step 6:

[0850] The server determines the urgency

[0851] The server determines the urgency of a post based on the results of the NLP and emotion engine. It analyzes keywords, phrases, and emotional data in the text and determines the urgency level from high to low. The input is the analyzed keywords and emotional information, and the output is the urgency level determination result. Specifically, it evaluates the extracted data and sets the urgency level.

[0852] Step 7:

[0853] The server notifies the relevant parties

[0854] The server notifies relevant organizations of specific information based on the results of the assessment. For example, if there is high-urgency information such as "water is not coming out in ward XX," it will notify the waterworks bureau. The input is the urgency assessment result, and the output is the sent notification. Specific operations include sending real-time notifications using APIs and webhooks.

[0855] This will enable the entire system to operate efficiently and to quickly and appropriately communicate the situation in the disaster-stricken areas to relevant organizations.

[0856] (Application example 2)

[0857] 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."

[0858] Conventional emergency response systems have difficulty in quickly and accurately grasping the situation in disaster-stricken areas, resulting in delayed appropriate responses. Furthermore, they often failed to properly assess the emotions and urgency contained in posts on social media, resulting in a failure to respond immediately to highly urgent situations. Furthermore, delays in notification to relevant organizations have also led to delays in rescue efforts for victims.

[0859] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0860] In this invention, the server includes: means for collecting posts related to urgency using a social networking service (SNS) API; means for sending inquiry content to a database server; means for analyzing the collected posts and inquiry content and extracting IP addresses and local area names; emotion engine means for analyzing the emotional state of the posts; means for identifying the local area and urgency level based on the analyzed content and emotional state; and means for notifying relevant organizations and security services of the identified information. This allows for rapid identification of the local area and urgency level of the collected posts, enabling immediate notification to relevant organizations. Furthermore, the emotion engine also performs emotion analysis of the posts, allowing for accurate identification of high-urgency situations, enabling rapid and appropriate responses. Furthermore, natural language processing and emotion analysis using a generative AI model enables more advanced information analysis and improved decision accuracy.

[0861] "SNS API" is an application programming interface for accessing data from social networking services (SNS).

[0862] A "database server" is a server that manages a database and performs operations such as storing, searching, updating, and deleting data.

[0863] "Posted content" refers to text and media information that users make public on social media and other communication platforms.

[0864] "Inquiry content" is text information of questions or opinions that users have made to companies or organizations.

[0865] An "IP address" is a unique number that identifies a device on the Internet.

[0866] A "region name" is a name that indicates a specific geographical area.

[0867] An "emotion engine" is a software module that analyzes emotions in text data and identifies the emotional state.

[0868] "Urgency" is an indicator of the level of urgency of a particular event or situation.

[0869] "Relevant organizations" refers to organizations or organisations directly involved in emergency and disaster response.

[0870] "Security services" is a general term for services that protect people and assets, prevent crime, and deal with disasters.

[0871] A "generative AI model" is an artificial intelligence model built using machine learning and deep learning, which learns from specific tasks and makes predictions and analyses.

[0872] A "prompt" is text that provides instructions or example input given to a generative AI model to perform a specific task.

[0873] The present invention is a system for quickly and accurately grasping the situation in a disaster area and prompting appropriate organizations to respond. Specific embodiments for carrying out the present invention are described below.

[0874] Overall system configuration

[0875] The system mainly consists of the following components:

[0876] 1. Terminal

[0877] 2. Server

[0878] 3. Social Media API

[0879] 4. Database Server

[0880] 5. Natural Language Processing (NLP) Module

[0881] 6. Emotion Engine

[0882] 7. Generative AI Models

[0883] Terminal

[0884] The device is responsible for collecting inquiries from users and businesses and sending this data to a server. Specifically, the device uses SNS APIs to periodically check for posts containing specific hashtags such as "disaster" or "rescue" and temporarily stores them. Inquiries to businesses are also collected in the same way and sent to the server.

[0885] server

[0886] The server receives the information sent from the device and stores it in a database server. The received text data is then analyzed using an NLP module. NLP analysis extracts IP addresses, local area names, and specific keywords and phrases from the text, and classifies the posted content into categories.

[0887] Emotion Engine

[0888] The server also uses an emotion engine to analyze the emotions in the posts and identify emotions such as "fear," "sadness," and "confusion."

[0889] Urgency judgment

[0890] The server identifies the region and urgency based on the data analyzed using the NLP module and emotion engine. Specifically, it analyzes keywords and phrases in the text as well as the extracted emotion data, and if it indicates a high level of urgency, it classifies it as "high urgency." For example, keywords such as "help" and "fire" are treated as high urgency, and if the emotion engine detects "fear," it is treated as an even higher level of urgency.

[0891] notification

[0892] The server then notifies relevant authorities and security services based on the identified information, using APIs and webhooks to prompt immediate action in real time.

[0893] Specific examples

[0894] Here's an example of this system in action:

[0895] Example 1: Collecting and analyzing social media posts

[0896] 1. Users

[0897] A user posts on Twitter, "Disaster Fire There's a fire in XX ward. It's very dangerous, please help."

[0898] 2. Terminal

[0899] The device periodically retrieves these posts using the SNS API, temporarily stores them, and then sends them to the server.

[0900] 3. Server

[0901] The server stores the posts received from the devices in a database server. The text data is analyzed to extract IP addresses and area names. Posts containing the keyword "fire" are classified as "high urgency."

[0902] 4. Emotion Engine

[0903] The emotion engine recognizes the emotion "It's very dangerous, please help" from the content of the post.

[0904] 5. Urgency determination

[0905] Based on text analysis and sentiment data, this post is determined to be of "high urgency."

[0906] 6. Notification

[0907] The server immediately notifies the fire department and security services of the information "There is a fire in ward XX."

[0908] Prompt Sentence Examples

[0909] Here are some example prompts to apply to generative AI models:

[0910] Prompt: "Create a program that analyzes the sentiment of posts collected from social media, extracts local information, and determines the level of urgency. If the level of urgency is high, include a function to notify the relevant authorities."

[0911] The above is the details of the "Mode for Carrying Out the Invention." By using this system, it is possible to quickly and accurately grasp the situation in the disaster area and respond appropriately.

[0912] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0913] Step 1:

[0914] A user posts an emergency situation on a social networking service (SNS). This post includes a hashtag (e.g., "disaster" or "fire") and a specific description of the situation (e.g., "There's a fire in ____ ward. It's very dangerous. Please help.").

[0915] Step 2:

[0916] The device periodically calls the SNS API to search and collect posts containing specific hashtags. This temporarily stores newly posted emergency information. The input is data from the SNS API, and the output is the temporarily stored post data.

[0917] Step 3:

[0918] The terminal transmits the temporarily saved posted data to the server. Here, the input is the temporarily saved posted data, and the output is the data sent to the server. This data includes the text of the post, the poster's IP address, and the posting date and time.

[0919] Step 4:

[0920] The server stores the received submission data in a database server. This ensures that the data required for subsequent analysis steps is stored persistently. The input is the data sent from the device, and the output is the data stored in the database.

[0921] Step 5:

[0922] The server analyzes the saved posting data using an NLP (Natural Language Processing) module, which extracts location-related information (place names and IP addresses) and specific keywords and phrases from the posting content. The input is the posting data retrieved from the database, and the output is the analyzed text data and extracted location information.

[0923] Step 6:

[0924] The server uses an emotion engine to analyze the emotional state of the post. Emotions such as "fear," "sadness," and "confusion" are identified. The input is the analyzed text data, and the output is the extracted emotional data.

[0925] Step 7:

[0926] The server determines the urgency level based on data analyzed by the NLP module and emotion engine. If the keyword "fire" or the emotion "fear" is identified, it is classified as high urgency. The input is the analyzed text data and emotion data, and the output is the determined urgency information.

[0927] Step 8:

[0928] The server notifies relevant organizations and security services based on the determined urgency information. Notifications are sent via API or web hooks, and if the urgency is high, notifications are sent immediately. The input is urgency information, and the output is notification data sent to relevant organizations.

[0929] Step 9:

[0930] The relevant authorities receive the notification from the server and take immediate action. Specifically, the fire department may be dispatched to the scene. The input is the notification data from the server, and the output is the actual response action.

[0931] The above is the specific flow of the processing of the present invention. Through these steps, it becomes possible to quickly and accurately grasp the situation in the disaster area and respond appropriately.

[0932] 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.

[0933] 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.

[0934] 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.

[0935] [Third embodiment]

[0936] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0937] 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.

[0938] 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).

[0939] 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.

[0940] 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.

[0941] 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).

[0942] 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.

[0943] 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.

[0944] 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.

[0945] 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.

[0946] 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.

[0947] 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."

[0948] This invention relates to a system for understanding the situation in disaster-stricken areas and taking prompt and appropriate action. This system collects social media posts and inquiries to companies, analyzes them, identifies the level of urgency and the area, and notifies relevant organizations.

[0949] Overall system configuration

[0950] The system mainly consists of the following components:

[0951] 1. Terminal

[0952] 2. Server

[0953] 3. Social Media API

[0954] 4. GeoIP Library

[0955] 5. Natural Language Processing (NLP) Module

[0956] Terminal

[0957] The device collects inquiries from users and companies and sends them to a server. Specifically, the device uses SNS APIs to periodically check for posts containing specific hashtags such as "disaster" or "rescue" and temporarily stores them. It also collects data on inquiries to the company and sends this data to a server.

[0958] server

[0959] The server receives the information sent from the device and stores it in a database. Next, it analyzes the received text data and extracts the IP address and area name. At this time, it uses the GeoIP library to obtain area information from the IP address. It then analyzes the text using NLP technology and classifies the post content into categories. For example, if the post content contains the keyword "no water," the information will be classified into the category "infrastructure problems."

[0960] Urgency judgment

[0961] The server identifies the region and urgency level based on the analyzed content. Specifically, it analyzes keywords and phrases in the text, and if they are of high urgency, it classifies them as "high urgency." For example, keywords such as "help" and "fire" are treated as high urgency.

[0962] notification

[0963] The server then notifies the relevant organizations based on the identified information. For example, if high-urgency information such as "water is not coming out in ward X" is extracted, the information is immediately sent to the waterworks bureau. This is done using real-time notification methods via APIs and webhooks.

[0964] Specific examples

[0965] Below are a series of examples of this system in action:

[0966] 1. Users

[0967] A user posts on Twitter, "There is no water in XX ward."

[0968] 2. Terminal

[0969] The device periodically retrieves these posts using the SNS API and temporarily stores them.

[0970] It then sends the saved post to the server.

[0971] 3. Server

[0972] The server stores the posts received from the terminals in a database.

[0973] Analyze the text data and extract IP addresses and area names.

[0974] Posts containing the keyword "no water" are categorized as "infrastructure problems."

[0975] 4. Urgency determination

[0976] Text analysis determines that this post is of "high urgency."

[0977] 5. Notification

[0978] The server immediately notifies the waterworks bureau of the information that "there is no water in XX ward."

[0979] In this way, this system can quickly and accurately grasp the situation in the disaster-stricken areas and prompt the appropriate relevant organizations to take prompt action, thereby enabling effective support to be provided to the disaster-stricken areas.

[0980] The processing flow will be explained below.

[0981] Step 1:

[0982] User

[0983] A user posts on social media, such as "There is no water in ward XX." The information posted by the user is stored on the social media platform.

[0984] Step 2:

[0985] Terminal

[0986] The device periodically connects to the SNS API to check for new posts containing specific hashtags or keywords such as "disaster" or "rescue." The new posts retrieved from the API are temporarily stored in the device's storage.

[0987] Step 3:

[0988] Terminal

[0989] The device analyzes the collected posting data, extracts metadata such as the user's IP address and the content of the post, and formats this data for transmission to the server.

[0990] Step 4:

[0991] Terminal

[0992] The formatted data is sent to the server via an API endpoint that is designed to ensure it reaches the server.

[0993] Step 5:

[0994] server

[0995] The server stores the data received from the device in a database, which is then used for subsequent analysis.

