System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting data from a plurality of information sources; means for analyzing the collected data and classifying the data by time, area, location, and presenter; means for providing relevant information from the classified data based on questions from users; means for identifying victim safety and location information using carrier data; and means for matching supporters based on resource needs registered on the site.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] When a disaster occurs, confusion and lack of information can occur between victims and supporters, making it difficult to respond quickly. Elderly people, in particular, have difficulty accessing and using new information technology, so they may not receive sufficient support. In addition, there are limitations to current methods of confirming the safety of victims and matching material support, which can prevent prompt and appropriate support from being provided. [Means for solving the problem]

[0005] This system provides necessary information in real time by combining a means for collecting data from multiple sources and analyzing it using natural language processing with a means for providing relevant information based on user questions. It also uses data from telecommunications companies to confirm the safety of disaster victims and identify their location, and provides a means for matching supporters based on the material needs registered on the site. In this way, the system aims to efficiently support communication between disaster victims and supporters, enabling prompt and appropriate support.

[0006] "Sources" are various platforms that provide data, such as social media, online news, and official government announcements.

[0007] "Data collection" is the process of capturing and storing data from multiple sources.

[0008] "Analysis" is the process of classifying collected data using techniques such as natural language processing to make its meaning easier to understand.

[0009] "Time, Region, Place, and Presenter" are categories used to organize collected data, indicating when, where, and to which location each piece of information relates, and by whom it was presented.

[0010] "Question answering" is the process of providing appropriate information in response to a specific question posed by a user.

[0011] "Relevant information" is the most relevant and important information from the analyzed data to the user's question.

[0012] A "telecommunications company" is a company that provides telecommunications services and collects and manages data such as communication history and location information.

[0013] "Safety confirmation" is the process of checking whether disaster victims are safe or not.

[0014] "Location information" is information that indicates the location where the victim last communicated and their current location.

[0015] "Material needs" refers to the items and quantities needed by disaster victims.

[0016] "Supporters" are people or organizations that provide supplies or other assistance to disaster victims.

[0017] "Matching" is the process of matching the material needs of disaster victims with the support capabilities of supporters to ensure that appropriate support is provided.

[0018] "Site" means the web platform through which users enter and review information.

[0019] "Natural Language Processing (NLP)" is a technology that enables computers to understand and analyze human language. [Brief explanation of the drawings]

[0020] [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

[0021] 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.

[0022] First, the terms used in the following description will be explained.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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."

[0028] [First embodiment]

[0029] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0030] 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.

[0031] 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).

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0037] 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.

[0038] 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.

[0039] 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.

[0040] 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."

[0041] This invention is a "disaster information and support system" for smoothly providing information and carrying out support activities when a disaster occurs. This system collects and organizes information from social media and online news, and provides information in response to user questions. It also utilizes data from telecommunications companies to check the safety and location of disaster victims, and has the function of matching supply needs with supporters.

[0042] System configuration

[0043] 1. Server:

[0044] The server collects and stores data in real time from multiple sources (e.g., social media, online news, official government announcements, etc.). It then analyzes the data using a natural language processing (NLP) engine and categorizes it by time, region, location, and presenter. The results of this analysis are stored in a database and can be searched and provided as needed.

[0045] 2. Terminal:

[0046] The device is used by users to access the site, search for information, register supplies, and confirm support. Examples of such devices include PCs, smartphones, and tablets.

[0047] 3. User:

[0048] Users include those who provide information (e.g., disaster victims, general users) and those who acquire information (e.g., family members, supporters). Users use the site to check safety and register / confirm supplies.

[0049] Program processing

[0050] 1. Data Collection and Analysis:

[0051] Server: Collects data from specified sources and analyzes it using a natural language processing engine. For example, it collects posts related to specific hashtags or keywords through social media APIs and categorizes these posts by date, time, location, and author.

[0052] Example: The server collects and analyzes social media posts containing the hashtag "disaster name." Through this analysis, the posts are classified as "October 15, 2023, Shibuya Ward, Tokyo, information from individual users."

[0053] 2. Question and Answer:

[0054] User: Enters a question on the site (e.g., "What is the current situation in Shibuya Ward?"). This question is sent to the server.

[0055] Server: Analyzes the question and searches the database for relevant information. Based on the analysis results, the generation AI generates an appropriate answer and provides it to the user.

[0056] Example: When a user asks, "What is the current situation in Shibuya Ward?", the server will respond based on the latest news and social media posts with something like, "Traffic restrictions are in place in Shibuya Ward, and the evacuation shelter is at XX Elementary School."

[0057] 3. Safety confirmation:

[0058] Server: Obtains communication history, Wi-Fi connection information, and GPS data from the telecommunications company's API, and checks the last location and safety of victims.

[0059] Users: Enter names and contact information on the site to check on the safety of family and loved ones.

[0060] Server: Based on the input information, searches for communication data and provides the user with the relevant safety information.

[0061] Example: When a user checks the safety of "Taro Tanaka," the server responds with information such as "Taro Tanaka was last contacted in front of Shibuya Station at 15:30."

[0062] 4. Registering material needs and matching donors:

[0063] Victims (users): Enter and register the supplies they need and their quantities on the site (for example, 10 liters of water, 3 blankets).

[0064] Server: Stores registered material needs in a database and makes them available for donors to view.

[0065] Donors (users): Select the supplies they can donate on the site and express their intention to donate.

[0066] Server: Confirms the supporter's selection, notifies the administrator, and instructs the appropriate arrangement procedure.

[0067] Example: A donor views the "List of victims in the Tohoku region" and selects "Provide three blankets to the Tanaka family." After confirmation, the administrator instructs the donor on how and when to deliver the relief supplies.

[0068] In this way, the system of the present invention can provide information quickly and appropriately when a disaster occurs, and efficiently support communication between victims and supporters.

[0069] The processing flow will be explained below.

[0070] Data collection and analysis

[0071] Step 1:

[0072] Server: Periodically sends requests to APIs of social media, online news, and government announcement sites to collect data.

[0073] Step 2:

[0074] Server: Adds collected data to a queue for analysis and passes it to the natural language processing engine.

[0075] Step 3:

[0076] Server: A natural language processing engine analyzes the data and categorizes it by date, time, location, and presenter.

[0077] Step 4:

[0078] Server: The analysis results are stored in a database and indexed for later retrieval.

[0079] Question and Answering

[0080] Step 1:

[0081] User: Enters a question into the site's search box (e.g., "What's the current situation in Shibuya Ward?").

[0082] Step 2:

[0083] Server: Receives questions from users and analyzes the content of the questions using natural language processing.

[0084] Step 3:

[0085] Server: Searches for relevant information from the database and generates appropriate answers using generative AI.

[0086] Step 4:

[0087] Server: Returns the answer to the user's terminal and displays it to the user.

[0088] Confirmation of safety

[0089] Step 1:

[0090] Server: Periodically obtains communication history, Wi-Fi connection information, and GPS data from the telecommunications company's API.

[0091] Step 2:

[0092] Server: Analyzes the acquired data and stores the victim's last location and safety information in a database.

[0093] Step 3:

[0094] User: Enters name and contact information into the safety confirmation form on the site.

[0095] Step 4:

[0096] Server: Searches the database based on the entered information and identifies the relevant safety information.

[0097] Step 5:

[0098] Server: Sends safety information to the user's device so that the user can check it.

[0099] Registering supply needs and matching supporters

[0100] Step 1:

[0101] Victims (users): Enter the supplies they need and their quantities in the supply registration form on the site (e.g., 10 liters of water, 3 blankets).

[0102] Step 2:

[0103] Server: Stores the input material needs information in a database.

[0104] Step 3:

[0105] Donor (user): Access the donation list page on the site and select the items they can donate.

[0106] Step 4:

[0107] Server: Confirms the supporter's selection and notifies the administrator.

[0108] Step 5:

[0109] Administrator (server): Checks the support details and sends instructions to the supporter for arrangements.

[0110] Step 6:

[0111] Supporter (user): Follow instructions, prepare supplies, and provide them to disaster victims.

[0112] The above is a specific processing flow for implementing the present invention. This system supports communication between disaster victims and supporters quickly and efficiently, and ensures the delivery of necessary information and supplies.

[0113] Example 1

[0114] 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."

[0115] When a disaster occurs, it is necessary to quickly and accurately grasp the damage situation, confirm the safety of victims, and provide supplies effectively. However, with conventional systems, the series of processes of information collection and analysis, question and answering, safety confirmation, and supply provision were fragmented, making efficient operation difficult. In addition, a lack of real-time information provision using generative AI models made it difficult to respond quickly.

[0116] 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.

[0117] In this invention, the server includes a means for collecting data from multiple information sources, a means for analyzing the collected data and classifying it by time, region, location, and presenter, a means for inputting user questions as prompts to a generative AI model and generating responses, a means for identifying the safety and location information of disaster victims using data from telecommunications carriers, and a means for matching supporters based on the material needs registered on the site. This enables the prompt and accurate provision of information in the event of a disaster and the smooth implementation of disaster victim support activities.

[0118] "Data collection tools" are tools for extracting and capturing data from multiple sources.

[0119] "Data analysis means" refers to means for analyzing collected data and classifying it based on specific criteria.

[0120] A "generative AI model" is a system that uses artificial intelligence technology to automatically generate responses based on input prompts.

[0121] A "prompt" is a question or instruction sentence that is input to a generative AI model.

[0122] "Telecommunications carrier data" refers to various data provided by companies that provide telecommunications services, such as communication history, wireless LAN connection information, and global positioning system data.

[0123] "Safety confirmation means" refers to a method of using telecommunications carrier data to determine the location of victims and whether they are safe.

[0124] The "material needs registration means" is a means for disaster victims to input and register the materials and quantities they need on the site.

[0125] The "supporter matching means" is a means for selecting and matching supporters based on the material needs registered on the site.

[0126] A "user question answering means" is a means for analyzing questions from users and generating and providing appropriate responses using a generative AI model.

[0127] "Natural language processing" is the technology that enables computers to understand, analyze, and generate human language.

[0128] This invention relates to a "disaster information and support system" for smoothly providing information and providing support activities when a disaster occurs. This system collects and analyzes data from multiple sources and provides information in response to user inquiries. It also utilizes data from telecommunications carriers to provide information on the safety and location of disaster victims, and has the function of matching relief supplies with supporters.

[0129] composition

[0130] 1. Server:

[0131] The server collects data in real time from multiple sources, such as social media, online news, and official government announcements, including social media APIs (e.g., Twitter API) and RSS feeds from news sites.

[0132] The collected data is analyzed through a natural language processing (NLP) engine (e.g., spaCy, NLTK) using programming languages ​​and libraries such as Python and TENSORFLOW®. After analysis, the data is categorized by time, region, location, and presenter and stored in an SQL database.

[0133] 2. Terminal:

[0134] Terminals are devices used by users to search for information, register supplies, and confirm assistance. These include computers, smartphones, and tablets.

[0135] 3. User:

[0136] Users include both those who provide information (disaster victims, general users) and those who receive information (family members, supporters). Users enter questions through a form on the website and receive answers generated by the server using a generative AI model (e.g., OpenAI (registered trademark) GPT-3 (registered trademark)).

[0137] System operation example

[0138] Data collection and analysis

[0139] The server uses the social networking service's API to collect posts containing the hashtag "disaster name." For example, the server sends a query to the Twitter API to retrieve related posts. The collected posts are analyzed using a natural language processing engine and classified into categories such as "October 15, 2023, Shibuya Ward, Tokyo, information from individual users."

[0140] Question and Answering

[0141] A user enters "What is the current situation in Shibuya Ward?" into a form on the website and sends the question to the server. The server analyzes the question and searches for relevant information from a database. The prompt "What is the current situation in Shibuya Ward?" is input into the generative AI model, and the generated answer "Traffic restrictions are in place in Shibuya Ward, and the evacuation shelter is XX Elementary School" is provided to the user.

[0142] Confirmation of safety

[0143] The user enters the name and contact information of a family member and requests a safety check on the site. For example, the user enters the name "Taro Tanaka" and clicks the confirmation button. The server retrieves communication history, WiFi connection information, and GPS data from the carrier's API, and responds to the user with information such as "Taro Tanaka was last contacted in front of Shibuya Station at 3:30 PM."

[0144] Registering supply needs and matching supporters

[0145] Victims (users) register the supplies they need and the quantities they require on the site. For example, they enter 10 liters of water and three blankets. The server stores this information in a database and makes it available for donors to view. Donors (users) select the supplies they can donate and express their willingness to donate. For example, a donor selects "provide three blankets to the Tanaka family." The server confirms the donor's selection, notifies the administrator, and instructs them on the appropriate procedures.

[0146] In this way, it will be possible to provide quick and accurate information and smoothly carry out relief activities when a disaster occurs.

[0147] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0148] Step 1:

[0149] Data collection and storage

[0150] Server: Collects data from multiple sources (social media, online news, official government announcements, etc.). Specifically, the server sends queries to social media APIs (e.g., Twitter API) to retrieve posts related to specific hashtags or keywords. Since the retrieved data is unorganized as is, all data is first stored in temporary storage.

[0151] Input: Specific hashtags or keywords

[0152] Output: Unorganized data (social media posts, news articles, etc.)

[0153] Step 2:

[0154] Data analysis and classification

[0155] Server: The data stored in temporary storage is analyzed using a natural language processing (NLP) engine. Python, TensorFlow, and NLP libraries (e.g., spaCy, NLTK) are used here. The analyzed data is categorized by time, region, location, and presenter. The categorized data is then stored in an SQL database.

[0156] Input: Unorganized data (social media posts, news articles, etc.)

[0157] Output: Categorised data (organised by time, region, location and presenter)

[0158] Specific operation: The NLP engine analyzes the collected social media posts and classifies them as "information from an individual user, Shibuya-ku, Tokyo, October 15, 2023."

[0159] Step 3:

[0160] Receiving questions from users

[0161] User: Enters a question into the input form on the site and clicks the submit button. For example, "What is the current situation in Shibuya Ward?" This question is sent to the server.

[0162] Input: User question (e.g. "What is the current situation in Shibuya Ward?")

[0163] Output: The question data sent to the server

[0164] Specific operation: The user types "What is the current situation in Shibuya Ward?" in the browser and clicks the submit button.

[0165] Step 4:

[0166] Question analysis and answer generation

[0167] Server: Analyzes the received question using a natural language processing engine, searches for relevant information in a database, and generates prompts using a generative AI model (e.g., OpenAI GPT-3) to generate appropriate answers.

[0168] Input: User question data

[0169] Output: Response data from the generative AI model

[0170] Specific operation: When the server sends the prompt message "What is the current situation in Shibuya Ward?" to the generation AI, the generation AI model generates a response saying "Traffic restrictions are in place in Shibuya Ward, and the evacuation shelter is XX Elementary School."

[0171] Step 5:

[0172] Response provision

[0173] Server: Sends data to the terminal to provide the generated response to the user.

[0174] Input: Response data from a generative AI model

[0175] Output: Response data sent to the user device

[0176] Specific operation: The server generates a response, "Traffic restrictions are in place in Shibuya Ward, and the evacuation shelter is XX Elementary School," and sends it to the user.

[0177] Step 6:

[0178] Acceptance of safety confirmation requests

[0179] User: Enter the name and contact information of a family member or close friend into a form on the site and click the confirm button. For example, enter "Taro Tanaka."

[0180] Input: User-entered data (name and contact information)

[0181] Output: Safety confirmation request data sent to the server

[0182] Specific operation: The user enters "Taro Tanaka" in the browser and clicks the confirmation button.

[0183] Step 7:

[0184] Data collection and safety information provision

[0185] Server: Obtains communication history, Wi-Fi connection information, and GPS data from the telecommunications carrier's API, and confirms the victim's last location and safety.

[0186] Input: Safety confirmation request data, data from telecommunications carrier API

[0187] Output: Safety information provided data

[0188] Specific operation: The server sends a query to the telecommunications company's API and returns the safety information it has obtained, "Taro Tanaka was last heard from in front of Shibuya Station at 15:30," to the user.

[0189] Step 8:

[0190] Registering supply needs

[0191] Victims (users): Enter the supplies they need and the quantity on the site, and click the registration button. For example, enter 10 liters of water and 3 blankets.

[0192] Input: Data on disaster victims' material needs

[0193] Output: Material needs data sent to the server

[0194] Specific actions: The victim enters "10 liters of water, 3 blankets" and clicks the registration button.

[0195] Step 9:

[0196] Store and display supply needs

[0197] Server: Stores registered material needs in a database and makes them available for donors to view.

[0198] Input: Material needs data

[0199] Output: Material needs information stored in a database

[0200] Specific operation: The server stores the material needs data in an SQL database and displays it on a web page.

[0201] Step 10:

[0202] Supporter matching

[0203] Donor (user): Selects available items on the site and expresses their intention to donate. For example, they can view the list of victims and select "Donate three blankets to the Tanaka family."

[0204] Input: Data provided by supporter

[0205] Output: Assistance provision data sent to the server

[0206] Specific action: The supporter selects "Provide three blankets to the Tanaka family" and clicks the "Provide" button.

[0207] Step 11:

[0208] Support arrangements

[0209] Server: Confirms the supporter's selection, notifies the administrator, and instructs the appropriate arrangement procedure.

[0210] Input: Assistance provision data

[0211] Output: Notification data to administrator and assistance arrangement information

[0212] Specific operation: The server checks the support provision data, automatically generates and sends a notification email to the administrator, who then arranges for the delivery of the support supplies.

[0213] (Application example 1)

[0214] 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."

[0215] When a disaster occurs, it is extremely important for logistics facility workers to quickly and accurately collect information and confirm the safety of their employees. However, with current systems, it takes time and effort to collect and analyze information, making it difficult for workers and managers to quickly grasp the actual situation at the disaster site. In addition, there is a lack of systems that can efficiently register the needs for supplies needed in the event of a disaster and efficiently match them with supporters. For these reasons, there is a need for a system that can consistently collect information, confirm the safety of employees, and match them with supporters at logistics facilities during a disaster.

[0216] 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.

[0217] In this invention, the server includes a means for collecting data from multiple information sources, a means for analyzing the collected data and classifying it by time, region, location, and presenter, and a means for providing related information from the classified data based on questions from users. This enables information collection, safety confirmation, supply needs registration, and supporter matching at logistics facilities in the event of a disaster.

[0218] "Source" refers to the source from which data is collected, including social media, online news, and official government announcements.

[0219] "Data analysis" refers to the process of classifying collected data by time, region, location, and presenter, and extracting relevant information.

[0220] "User question" refers to information or questions that a user inputs into the system.

[0221] "Telecommunications company data" refers to data provided by telecommunications companies, including communication history, Wi-Fi connection information, GPS data, and location and safety information.

[0222] "Material needs" refers to information about the supplies and quantities needed by disaster victims.

[0223] "Donor matching" refers to the process of connecting donors with disaster victims based on their material needs.

[0224] A "logistics facility" refers to a location or building used to manage the distribution of goods and materials.

[0225] "Server" refers to the primary computer system that responds to user queries, analyzes data, and provides information.

[0226] "Natural language processing" refers to technologies that automate the analysis and classification of text data, and includes generative AI models.

[0227] "Safety confirmation" refers to the process of confirming the safety status and current location of disaster victims.

[0228] A "generative AI model" refers to a type of artificial intelligence that performs natural language processing based on large amounts of data and generates appropriate responses to questions.

[0229] This invention is a system for efficiently collecting information, confirming the safety of people, registering supply needs, and matching supporters at logistics facilities during disasters. This system functions in cooperation with data from a server, user terminals, and telecommunications companies.

[0230] server

[0231] The server collects and stores data in real time from multiple sources (e.g., social media, online news, official government announcements, etc.). It analyzes the data using a natural language processing (NLP) engine (e.g., Spacy, BERT) and categorizes it by time, region, location, and presenter. The results of this analysis are stored in a database and can be searched and provided as needed. The server also uses a generative AI model (e.g., GPT-3) to generate appropriate answers to user questions and provide information in real time.

[0232] Terminal

[0233] At the logistics facility, workers access the system using their smartphones. A dedicated application is installed on the terminals, allowing them to access information and functions necessary in the event of a disaster. Through the terminals, users can input questions and receive responses from the server. They can also register needed supplies and check the contents of supplies provided by supporters.

[0234] User

[0235] Users of this system include workers and managers at logistics facilities. They use the system to collect information, confirm the safety of people, register needs for supplies, and match supporters during disasters. As a specific example of operation, a user can ask the system, "What is the current situation in XX area?" and receive a response from the server such as, "Traffic restrictions in place. Evacuation shelters are located at XX location."

[0236] Hardware and software used

[0237] Hardware: Smartphone (iOS, ANDROID (registered trademark))

[0238] Software: Flask, Django (backend), MySQL (registered trademark) (database), Python (request processing), natural language processing engine (Spacy, BERT), generative AI model (GPT-3)

[0239] Data processing and calculation

[0240] The server continuously retrieves data from social media, online news, and telecommunications company APIs, analyzes the data using a natural language processing engine, and extracts and classifies relevant information. Information stored in a cloud database is analyzed and responded to using a generative AI model to respond to user questions in real time. It also integrates and processes communication history, Wi-Fi connection information, and GPS data to check the safety of logistics facility employees.

[0241] Specific examples (prompt sentence examples)

[0242] When a user asks, "What is the current situation in district X?", the question is sent to the server, which then uses a generative AI model to create an answer based on the latest news and social media posts, such as "Traffic restrictions are in place in district X, and evacuation shelters are located at X location."

[0243] The present invention enables logistics facilities to quickly and efficiently collect and provide information in the event of a disaster, confirm the safety of people, register material needs, and match supporters.

[0244] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0245] Step 1:

[0246] Information Collection and Storage

[0247] Input: Social media, online news, official government announcements, and other sources

[0248] Output: Raw data collected

[0249] The server collects data in real time from social media APIs, news site RSS feeds, and official government announcement sites, and stores the collected raw data in a database.