[0996] Step 6:

[0997] server

[0998] The server then analyzes the received text data using natural language processing (NLP), which involves extracting IP addresses, location names, and specific keywords and phrases from the text.

[0999] Step 7:

[1000] server

[1001] Based on the parsed data, we use the GeoIP library to extract location information from IP addresses, which allows us to determine which region a post originates from.

[1002] Step 8:

[1003] server

[1004] The posts are then categorized based on the extracted keywords and phrases. For example, a post about "no water" would be classified as "infrastructure problems."

[1005] Step 9:

[1006] server

[1007] An urgency assessment algorithm is applied to assess the urgency of the analyzed data. Posts that are deemed to be of high urgency require immediate and appropriate action.

[1008] Step 10:

[1009] server

[1010] Once the urgency assessment is complete, appropriate relevant organizations (national government, local government, medical organizations, etc.) will be notified. Notifications will be sent in real time via API or webhook.

[1011] Step 11:

[1012] server

[1013] The system confirms that notifications have been sent successfully and records the history in a database, making it possible to track which information was sent to which institution and when.

[1014] Through the above processing steps, the system quickly collects and analyzes information of high urgency in the affected area and notifies the appropriate relevant agencies, thereby facilitating a rapid response.

[1015] Example 1

[1016] 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."

[1017] During natural disasters and emergencies, many people use social media and email to seek help, but there is a problem of difficulty in collecting and analyzing this information appropriately and quickly and notifying the relevant authorities. In particular, if geographic information is not accurately identified and the level of urgency is not accurately assessed, appropriate responses may be delayed. In conventional systems, these tasks are often performed manually, requiring a great deal of time and effort. Furthermore, response delays are likely to occur due to delayed recognition and overlooked information.

[1018] 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.

[1019] In this invention, the server includes a means for automatically collecting information about the level of urgency from SNS, a means for storing data sent directly from users in a central database, and a means for extracting meaning from the collected text data using text analysis technology. This makes it possible to automatically collect emergency information, appropriately analyze it, and promptly notify relevant organizations.

[1020] "SNS" stands for Social Networking Service, a platform for people to interact and share information online.

[1021] "Text analytics" is the process of extracting meaning and information from text data using natural language processing techniques.

[1022] "Urgency" is an index that evaluates how quickly the information requires a response.

[1023] "Categorization" is the process of grouping text data based on specific themes or content.

[1024] "Text data" is a collection of textual information written in a human-readable format.

[1025] "Relevant organizations" is a general term for organizations and groups that are responsible for receiving and responding to emergency information.

[1026] "Geographic identification technology" is a technology that identifies geographical locations and regions from information such as IP addresses.

[1027] MODE FOR CARRYING OUT THE INVENTION

[1028] This invention is a system for quickly grasping the situation in disaster-stricken areas and taking appropriate measures. This system comprises a series of processes that collect and analyze social media posts and inquiries, and notify relevant organizations of the results. The detailed components and processing procedures of the system are described below.

[1029] System Configuration

[1030] The system consists of the following main components:

[1031] 1. Terminal

[1032] 2. Server

[1033] 3. Social Media API

[1034] 4. GeoIP Library

[1035] 5. Natural Language Processing (NLP) Module

[1036] Hardware and Software Use

[1037] Terminal

[1038] The device is responsible for collecting inquiries from users and businesses and sending them to a server. Specifically, the device uses SNS APIs (e.g., Twitter API, Facebook Graph API) to periodically check for posts containing specific hashtags (e.g., "disaster" or "rescue") and temporarily store them. It also collects data on inquiries to businesses in a similar manner and periodically sends this data to the server. For example, the device can make a request to the SNS API every 15 minutes to retrieve new posts and store them in local storage.

[1039] server

[1040] The server receives the information sent from the device and stores it in a database. Next, it uses NLP technology to analyze the received text data and uses the GeoIP library to extract IP addresses and area names. For example, the server uses an NLP module (e.g., spaCy, BERT) to analyze the text, extract specific keywords, and understand the content. It also uses a GeoIP library (e.g., GeoIP2) to obtain geographical information from the IP address. This series of processes allows it to extract specific phrases such as "no water" or "need help" and identify area information based on them.

[1041] Urgency assessment and notification

[1042] The server evaluates the urgency level based on the analyzed data and identifies those with high urgency. It calculates an urgency score for each category, and if the score exceeds a predetermined threshold, it marks it as "high urgency." For example, the server recognizes posts containing keywords such as "help" or "fire" as high urgency. The server then notifies relevant authorities of high urgency information. This can be done in real time using APIs or webhooks. For example, it can send a request to the API endpoint of a waterworks or fire department to convey emergency information.

[1043] Specific examples

[1044] Below is an example of how this system works:

[1045] 1. Users

[1046] A user posts on Twitter, "There is no water in XX ward."

[1047] 2. Terminal

[1048] The device periodically retrieves these posts using the SNS API, temporarily stores them, and then sends them to the server.

[1049] 3. Server

[1050] The server stores the posts received from the devices in a database. It then analyzes the text data to extract IP addresses and area names. Posts containing the keyword "no water" are categorized as "infrastructure problems."

[1051] 4. Urgency determination

[1052] Text analysis determines that this post is of "high urgency."

[1053] 5. Notification

[1054] The server immediately notifies the waterworks bureau of the information that "there is no water in XX ward."

[1055] In this way, the system can quickly and accurately grasp the situation in the disaster-stricken areas and prompt the appropriate relevant organizations to take prompt action.

[1056] Prompt Sentence Examples

[1057] Below are some example prompts to input to a generative AI model:

[1058] Please explain the system that efficiently collects and analyzes information about disaster areas posted on social media such as Twitter and Instagram to identify the level of urgency and area, and promptly notifies relevant organizations.

[1059] Components of this system

[1060] How we collect information

[1061] Analysis and classification methods

[1062] Urgency assessment criteria

[1063] Notification method description

[1064] Actual operation example

[1065] This enables the system to automatically collect emergency information, analyze it appropriately, and quickly notify relevant agencies.

[1066] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1067] Step 1:

[1068] The device uses the SNS API to collect posts containing specific hashtags (e.g., "disaster," "rescue"). The input is the post data obtained from the SNS API, and this data is temporarily stored in the device's local storage. The collected and stored data is output. Specifically, the device sends a request to the Twitter API every 15 minutes to obtain the latest posts.

[1069] Step 2:

[1070] The device collects inquiries from users to the company. The input is emails and chat messages from the customer support system, which are temporarily stored in the device's local storage. The collected inquiry data is output. Specifically, the device connects to the email server, retrieves unread emails from a specific folder, and saves them.

[1071] Step 3:

[1072] The device sends the collected SNS posts and inquiries to the server. The input is data stored in the device's local storage and is sent to the server using the HTTPS protocol. The sent data is received by the server. Specifically, the device periodically compiles the collected data in batch format and sends a POST request to the server's API endpoint.

[1073] Step 4:

[1074] The server analyzes the received text data using NLP technology. The input is text data from social media posts and inquiries, and meaning is extracted using an NLP module (e.g., spaCy, BERT). The extracted semantic information is output. Specifically, the server uses an NLP library to perform morphological analysis of the text and identify important keywords and phrases.

[1075] Step 5:

[1076] The server uses a GeoIP library to extract region information from IP addresses. The input is the IP address contained in a post or query, and a GeoIP library (e.g., GeoIP2) is used to obtain the geographic coordinates and region name. The extracted region information is output. Specifically, the server queries the GeoIP database for the IP address and obtains the corresponding region information.

[1077] Step 6:

[1078] The server classifies the posts into categories based on the results of text analysis. The input is the extraction results from NLP, and the data is grouped using a categorization algorithm. The classified category information is output. Specifically, the server classifies posts into categories such as "infrastructure issues" and "lifesaving" based on specific keywords.

[1079] Step 7:

[1080] The server evaluates the urgency level based on the classified data. The input is categorized data, and the urgency level is determined using an algorithm that calculates an urgency score. Data with a high urgency level is output as "high urgency." Specifically, the server calculates the urgency score based on the presence or absence of keywords such as "help" or "fire," and marks anything that exceeds a threshold as high urgency.

[1081] Step 8:

[1082] The server notifies the relevant authorities of any identified high-urgency information. The input is data determined to be of high urgency, and notifications are sent in real time using APIs and web hooks. The notified information is then output. Specifically, the server sends requests to APIs of waterworks departments, fire departments, etc., to convey the necessary emergency information. Notifications are also sent via email and SMS.

[1083] (Application example 1)

[1084] 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."

[1085] Conventional information gathering and emergency response systems in disaster areas have the problem of taking time to gather and analyze information, making it difficult to respond quickly. In particular, in the event of trouble or an emergency at a factory, a fast and effective response is required. Against this background, there is a growing need for a system that can collect and analyze information in real time and immediately notify relevant organizations and employees.

[1086] 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.

[1087] In this invention, the server includes means for collecting posts related to urgency using an SNS API, means for sending the content of inquiries to an information processing device, and means for analyzing the collected posts and inquiry content and extracting communication point information and location names. This makes it possible to display notification content on the smart glasses in real time.

[1088] "SNS API" refers to an application programming interface published by a social network service (SNS) provider, through which data on the SNS can be obtained and manipulated.

[1089] "Content of inquiry" refers to the content of communication including information provided, questions, reports, etc. from users and related parties, and the system uses this as data to be analyzed.

[1090] An "information processing device" is part of a computer system that collects, analyzes, stores, and notifies data, and includes servers and cloud services.

[1091] "Communication location information" refers to data obtained as location information of communication devices, and geographical information is identified based on this data.

[1092] "Place name" refers to a geographical name or area name, and is used to extract location information.

[1093] "Smart glasses" are a type of wearable device, a pair of eyeglass-type electronic devices that provide information to users by displaying visual information on a display.

[1094] "Real-time" means being able to process an event the moment it occurs, and being able to provide and process information without delay.

[1095] "NLP" stands for natural language processing, and is a technology that analyzes, understands, and interprets information contained in text data and spoken language.

[1096] "GeoIP Library" means a software library for obtaining geographic location information from an IP address, which is used in conjunction with an IP address to determine location.

[1097] The present invention is a system that uses a social networking service (SNS) API to collect posts related to urgency, transmits the contents of inquiries to an information processing device, analyzes the collected posts and inquiry contents, extracts communication point information and location names, identifies the location and urgency based on the analyzed contents, notifies related devices of the identified information, and displays the notification contents on smart glasses in real time.

[1098] Overall system configuration

[1099] The system mainly consists of the following components:

[1100] 1. Terminal

[1101] 2. Server

[1102] 3. Social Media API

[1103] 4. GeoIP Library

[1104] 5. Natural Language Processing (NLP) Module

[1105] 6. Smart Glasses

[1106] Terminal

[1107] The device collects posts from users and related parties related to inquiries and their urgency, and sends them to the server. Specifically, the device uses SNS APIs to periodically check for posts containing specific hashtags such as "factory trouble" and temporarily saves them. It also collects inquiry data and sends it to the server.

[1108] server

[1109] The server receives the information sent from the device and stores it in a database. Next, it analyzes the received text data and extracts communication point information and location names. At this time, it uses the GeoIP library to obtain region information from IP addresses. It then uses NLP technology to analyze the text and classify the post content into categories. For example, if the post content contains the keyword "fire broke out," the information will be classified into the category "fire accident."

[1110] Urgency judgment

[1111] The server identifies the location and urgency based on the analyzed content. Specifically, it analyzes keywords and phrases in the text, and if they are of high urgency, it classifies them as "high urgency." For example, keywords such as "fire" and "explosion" are treated as high urgency.

[1112] Notifications and Displays

[1113] The server then sends notifications to relevant devices based on the identified information. For example, if high-urgency information such as "A fire has broken out at Factory A" is extracted, the information is immediately sent to the fire department and relevant parties. Furthermore, the notification content is displayed in real time on the smart glasses, accelerating response.