[0250] Step 2:

[0251] Data analysis and classification

[0252] Input: Raw data collected

[0253] Output: Parsed and classified data

[0254] The server analyzes the collected raw data using a natural language processing (NLP) engine (e.g., Spacy, BERT) and categorizes it by time, region, location, and presenter. The analyzed data is stored in a database and made searchable.

[0255] Step 3:

[0256] Accepting user questions

[0257] Input: User question

[0258] Output: Question

[0259] The terminal provides an interface for users to input questions. The user uses a smartphone to input a question such as "What is the current situation in the X area?" This question is then sent to the server.

[0260] Step 4:

[0261] Question analysis and response generation

[0262] Input: User question

[0263] Output: The generated response

[0264] The server analyzes the question received from the user, searches for relevant information from the database, and uses a generative AI model (e.g., GPT-3) to generate an appropriate response based on the relevant information.

[0265] Step 5:

[0266] Providing a response

[0267] Input: Generated response

[0268] Output: Display the answer to the user

[0269] The server generates a response and sends it to the device, which then displays it on the user's smartphone. For example, if a user asks, "What is the current situation in district X?", the device displays, "Traffic restrictions are in place in district X, and the evacuation shelter is at location X."

[0270] Step 6:

[0271] Confirmation of safety

[0272] Input: User safety confirmation request, name, contact information

[0273] Output: Safety information

[0274] The server obtains information on the last location and safety of disaster victims based on communication history, Wi-Fi connection information, and GPS data provided by the telecommunications company, allowing users to check the safety of their family and colleagues.

[0275] Step 7:

[0276] Registering supply needs

[0277] Input: Information on supply needs from disaster victims (users)

[0278] Output: List of material needs

[0279] The terminal provides an interface where disaster victims can input the supplies and quantities they need, and sends the registered information to a server, which stores the information in a database and makes it available to supporters.

[0280] Step 8:

[0281] Donors' declaration of intent to donate supplies

[0282] Input: Information on supplies provided by supporters (users)

[0283] Output: Notification of matched relief supplies and relief arrangements

[0284] Donors use their terminals to select registered material needs and express their willingness to donate. The server verifies this information and notifies the administrator. The administrator then instructs the donors on how and when to deliver the supplies.

[0285] The above is the processing flow of the "Disaster Information and Support System" at logistics facilities.

[0286] 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.

[0287] This invention is a "disaster information and support system" for smoothly providing information and providing support activities when a disaster occurs. This system collects and organizes information from social media and online news, and provides information in response to user questions. It also utilizes data from telecommunications companies to check the safety of disaster victims, provide location information, and match material needs with supporters. Furthermore, this invention incorporates an emotion engine that recognizes the user's emotions, and can adjust the information provided based on the user's emotions.

[0288] System configuration

[0289] 1. Server:

[0290] The server collects and stores data in real time from multiple sources (e.g., social media, online news, official government announcements, etc.). It then analyzes the data using a natural language processing (NLP) engine and categorizes it by time, region, location, and issuer. The results of this analysis are stored in a database and can be searched and provided as needed. It also uses data from telecommunications companies to confirm the safety of victims and identify their locations.

[0291] 2. Terminal:

[0292] The device is used by users to access the site, search for information, register supplies, and confirm support. Examples of such devices include PCs, smartphones, and tablets.

[0293] 3. User:

[0294] Users include those who provide information (e.g., disaster victims, general users) and those who acquire information (e.g., family members, supporters). Users use the site to check safety and register / confirm supplies.

[0295] 4. Emotion Engine:

[0296] The emotion engine analyzes emotions from text and voice input by the user and adjusts the information provided based on those emotions. For example, if the user is feeling anxious, it will provide more reassuring information.

[0297] Program processing

[0298] 1. Data Collection and Analysis:

[0299] Server: Collects data from specified sources and analyzes it using a natural language processing engine. For example, it collects posts related to specific hashtags or keywords through social media APIs and categorizes these posts by date, time, location, and author.

[0300] Example: The server collects and analyzes social media posts containing the hashtag "disaster name." Through this analysis, the posts are classified as "October 15, 2023, Shibuya Ward, Tokyo, information from individual users."

[0301] 2. Question and Answer:

[0302] User: Enters a question on the site (e.g., "What is the current situation in Shibuya Ward?"). This question is sent to the server.

[0303] Server: Analyzes the question and searches the database for relevant information. Based on the analysis results, the generation AI generates an appropriate answer and provides it to the user. It also uses an emotion engine to recognize the user's emotions and adjust the information provided as needed.

[0304] Example: When a user asks, "What is the current situation in Shibuya Ward?", the server will respond based on the latest news and social media posts with, for example, "Traffic restrictions are in place in Shibuya Ward, and the evacuation shelter is at X Elementary School." If the user asks the question with an anxious expression or tone, the server will adjust the response to something more reassuring, such as, "Many evacuation shelters have now been opened in Shibuya Ward, and there are many places where you can safely evacuate."

[0305] 3. Safety confirmation:

[0306] Server: Obtains communication history, Wi-Fi connection information, and GPS data from the telecommunications company's API, and checks the last location and safety of victims.

[0307] Users: Enter names and contact information on the site to check on the safety of family and loved ones.

[0308] Server: Searches the database based on the input information and provides the relevant safety information to the user. It also adjusts the way the information is provided using an emotion engine.

[0309] Example: When a user checks the safety of "Taro Tanaka," the server responds with information like, "Taro Tanaka was last heard from in front of Shibuya Station at 3:30 PM." If the user seems very worried, the server might add, "Taro Tanaka has been heard from recently and may be in a relatively safe location."

[0310] 4. Registering material needs and matching donors:

[0311] Victims (users): Enter the required supplies and their quantities in the supply registration form on the site and register (e.g., 10 liters of water, 3 blankets).

[0312] Server: Stores the inputted material needs in a database and makes them available for donors to view.

[0313] Donor (user): Access the donation list page on the site and select the items they can donate.

[0314] Server: Confirms the supporter's selection, notifies the administrator, and instructs the appropriate arrangement procedure. It also uses an emotion engine to provide appropriate communication tools.

[0315] Example: A donor views the "List of victims in the Tohoku region" and selects "Provide three blankets to the Tanaka family." After confirmation, the administrator instructs the donor on how and when to deliver the relief supplies. If this is the first time the donor is providing relief, the emotion engine is used to simultaneously provide a message such as, "Thank you for your first donation. We will explain the procedure so that you can feel at ease."

[0316] In this way, the system of the present invention can provide information quickly and appropriately when a disaster occurs, and efficiently support communication between victims and supporters. By incorporating an emotion engine, it becomes possible to provide information and responses according to the user's emotions, realizing support that gives a greater sense of security.

[0317] The processing flow will be explained below.

[0318] Data collection and analysis

[0319] Step 1:

[0320] Server: Periodically sends requests to APIs of social media, online news, and government announcement sites to collect data.

[0321] Step 2:

[0322] Server: Adds collected data to a queue for analysis and passes it to the natural language processing engine.

[0323] Step 3:

[0324] Server: A natural language processing engine analyzes the data and categorizes it by date, time, location, and presenter.

[0325] Step 4:

[0326] Server: The analysis results are stored in a database and indexed for later retrieval.

[0327] Question and Answering

[0328] Step 1:

[0329] User: Enters a question into the site's search box (e.g., "What's the current situation in Shibuya Ward?").

[0330] Step 2:

[0331] Server: Receives questions from users and analyzes the content of the questions using natural language processing.

[0332] Step 3:

[0333] Server: Searches for relevant information from the database and generates appropriate answers using generative AI.

[0334] Step 4:

[0335] Server: Uses an emotion engine to analyze emotions from the user's input and tone.

[0336] Step 5:

[0337] Server: Adjusts the generated answer based on the user's emotions. For example, if the user is feeling anxious, adds reassuring information.

[0338] Step 6:

[0339] Server: Returns the adjusted answer to the user's terminal and displays it to the user.

[0340] Confirmation of safety

[0341] Step 1:

[0342] Server: Periodically obtains communication history, Wi-Fi connection information, and GPS data from the telecommunications company's API.

[0343] Step 2:

[0344] Server: Analyzes the acquired data and stores the victim's last location and safety information in a database.

[0345] Step 3:

[0346] User: Enters name and contact information into the safety confirmation form on the site.

[0347] Step 4:

[0348] Server: Searches the database based on the entered information and identifies the relevant safety information.

[0349] Step 5:

[0350] Server: Sends safety information to the user's device so that the user can check it.

[0351] Step 6:

[0352] Server: Uses the emotion engine to tailor how safety information is provided. If the user is very worried, provide additional reassuring information.

[0353] Registering supply needs and matching supporters

[0354] Step 1:

[0355] Victims (users): Enter the supplies they need and their quantities in the supply registration form on the site (e.g., 10 liters of water, 3 blankets).

[0356] Step 2:

[0357] Server: Stores the input material needs information in a database.

[0358] Step 3:

[0359] Donor (user): Access the donation list page on the site and select the items they can donate.

[0360] Step 4:

[0361] Server: Confirms the supporter's selection and notifies the administrator.

[0362] Step 5:

[0363] Administrator (server): Checks the support details and sends instructions to the supporter for arrangements.

[0364] Step 6:

[0365] Server: Uses the emotion engine to provide appropriate communication to supporters. For example, for supporters providing support for the first time, a message containing instructions on how to provide support will be sent to put them at ease.

[0366] Step 7:

[0367] Supporter (user): Follow instructions, prepare supplies, and provide them to disaster victims.

[0368] In this way, the system of the present invention can provide information quickly and appropriately when a disaster occurs, and efficiently support communication between victims and supporters. By incorporating an emotion engine, it becomes possible to provide information and responses according to the user's emotions, realizing support that gives a greater sense of security.

[0369] Example 2

[0370] 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."

[0371] In the event of a disaster, it is necessary to provide victims, their families, and supporters with fast and accurate information. However, because information is scattered and vast, it is difficult to quickly obtain the necessary information. It is also difficult to smoothly confirm the safety of victims and carry out procedures for providing material support. Furthermore, there is a lack of emotionally sensitive information provided to users who feel excessive stress and anxiety during a disaster. Effective means to solve these problems are desired.

[0372] 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.

[0373] In this invention, the server includes means for collecting data from multiple information sources, means for analyzing the collected data using natural language processing and classifying it by time, region, location, and presenter, means for providing relevant information from the classified data based on questions from users and adjusting the content of the information using an emotion engine, means for identifying the safety and location information of disaster victims using data from communication service providers, and means for matching supporters based on material needs registered on the site and providing appropriate communication to the supporters using the emotion engine.This enables the provision of quick and accurate information, safety confirmation, smooth procedures for material support, and the provision of information that takes emotions into consideration in the event of a disaster.

[0374] "Sources" refer to external data providers from which data is collected, such as social media, online news, and official government announcements.

[0375] "Natural language processing" is a technology that enables computers to understand, analyze, and generate human language.

[0376] An "emotion engine" is a software engine that analyzes emotions from text and voice input by the user and adjusts the information and responses provided based on those emotions.

[0377] "Telecommunications service provider" refers to a company or organization that provides telecommunications services through a telecommunications network.

[0378] "Safety confirmation" refers to the act of collecting and providing information to confirm the safety and current location of disaster victims.

[0379] "Material needs" refers to the types and quantities of supplies and items needed by disaster victims.

[0380] "Supporters" refers to people and organizations whose role is to provide supplies and services to disaster victims during a disaster.

[0381] "Matching" refers to the process of connecting the needs of disaster victims with the resources available to supporters.

[0382] "Data classification" refers to the process of organizing and dividing collected data by different criteria such as time, region, location, and presenter.

[0383] A "database" refers to a system that organizes and stores collected and analyzed data so that it can be searched and retrieved as needed.

[0384] "Global Positioning System Data" refers to data used to measure specific locations on Earth using satellites.

[0385] "Wireless communication network connection information" refers to information about the WiFi network or cell tower to which a mobile device is connected.

[0386] This invention is a "disaster information and support system" for smoothly providing information and carrying out support activities when a disaster occurs. This system collects data from multiple sources, such as social media and online news, and analyzes and classifies it to provide users with appropriate information.

[0387] 1. Data Collection

[0388] Server: The server collects data from sources such as social media, online news, and official government announcements. It collects posts containing specific hashtags or keywords through the APIs of the social media platforms used.

[0389] Example: A server collects all Twitter posts containing the hashtag "Disaster Breaking News" and stores this data.

[0390] 2. Data analysis and classification

[0391] Server: The server analyzes the collected data using natural language processing (NLP) techniques and categorizes the data by time, region, location, and presenter.

[0392] Software used: General NLP engine

[0393] Example: The server analyzes collected Twitter posts and classifies them as "information from an individual user, Shibuya-ku, Tokyo, October 15, 2023."

[0394] 3. Question and Answering

[0395] User: A user types a question into a search box on the site (e.g., "What's the current situation in Shibuya Ward?").

[0396] Server: The server receives the question, searches for relevant information from a database, and responds. Generative AI generates appropriate answers, and an emotion engine is used to tailor the information according to the user's emotions.

[0397] Example: When a user asks, "What is the current situation in Shibuya Ward?", the server responds, "Traffic restrictions are currently in place in Shibuya Ward. An evacuation shelter has been opened at X Elementary School." Furthermore, if the emotion engine detects that the user is anxious, it adds reassuring information, such as, "There are many safe places to evacuate to in Shibuya Ward."

[0398] 4. Safety confirmation

[0399] User: Users enter the names and contact information of family members and acquaintances on the site to check on their safety.

[0400] Server: The server uses the communication service provider's API to obtain communication history and GPS data, and checks the last location and safety information of the victims. It uses an emotion engine to adjust how the information is provided.

[0401] Example: When a user checks the safety of "Taro Tanaka," the server responds with information such as, "Taro Tanaka was last contacted in front of Shibuya Station at 3:30 PM." If the user feels uneasy, the server provides additional reassuring information such as, "Taro Tanaka has been in contact recently and is likely in a safe location."

[0402] 5. Registering supply needs and matching supporters

[0403] Victims (users): Victims enter the supplies they need and their quantities in the site's supply registration form (e.g., "10 liters of water, 3 blankets").

[0404] Server: The entered information is saved in a database and made available for supporters to view.

[0405] Donors (users): Donors access the donation list page on the site and select the items they can donate.

[0406] Server: Confirms the supporter's selection, notifies the administrator, and instructs appropriate arrangements. Uses the emotion engine to provide supporters with appropriate communication tools.

[0407] Example: A donor views the "List of victims in the Tohoku region" and selects "Provide three blankets to the Tanaka family." The server notifies the administrator and instructs them to arrange for delivery. Also, for first-time donors, a message is displayed saying, "Thank you for your first donation. We will explain the donation procedure so you can feel at ease."

[0408] By combining these functions, the system of the present invention can provide prompt and appropriate information in the event of a disaster, confirm the safety of people, facilitate smooth procedures for providing material support, and provide information that takes emotions into consideration.

[0409] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0410] Step 1: Data collection

[0411] Server: The server collects data from multiple sources, such as social media, online news, and official government announcements. Specifically, it uses social media APIs to retrieve posts containing specific hashtags or keywords.

[0412] Input: A specific hashtag or keyword (e.g., "disaster breaking news")

[0413] Output: Collected post data (e.g. Twitter posts)

[0414] Specific operation: The server collects all Twitter posts containing the hashtag "Disaster Breaking News" and stores this data.

[0415] Step 2: Data analysis and classification

[0416] Server: The server analyzes the collected data using a natural language processing engine (e.g., a general NLP engine) and categorizes the data by time, region, location, and presenter. The analyzed data is stored in a database.

[0417] Input: Collected post data (e.g., Twitter posts)

[0418] Output: Classified data (e.g., "Information from an individual user, Shibuya Ward, Tokyo, October 15, 2023")

[0419] Specific operation: The server analyzes the collected Twitter posts and classifies them as "information from an individual user in Shibuya Ward, Tokyo, on October 15, 2023." This classification result is stored in a database.

[0420] Step 3: Question and Answer

[0421] User: A user types a question into a search box on the site (e.g., "What's the current situation in Shibuya Ward?").

[0422] Server: The server receives the question, searches for relevant information from a database, uses a generative AI model to generate an appropriate answer, and uses an emotion engine to tailor the information according to the user's emotions.

[0423] Input: User question (e.g. "What is the current situation in Shibuya Ward?")

[0424] Output: Generated answer (e.g. "Traffic restrictions are in place in Shibuya Ward. An evacuation shelter has been opened at XX Elementary School.")

[0425] Specific operation: The server analyzes the user's question and searches the database for relevant information. The generation AI generates a response such as, "Traffic restrictions are in place in Shibuya Ward. An evacuation shelter has been opened at X-X Elementary School." Furthermore, if the emotion engine detects the user's feelings of anxiety, it adds, "There are many safe places to evacuate to in Shibuya Ward."

[0426] Step 4: Safety confirmation

[0427] User: Users enter the names and contact information of family members and acquaintances on the site to check on their safety.

[0428] Server: The server uses the communication service provider's API to obtain communication history and GPS data, and checks the last location and safety information of the victims. It uses an emotion engine to adjust how the information is provided.

[0429] Input: Names and contact information of family members or acquaintances (e.g., "Taro Tanaka")

[0430] Output: Safety information (e.g. "Taro Tanaka was last heard from in front of Shibuya Station at 15:30")

[0431] Specific operation: Based on the name and contact information of "Taro Tanaka" entered by the user, the server uses the communication service provider's API to obtain communication history and GPS data. This provides information such as "Taro Tanaka was last contacted in front of Shibuya Station at 3:30 PM." For users who feel uneasy, the server provides additional information to reassure them, such as "Taro Tanaka has been in communication recently and is likely in a safe location."

[0432] Step 5: Register your supply needs

[0433] Victims (users): Victims enter the supplies they need and their quantities in the site's supply registration form (e.g., "10 liters of water, 3 blankets").

[0434] Server: The entered information is saved in a database and made available for supporters to view.

[0435] Input: The supplies you need and their quantities (e.g., "10 liters of water, 3 blankets")

[0436] Output: Registered supply information (e.g., "10 liters of water, 3 blankets")

[0437] Specific operation: When a victim registers "10 liters of water, 3 blankets" on the site, the server saves this in the database and allows supporters to proceed and view it.

[0438] Step 6: Supporter Matching

[0439] Donors (users): Donors access the donation list page on the site and select the items they can donate.

[0440] Server: Confirms the supporter's selection, notifies the administrator, and instructs appropriate arrangements. Uses the emotion engine to provide supporters with appropriate communication tools.

[0441] Input: The items that donors can provide (e.g., "3 blankets")

[0442] Output: Instructions for providing assistance (e.g., "Provide three blankets to the Tanaka family")

[0443] Specific operation: A donor views the "List of victims in the Tohoku region" and selects "Provide three blankets to the Tanaka family." The server notifies the administrator and instructs them to arrange for delivery. For first-time donors, the server also displays a message saying, "Thank you for your first donation. We will explain the donation procedure so you can feel at ease."

[0444] (Application example 2)

[0445] 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."

[0446] When a disaster occurs, there is a need for a system that can provide information quickly and appropriately and facilitate smooth communication between victims and supporters. Current systems have issues with obtaining information in real time and providing information that reflects emotions, as well as issues with smoothly confirming the safety of victims and matching supplies. There is a need for a system that can solve these issues and support more effective support activities.

[0447] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data from multiple information sources, means for analyzing the collected data and classifying it by time, region, location, and presenter, means for providing related information from the classified data based on questions from users, means for identifying the safety and location information of disaster victims using data from telecommunications companies, means for matching supporters based on material needs registered on the site, and means for analyzing user emotions and providing information according to the results. This makes it possible to provide information and support activities quickly and appropriately when a disaster occurs.

[0448] "Sources" are the origins of information provided by various digital media and platforms (e.g., social networking services, online news, official government announcements, etc.).

[0449] "Data collection methods" are the mechanisms and techniques used to obtain necessary data from various sources and incorporate it into the system.

[0450] "Data analysis tools" are techniques and methods for analyzing collected data and categorizing it based on specific criteria (e.g., time, region, location, presenter, etc.).

[0451] The "user question answering means" is a system or function for accepting questions from users and searching for and providing related information based on those questions.

[0452] "Safety confirmation means" refers to technology or methods for confirming the safety and location of disaster victims using data from telecommunications companies (e.g., communication history, wireless connection information, global positioning system data).

[0453] "Supply matching tools" are systems and functions that connect the supply needs registered on the site with supporters, enabling efficient distribution of supplies.

[0454] "Emotion analysis means" refers to a technique or method for analyzing emotions from user input (e.g., text or voice) and adjusting the information provided based on the results.

[0455] "Natural language processing" is a technical field that uses computers to understand, interpret, and manipulate human language, and is particularly used for analyzing text data.

[0456] "Global Positioning System data" is data used to obtain highly accurate positional information of any point on Earth using satellites.

[0457] Specific embodiments for carrying out the present invention will be described below.

[0458] This system consists of three components: a server, terminals, and users. The server plays a central role in collecting data from various information sources and analyzing and classifying it. The terminals are devices that users use to obtain information, check the safety of others, register supplies, and confirm support, and users are the entities that actually use these functions.

[0459] First, the server collects data from multiple sources, such as social networking services (SNS), online news, and official government announcements. The server obtains data from these sources in real time, analyzes it using a natural language processing (NLP) engine (described below), and classifies it by time, region, location, and issuer.

[0460] The NLP engine uses the open source TextBlob and generative AI models using deep learning (such as GPT). Through this analysis, for example, a social media post containing the hashtag "disaster name" is classified as "information from an individual user, Tokyo, October 15, 2023."