[1114] Specific examples

[1115] A series of examples of how the system can be implemented include the following:

[1116] 1. Users

[1117] A user posts on Twitter, "There's a fire at Factory A."

[1118] 2. Terminal

[1119] The device periodically retrieves these posts using the SNS API, temporarily stores them, and then sends them to the server.

[1120] 3. Server

[1121] The server stores the posts received from the devices in a database, analyzes the text data, and extracts communication point information and location names. Posts containing the keyword "fire breaks out" are categorized as "fire accidents."

[1122] 4. Urgency determination

[1123] Text analysis determines that this post is of "high urgency."

[1124] 5. Notices and Displays

[1125] The server immediately notifies the fire department that "a fire has broken out at Factory A," and the smart glasses display a message saying "Fire has broken out. Please take emergency action."

[1126] Prompt Sentence Examples

[1127] "Please build an emergency assessment system to detect and respond to factory troubles. This system will assess the emergency level and respond appropriately by collecting and analyzing social media posts containing the following specific hashtags."

[1128] This will enable quick and appropriate responses to troubles and emergencies within the factory.

[1129] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1130] Step 1:

[1131] The device uses SNS APIs to collect posts related to urgency. During this process, the device periodically checks for posts containing specific hashtags (e.g., "factory trouble") and temporarily stores their contents. The input is the raw data of SNS posts, and the output is the temporarily stored post data related to urgency. Data processing involves filtering and storing the raw data obtained through the SNS API.

[1132] Step 2:

[1133] The terminal sends the collected posts and inquiry contents to the information processing device. The saved post data related to urgency is sent to the server. The input is the post data saved in step 1, and the output is the post data sent to the server. Data processing includes sending the saved data on the terminal to the server via network communication.

[1134] Step 3:

[1135] The server stores the received post data in a database and uses an NLP module to analyze the text data. The input is the post data sent to the server, and the output is the analysis results. Specifically, NLP technology is used to classify the post content into categories and extract important keywords and phrases.

[1136] Step 4:

[1137] The server uses the GeoIP library to obtain communication point information from the poster's IP address and identify the location name. The input is the IP address and analysis results contained in the posted data, and the output is communication point information and the location name. Specifically, the GeoIP library analyzes the IP address to extract geographical location information.

[1138] Step 5:

[1139] The server identifies the location and urgency based on the analyzed content. Information with a high urgency level is classified as "high urgency" based on keywords and phrases in the text. The input is the NLP analysis results and communication point information, and the output is the urgency classification result. For data calculation, an urgency determination algorithm is used to evaluate and classify the text analysis results.

[1140] Step 6:

[1141] The server notifies the relevant devices of the identified information. For example, if there is information that "a fire has broken out at Factory A," it will immediately notify the fire department and relevant parties. The input is the urgency classification result and specific location information, and the output is a notification message. Specifically, it uses a notification API or web hook to send information to relevant devices in real time.

[1142] Step 7:

[1143] The server displays the notification content on the smart glasses in real time. The input is the notification message, and the output is the information displayed on the smart glasses' display. The server sends the same notification as the information sent to the related devices to the smart glasses, providing the user with information in real time. Specifically, the message is displayed through an API dedicated to the smart glasses.

[1144] 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.

[1145] This invention relates to a system for grasping the situation in disaster-stricken areas and taking prompt and appropriate action. This system collects and analyzes social media posts and company inquiries to identify the level of urgency and the area, and notifies relevant organizations. Furthermore, it combines an emotion engine that recognizes user emotions to analyze the emotions in the posts and help identify the level of urgency.

[1146] Overall system configuration

[1147] The system mainly consists of the following components:

[1148] 1. Terminal

[1149] 2. Server

[1150] 3. Social Media API

[1151] 4. GeoIP Library

[1152] 5. Natural Language Processing (NLP) Module

[1153] 6. Emotion Engine

[1154] Terminal

[1155] The device collects inquiries from users and companies and sends them to a server. Specifically, the device uses SNS APIs to periodically check for posts containing specific hashtags such as "disaster" or "rescue" and temporarily stores them. It also collects data on inquiries to the company and sends this data to a server.

[1156] server

[1157] The server receives the information sent from the device and stores it in a database. The received text data is then analyzed using natural language processing (NLP). NLP analysis extracts IP addresses, local area names, and specific keywords and phrases from the text, and classifies the post content into categories. For example, if a post contains the keyword "no water," the information will be classified into the category "infrastructure problems."

[1158] Emotion Engine

[1159] The analysis on the server also uses an emotion engine. The emotion engine analyzes the emotions in the posted content and can identify emotions such as "sadness," "fear," and "anger." The emotion data obtained by the emotion engine is used to assist in determining the level of urgency.

[1160] Urgency judgment

[1161] The server uses NLP and an emotion engine to analyze the data and identify the region and level of urgency. Specifically, it analyzes keywords and phrases in the text, as well as the extracted emotion data, and classifies any that indicate a high level of urgency as "high urgency." For example, keywords such as "help" and "fire" are treated as high urgency, and if the emotion engine detects "fear," it is treated as an even higher level of urgency.

[1162] notification

[1163] The server then notifies the relevant organizations based on the identified information. For example, if high-urgency information such as "water is not coming out in ward X" is extracted, the information is immediately sent to the waterworks bureau. This is done using real-time notification methods via APIs and webhooks.

[1164] Specific examples

[1165] Below are a series of examples of this system in action:

[1166] 1. Users

[1167] A user posts on Twitter, "There is no water in XX ward." This post conveys the emotion of "I am in great trouble."

[1168] 2. Terminal

[1169] The device periodically retrieves these posts using the SNS API, temporarily stores them, and then sends them to the server.

[1170] 3. Server

[1171] The server stores the posts received from the devices in a database. It analyzes the text data and extracts IP addresses and area names. Posts containing the keyword "no water" are classified into the category "infrastructure problems."

[1172] 4. Emotion Engine

[1173] The emotion engine recognizes the emotion "very troubled" from the content of the post.

[1174] 5. Urgency determination

[1175] Based on text analysis and sentiment data, this post is determined to be of "high urgency."

[1176] 6. Notification

[1177] The server immediately notifies the waterworks bureau of the information that "there is no water in XX ward."

[1178] In this way, the system can quickly and accurately grasp the situation in the disaster area and prompt the appropriate relevant organizations to take prompt action. By adding an emotion engine, it becomes possible to make more accurate urgency judgments and gain a deeper understanding of the condition of the victims.

[1179] The processing flow will be explained below.

[1180] Step 1:

[1181] User

[1182] A user posts on social media, such as "There is no water in ward XX." The information posted by the user is stored on the social media platform.

[1183] Step 2:

[1184] Terminal

[1185] The device periodically connects to the SNS API to check for new posts containing specific hashtags or keywords such as "disaster" or "rescue." The new posts retrieved from the API are temporarily stored in the device's storage.

[1186] Step 3:

[1187] Terminal

[1188] The device analyzes the collected posting data, extracts metadata such as the user's IP address and the content of the post, and formats this data for transmission to the server.

[1189] Step 4:

[1190] Terminal

[1191] The formatted data is sent to the server via an API endpoint that is designed to ensure it reaches the server.

[1192] Step 5:

[1193] server

[1194] The server stores the data received from the device in a database, which is used for subsequent analysis.

[1195] Step 6:

[1196] server

[1197] The server then analyzes the received text data using natural language processing (NLP), which involves extracting IP addresses, location names, and specific keywords and phrases from the text.

[1198] Step 7:

[1199] server

[1200] Using data obtained from NLP analysis, we use the GeoIP library to extract geographic information from IP addresses, thereby identifying the region from which a post originates.

[1201] Step 8:

[1202] server

[1203] The NLP module classifies posts into categories based on keywords and phrases extracted. For example, a post about "no water" would be classified as "infrastructure problems."

[1204] Step 9:

[1205] server

[1206] The server uses an emotion engine to analyze the sentiment of the posts, using an emotion-identifying algorithm to identify emotions such as "sadness," "fear," and "anger."

[1207] Step 10:

[1208] server

[1209] Based on data obtained from NLP analysis and sentiment analysis, an urgency assessment algorithm is applied to assess the urgency of posts. Posts that are deemed to be of high urgency are immediately classified as "high urgency."

[1210] Step 11:

[1211] server

[1212] Based on information deemed to be of high urgency, relevant organizations (national government, local government, medical organizations, etc.) are notified. Notifications are sent in real time via API or webhook.

[1213] Step 12:

[1214] server

[1215] The system confirms that notifications have been sent successfully and records the history in a database, making it possible to track which information was sent to which institution and when.

[1216] Specific examples

[1217] Below are the steps by which the system actually works in a concrete example:

[1218] 1. Users

[1219] A user posts on Twitter, "There is no water in XX ward." This post conveys the emotion of "I am in great trouble."

[1220] 2. Terminal

[1221] The device uses the Twitter API to check posts with the hashtag "disaster," retrieves these posts, stores them temporarily, and then sends the data to the server.

[1222] 3. Server

[1223] The server receives the posted data obtained from the terminal and stores it in a database.

[1224] 4. Server

[1225] It uses an NLP module to parse the text and extract keywords like "no water," while also using the GeoIP library to determine the region of the post from its IP address.

[1226] 5. Server

[1227] Using a sentiment engine, the sentiment of the post is identified as "very distressed."

[1228] 6. Server

[1229] Using an urgency assessment algorithm, messages are classified as "high urgency" based on information obtained from text analysis and sentiment analysis.

[1230] 7. Server

[1231] Based on highly urgent information such as "water is not coming out in ward XX," the waterworks bureau is notified immediately.

[1232] 8. Server

[1233] Records that the notification was successful and stores the history in a database.

[1234] In this way, the system can quickly and accurately grasp the situation in the disaster area and prompt the appropriate relevant organizations to take prompt action. By adding an emotion engine, it becomes possible to make more accurate urgency judgments and gain a deeper understanding of the condition of the victims.

[1235] Example 2

[1236] 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."

[1237] The problem is that it is difficult to gather and analyze information to quickly and accurately grasp the situation in disaster-stricken areas and take appropriate measures. In particular, the technical challenge is extracting useful information from the vast amount of data on social media and inquiries, and determining the level of urgency. Furthermore, by adding emotion analysis, more accurate urgency determination is required.

[1238] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1239] In this invention, the server includes: [means for collecting posts related to urgency using an SNS API;] [means for sending the content of inquiries to the organization's server;] [means for analyzing the collected posts and inquiry content and extracting IP addresses and regional information;] [means for analyzing the content of posts using a Natural Language Processing (NLP) module and extracting keywords and phrases;] ​​[means for analyzing the emotions of the content of posts using an emotion engine;] [means for identifying the region and urgency based on the analyzed content; and [means for notifying relevant organizations of the identified information.] This makes it possible to quickly and accurately grasp the situation in the disaster-stricken areas and to promptly notify appropriate relevant organizations.

[1240] "SNS API" is an application programming interface that allows programs to use posted data from social networking services.

[1241] "Inquiries" refer to the content of communication such as questions, consultations, and requests made by users and related parties to an organization.

[1242] A "server" is a computer system that receives, stores, analyzes, and transmits data over a network.

[1243] "IP address" refers to a unique numeric code used when sending and receiving data on the Internet.

[1244] "Region information" refers to information about a particular geographic area, including city, ward, town, village name, postal code, etc.

[1245] A "Natural Language Processing (NLP) module" is a software component that allows a computer to analyze human natural language and understand its meaning and structure.

[1246] "Keywords" refer to words or phrases that are particularly important within text data.

[1247] An "emotion engine" is a software component that analyzes emotions from text data and classifies them into specific emotion categories (e.g., joy, sadness, fear, etc.).

[1248] "Analyzed content" refers to the information obtained as a result of analyzing collected data using an NLP module or emotion engine.

[1249] "Urgency" is a measure that indicates the level of urgency of data or an event, and is used to determine the priority of responses.

[1250] "Relevant organizations" refer to government agencies, private companies, non-governmental organizations (NGOs), etc. that need to respond based on specific information.

[1251] This invention relates to a system for quickly and accurately grasping the situation in disaster-stricken areas and taking appropriate measures. This system collects social media posts and inquiries to companies, analyzes them, identifies the level of urgency and the area, and notifies the relevant organizations.

[1252] Overall system configuration

[1253] The system mainly consists of the following components:

[1254] 1. Terminal

[1255] 2. Server

[1256] 3. Social Media API

[1257] 4. GeoIP Library

[1258] 5. Natural Language Processing (NLP) Module

[1259] 6. Emotion Engine

[1260] Terminal

[1261] The device collects inquiries from users and companies and sends them to a server. Specifically, the device uses SNS APIs to periodically check for posts containing specific hashtags such as "disaster" or "rescue" and temporarily stores them. It also collects data on inquiries to the company and sends this data to a server.

[1262] server

[1263] The server receives the information sent from the device and stores it in a database. Next, it analyzes the received text data using a natural language processing (NLP) module. NLP analysis extracts IP addresses, local area names, and specific keywords and phrases from the text, and classifies the post content into categories. For example, if the post content contains the keyword "no water," the information will be classified into the category "infrastructure problems."

[1264] Emotion Engine

[1265] The analysis on the server also uses an emotion engine. The emotion engine analyzes the emotions in the posted content and can identify emotions such as "sadness," "fear," and "anger." The emotion data obtained by the emotion engine is used to assist in determining the level of urgency.

[1266] Urgency judgment

[1267] The server uses NLP and an emotion engine to analyze the data and identify the region and level of urgency. Specifically, it analyzes keywords and phrases in the text, as well as the extracted emotion data, and classifies any that indicate a high level of urgency as "high urgency." For example, keywords such as "help" and "fire" are treated as high urgency, and if the emotion engine detects "fear," it is treated as an even higher level of urgency.

[1268] notification

[1269] The server then notifies the relevant organizations based on the identified information. For example, if high-urgency information such as "water is not coming out in ward X" is extracted, the information is immediately sent to the waterworks bureau. This is done using real-time notification methods via APIs and webhooks.

[1270] Specific examples

[1271] Below are a series of examples of this system in action:

[1272] 1. Users

[1273] A user posts on Twitter, "There is no water in XX ward." This post conveys the emotion of "I am in great trouble."

[1274] 2. Terminal

[1275] The device periodically retrieves these posts using the SNS API, temporarily stores them, and then sends them to the server.

[1276] 3. Server

[1277] The server stores the posts received from the devices in a database. It analyzes the text data and extracts IP addresses and area names. Posts containing the keyword "no water" are classified into the category "infrastructure problems."

[1278] 4. Emotion Engine

[1279] The emotion engine recognizes the emotion "very troubled" from the content of the post.

[1280] 5. Urgency determination

[1281] Based on text analysis and sentiment data, this post is determined to be of "high urgency."

[1282] 6. Notification

[1283] The server immediately notifies the waterworks bureau of the information that "there is no water in XX ward."

[1284] In this way, the system can quickly and accurately grasp the situation in the disaster area and prompt the appropriate relevant organizations to take prompt action.In addition, by using the emotion engine, the accuracy of urgency determination can be improved, enabling a deeper understanding of the condition of the victims.

[1285] Prompt Sentence Examples

[1286] Please explain how the system works: collects posts on Twitter that contain the hashtags "disaster" and "rescue," determines the area and urgency based on the content, and notifies the relevant organizations.

[1287] Using this prompt, the generative AI model can generate sentences like the one above that detail the process of the system.

[1288] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1289] Step 1:

[1290] User posts to SNS

[1291] Users post on Twitter or other SNSs using hashtags such as "disaster" or "rescue." For example, they might post something like, "There's no water in XX ward. We're in a lot of trouble." The input is the user's SNS post, and the output is the post itself. The specific actions a user takes are logging in to the SNS using a smartphone or PC and posting.

[1292] Step 2:

[1293] The device collects posts

[1294] The device periodically checks for posts containing these hashtags using the SNS API. The device collects the posts, temporarily stores them in local storage, and then sends them to the server. The input is the user's SNS posts, and the output is the collected post data. Specifically, the device searches for posts using the SNS API, retrieves and saves the relevant posts, and sends them to the server.

[1295] Step 3:

[1296] The server receives the data

[1297] The server receives the posted data sent from the device and stores it in a database. The input is the posted data sent from the device, and the output is the data stored in the database. Specifically, the server analyzes the received data, formats it, and then inserts it into the database.

[1298] Step 4:

[1299] The server uses the NLP module to analyze the text.

[1300] The server uses an NLP module to analyze the received text data. It extracts IP addresses, local area names, and specific keywords and phrases from the text and categorizes the posts. The input is the received text data, and the output is data such as analyzed keywords, local area names, and IP addresses. Specifically, it runs the NLP module to analyze and extract each element of the text.

[1301] Step 5:

[1302] The server performs emotion analysis using the emotion engine.

[1303] The server uses an emotion engine to analyze the emotions in the posted content. For example, emotions such as "fear" or "confusion" can be identified from the text data. The input is the text data, and the output is the detected emotion information. Specifically, the emotion engine is executed to extract emotion data from the text and identify which emotions are contained.

[1304] Step 6:

[1305] The server determines the urgency

[1306] The server determines the urgency of a post based on the results of the NLP and emotion engine. It analyzes keywords, phrases, and emotional data in the text and determines the urgency level from high to low. The input is the analyzed keywords and emotional information, and the output is the urgency level determination result. Specifically, it evaluates the extracted data and sets the urgency level.

[1307] Step 7:

[1308] The server notifies the relevant parties

[1309] The server notifies relevant organizations of specific information based on the results of the assessment. For example, if there is high-urgency information such as "water is not coming out in ward XX," it will notify the waterworks bureau. The input is the urgency assessment result, and the output is the sent notification. Specific operations include sending real-time notifications using APIs and webhooks.

[1310] This will enable the entire system to operate efficiently and to quickly and appropriately communicate the situation in the disaster-stricken areas to relevant organizations.

[1311] (Application example 2)

[1312] 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."

[1313] Conventional emergency response systems have difficulty in quickly and accurately grasping the situation in disaster-stricken areas, resulting in delayed appropriate responses. Furthermore, they often failed to properly assess the emotions and urgency contained in posts on social media, resulting in a failure to respond immediately to highly urgent situations. Furthermore, delays in notification to relevant organizations have also led to delays in rescue efforts for victims.

[1314] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1315] In this invention, the server includes: means for collecting posts related to urgency using a social networking service (SNS) API; means for sending inquiry content to a database server; means for analyzing the collected posts and inquiry content and extracting IP addresses and local area names; emotion engine means for analyzing the emotional state of the posts; means for identifying the local area and urgency level based on the analyzed content and emotional state; and means for notifying relevant organizations and security services of the identified information. This allows for rapid identification of the local area and urgency level of the collected posts, enabling immediate notification to relevant organizations. Furthermore, the emotion engine also performs emotion analysis of the posts, allowing for accurate identification of high-urgency situations, enabling rapid and appropriate responses. Furthermore, natural language processing and emotion analysis using a generative AI model enables more advanced information analysis and improved decision accuracy.

[1316] "SNS API" is an application programming interface for accessing data from social networking services (SNS).

[1317] A "database server" is a server that manages a database and performs operations such as storing, searching, updating, and deleting data.

[1318] "Posted content" refers to text and media information that users make public on social media and other communication platforms.

[1319] "Inquiry content" is text information of questions or opinions that users have made to companies or organizations.

[1320] An "IP address" is a unique number that identifies a device on the Internet.

[1321] A "region name" is a name that indicates a specific geographical area.

[1322] An "emotion engine" is a software module that analyzes emotions in text data and identifies the emotional state.

[1323] "Urgency" is an indicator of the level of urgency of a particular event or situation.

[1324] "Relevant organizations" refers to organizations or organisations directly involved in emergency and disaster response.

[1325] "Security services" is a general term for services that protect people and assets, prevent crime, and deal with disasters.

[1326] A "generative AI model" is an artificial intelligence model built using machine learning and deep learning, which learns from specific tasks and makes predictions and analyses.

[1327] A "prompt" is text that provides instructions or example input given to a generative AI model to perform a specific task.

[1328] The present invention is a system for quickly and accurately grasping the situation in a disaster area and prompting appropriate organizations to respond. Specific embodiments for carrying out the present invention are described below.

[1329] Overall system configuration

[1330] The system mainly consists of the following components:

[1331] 1. Terminal

[1332] 2. Server

[1333] 3. Social Media API

[1334] 4. Database Server

[1335] 5. Natural Language Processing (NLP) Module

[1336] 6. Emotion Engine

[1337] 7. Generative AI Models

[1338] Terminal

[1339] The device is responsible for collecting inquiries from users and businesses and sending this data to a server. Specifically, the device uses SNS APIs to periodically check for posts containing specific hashtags such as "disaster" or "rescue" and temporarily stores them. Inquiries to businesses are also collected in the same way and sent to the server.

[1340] server

[1341] The server receives the information sent from the device and stores it in a database server. The received text data is then analyzed using an NLP module. NLP analysis extracts IP addresses, local area names, and specific keywords and phrases from the text, and classifies the posted content into categories.

[1342] Emotion Engine

[1343] The server also uses an emotion engine to analyze the emotions in the posts and identify emotions such as "fear," "sadness," and "confusion."

[1344] Urgency judgment

[1345] The server identifies the region and urgency based on the data analyzed using the NLP module and emotion engine. Specifically, it analyzes keywords and phrases in the text as well as the extracted emotion data, and if it indicates a high level of urgency, it classifies it as "high urgency." For example, keywords such as "help" and "fire" are treated as high urgency, and if the emotion engine detects "fear," it is treated as an even higher level of urgency.

[1346] notification

[1347] The server then notifies relevant authorities and security services based on the identified information, using APIs and webhooks to prompt immediate action in real time.

[1348] Specific examples

[1349] Here's an example of this system in action:

[1350] Example 1: Collecting and analyzing social media posts

[1351] 1. Users

[1352] A user posts on Twitter, "Disaster Fire There's a fire in XX ward. It's very dangerous, please help."

[1353] 2. Terminal

[1354] The device periodically retrieves these posts using the SNS API, temporarily stores them, and then sends them to the server.

[1355] 3. Server

[1356] The server stores the posts received from the devices in a database server. The text data is analyzed to extract IP addresses and area names. Posts containing the keyword "fire" are classified as "high urgency."

[1357] 4. Emotion Engine

[1358] The emotion engine recognizes the emotion "It's very dangerous, please help" from the content of the post.

[1359] 5. Urgency determination

[1360] Based on text analysis and sentiment data, this post is determined to be of "high urgency."

[1361] 6. Notification

[1362] The server immediately notifies the fire department and security services of the information "There is a fire in ward XX."

[1363] Prompt Sentence Examples

[1364] Here are some example prompts to apply to generative AI models:

[1365] Prompt: "Create a program that analyzes the sentiment of posts collected from social media, extracts local information, and determines the level of urgency. If the level of urgency is high, include a function to notify the relevant authorities."

[1366] The above is the details of the "Mode for Carrying Out the Invention." By using this system, it is possible to quickly and accurately grasp the situation in the disaster area and respond appropriately.

[1367] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1368] Step 1:

[1369] A user posts an emergency situation on a social networking service (SNS). This post includes a hashtag (e.g., "disaster" or "fire") and a specific description of the situation (e.g., "There's a fire in ____ ward. It's very dangerous. Please help.").

[1370] Step 2:

[1371] The device periodically calls the SNS API to search and collect posts containing specific hashtags. This temporarily stores newly posted emergency information. The input is data from the SNS API, and the output is the temporarily stored post data.

[1372] Step 3:

[1373] The terminal transmits the temporarily saved posted data to the server. Here, the input is the temporarily saved posted data, and the output is the data sent to the server. This data includes the text of the post, the poster's IP address, and the posting date and time.