[0461] When a user inputs a question through their device, the question is sent to the server. For example, if the user inputs the question, "What is the current situation in Shibuya Ward?", the server searches for relevant information from the database, and the generative AI generates the optimal answer based on the analysis results and provides it to the user. An example of a prompt sentence is, "What is the current situation in Shibuya Ward?" Furthermore, an emotion engine is used to analyze the user's emotions and adjust the way information is presented as necessary. If the user asks a question with an anxious expression or tone, the content is changed to one that gives a sense of security.

[0462] For safety checks, the server obtains communication history, wireless connection information, and Global Positioning System (GPS) data from the telecommunications company's API. For example, when a user enters the name and contact information of "Taro Tanaka" to check the user's safety, the server searches the database and returns information such as "Taro Tanaka was last contacted in front of Shibuya Station at 3:30 PM." If the user appears very worried, the emotion engine provides additional information such as "He may be in a relatively safe location."

[0463] To match supplies, disaster victims register the supplies they need and the quantities they require on the site. For example, they might enter "10 liters of water, 3 blankets." The server stores this information in a database and makes it available for donors to view. When a donor selects supplies available on the site, the server notifies the administrator and instructs them on the appropriate procedures for arranging supplies. Using an emotion engine, the system also provides reassuring messages when donors are donating for the first time.

[0464] In this way, the server and terminals work together to provide prompt and appropriate information and support activities in the event of a disaster. Examples of prompt sentences introduced include user questions such as "What is the current situation in Shibuya Ward?" and "I want to check on the safety of my daughter."

[0465] The above is a specific embodiment for carrying out the present invention, and this system will improve the efficiency of information provision and support activities in the event of a disaster.

[0466] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0467] Step 1:

[0468] The server collects data from multiple sources, specifically social networking services (SNS), online news, official government announcements, etc., and obtains data in real time through APIs. Data from these sources is used as input, and the raw data is stored on the server as output.

[0469] Step 2:

[0470] The server analyzes the collected data and categorizes it by time, region, location, and presenter. Specifically, it processes the data with a natural language processing engine using TextBlob and generative AI models (e.g., GPT). It uses the collected raw data as input and provides data categorized by time, region, location, and presenter as output.

[0471] Step 3:

[0472] The user inputs a question through a terminal. For example, they input "What is the current situation in Shibuya Ward?" on the application screen of a smartphone or PC. The user's question text is used as input, and the question content is sent to the server as output.

[0473] Step 4:

[0474] The server searches for relevant information from the database based on the user's question, and the generative AI generates an appropriate answer based on the analysis results. The user's question and classified data are used as input, and the generated answer text is obtained as output.

[0475] Step 5:

[0476] The server uses an emotion engine to analyze the user's emotions and adjust the information provided. Specifically, it analyzes the user's input text using TextBlob or other emotion analysis tools. The input is the user's question text, and the output is the user's emotion score. For example, if the user asks a question with an anxious expression or tone, the server adjusts the answer to make it more reassuring.

[0477] Step 6:

[0478] The server obtains communication history, wireless connection information, and Global Positioning System (GPS) data from the telecommunications company's API and checks the safety of disaster victims. Location information data from the telecommunications company is used as input, and information on the safety of disaster victims is obtained as output. This provides information such as, "Taro Tanaka was last heard from in front of Shibuya Station at 3:30 PM."

[0479] Step 7:

[0480] Users register information about required supplies through their terminals. For example, they input specific needs such as "10 liters of water, 3 blankets." The input is the information about the needs of disaster victims, and the output is stored on the server.

[0481] Step 8:

[0482] The server matches supporters based on the material needs registered on the site. Specifically, it compares the information on the materials that can be provided selected by the supporter with the information on the needs of the disaster victims to make the optimal match. The input is the information on the material needs of the disaster victims and the information on the materials that can be provided by the supporter, and the matching results are obtained as the output.

[0483] The above is the specific processing flow of this system's program. At each step, the necessary data is input, specific data processing and data calculations are performed, and ultimately useful information and support is provided to the user.

[0484] 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.

[0485] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0486] 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.

[0487] [Second embodiment]

[0488] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0489] 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.

[0490] 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).

[0491] 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.

[0492] 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.

[0493] 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).

[0494] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0495] 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.

[0496] 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.

[0497] 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.

[0498] 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.

[0499] 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."

[0500] This invention is a "disaster information and support system" for smoothly providing information and carrying out support activities when a disaster occurs. This system collects and organizes information from social media and online news, and provides information in response to user questions. It also utilizes data from telecommunications companies to check the safety and location of disaster victims, and has the function of matching supply needs with supporters.

[0501] System configuration

[0502] 1. Server:

[0503] The server collects and stores data in real time from multiple sources (e.g., social media, online news, official government announcements, etc.). It then analyzes the data using a natural language processing (NLP) engine and categorizes it by time, region, location, and presenter. The results of this analysis are stored in a database and can be searched and provided as needed.

[0504] 2. Terminal:

[0505] The device is used by users to access the site, search for information, register supplies, and confirm support. Examples of such devices include PCs, smartphones, and tablets.

[0506] 3. User:

[0507] Users include those who provide information (e.g., disaster victims, general users) and those who acquire information (e.g., family members, supporters). Users use the site to check safety and register / confirm supplies.

[0508] Program processing

[0509] 1. Data Collection and Analysis:

[0510] Server: Collects data from specified sources and analyzes it using a natural language processing engine. For example, it collects posts related to specific hashtags or keywords through social media APIs and categorizes these posts by date, time, location, and author.

[0511] Example: The server collects and analyzes social media posts containing the hashtag "disaster name." Through this analysis, the posts are classified as "October 15, 2023, Shibuya Ward, Tokyo, information from individual users."

[0512] 2. Question and Answer:

[0513] User: Enters a question on the site (e.g., "What is the current situation in Shibuya Ward?"). This question is sent to the server.

[0514] Server: Analyzes the question and searches the database for relevant information. Based on the analysis results, the generation AI generates an appropriate answer and provides it to the user.

[0515] Example: When a user asks, "What is the current situation in Shibuya Ward?", the server will respond based on the latest news and social media posts with something like, "Traffic restrictions are in place in Shibuya Ward, and the evacuation shelter is at XX Elementary School."

[0516] 3. Safety confirmation:

[0517] Server: Obtains communication history, Wi-Fi connection information, and GPS data from the telecommunications company's API, and checks the last location and safety of victims.

[0518] Users: Enter names and contact information on the site to check on the safety of family and loved ones.

[0519] Server: Based on the input information, searches for communication data and provides the user with the relevant safety information.

[0520] Example: When a user checks the safety of "Taro Tanaka," the server responds with information such as "Taro Tanaka was last contacted in front of Shibuya Station at 15:30."

[0521] 4. Registering material needs and matching donors:

[0522] Victims (users): Enter and register the supplies they need and their quantities on the site (for example, 10 liters of water, 3 blankets).

[0523] Server: Stores registered material needs in a database and makes them available for donors to view.

[0524] Donors (users): Select the supplies they can donate on the site and express their intention to donate.

[0525] Server: Confirms the supporter's selection, notifies the administrator, and instructs the appropriate arrangement procedure.

[0526] Example: A donor views the "List of victims in the Tohoku region" and selects "Provide three blankets to the Tanaka family." After confirmation, the administrator instructs the donor on how and when to deliver the relief supplies.

[0527] In this way, the system of the present invention can provide information quickly and appropriately when a disaster occurs, and efficiently support communication between victims and supporters.

[0528] The processing flow will be explained below.

[0529] Data collection and analysis

[0530] Step 1:

[0531] Server: Periodically sends requests to APIs of social media, online news, and government announcement sites to collect data.

[0532] Step 2:

[0533] Server: Adds collected data to a queue for analysis and passes it to the natural language processing engine.

[0534] Step 3:

[0535] Server: A natural language processing engine analyzes the data and categorizes it by date, time, location, and presenter.

[0536] Step 4:

[0537] Server: The analysis results are stored in a database and indexed for later retrieval.

[0538] Question and Answering

[0539] Step 1:

[0540] User: Enters a question into the site's search box (e.g., "What's the current situation in Shibuya Ward?").

[0541] Step 2:

[0542] Server: Receives questions from users and analyzes the content of the questions using natural language processing.

[0543] Step 3:

[0544] Server: Searches for relevant information from the database and generates appropriate answers using generative AI.

[0545] Step 4:

[0546] Server: Returns the answer to the user's terminal and displays it to the user.

[0547] Confirmation of safety

[0548] Step 1:

[0549] Server: Periodically obtains communication history, Wi-Fi connection information, and GPS data from the telecommunications company's API.

[0550] Step 2:

[0551] Server: Analyzes the acquired data and stores the victim's last location and safety information in a database.

[0552] Step 3:

[0553] User: Enters name and contact information into the safety confirmation form on the site.

[0554] Step 4:

[0555] Server: Searches the database based on the entered information and identifies the relevant safety information.

[0556] Step 5:

[0557] Server: Sends safety information to the user's device so that the user can check it.

[0558] Registering supply needs and matching supporters

[0559] Step 1:

[0560] Victims (users): Enter the supplies they need and their quantities in the supply registration form on the site (e.g., 10 liters of water, 3 blankets).

[0561] Step 2:

[0562] Server: Stores the input material needs information in a database.

[0563] Step 3:

[0564] Donor (user): Access the donation list page on the site and select the items they can donate.

[0565] Step 4:

[0566] Server: Confirms the supporter's selection and notifies the administrator.

[0567] Step 5:

[0568] Administrator (server): Checks the support details and sends instructions to the supporter for arrangements.

[0569] Step 6:

[0570] Supporter (user): Follow instructions, prepare supplies, and provide them to disaster victims.

[0571] The above is a specific processing flow for implementing the present invention. This system supports communication between disaster victims and supporters quickly and efficiently, and ensures the delivery of necessary information and supplies.

[0572] Example 1

[0573] 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."

[0574] When a disaster occurs, it is necessary to quickly and accurately grasp the damage situation, confirm the safety of victims, and provide supplies effectively. However, with conventional systems, the series of processes of information collection and analysis, question and answering, safety confirmation, and supply provision were fragmented, making efficient operation difficult. In addition, a lack of real-time information provision using generative AI models made it difficult to respond quickly.

[0575] 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.

[0576] In this invention, the server includes a means for collecting data from multiple information sources, a means for analyzing the collected data and classifying it by time, region, location, and presenter, a means for inputting user questions as prompts to a generative AI model and generating responses, a means for identifying the safety and location information of disaster victims using data from telecommunications carriers, and a means for matching supporters based on the material needs registered on the site. This enables the prompt and accurate provision of information in the event of a disaster and the smooth implementation of disaster victim support activities.

[0577] "Data collection tools" are tools for extracting and capturing data from multiple sources.

[0578] "Data analysis means" refers to means for analyzing collected data and classifying it based on specific criteria.

[0579] A "generative AI model" is a system that uses artificial intelligence technology to automatically generate responses based on input prompts.

[0580] A "prompt" is a question or instruction sentence that is input to a generative AI model.

[0581] "Telecommunications carrier data" refers to various data provided by companies that provide telecommunications services, such as communication history, wireless LAN connection information, and global positioning system data.

[0582] "Safety confirmation means" refers to a method of using telecommunications carrier data to determine the location of victims and whether they are safe.