[1374] Step 4:

[1375] The server stores the received submission data in a database server. This ensures that the data required for subsequent analysis steps is stored persistently. The input is the data sent from the device, and the output is the data stored in the database.

[1376] Step 5:

[1377] The server analyzes the saved posting data using an NLP (Natural Language Processing) module, which extracts location-related information (place names and IP addresses) and specific keywords and phrases from the posting content. The input is the posting data retrieved from the database, and the output is the analyzed text data and extracted location information.

[1378] Step 6:

[1379] The server uses an emotion engine to analyze the emotional state of the post. Emotions such as "fear," "sadness," and "confusion" are identified. The input is the analyzed text data, and the output is the extracted emotional data.

[1380] Step 7:

[1381] The server determines the urgency level based on data analyzed by the NLP module and emotion engine. If the keyword "fire" or the emotion "fear" is identified, it is classified as high urgency. The input is the analyzed text data and emotion data, and the output is the determined urgency information.

[1382] Step 8:

[1383] The server notifies relevant organizations and security services based on the determined urgency information. Notifications are sent via API or web hooks, and if the urgency is high, notifications are sent immediately. The input is urgency information, and the output is notification data sent to relevant organizations.

[1384] Step 9:

[1385] The relevant authorities receive the notification from the server and take immediate action. Specifically, the fire department may be dispatched to the scene. The input is the notification data from the server, and the output is the actual response action.

[1386] The above is the specific flow of the processing of the present invention. Through these steps, it becomes possible to quickly and accurately grasp the situation in the disaster area and respond appropriately.

[1387] 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.

[1388] 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.

[1389] 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.

[1390] [Fourth embodiment]

[1391] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1392] 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.

[1393] 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).

[1394] 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.

[1395] 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.

[1396] 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).

[1397] 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.

[1398] 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.

[1399] 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.

[1400] 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.

[1401] 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.

[1402] 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.

[1403] 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."

[1404] This invention relates to a system for understanding the situation in disaster-stricken areas and taking prompt and appropriate action. This system collects social media posts and inquiries to companies, analyzes them, identifies the level of urgency and the area, and notifies relevant organizations.

[1405] Overall system configuration

[1406] The system mainly consists of the following components:

[1407] 1. Terminal

[1408] 2. Server

[1409] 3. Social Media API

[1410] 4. GeoIP Library

[1411] 5. Natural Language Processing (NLP) Module

[1412] Terminal

[1413] The device collects inquiries from users and companies and sends them to a server. Specifically, the device uses SNS APIs to periodically check for posts containing specific hashtags such as "disaster" or "rescue" and temporarily stores them. It also collects data on inquiries to the company and sends this data to a server.

[1414] server

[1415] The server receives the information sent from the device and stores it in a database. Next, it analyzes the received text data and extracts the IP address and area name. At this time, it uses the GeoIP library to obtain area information from the IP address. It then analyzes the text using NLP technology and classifies the post content into categories. For example, if the post content contains the keyword "no water," the information will be classified into the category "infrastructure problems."

[1416] Urgency judgment

[1417] The server identifies the region and urgency level based on the analyzed content. Specifically, it analyzes keywords and phrases in the text, and if they are of high urgency, it classifies them as "high urgency." For example, keywords such as "help" and "fire" are treated as high urgency.

[1418] notification

[1419] The server then notifies the relevant organizations based on the identified information. For example, if high-urgency information such as "water is not coming out in ward X" is extracted, the information is immediately sent to the waterworks bureau. This is done using real-time notification methods via APIs and webhooks.

[1420] Specific examples

[1421] Below are a series of examples of this system in action:

[1422] 1. Users

[1423] A user posts on Twitter, "There is no water in XX ward."

[1424] 2. Terminal

[1425] The device periodically retrieves these posts using the SNS API and temporarily stores them.

[1426] It then sends the saved post to the server.

[1427] 3. Server

[1428] The server stores the posts received from the terminals in a database.

[1429] Analyze the text data and extract IP addresses and area names.

[1430] Posts containing the keyword "no water" are categorized as "infrastructure problems."

[1431] 4. Urgency determination

[1432] Text analysis determines that this post is of "high urgency."

[1433] 5. Notification

[1434] The server immediately notifies the waterworks bureau of the information that "there is no water in XX ward."

[1435] In this way, this system can quickly and accurately grasp the situation in the disaster-stricken areas and prompt the appropriate relevant organizations to take prompt action, thereby enabling effective support to be provided to the disaster-stricken areas.

[1436] The processing flow will be explained below.

[1437] Step 1:

[1438] User

[1439] A user posts on social media, such as "There is no water in ward XX." The information posted by the user is stored on the social media platform.

[1440] Step 2:

[1441] Terminal

[1442] The device periodically connects to the SNS API to check for new posts containing specific hashtags or keywords such as "disaster" or "rescue." The new posts retrieved from the API are temporarily stored in the device's storage.

[1443] Step 3:

[1444] Terminal

[1445] The device analyzes the collected posting data, extracts metadata such as the user's IP address and the content of the post, and formats this data for transmission to the server.

[1446] Step 4:

[1447] Terminal

[1448] The formatted data is sent to the server via an API endpoint that is designed to ensure it reaches the server.

[1449] Step 5:

[1450] server

[1451] The server stores the data received from the device in a database, which is then used for subsequent analysis.

[1452] Step 6:

[1453] server

[1454] The server then analyzes the received text data using natural language processing (NLP), which involves extracting IP addresses, location names, and specific keywords and phrases from the text.

[1455] Step 7:

[1456] server

[1457] Based on the parsed data, we use the GeoIP library to extract location information from IP addresses, which allows us to determine which region a post originates from.

[1458] Step 8:

[1459] server

[1460] The posts are then categorized based on the extracted keywords and phrases. For example, a post about "no water" would be classified as "infrastructure problems."

[1461] Step 9:

[1462] server

[1463] An urgency assessment algorithm is applied to assess the urgency of the analyzed data. Posts that are deemed to be of high urgency require immediate and appropriate action.

[1464] Step 10:

[1465] server

[1466] Once the urgency assessment is complete, appropriate relevant organizations (national government, local government, medical organizations, etc.) will be notified. Notifications will be sent in real time via API or webhook.

[1467] Step 11:

[1468] server

[1469] The system confirms that notifications have been sent successfully and records the history in a database, making it possible to track which information was sent to which institution and when.

[1470] Through the above processing steps, the system quickly collects and analyzes information of high urgency in the affected area and notifies the appropriate relevant agencies, thereby facilitating a rapid response.

[1471] Example 1

[1472] 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."

[1473] During natural disasters and emergencies, many people use social media and email to seek help, but there is a problem of difficulty in collecting and analyzing this information appropriately and quickly and notifying the relevant authorities. In particular, if geographic information is not accurately identified and the level of urgency is not accurately assessed, appropriate responses may be delayed. In conventional systems, these tasks are often performed manually, requiring a great deal of time and effort. Furthermore, response delays are likely to occur due to delayed recognition and overlooked information.

[1474] 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.

[1475] In this invention, the server includes a means for automatically collecting information about the level of urgency from SNS, a means for storing data sent directly from users in a central database, and a means for extracting meaning from the collected text data using text analysis technology. This makes it possible to automatically collect emergency information, appropriately analyze it, and promptly notify relevant organizations.

[1476] "SNS" stands for Social Networking Service, a platform for people to interact and share information online.

[1477] "Text analytics" is the process of extracting meaning and information from text data using natural language processing techniques.

[1478] "Urgency" is an index that evaluates how quickly the information requires a response.

[1479] "Categorization" is the process of grouping text data based on specific themes or content.

[1480] "Text data" is a collection of textual information written in a human-readable format.

[1481] "Relevant organizations" is a general term for organizations and groups that are responsible for receiving and responding to emergency information.

[1482] "Geographic identification technology" is a technology that identifies geographical locations and regions from information such as IP addresses.

[1483] MODE FOR CARRYING OUT THE INVENTION

[1484] This invention is a system for quickly grasping the situation in disaster-stricken areas and taking appropriate measures. This system comprises a series of processes that collect and analyze social media posts and inquiries, and notify relevant organizations of the results. The detailed components and processing procedures of the system are described below.

[1485] System Configuration

[1486] The system consists of the following main components:

[1487] 1. Terminal

[1488] 2. Server

[1489] 3. Social Media API

[1490] 4. GeoIP Library

[1491] 5. Natural Language Processing (NLP) Module

[1492] Hardware and Software Use

[1493] Terminal

[1494] The device is responsible for collecting inquiries from users and businesses and sending them to a server. Specifically, the device uses SNS APIs (e.g., Twitter API, Facebook Graph API) to periodically check for posts containing specific hashtags (e.g., "disaster" or "rescue") and temporarily store them. It also collects data on inquiries to businesses in a similar manner and periodically sends this data to the server. For example, the device can make a request to the SNS API every 15 minutes to retrieve new posts and store them in local storage.

[1495] server

[1496] The server receives the information sent from the device and stores it in a database. Next, it uses NLP technology to analyze the received text data and uses the GeoIP library to extract IP addresses and area names. For example, the server uses an NLP module (e.g., spaCy, BERT) to analyze the text, extract specific keywords, and understand the content. It also uses a GeoIP library (e.g., GeoIP2) to obtain geographical information from the IP address. This series of processes allows it to extract specific phrases such as "no water" or "need help" and identify area information based on them.

[1497] Urgency assessment and notification

[1498] The server evaluates the urgency level based on the analyzed data and identifies those with high urgency. It calculates an urgency score for each category, and if the score exceeds a predetermined threshold, it marks it as "high urgency." For example, the server recognizes posts containing keywords such as "help" or "fire" as high urgency. The server then notifies relevant authorities of high urgency information. This can be done in real time using APIs or webhooks. For example, it can send a request to the API endpoint of a waterworks or fire department to convey emergency information.

[1499] Specific examples

[1500] Below is an example of how this system works:

[1501] 1. Users

[1502] A user posts on Twitter, "There is no water in XX ward."

[1503] 2. Terminal

[1504] The device periodically retrieves these posts using the SNS API, temporarily stores them, and then sends them to the server.

[1505] 3. Server

[1506] The server stores the posts received from the devices in a database. It then analyzes the text data to extract IP addresses and area names. Posts containing the keyword "no water" are categorized as "infrastructure problems."

[1507] 4. Urgency determination

[1508] Text analysis determines that this post is of "high urgency."

[1509] 5. Notification

[1510] The server immediately notifies the waterworks bureau of the information that "there is no water in XX ward."

[1511] In this way, the system can quickly and accurately grasp the situation in the disaster-stricken areas and prompt the appropriate relevant organizations to take prompt action.

[1512] Prompt Sentence Examples

[1513] Below are some example prompts to input to a generative AI model:

[1514] Please explain the system that efficiently collects and analyzes information about disaster areas posted on social media such as Twitter and Instagram to identify the level of urgency and area, and promptly notifies relevant organizations.

[1515] Components of this system

[1516] How we collect information

[1517] Analysis and classification methods

[1518] Urgency assessment criteria

[1519] Notification method description

[1520] Actual operation example

[1521] This enables the system to automatically collect emergency information, analyze it appropriately, and quickly notify relevant agencies.

[1522] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1523] Step 1:

[1524] The device uses the SNS API to collect posts containing specific hashtags (e.g., "disaster," "rescue"). The input is the post data obtained from the SNS API, and this data is temporarily stored in the device's local storage. The collected and stored data is output. Specifically, the device sends a request to the Twitter API every 15 minutes to obtain the latest posts.

[1525] Step 2:

[1526] The device collects inquiries from users to the company. The input is emails and chat messages from the customer support system, which are temporarily stored in the device's local storage. The collected inquiry data is output. Specifically, the device connects to the email server, retrieves unread emails from a specific folder, and saves them.

[1527] Step 3:

[1528] The device sends the collected SNS posts and inquiries to the server. The input is data stored in the device's local storage and is sent to the server using the HTTPS protocol. The sent data is received by the server. Specifically, the device periodically compiles the collected data in batch format and sends a POST request to the server's API endpoint.

[1529] Step 4:

[1530] The server analyzes the received text data using NLP technology. The input is text data from social media posts and inquiries, and meaning is extracted using an NLP module (e.g., spaCy, BERT). The extracted semantic information is output. Specifically, the server uses an NLP library to perform morphological analysis of the text and identify important keywords and phrases.

[1531] Step 5:

[1532] The server uses a GeoIP library to extract region information from IP addresses. The input is the IP address contained in a post or query, and a GeoIP library (e.g., GeoIP2) is used to obtain the geographic coordinates and region name. The extracted region information is output. Specifically, the server queries the GeoIP database for the IP address and obtains the corresponding region information.

[1533] Step 6:

[1534] The server classifies the posts into categories based on the results of text analysis. The input is the extraction results from NLP, and the data is grouped using a categorization algorithm. The classified category information is output. Specifically, the server classifies posts into categories such as "infrastructure issues" and "lifesaving" based on specific keywords.

[1535] Step 7:

[1536] The server evaluates the urgency level based on the classified data. The input is categorized data, and the urgency level is determined using an algorithm that calculates an urgency score. Data with a high urgency level is output as "high urgency." Specifically, the server calculates the urgency score based on the presence or absence of keywords such as "help" or "fire," and marks anything that exceeds a threshold as high urgency.

[1537] Step 8:

[1538] The server notifies the relevant authorities of any identified high-urgency information. The input is data determined to be of high urgency, and notifications are sent in real time using APIs and web hooks. The notified information is then output. Specifically, the server sends requests to APIs of waterworks departments, fire departments, etc., to convey the necessary emergency information. Notifications are also sent via email and SMS.

[1539] (Application example 1)

[1540] 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."

[1541] Conventional information gathering and emergency response systems in disaster areas have the problem of taking time to gather and analyze information, making it difficult to respond quickly. In particular, in the event of trouble or an emergency at a factory, a fast and effective response is required. Against this background, there is a growing need for a system that can collect and analyze information in real time and immediately notify relevant organizations and employees.

[1542] 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.

[1543] In this invention, the server includes means for collecting posts related to urgency using an SNS API, means for sending the content of inquiries to an information processing device, and means for analyzing the collected posts and inquiry content and extracting communication point information and location names. This makes it possible to display notification content on the smart glasses in real time.

[1544] "SNS API" refers to an application programming interface published by a social network service (SNS) provider, through which data on the SNS can be obtained and manipulated.

[1545] "Content of inquiry" refers to the content of communication including information provided, questions, reports, etc. from users and related parties, and the system uses this as data to be analyzed.

[1546] An "information processing device" is part of a computer system that collects, analyzes, stores, and notifies data, and includes servers and cloud services.

[1547] "Communication location information" refers to data obtained as location information of communication devices, and geographical information is identified based on this data.

[1548] "Place name" refers to a geographical name or area name, and is used to extract location information.

[1549] "Smart glasses" are a type of wearable device, a pair of eyeglass-type electronic devices that provide information to users by displaying visual information on a display.

[1550] "Real-time" means being able to process an event the moment it occurs, and being able to provide and process information without delay.

[1551] "NLP" stands for natural language processing, and is a technology that analyzes, understands, and interprets information contained in text data and spoken language.

[1552] "GeoIP Library" means a software library for obtaining geographic location information from an IP address, which is used in conjunction with an IP address to determine location.

[1553] The present invention is a system that uses a social networking service (SNS) API to collect posts related to urgency, transmits the contents of inquiries to an information processing device, analyzes the collected posts and inquiry contents, extracts communication point information and location names, identifies the location and urgency based on the analyzed contents, notifies related devices of the identified information, and displays the notification contents on smart glasses in real time.

[1554] Overall system configuration

[1555] The system mainly consists of the following components:

[1556] 1. Terminal

[1557] 2. Server

[1558] 3. Social Media API

[1559] 4. GeoIP Library

[1560] 5. Natural Language Processing (NLP) Module

[1561] 6. Smart Glasses

[1562] Terminal

[1563] The device collects posts from users and related parties related to inquiries and their urgency, and sends them to the server. Specifically, the device uses SNS APIs to periodically check for posts containing specific hashtags such as "factory trouble" and temporarily saves them. It also collects inquiry data and sends it to the server.

[1564] server

[1565] The server receives the information sent from the device and stores it in a database. Next, it analyzes the received text data and extracts communication point information and location names. At this time, it uses the GeoIP library to obtain region information from IP addresses. It then uses NLP technology to analyze the text and classify the post content into categories. For example, if the post content contains the keyword "fire broke out," the information will be classified into the category "fire accident."

[1566] Urgency judgment

[1567] The server identifies the location and urgency based on the analyzed content. Specifically, it analyzes keywords and phrases in the text, and if they are of high urgency, it classifies them as "high urgency." For example, keywords such as "fire" and "explosion" are treated as high urgency.

[1568] Notifications and Displays

[1569] The server then sends notifications to relevant devices based on the identified information. For example, if high-urgency information such as "A fire has broken out at Factory A" is extracted, the information is immediately sent to the fire department and relevant parties. Furthermore, the notification content is displayed in real time on the smart glasses, accelerating response.

[1570] Specific examples

[1571] A series of examples of how the system can be implemented include the following:

[1572] 1. Users

[1573] A user posts on Twitter, "There's a fire at Factory A."

[1574] 2. Terminal

[1575] The device periodically retrieves these posts using the SNS API, temporarily stores them, and then sends them to the server.

[1576] 3. Server

[1577] The server stores the posts received from the devices in a database, analyzes the text data, and extracts communication point information and location names. Posts containing the keyword "fire breaks out" are categorized as "fire accidents."

[1578] 4. Urgency determination

[1579] Text analysis determines that this post is of "high urgency."

[1580] 5. Notices and Displays

[1581] The server immediately notifies the fire department that "a fire has broken out at Factory A," and the smart glasses display a message saying "Fire has broken out. Please take emergency action."

[1582] Prompt Sentence Examples

[1583] "Please build an emergency assessment system to detect and respond to factory troubles. This system will assess the emergency level and respond appropriately by collecting and analyzing social media posts containing the following specific hashtags."

[1584] This will enable quick and appropriate responses to troubles and emergencies within the factory.

[1585] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1586] Step 1:

[1587] The device uses SNS APIs to collect posts related to urgency. During this process, the device periodically checks for posts containing specific hashtags (e.g., "factory trouble") and temporarily stores their contents. The input is the raw data of SNS posts, and the output is the temporarily stored post data related to urgency. Data processing involves filtering and storing the raw data obtained through the SNS API.

[1588] Step 2:

[1589] The terminal sends the collected posts and inquiry contents to the information processing device. The saved post data related to urgency is sent to the server. The input is the post data saved in step 1, and the output is the post data sent to the server. Data processing includes sending the saved data on the terminal to the server via network communication.

[1590] Step 3:

[1591] The server stores the received post data in a database and uses an NLP module to analyze the text data. The input is the post data sent to the server, and the output is the analysis results. Specifically, NLP technology is used to classify the post content into categories and extract important keywords and phrases.

[1592] Step 4:

[1593] The server uses the GeoIP library to obtain communication point information from the poster's IP address and identify the location name. The input is the IP address and analysis results contained in the posted data, and the output is communication point information and the location name. Specifically, the GeoIP library analyzes the IP address to extract geographical location information.

[1594] Step 5:

[1595] The server identifies the location and urgency based on the analyzed content. Information with a high urgency level is classified as "high urgency" based on keywords and phrases in the text. The input is the NLP analysis results and communication point information, and the output is the urgency classification result. For data calculation, an urgency determination algorithm is used to evaluate and classify the text analysis results.

[1596] Step 6:

[1597] The server notifies the relevant devices of the identified information. For example, if there is information that "a fire has broken out at Factory A," it will immediately notify the fire department and relevant parties. The input is the urgency classification result and specific location information, and the output is a notification message. Specifically, it uses a notification API or web hook to send information to relevant devices in real time.

[1598] Step 7:

[1599] The server displays the notification content on the smart glasses in real time. The input is the notification message, and the output is the information displayed on the smart glasses' display. The server sends the same notification as the information sent to the related devices to the smart glasses, providing the user with information in real time. Specifically, the message is displayed through an API dedicated to the smart glasses.

[1600] 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.

[1601] This invention relates to a system for grasping the situation in disaster-stricken areas and taking prompt and appropriate action. This system collects and analyzes social media posts and company inquiries to identify the level of urgency and the area, and notifies relevant organizations. Furthermore, it combines an emotion engine that recognizes user emotions to analyze the emotions in the posts and help identify the level of urgency.

[1602] Overall system configuration

[1603] The system mainly consists of the following components:

[1604] 1. Terminal

[1605] 2. Server

[1606] 3. Social Media API

[1607] 4. GeoIP Library

[1608] 5. Natural Language Processing (NLP) Module

[1609] 6. Emotion Engine

[1610] Terminal

[1611] The device collects inquiries from users and companies and sends them to a server. Specifically, the device uses SNS APIs to periodically check for posts containing specific hashtags such as "disaster" or "rescue" and temporarily stores them. It also collects data on inquiries to the company and sends this data to a server.

[1612] server

[1613] The server receives the information sent from the device and stores it in a database. The received text data is then analyzed using natural language processing (NLP). NLP analysis extracts IP addresses, local area names, and specific keywords and phrases from the text, and classifies the post content into categories. For example, if a post contains the keyword "no water," the information will be classified into the category "infrastructure problems."

[1614] Emotion Engine

[1615] The analysis on the server also uses an emotion engine. The emotion engine analyzes the emotions in the posted content and can identify emotions such as "sadness," "fear," and "anger." The emotion data obtained by the emotion engine is used to assist in determining the level of urgency.

[1616] Urgency judgment

[1617] The server uses NLP and an emotion engine to analyze the data and identify the region and level of urgency. Specifically, it analyzes keywords and phrases in the text, as well as the extracted emotion data, and classifies any that indicate a high level of urgency as "high urgency." For example, keywords such as "help" and "fire" are treated as high urgency, and if the emotion engine detects "fear," it is treated as an even higher level of urgency.

[1618] notification

[1619] The server then notifies the relevant organizations based on the identified information. For example, if high-urgency information such as "water is not coming out in ward X" is extracted, the information is immediately sent to the waterworks bureau. This is done using real-time notification methods via APIs and webhooks.

[1620] Specific examples

[1621] Below are a series of examples of this system in action:

[1622] 1. Users

[1623] A user posts on Twitter, "There is no water in XX ward." This post conveys the emotion of "I am in great trouble."

[1624] 2. Terminal

[1625] The device periodically retrieves these posts using the SNS API, temporarily stores them, and then sends them to the server.

[1626] 3. Server

[1627] The server stores the posts received from the devices in a database. It analyzes the text data and extracts IP addresses and area names. Posts containing the keyword "no water" are classified into the category "infrastructure problems."

[1628] 4. Emotion Engine

[1629] The emotion engine recognizes the emotion "very troubled" from the content of the post.

[1630] 5. Urgency determination

[1631] Based on text analysis and sentiment data, this post is determined to be of "high urgency."

[1632] 6. Notification

[1633] The server immediately notifies the waterworks bureau of the information that "there is no water in XX ward."

[1634] In this way, the system can quickly and accurately grasp the situation in the disaster area and prompt the appropriate relevant organizations to take prompt action. By adding an emotion engine, it becomes possible to make more accurate urgency judgments and gain a deeper understanding of the condition of the victims.

[1635] The processing flow will be explained below.

[1636] Step 1:

[1637] User

[1638] A user posts on social media, such as "There is no water in ward XX." The information posted by the user is stored on the social media platform.

[1639] Step 2:

[1640] Terminal

[1641] The device periodically connects to the SNS API to check for new posts containing specific hashtags or keywords such as "disaster" or "rescue." The new posts retrieved from the API are temporarily stored in the device's storage.