[0583] The "material needs registration means" is a means for disaster victims to input and register the materials and quantities they need on the site.

[0584] The "supporter matching means" is a means for selecting and matching supporters based on the material needs registered on the site.

[0585] A "user question answering means" is a means for analyzing questions from users and generating and providing appropriate responses using a generative AI model.

[0586] "Natural language processing" is the technology that enables computers to understand, analyze, and generate human language.

[0587] This invention relates to a "disaster information and support system" for smoothly providing information and providing support activities when a disaster occurs. This system collects and analyzes data from multiple sources and provides information in response to user inquiries. It also utilizes data from telecommunications carriers to provide information on the safety and location of disaster victims, and has the function of matching relief supplies with supporters.

[0588] composition

[0589] 1. Server:

[0590] The server collects data in real time from multiple sources, such as social media, online news, and official government announcements, including social media APIs (e.g., Twitter API) and RSS feeds from news sites.

[0591] The collected data is analyzed using natural language processing (NLP) engines (e.g., spaCy, NLTK) that use programming languages ​​and libraries such as Python and TensorFlow. After analysis, the data is categorized by time, region, location, and presenter and stored in an SQL database.

[0592] 2. Terminal:

[0593] Terminals are devices used by users to search for information, register supplies, and confirm assistance. These include computers, smartphones, and tablets.

[0594] 3. User:

[0595] Users include both information providers (disaster victims, general users) and information recipients (family members, supporters). Users enter questions through a website form and receive answers generated by the server using a generative AI model (e.g., OpenAI GPT-3).

[0596] System operation example

[0597] Data collection and analysis

[0598] The server uses the social networking service's API to collect posts containing the hashtag "disaster name." For example, the server sends a query to the Twitter API to retrieve related posts. The collected posts are analyzed using a natural language processing engine and classified into categories such as "October 15, 2023, Shibuya Ward, Tokyo, information from individual users."

[0599] Question and Answering

[0600] A user enters "What is the current situation in Shibuya Ward?" into a form on the website and sends the question to the server. The server analyzes the question and searches for relevant information from a database. The prompt "What is the current situation in Shibuya Ward?" is input into the generative AI model, and the generated answer "Traffic restrictions are in place in Shibuya Ward, and the evacuation shelter is XX Elementary School" is provided to the user.

[0601] Confirmation of safety

[0602] The user enters the name and contact information of a family member and requests a safety check on the site. For example, the user enters the name "Taro Tanaka" and clicks the confirmation button. The server retrieves communication history, WiFi connection information, and GPS data from the carrier's API, and responds to the user with information such as "Taro Tanaka was last contacted in front of Shibuya Station at 3:30 PM."

[0603] Registering supply needs and matching supporters

[0604] Victims (users) register the supplies they need and the quantities they require on the site. For example, they enter 10 liters of water and three blankets. The server stores this information in a database and makes it available for donors to view. Donors (users) select the supplies they can donate and express their willingness to donate. For example, a donor selects "provide three blankets to the Tanaka family." The server confirms the donor's selection, notifies the administrator, and instructs them on the appropriate procedures.

[0605] In this way, it will be possible to provide quick and accurate information and smoothly carry out relief activities when a disaster occurs.

[0606] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0607] Step 1:

[0608] Data collection and storage

[0609] Server: Collects data from multiple sources (social media, online news, official government announcements, etc.). Specifically, the server sends queries to social media APIs (e.g., Twitter API) to retrieve posts related to specific hashtags or keywords. Since the retrieved data is unorganized as is, all data is first stored in temporary storage.

[0610] Input: Specific hashtags or keywords

[0611] Output: Unorganized data (social media posts, news articles, etc.)

[0612] Step 2:

[0613] Data analysis and classification

[0614] Server: The data stored in temporary storage is analyzed using a natural language processing (NLP) engine. Python, TensorFlow, and NLP libraries (e.g., spaCy, NLTK) are used here. The analyzed data is categorized by time, region, location, and presenter. The categorized data is then stored in an SQL database.

[0615] Input: Unorganized data (social media posts, news articles, etc.)

[0616] Output: Categorised data (organised by time, region, location and presenter)

[0617] Specific operation: The NLP engine analyzes the collected social media posts and classifies them as "information from an individual user, Shibuya-ku, Tokyo, October 15, 2023."

[0618] Step 3:

[0619] Receiving questions from users

[0620] User: Enters a question into the input form on the site and clicks the submit button. For example, "What is the current situation in Shibuya Ward?" This question is sent to the server.

[0621] Input: User question (e.g. "What is the current situation in Shibuya Ward?")

[0622] Output: The question data sent to the server

[0623] Specific operation: The user types "What is the current situation in Shibuya Ward?" in the browser and clicks the submit button.

[0624] Step 4:

[0625] Question analysis and answer generation

[0626] Server: Analyzes the received question using a natural language processing engine, searches for relevant information in a database, and generates prompts using a generative AI model (e.g., OpenAI GPT-3) to generate appropriate answers.

[0627] Input: User question data

[0628] Output: Response data from the generative AI model

[0629] Specific operation: When the server sends the prompt message "What is the current situation in Shibuya Ward?" to the generation AI, the generation AI model generates a response saying "Traffic restrictions are in place in Shibuya Ward, and the evacuation shelter is XX Elementary School."

[0630] Step 5:

[0631] Response provision

[0632] Server: Sends data to the terminal to provide the generated response to the user.

[0633] Input: Response data from a generative AI model

[0634] Output: Response data sent to the user device

[0635] Specific operation: The server generates a response, "Traffic restrictions are in place in Shibuya Ward, and the evacuation shelter is XX Elementary School," and sends it to the user.

[0636] Step 6:

[0637] Acceptance of safety confirmation requests

[0638] User: Enter the name and contact information of a family member or close friend into a form on the site and click the confirm button. For example, enter "Taro Tanaka."

[0639] Input: User-entered data (name and contact information)

[0640] Output: Safety confirmation request data sent to the server

[0641] Specific operation: The user enters "Taro Tanaka" in the browser and clicks the confirmation button.

[0642] Step 7:

[0643] Data collection and safety information provision

[0644] Server: Obtains communication history, Wi-Fi connection information, and GPS data from the telecommunications carrier's API, and confirms the victim's last location and safety.

[0645] Input: Safety confirmation request data, data from telecommunications carrier API

[0646] Output: Safety information provided data

[0647] Specific operation: The server sends a query to the telecommunications company's API and returns the safety information it has obtained, "Taro Tanaka was last heard from in front of Shibuya Station at 15:30," to the user.

[0648] Step 8:

[0649] Registering supply needs

[0650] Victims (users): Enter the supplies they need and the quantity on the site, and click the registration button. For example, enter 10 liters of water and 3 blankets.

[0651] Input: Data on disaster victims' material needs

[0652] Output: Material needs data sent to the server

[0653] Specific actions: The victim enters "10 liters of water, 3 blankets" and clicks the registration button.

[0654] Step 9:

[0655] Store and display supply needs

[0656] Server: Stores registered material needs in a database and makes them available for donors to view.

[0657] Input: Material needs data

[0658] Output: Material needs information stored in a database

[0659] Specific operation: The server stores the material needs data in an SQL database and displays it on a web page.

[0660] Step 10:

[0661] Supporter matching

[0662] Donor (user): Selects available items on the site and expresses their intention to donate. For example, they can view the list of victims and select "Donate three blankets to the Tanaka family."

[0663] Input: Data provided by supporter

[0664] Output: Assistance provision data sent to the server

[0665] Specific action: The supporter selects "Provide three blankets to the Tanaka family" and clicks the "Provide" button.

[0666] Step 11:

[0667] Support arrangements

[0668] Server: Confirms the supporter's selection, notifies the administrator, and instructs the appropriate arrangement procedure.

[0669] Input: Assistance provision data

[0670] Output: Notification data to administrator and assistance arrangement information

[0671] Specific operation: The server checks the support provision data, automatically generates and sends a notification email to the administrator, who then arranges for the delivery of the support supplies.

[0672] (Application example 1)

[0673] 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."

[0674] When a disaster occurs, it is extremely important for logistics facility workers to quickly and accurately collect information and confirm the safety of their employees. However, with current systems, it takes time and effort to collect and analyze information, making it difficult for workers and managers to quickly grasp the actual situation at the disaster site. In addition, there is a lack of systems that can efficiently register the needs for supplies needed in the event of a disaster and efficiently match them with supporters. For these reasons, there is a need for a system that can consistently collect information, confirm the safety of employees, and match them with supporters at logistics facilities during a disaster.

[0675] 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.

[0676] In this invention, the server includes a means for collecting data from multiple information sources, a means for analyzing the collected data and classifying it by time, region, location, and presenter, and a means for providing related information from the classified data based on questions from users. This enables information collection, safety confirmation, supply needs registration, and supporter matching at logistics facilities in the event of a disaster.

[0677] "Source" refers to the source from which data is collected, including social media, online news, and official government announcements.

[0678] "Data analysis" refers to the process of classifying collected data by time, region, location, and presenter, and extracting relevant information.

[0679] "User question" refers to information or questions that a user inputs into the system.

[0680] "Telecommunications company data" refers to data provided by telecommunications companies, including communication history, Wi-Fi connection information, GPS data, and location and safety information.

[0681] "Material needs" refers to information about the supplies and quantities needed by disaster victims.

[0682] "Donor matching" refers to the process of connecting donors with disaster victims based on their material needs.

[0683] A "logistics facility" refers to a location or building used to manage the distribution of goods and materials.

[0684] "Server" refers to the primary computer system that responds to user queries, analyzes data, and provides information.

[0685] "Natural language processing" refers to technologies that automate the analysis and classification of text data, and includes generative AI models.

[0686] "Safety confirmation" refers to the process of confirming the safety status and current location of disaster victims.

[0687] A "generative AI model" refers to a type of artificial intelligence that performs natural language processing based on large amounts of data and generates appropriate responses to questions.

[0688] This invention is a system for efficiently collecting information, confirming the safety of people, registering supply needs, and matching supporters at logistics facilities during disasters. This system functions in cooperation with data from a server, user terminals, and telecommunications companies.

[0689] server

[0690] The server collects and stores data in real time from multiple sources (e.g., social media, online news, official government announcements, etc.). It analyzes the data using a natural language processing (NLP) engine (e.g., Spacy, BERT) and categorizes it by time, region, location, and presenter. The results of this analysis are stored in a database and can be searched and provided as needed. The server also uses a generative AI model (e.g., GPT-3) to generate appropriate answers to user questions and provide information in real time.

[0691] Terminal

[0692] At the logistics facility, workers access the system using their smartphones. A dedicated application is installed on the terminals, allowing them to access information and functions necessary in the event of a disaster. Through the terminals, users can input questions and receive responses from the server. They can also register needed supplies and check the contents of supplies provided by supporters.

[0693] User

[0694] Users of this system include workers and managers at logistics facilities. They use the system to collect information, confirm the safety of people, register needs for supplies, and match supporters during disasters. As a specific example of operation, a user can ask the system, "What is the current situation in XX area?" and receive a response from the server such as, "Traffic restrictions in place. Evacuation shelters are located at XX location."