[1642] Step 3:

[1643] Terminal

[1644] The device analyzes the collected posting data, extracts metadata such as the user's IP address and the content of the post, and formats this data for transmission to the server.

[1645] Step 4:

[1646] Terminal

[1647] The formatted data is sent to the server via an API endpoint that is designed to ensure it reaches the server.

[1648] Step 5:

[1649] server

[1650] The server stores the data received from the device in a database, which is used for subsequent analysis.

[1651] Step 6:

[1652] server

[1653] The server then analyzes the received text data using natural language processing (NLP), which involves extracting IP addresses, location names, and specific keywords and phrases from the text.

[1654] Step 7:

[1655] server

[1656] Using data obtained from NLP analysis, we use the GeoIP library to extract geographic information from IP addresses, thereby identifying the region from which a post originates.

[1657] Step 8:

[1658] server

[1659] The NLP module classifies posts into categories based on keywords and phrases extracted. For example, a post about "no water" would be classified as "infrastructure problems."

[1660] Step 9:

[1661] server

[1662] The server uses an emotion engine to analyze the sentiment of the posts, using an emotion-identifying algorithm to identify emotions such as "sadness," "fear," and "anger."

[1663] Step 10:

[1664] server

[1665] Based on data obtained from NLP analysis and sentiment analysis, an urgency assessment algorithm is applied to assess the urgency of posts. Posts that are deemed to be of high urgency are immediately classified as "high urgency."

[1666] Step 11:

[1667] server

[1668] Based on information deemed to be of high urgency, relevant organizations (national government, local government, medical organizations, etc.) are notified. Notifications are sent in real time via API or webhook.

[1669] Step 12:

[1670] server

[1671] The system confirms that notifications have been sent successfully and records the history in a database, making it possible to track which information was sent to which institution and when.

[1672] Specific examples

[1673] Below are the steps by which the system actually works in a concrete example:

[1674] 1. Users

[1675] A user posts on Twitter, "There is no water in XX ward." This post conveys the emotion of "I am in great trouble."

[1676] 2. Terminal

[1677] The device uses the Twitter API to check posts with the hashtag "disaster," retrieves these posts, stores them temporarily, and then sends the data to the server.

[1678] 3. Server

[1679] The server receives the posted data obtained from the terminal and stores it in a database.

[1680] 4. Server

[1681] It uses an NLP module to parse the text and extract keywords like "no water," while also using the GeoIP library to determine the region of the post from its IP address.

[1682] 5. Server

[1683] Using a sentiment engine, the sentiment of the post is identified as "very distressed."

[1684] 6. Server

[1685] Using an urgency assessment algorithm, messages are classified as "high urgency" based on information obtained from text analysis and sentiment analysis.

[1686] 7. Server

[1687] Based on highly urgent information such as "water is not coming out in ward XX," the waterworks bureau is notified immediately.

[1688] 8. Server

[1689] Records that the notification was successful and stores the history in a database.

[1690] In this way, the system can quickly and accurately grasp the situation in the disaster area and prompt the appropriate relevant organizations to take prompt action. By adding an emotion engine, it becomes possible to make more accurate urgency judgments and gain a deeper understanding of the condition of the victims.

[1691] Example 2

[1692] 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."

[1693] The problem is that it is difficult to gather and analyze information to quickly and accurately grasp the situation in disaster-stricken areas and take appropriate measures. In particular, the technical challenge is extracting useful information from the vast amount of data on social media and inquiries, and determining the level of urgency. Furthermore, by adding emotion analysis, more accurate urgency determination is required.

[1694] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1695] In this invention, the server includes: [means for collecting posts related to urgency using an SNS API;] [means for sending the content of inquiries to the organization's server;] [means for analyzing the collected posts and inquiry content and extracting IP addresses and regional information;] [means for analyzing the content of posts using a Natural Language Processing (NLP) module and extracting keywords and phrases;] ​​[means for analyzing the emotions of the content of posts using an emotion engine;] [means for identifying the region and urgency based on the analyzed content; and [means for notifying relevant organizations of the identified information.] This makes it possible to quickly and accurately grasp the situation in the disaster-stricken areas and to promptly notify appropriate relevant organizations.

[1696] "SNS API" is an application programming interface that allows programs to use posted data from social networking services.

[1697] "Inquiries" refer to the content of communication such as questions, consultations, and requests made by users and related parties to an organization.

[1698] A "server" is a computer system that receives, stores, analyzes, and transmits data over a network.

[1699] "IP address" refers to a unique numeric code used when sending and receiving data on the Internet.

[1700] "Region information" refers to information about a particular geographic area, including city, ward, town, village name, postal code, etc.

[1701] A "Natural Language Processing (NLP) module" is a software component that allows a computer to analyze human natural language and understand its meaning and structure.

[1702] "Keywords" refer to words or phrases that are particularly important within text data.

[1703] An "emotion engine" is a software component that analyzes emotions from text data and classifies them into specific emotion categories (e.g., joy, sadness, fear, etc.).

[1704] "Analyzed content" refers to the information obtained as a result of analyzing collected data using an NLP module or emotion engine.

[1705] "Urgency" is a measure that indicates the level of urgency of data or an event, and is used to determine the priority of responses.

[1706] "Relevant organizations" refer to government agencies, private companies, non-governmental organizations (NGOs), etc. that need to respond based on specific information.

[1707] This invention relates to a system for quickly and accurately grasping the situation in disaster-stricken areas and taking appropriate measures. This system collects social media posts and inquiries to companies, analyzes them, identifies the level of urgency and the area, and notifies the relevant organizations.

[1708] Overall system configuration

[1709] The system mainly consists of the following components:

[1710] 1. Terminal

[1711] 2. Server

[1712] 3. Social Media API

[1713] 4. GeoIP Library

[1714] 5. Natural Language Processing (NLP) Module

[1715] 6. Emotion Engine

[1716] Terminal

[1717] The device collects inquiries from users and companies and sends them to a server. Specifically, the device uses SNS APIs to periodically check for posts containing specific hashtags such as "disaster" or "rescue" and temporarily stores them. It also collects data on inquiries to the company and sends this data to a server.

[1718] server

[1719] The server receives the information sent from the device and stores it in a database. Next, it analyzes the received text data using a natural language processing (NLP) module. NLP analysis extracts IP addresses, local area names, and specific keywords and phrases from the text, and classifies the post content into categories. For example, if the post content contains the keyword "no water," the information will be classified into the category "infrastructure problems."

[1720] Emotion Engine

[1721] The analysis on the server also uses an emotion engine. The emotion engine analyzes the emotions in the posted content and can identify emotions such as "sadness," "fear," and "anger." The emotion data obtained by the emotion engine is used to assist in determining the level of urgency.

[1722] Urgency judgment

[1723] The server uses NLP and an emotion engine to analyze the data and identify the region and level of urgency. Specifically, it analyzes keywords and phrases in the text, as well as the extracted emotion data, and classifies any that indicate a high level of urgency as "high urgency." For example, keywords such as "help" and "fire" are treated as high urgency, and if the emotion engine detects "fear," it is treated as an even higher level of urgency.

[1724] notification

[1725] The server then notifies the relevant organizations based on the identified information. For example, if high-urgency information such as "water is not coming out in ward X" is extracted, the information is immediately sent to the waterworks bureau. This is done using real-time notification methods via APIs and webhooks.

[1726] Specific examples

[1727] Below are a series of examples of this system in action:

[1728] 1. Users

[1729] A user posts on Twitter, "There is no water in XX ward." This post conveys the emotion of "I am in great trouble."

[1730] 2. Terminal

[1731] The device periodically retrieves these posts using the SNS API, temporarily stores them, and then sends them to the server.

[1732] 3. Server

[1733] The server stores the posts received from the devices in a database. It analyzes the text data and extracts IP addresses and area names. Posts containing the keyword "no water" are classified into the category "infrastructure problems."

[1734] 4. Emotion Engine

[1735] The emotion engine recognizes the emotion "very troubled" from the content of the post.

[1736] 5. Urgency determination

[1737] Based on text analysis and sentiment data, this post is determined to be of "high urgency."

[1738] 6. Notification

[1739] The server immediately notifies the waterworks bureau of the information that "there is no water in XX ward."

[1740] In this way, the system can quickly and accurately grasp the situation in the disaster area and prompt the appropriate relevant organizations to take prompt action.In addition, by using the emotion engine, the accuracy of urgency determination can be improved, enabling a deeper understanding of the condition of the victims.

[1741] Prompt Sentence Examples

[1742] Please explain how the system works: collects posts on Twitter that contain the hashtags "disaster" and "rescue," determines the area and urgency based on the content, and notifies the relevant organizations.

[1743] Using this prompt, the generative AI model can generate sentences like the one above that detail the process of the system.

[1744] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1745] Step 1:

[1746] User posts to SNS

[1747] Users post on Twitter or other SNSs using hashtags such as "disaster" or "rescue." For example, they might post something like, "There's no water in XX ward. We're in a lot of trouble." The input is the user's SNS post, and the output is the post itself. The specific actions a user takes are logging in to the SNS using a smartphone or PC and posting.

[1748] Step 2:

[1749] The device collects posts

[1750] The device periodically checks for posts containing these hashtags using the SNS API. The device collects the posts, temporarily stores them in local storage, and then sends them to the server. The input is the user's SNS posts, and the output is the collected post data. Specifically, the device searches for posts using the SNS API, retrieves and saves the relevant posts, and sends them to the server.

[1751] Step 3:

[1752] The server receives the data

[1753] The server receives the posted data sent from the device and stores it in a database. The input is the posted data sent from the device, and the output is the data stored in the database. Specifically, the server analyzes the received data, formats it, and then inserts it into the database.

[1754] Step 4:

[1755] The server uses the NLP module to analyze the text.

[1756] The server uses an NLP module to analyze the received text data. It extracts IP addresses, local area names, and specific keywords and phrases from the text and categorizes the posts. The input is the received text data, and the output is data such as analyzed keywords, local area names, and IP addresses. Specifically, it runs the NLP module to analyze and extract each element of the text.

[1757] Step 5:

[1758] The server performs emotion analysis using the emotion engine.

[1759] The server uses an emotion engine to analyze the emotions in the posted content. For example, emotions such as "fear" or "confusion" can be identified from the text data. The input is the text data, and the output is the detected emotion information. Specifically, the emotion engine is executed to extract emotion data from the text and identify which emotions are contained.

[1760] Step 6:

[1761] The server determines the urgency

[1762] The server determines the urgency of a post based on the results of the NLP and emotion engine. It analyzes keywords, phrases, and emotional data in the text and determines the urgency level from high to low. The input is the analyzed keywords and emotional information, and the output is the urgency level determination result. Specifically, it evaluates the extracted data and sets the urgency level.

[1763] Step 7:

[1764] The server notifies the relevant parties

[1765] The server notifies relevant organizations of specific information based on the results of the assessment. For example, if there is high-urgency information such as "water is not coming out in ward XX," it will notify the waterworks bureau. The input is the urgency assessment result, and the output is the sent notification. Specific operations include sending real-time notifications using APIs and webhooks.

[1766] This will enable the entire system to operate efficiently and to quickly and appropriately communicate the situation in the disaster-stricken areas to relevant organizations.

[1767] (Application example 2)

[1768] 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."

[1769] Conventional emergency response systems have difficulty in quickly and accurately grasping the situation in disaster-stricken areas, resulting in delayed appropriate responses. Furthermore, they often failed to properly assess the emotions and urgency contained in posts on social media, resulting in a failure to respond immediately to highly urgent situations. Furthermore, delays in notification to relevant organizations have also led to delays in rescue efforts for victims.

[1770] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1771] In this invention, the server includes: means for collecting posts related to urgency using a social networking service (SNS) API; means for sending inquiry content to a database server; means for analyzing the collected posts and inquiry content and extracting IP addresses and local area names; emotion engine means for analyzing the emotional state of the posts; means for identifying the local area and urgency level based on the analyzed content and emotional state; and means for notifying relevant organizations and security services of the identified information. This allows for rapid identification of the local area and urgency level of the collected posts, enabling immediate notification to relevant organizations. Furthermore, the emotion engine also performs emotion analysis of the posts, allowing for accurate identification of high-urgency situations, enabling rapid and appropriate responses. Furthermore, natural language processing and emotion analysis using a generative AI model enables more advanced information analysis and improved decision accuracy.

[1772] "SNS API" is an application programming interface for accessing data from social networking services (SNS).

[1773] A "database server" is a server that manages a database and performs operations such as storing, searching, updating, and deleting data.

[1774] "Posted content" refers to text and media information that users make public on social media and other communication platforms.

[1775] "Inquiry content" is text information of questions or opinions that users have made to companies or organizations.

[1776] An "IP address" is a unique number that identifies a device on the Internet.

[1777] A "region name" is a name that indicates a specific geographical area.

[1778] An "emotion engine" is a software module that analyzes emotions in text data and identifies the emotional state.

[1779] "Urgency" is an indicator of the level of urgency of a particular event or situation.

[1780] "Relevant organizations" refers to organizations or organisations directly involved in emergency and disaster response.

[1781] "Security services" is a general term for services that protect people and assets, prevent crime, and deal with disasters.

[1782] A "generative AI model" is an artificial intelligence model built using machine learning and deep learning, which learns from specific tasks and makes predictions and analyses.

[1783] A "prompt" is text that provides instructions or example input given to a generative AI model to perform a specific task.

[1784] The present invention is a system for quickly and accurately grasping the situation in a disaster area and prompting appropriate organizations to respond. Specific embodiments for carrying out the present invention are described below.

[1785] Overall system configuration

[1786] The system mainly consists of the following components:

[1787] 1. Terminal

[1788] 2. Server

[1789] 3. Social Media API

[1790] 4. Database Server

[1791] 5. Natural Language Processing (NLP) Module

[1792] 6. Emotion Engine

[1793] 7. Generative AI Models

[1794] Terminal

[1795] The device is responsible for collecting inquiries from users and businesses and sending this data to a server. Specifically, the device uses SNS APIs to periodically check for posts containing specific hashtags such as "disaster" or "rescue" and temporarily stores them. Inquiries to businesses are also collected in the same way and sent to the server.

[1796] server

[1797] The server receives the information sent from the device and stores it in a database server. The received text data is then analyzed using an NLP module. NLP analysis extracts IP addresses, local area names, and specific keywords and phrases from the text, and classifies the posted content into categories.

[1798] Emotion Engine

[1799] The server also uses an emotion engine to analyze the emotions in the posts and identify emotions such as "fear," "sadness," and "confusion."

[1800] Urgency judgment

[1801] The server identifies the region and urgency based on the data analyzed using the NLP module and emotion engine. Specifically, it analyzes keywords and phrases in the text as well as the extracted emotion data, and if it indicates a high level of urgency, it classifies it as "high urgency." For example, keywords such as "help" and "fire" are treated as high urgency, and if the emotion engine detects "fear," it is treated as an even higher level of urgency.

[1802] notification

[1803] The server then notifies relevant authorities and security services based on the identified information, using APIs and webhooks to prompt immediate action in real time.

[1804] Specific examples

[1805] Here's an example of this system in action:

[1806] Example 1: Collecting and analyzing social media posts

[1807] 1. Users

[1808] A user posts on Twitter, "Disaster Fire There's a fire in XX ward. It's very dangerous, please help."

[1809] 2. Terminal

[1810] The device periodically retrieves these posts using the SNS API, temporarily stores them, and then sends them to the server.

[1811] 3. Server

[1812] The server stores the posts received from the devices in a database server. The text data is analyzed to extract IP addresses and area names. Posts containing the keyword "fire" are classified as "high urgency."

[1813] 4. Emotion Engine

[1814] The emotion engine recognizes the emotion "It's very dangerous, please help" from the content of the post.

[1815] 5. Urgency determination

[1816] Based on text analysis and sentiment data, this post is determined to be of "high urgency."

[1817] 6. Notification

[1818] The server immediately notifies the fire department and security services of the information "There is a fire in ward XX."

[1819] Prompt Sentence Examples

[1820] Here are some example prompts to apply to generative AI models:

[1821] Prompt: "Create a program that analyzes the sentiment of posts collected from social media, extracts local information, and determines the level of urgency. If the level of urgency is high, include a function to notify the relevant authorities."

[1822] The above is the details of the "Mode for Carrying Out the Invention." By using this system, it is possible to quickly and accurately grasp the situation in the disaster area and respond appropriately.

[1823] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1824] Step 1:

[1825] A user posts an emergency situation on a social networking service (SNS). This post includes a hashtag (e.g., "disaster" or "fire") and a specific description of the situation (e.g., "There's a fire in ____ ward. It's very dangerous. Please help.").

[1826] Step 2:

[1827] The device periodically calls the SNS API to search and collect posts containing specific hashtags. This temporarily stores newly posted emergency information. The input is data from the SNS API, and the output is the temporarily stored post data.

[1828] Step 3:

[1829] The terminal transmits the temporarily saved posted data to the server. Here, the input is the temporarily saved posted data, and the output is the data sent to the server. This data includes the text of the post, the poster's IP address, and the posting date and time.

[1830] Step 4:

[1831] The server stores the received submission data in a database server. This ensures that the data required for subsequent analysis steps is stored persistently. The input is the data sent from the device, and the output is the data stored in the database.

[1832] Step 5:

[1833] The server analyzes the saved posting data using an NLP (Natural Language Processing) module, which extracts location-related information (place names and IP addresses) and specific keywords and phrases from the posting content. The input is the posting data retrieved from the database, and the output is the analyzed text data and extracted location information.

[1834] Step 6:

[1835] The server uses an emotion engine to analyze the emotional state of the post. Emotions such as "fear," "sadness," and "confusion" are identified. The input is the analyzed text data, and the output is the extracted emotional data.

[1836] Step 7:

[1837] The server determines the urgency level based on data analyzed by the NLP module and emotion engine. If the keyword "fire" or the emotion "fear" is identified, it is classified as high urgency. The input is the analyzed text data and emotion data, and the output is the determined urgency information.

[1838] Step 8:

[1839] The server notifies relevant organizations and security services based on the determined urgency information. Notifications are sent via API or web hooks, and if the urgency is high, notifications are sent immediately. The input is urgency information, and the output is notification data sent to relevant organizations.

[1840] Step 9:

[1841] The relevant authorities receive the notification from the server and take immediate action. Specifically, the fire department may be dispatched to the scene. The input is the notification data from the server, and the output is the actual response action.

[1842] The above is the specific flow of the processing of the present invention. Through these steps, it becomes possible to quickly and accurately grasp the situation in the disaster area and respond appropriately.

[1843] 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.

[1844] 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.

[1845] 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.

[1846] 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.

[1847] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1848] 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.

[1849] 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).

[1850] 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.

[1851] 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."

[1852] 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.

[1853] 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).

[1854] 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.

[1855] 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.

[1856] 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.

[1857] 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.

[1858] 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.

[1859] 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.

[1860] 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.

[1861] 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.

[1862] 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.

[1863] 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.

[1864] The following is further disclosed regarding the above embodiment.

[1865] (Claim 1)

[1866] [Method of collecting posts related to urgency using SNS API,

[1867] [Means for sending the contents of the inquiry to the company's server,

[1868] [Means of analyzing collected posts and inquiries and extracting IP addresses and area names,

[1869] [Means to identify the area and urgency based on the analyzed content, and

[1870] [Means of notifying relevant authorities of the identified information;

[1871] A system including:

[1872] (Claim 2)

[1873] [The system of claim 1, which uses Natural Language Processing (NLP) to categorize posts.

[1874] (Claim 3)

[1875] [The system according to claim 1, wherein the system obtains regional information from an IP address using a GeoIP library.

[1876] "Example 1"

[1877] (Claim 1)

[1878] [Means for automatically collecting information on urgency from SNS,

[1879] [Means for storing data submitted directly by users in a central database; and

[1880] [Means for extracting meaning from collected text data using text analysis technology;

[1881] [Means to classify each data into specific categories based on extracted regional information and keywords, and

[1882] [Means for evaluating the urgency of the analyzed data and identifying data of high urgency;

[1883] [Means for immediately notifying relevant authorities of identified high-urgency information; and

[1884] A system including:

[1885] (Claim 2)

[1886] [The system according to claim 1, wherein the text data is analyzed and classified into categories using Natural Language Processing technology.

[1887] (Claim 3)

[1888] [The system of claim 1, utilizing geographic identification technology to extract region information from IP address information.

[1889] "Application Example 1"

[1890] (Claim 1)

[1891] [Method of collecting posts related to urgency using SNS API,

[1892] [Means for transmitting the contents of the inquiry to the information processing device;

[1893] [Means for analyzing collected posts and inquiries and extracting communication point information and place names;

[1894] [Means for identifying the location and urgency based on the analyzed content, and

[1895] [Means for notifying related devices of the identified information;

[1896] [Means for displaying notification content on smart glasses in real time;

[1897] A system including:

[1898] (Claim 2)

[1899] [The system of claim 1, which uses Natural Language Processing (NLP) to categorize posts.

[1900] (Claim 3)

[1901] [The system according to claim 1, wherein the location name is obtained from the communication point information using a GeoIP library.

[1902] "Example 2: Combining Emotion Engines"

[1903] (Claim 1)

[1904] [Method of collecting posts related to urgency using SNS API,

[1905] [Means for transmitting the contents of the inquiry to the organization's server;

[1906] [Means of analyzing collected posts and inquiries and extracting IP addresses and regional information;

[1907] [Method of analyzing posts and extracting keywords and phrases using Natural Language Processing (NLP) module;

[1908] [Means for analyzing the sentiment of posts using a sentiment engine;

[1909] [Means to identify the area and urgency based on the analyzed content, and

[1910] [Means of notifying relevant organizations of the identified information; and

[1911] A system including:

[1912] (Claim 2)

[1913] The system of claim 1, wherein Natural Language Processing (NLP) is used to classify posts into categories.

[1914] (Claim 3)

[1915] [The system according to claim 1, wherein the system obtains regional information from an IP address using a GeoIP library.

[1916] "Application example 2 when combining emotion engines"

[1917] (Claim 1)

[1918] [Method of collecting posts related to urgency using SNS API,

[1919] [Means for sending the query to a database server;

[1920] [Means of analyzing collected posts and inquiries and extracting IP addresses and area names,

[1921] [an emotion engine means for analyzing the emotional state of the posted content;

[1922] [Means for identifying the location and urgency based on the analyzed content and emotional state;

[1923] [Means of communicating identified information to relevant authorities and security services;

[1924] A system including:

[1925] (Claim 2)

[1926] [The system of claim 1, which uses Natural Language Processing (NLP) to categorize posts.

[1927] (Claim 3)

[1928] [The system according to claim 1, wherein the system obtains regional information from an IP address using a GeoIP library.

[1929] (Claim 4)

[1930] [The system according to claim 1 notifies relevant organizations in real time of extracted posts with high urgency.

[1931] (Claim 5)

[1932] [After collecting the content of posts, it analyzes their emotions and increases the urgency if the emotional state is "fear," "sadness," or "confusion."]

[1933] 10. The system of claim 1.

[1934] (Claim 6)

[1935] [The system of claim 1 applies prompt sentences that perform natural language processing and sentiment analysis using a generative AI model. [Explanation of symbols]

[1936] 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 of collecting posts related to urgency using SNS API, A means for transmitting the contents of the inquiry to the company's server; A method for analyzing collected posts and inquiries and extracting IP addresses and area names; A means to identify the area and urgency based on the analyzed content, and a means of notifying relevant authorities of the identified information; A system including:

2. The system of claim 1 , wherein the system uses Natural Language Processing to categorize posts.

3. The system according to claim 1, wherein the system obtains the region information from the IP address using a GeoIP library.

Images