[0695] Hardware and software used

[0696] Hardware: Smartphone (iOS, Android)

[0697] Software: Flask, Django (backend), MySQL (database), Python (request processing), natural language processing engine (Spacy, BERT), generative AI model (GPT-3)

[0698] Data processing and calculation

[0699] The server continuously retrieves data from social media, online news, and telecommunications company APIs, analyzes the data using a natural language processing engine, and extracts and classifies relevant information. Information stored in a cloud database is analyzed and responded to using a generative AI model to respond to user questions in real time. It also integrates and processes communication history, Wi-Fi connection information, and GPS data to check the safety of logistics facility employees.

[0700] Specific examples (prompt sentence examples)

[0701] When a user asks, "What is the current situation in district X?", the question is sent to the server, which then uses a generative AI model to create an answer based on the latest news and social media posts, such as "Traffic restrictions are in place in district X, and evacuation shelters are located at X location."

[0702] The present invention enables logistics facilities to quickly and efficiently collect and provide information in the event of a disaster, confirm the safety of people, register material needs, and match supporters.

[0703] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0704] Step 1:

[0705] Information Collection and Storage

[0706] Input: Social media, online news, official government announcements, and other sources

[0707] Output: Raw data collected

[0708] The server collects data in real time from social media APIs, news site RSS feeds, and official government announcement sites, and stores the collected raw data in a database.

[0709] Step 2:

[0710] Data analysis and classification

[0711] Input: Raw data collected

[0712] Output: Parsed and classified data

[0713] The server analyzes the collected raw data using a natural language processing (NLP) engine (e.g., Spacy, BERT) and categorizes it by time, region, location, and presenter. The analyzed data is stored in a database and made searchable.

[0714] Step 3:

[0715] Accepting user questions

[0716] Input: User question

[0717] Output: Question

[0718] The terminal provides an interface for users to input questions. The user uses a smartphone to input a question such as "What is the current situation in the X area?" This question is then sent to the server.

[0719] Step 4:

[0720] Question analysis and response generation

[0721] Input: User question

[0722] Output: The generated response

[0723] The server analyzes the question received from the user, searches for relevant information from the database, and uses a generative AI model (e.g., GPT-3) to generate an appropriate response based on the relevant information.

[0724] Step 5:

[0725] Providing a response

[0726] Input: Generated response

[0727] Output: Display the answer to the user

[0728] The server generates a response and sends it to the device, which then displays it on the user's smartphone. For example, if a user asks, "What is the current situation in district X?", the device displays, "Traffic restrictions are in place in district X, and the evacuation shelter is at location X."

[0729] Step 6:

[0730] Confirmation of safety

[0731] Input: User safety confirmation request, name, contact information

[0732] Output: Safety information

[0733] The server obtains information on the last location and safety of disaster victims based on communication history, Wi-Fi connection information, and GPS data provided by the telecommunications company, allowing users to check the safety of their family and colleagues.

[0734] Step 7:

[0735] Registering supply needs

[0736] Input: Information on supply needs from disaster victims (users)

[0737] Output: List of material needs

[0738] The terminal provides an interface where disaster victims can input the supplies and quantities they need, and sends the registered information to a server, which stores the information in a database and makes it available to supporters.

[0739] Step 8:

[0740] Donors' declaration of intent to donate supplies

[0741] Input: Information on supplies provided by supporters (users)

[0742] Output: Notification of matched relief supplies and relief arrangements

[0743] Donors use their terminals to select registered material needs and express their willingness to donate. The server verifies this information and notifies the administrator. The administrator then instructs the donors on how and when to deliver the supplies.

[0744] The above is the processing flow of the "Disaster Information and Support System" at logistics facilities.

[0745] 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.

[0746] This invention is a "disaster information and support system" for smoothly providing information and providing support activities when a disaster occurs. This system collects and organizes information from social media and online news, and provides information in response to user questions. It also utilizes data from telecommunications companies to check the safety of disaster victims, provide location information, and match material needs with supporters. Furthermore, this invention incorporates an emotion engine that recognizes the user's emotions, and can adjust the information provided based on the user's emotions.

[0747] System configuration

[0748] 1. Server:

[0749] The server collects and stores data in real time from multiple sources (e.g., social media, online news, official government announcements, etc.). It then analyzes the data using a natural language processing (NLP) engine and categorizes it by time, region, location, and issuer. The results of this analysis are stored in a database and can be searched and provided as needed. It also uses data from telecommunications companies to confirm the safety of victims and identify their locations.

[0750] 2. Terminal:

[0751] The device is used by users to access the site, search for information, register supplies, and confirm support. Examples of such devices include PCs, smartphones, and tablets.

[0752] 3. User:

[0753] Users include those who provide information (e.g., disaster victims, general users) and those who acquire information (e.g., family members, supporters). Users use the site to check safety and register / confirm supplies.

[0754] 4. Emotion Engine:

[0755] The emotion engine analyzes emotions from text and voice input by the user and adjusts the information provided based on those emotions. For example, if the user is feeling anxious, it will provide more reassuring information.

[0756] Program processing

[0757] 1. Data Collection and Analysis:

[0758] Server: Collects data from specified sources and analyzes it using a natural language processing engine. For example, it collects posts related to specific hashtags or keywords through social media APIs and categorizes these posts by date, time, location, and author.

[0759] Example: The server collects and analyzes social media posts containing the hashtag "disaster name." Through this analysis, the posts are classified as "October 15, 2023, Shibuya Ward, Tokyo, information from individual users."

[0760] 2. Question and Answer:

[0761] User: Enters a question on the site (e.g., "What is the current situation in Shibuya Ward?"). This question is sent to the server.

[0762] Server: Analyzes the question and searches the database for relevant information. Based on the analysis results, the generation AI generates an appropriate answer and provides it to the user. It also uses an emotion engine to recognize the user's emotions and adjust the information provided as needed.

[0763] Example: When a user asks, "What is the current situation in Shibuya Ward?", the server will respond based on the latest news and social media posts with, for example, "Traffic restrictions are in place in Shibuya Ward, and the evacuation shelter is at X Elementary School." If the user asks the question with an anxious expression or tone, the server will adjust the response to something more reassuring, such as, "Many evacuation shelters have now been opened in Shibuya Ward, and there are many places where you can safely evacuate."

[0764] 3. Safety confirmation:

[0765] Server: Obtains communication history, Wi-Fi connection information, and GPS data from the telecommunications company's API, and checks the last location and safety of victims.

[0766] Users: Enter names and contact information on the site to check on the safety of family and loved ones.

[0767] Server: Searches the database based on the input information and provides the relevant safety information to the user. It also adjusts the way the information is provided using an emotion engine.

[0768] Example: When a user checks the safety of "Taro Tanaka," the server responds with information like, "Taro Tanaka was last heard from in front of Shibuya Station at 3:30 PM." If the user seems very worried, the server might add, "Taro Tanaka has been heard from recently and may be in a relatively safe location."

[0769] 4. Registering material needs and matching donors:

[0770] Victims (users): Enter the required supplies and their quantities in the supply registration form on the site and register (e.g., 10 liters of water, 3 blankets).

[0771] Server: Stores the inputted material needs in a database and makes them available for donors to view.

[0772] Donor (user): Access the donation list page on the site and select the items they can donate.

[0773] Server: Confirms the supporter's selection, notifies the administrator, and instructs the appropriate arrangement procedure. It also uses an emotion engine to provide appropriate communication tools.

[0774] Example: A donor views the "List of victims in the Tohoku region" and selects "Provide three blankets to the Tanaka family." After confirmation, the administrator instructs the donor on how and when to deliver the relief supplies. If this is the first time the donor is providing relief, the emotion engine is used to simultaneously provide a message such as, "Thank you for your first donation. We will explain the procedure so that you can feel at ease."

[0775] In this way, the system of the present invention can provide information quickly and appropriately when a disaster occurs, and efficiently support communication between victims and supporters. By incorporating an emotion engine, it becomes possible to provide information and responses according to the user's emotions, realizing support that gives a greater sense of security.

[0776] The processing flow will be explained below.

[0777] Data collection and analysis

[0778] Step 1:

[0779] Server: Periodically sends requests to APIs of social media, online news, and government announcement sites to collect data.

[0780] Step 2:

[0781] Server: Adds collected data to a queue for analysis and passes it to the natural language processing engine.

[0782] Step 3:

[0783] Server: A natural language processing engine analyzes the data and categorizes it by date, time, location, and presenter.

[0784] Step 4:

[0785] Server: The analysis results are stored in a database and indexed for later retrieval.

[0786] Question and Answering

[0787] Step 1:

[0788] User: Enters a question into the site's search box (e.g., "What's the current situation in Shibuya Ward?").

[0789] Step 2:

[0790] Server: Receives questions from users and analyzes the content of the questions using natural language processing.

[0791] Step 3:

[0792] Server: Searches for relevant information from the database and generates appropriate answers using generative AI.

[0793] Step 4:

[0794] Server: Uses an emotion engine to analyze emotions from the user's input and tone.

[0795] Step 5:

[0796] Server: Adjusts the generated answer based on the user's emotions. For example, if the user is feeling anxious, adds reassuring information.

[0797] Step 6:

[0798] Server: Returns the adjusted answer to the user's terminal and displays it to the user.

[0799] Confirmation of safety

[0800] Step 1:

[0801] Server: Periodically obtains communication history, Wi-Fi connection information, and GPS data from the telecommunications company's API.

[0802] Step 2:

[0803] Server: Analyzes the acquired data and stores the victim's last location and safety information in a database.

[0804] Step 3:

[0805] User: Enters name and contact information into the safety confirmation form on the site.

[0806] Step 4:

[0807] Server: Searches the database based on the entered information and identifies the relevant safety information.

[0808] Step 5:

[0809] Server: Sends safety information to the user's device so that the user can check it.

[0810] Step 6:

[0811] Server: Uses the emotion engine to tailor how safety information is provided. If the user is very worried, provide additional reassuring information.

[0812] Registering supply needs and matching supporters

[0813] Step 1:

[0814] Victims (users): Enter the supplies they need and their quantities in the supply registration form on the site (e.g., 10 liters of water, 3 blankets).

[0815] Step 2:

[0816] Server: Stores the input material needs information in a database.

[0817] Step 3:

[0818] Donor (user): Access the donation list page on the site and select the items they can donate.

[0819] Step 4:

[0820] Server: Confirms the supporter's selection and notifies the administrator.

[0821] Step 5:

[0822] Administrator (server): Checks the support details and sends instructions to the supporter for arrangements.

[0823] Step 6:

[0824] Server: Uses the emotion engine to provide appropriate communication to supporters. For example, for supporters providing support for the first time, a message containing instructions on how to provide support will be sent to put them at ease.

[0825] Step 7:

[0826] Supporter (user): Follow instructions, prepare supplies, and provide them to disaster victims.

[0827] In this way, the system of the present invention can provide information quickly and appropriately when a disaster occurs, and efficiently support communication between victims and supporters. By incorporating an emotion engine, it becomes possible to provide information and responses according to the user's emotions, realizing support that gives a greater sense of security.

[0828] Example 2

[0829] 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."

[0830] In the event of a disaster, it is necessary to provide victims, their families, and supporters with fast and accurate information. However, because information is scattered and vast, it is difficult to quickly obtain the necessary information. It is also difficult to smoothly confirm the safety of victims and carry out procedures for providing material support. Furthermore, there is a lack of emotionally sensitive information provided to users who feel excessive stress and anxiety during a disaster. Effective means to solve these problems are desired.

[0831] 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.

[0832] In this invention, the server includes means for collecting data from multiple information sources, means for analyzing the collected data using natural language processing and classifying it by time, region, location, and presenter, means for providing relevant information from the classified data based on questions from users and adjusting the content of the information using an emotion engine, means for identifying the safety and location information of disaster victims using data from communication service providers, and means for matching supporters based on material needs registered on the site and providing appropriate communication to the supporters using the emotion engine.This enables the provision of quick and accurate information, safety confirmation, smooth procedures for material support, and the provision of information that takes emotions into consideration in the event of a disaster.

[0833] "Sources" refer to external data providers from which data is collected, such as social media, online news, and official government announcements.

[0834] "Natural language processing" is a technology that enables computers to understand, analyze, and generate human language.

[0835] An "emotion engine" is a software engine that analyzes emotions from text and voice input by the user and adjusts the information and responses provided based on those emotions.

[0836] "Telecommunications service provider" refers to a company or organization that provides telecommunications services through a telecommunications network.

[0837] "Safety confirmation" refers to the act of collecting and providing information to confirm the safety and current location of disaster victims.

[0838] "Material needs" refers to the types and quantities of supplies and items needed by disaster victims.

[0839] "Supporters" refers to people and organizations whose role is to provide supplies and services to disaster victims during a disaster.

[0840] "Matching" refers to the process of connecting the needs of disaster victims with the resources available to supporters.

[0841] "Data classification" refers to the process of organizing and dividing collected data by different criteria such as time, region, location, and presenter.

[0842] A "database" refers to a system that organizes and stores collected and analyzed data so that it can be searched and retrieved as needed.

[0843] "Global Positioning System Data" refers to data used to measure specific locations on Earth using satellites.

[0844] "Wireless communication network connection information" refers to information about the WiFi network or cell tower to which a mobile device is connected.

[0845] This invention is a "disaster information and support system" for smoothly providing information and carrying out support activities when a disaster occurs. This system collects data from multiple sources, such as social media and online news, and analyzes and classifies it to provide users with appropriate information.

[0846] 1. Data Collection

[0847] Server: The server collects data from sources such as social media, online news, and official government announcements. It collects posts containing specific hashtags or keywords through the APIs of the social media platforms used.

[0848] Example: A server collects all Twitter posts containing the hashtag "Disaster Breaking News" and stores this data.

[0849] 2. Data analysis and classification

[0850] Server: The server analyzes the collected data using natural language processing (NLP) techniques and categorizes the data by time, region, location, and presenter.

[0851] Software used: General NLP engine

[0852] Example: The server analyzes collected Twitter posts and classifies them as "information from an individual user, Shibuya-ku, Tokyo, October 15, 2023."

[0853] 3. Question and Answering

[0854] User: A user types a question into a search box on the site (e.g., "What's the current situation in Shibuya Ward?").

[0855] Server: The server receives the question, searches for relevant information from a database, and responds. Generative AI generates appropriate answers, and an emotion engine is used to tailor the information according to the user's emotions.

[0856] Example: When a user asks, "What is the current situation in Shibuya Ward?", the server responds, "Traffic restrictions are currently in place in Shibuya Ward. An evacuation shelter has been opened at X Elementary School." Furthermore, if the emotion engine detects that the user is anxious, it adds reassuring information, such as, "There are many safe places to evacuate to in Shibuya Ward."

[0857] 4. Safety confirmation

[0858] User: Users enter the names and contact information of family members and acquaintances on the site to check on their safety.

[0859] Server: The server uses the communication service provider's API to obtain communication history and GPS data, and checks the last location and safety information of the victims. It uses an emotion engine to adjust how the information is provided.

[0860] Example: When a user checks the safety of "Taro Tanaka," the server responds with information such as, "Taro Tanaka was last contacted in front of Shibuya Station at 3:30 PM." If the user feels uneasy, the server provides additional reassuring information such as, "Taro Tanaka has been in contact recently and is likely in a safe location."

[0861] 5. Registering supply needs and matching supporters

[0862] Victims (users): Victims enter the supplies they need and their quantities in the site's supply registration form (e.g., "10 liters of water, 3 blankets").

[0863] Server: The entered information is saved in a database and made available for supporters to view.

[0864] Donors (users): Donors access the donation list page on the site and select the items they can donate.

[0865] Server: Confirms the supporter's selection, notifies the administrator, and instructs appropriate arrangements. Uses the emotion engine to provide supporters with appropriate communication tools.

[0866] Example: A donor views the "List of victims in the Tohoku region" and selects "Provide three blankets to the Tanaka family." The server notifies the administrator and instructs them to arrange for delivery. Also, for first-time donors, a message is displayed saying, "Thank you for your first donation. We will explain the donation procedure so you can feel at ease."

[0867] By combining these functions, the system of the present invention can provide prompt and appropriate information in the event of a disaster, confirm the safety of people, facilitate smooth procedures for providing material support, and provide information that takes emotions into consideration.

[0868] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0869] Step 1: Data collection

[0870] Server: The server collects data from multiple sources, such as social media, online news, and official government announcements. Specifically, it uses social media APIs to retrieve posts containing specific hashtags or keywords.

[0871] Input: A specific hashtag or keyword (e.g., "disaster breaking news")

[0872] Output: Collected post data (e.g. Twitter posts)

[0873] Specific operation: The server collects all Twitter posts containing the hashtag "Disaster Breaking News" and stores this data.

[0874] Step 2: Data analysis and classification

[0875] Server: The server analyzes the collected data using a natural language processing engine (e.g., a general NLP engine) and categorizes the data by time, region, location, and presenter. The analyzed data is stored in a database.

[0876] Input: Collected post data (e.g., Twitter posts)

[0877] Output: Classified data (e.g., "Information from an individual user, Shibuya Ward, Tokyo, October 15, 2023")

[0878] Specific operation: The server analyzes the collected Twitter posts and classifies them as "information from an individual user in Shibuya Ward, Tokyo, on October 15, 2023." This classification result is stored in a database.

[0879] Step 3: Question and Answer

[0880] User: A user types a question into a search box on the site (e.g., "What's the current situation in Shibuya Ward?").

[0881] Server: The server receives the question, searches for relevant information from a database, uses a generative AI model to generate an appropriate answer, and uses an emotion engine to tailor the information according to the user's emotions.

[0882] Input: User question (e.g. "What is the current situation in Shibuya Ward?")

[0883] Output: Generated answer (e.g. "Traffic restrictions are in place in Shibuya Ward. An evacuation shelter has been opened at XX Elementary School.")

[0884] Specific operation: The server analyzes the user's question and searches the database for relevant information. The generation AI generates a response such as, "Traffic restrictions are in place in Shibuya Ward. An evacuation shelter has been opened at X-X Elementary School." Furthermore, if the emotion engine detects the user's feelings of anxiety, it adds, "There are many safe places to evacuate to in Shibuya Ward."

[0885] Step 4: Safety confirmation

[0886] User: Users enter the names and contact information of family members and acquaintances on the site to check on their safety.

[0887] Server: The server uses the communication service provider's API to obtain communication history and GPS data, and checks the last location and safety information of the victims. It uses an emotion engine to adjust how the information is provided.

[0888] Input: Names and contact information of family members or acquaintances (e.g., "Taro Tanaka")

[0889] Output: Safety information (e.g. "Taro Tanaka was last heard from in front of Shibuya Station at 15:30")

[0890] Specific operation: Based on the name and contact information of "Taro Tanaka" entered by the user, the server uses the communication service provider's API to obtain communication history and GPS data. This provides information such as "Taro Tanaka was last contacted in front of Shibuya Station at 3:30 PM." For users who feel uneasy, the server provides additional information to reassure them, such as "Taro Tanaka has been in communication recently and is likely in a safe location."

[0891] Step 5: Register your supply needs

[0892] Victims (users): Victims enter the supplies they need and their quantities in the site's supply registration form (e.g., "10 liters of water, 3 blankets").

[0893] Server: The entered information is saved in a database and made available for supporters to view.

[0894] Input: The supplies you need and their quantities (e.g., "10 liters of water, 3 blankets")

[0895] Output: Registered supply information (e.g., "10 liters of water, 3 blankets")

[0896] Specific operation: When a victim registers "10 liters of water, 3 blankets" on the site, the server saves this in the database and allows supporters to proceed and view it.

[0897] Step 6: Supporter Matching

[0898] Donors (users): Donors access the donation list page on the site and select the items they can donate.

[0899] Server: Confirms the supporter's selection, notifies the administrator, and instructs appropriate arrangements. Uses the emotion engine to provide supporters with appropriate communication tools.

[0900] Input: The items that donors can provide (e.g., "3 blankets")

[0901] Output: Instructions for providing assistance (e.g., "Provide three blankets to the Tanaka family")

[0902] Specific operation: A donor views the "List of victims in the Tohoku region" and selects "Provide three blankets to the Tanaka family." The server notifies the administrator and instructs them to arrange for delivery. For first-time donors, the server also displays a message saying, "Thank you for your first donation. We will explain the donation procedure so you can feel at ease."

[0903] (Application example 2)

[0904] 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."

[0905] When a disaster occurs, there is a need for a system that can provide information quickly and appropriately and facilitate smooth communication between victims and supporters. Current systems have issues with obtaining information in real time and providing information that reflects emotions, as well as issues with smoothly confirming the safety of victims and matching supplies. There is a need for a system that can solve these issues and support more effective support activities.

[0906] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data from multiple information sources, means for analyzing the collected data and classifying it by time, region, location, and presenter, means for providing related information from the classified data based on questions from users, means for identifying the safety and location information of disaster victims using data from telecommunications companies, means for matching supporters based on material needs registered on the site, and means for analyzing user emotions and providing information according to the results. This makes it possible to provide information and support activities quickly and appropriately when a disaster occurs.

[0907] "Sources" are the origins of information provided by various digital media and platforms (e.g., social networking services, online news, official government announcements, etc.).

[0908] "Data collection methods" are the mechanisms and techniques used to obtain necessary data from various sources and incorporate it into the system.

[0909] "Data analysis tools" are techniques and methods for analyzing collected data and categorizing it based on specific criteria (e.g., time, region, location, presenter, etc.).

[0910] The "user question answering means" is a system or function for accepting questions from users and searching for and providing related information based on those questions.

[0911] "Safety confirmation means" refers to technology or methods for confirming the safety and location of disaster victims using data from telecommunications companies (e.g., communication history, wireless connection information, global positioning system data).

[0912] "Supply matching tools" are systems and functions that connect the supply needs registered on the site with supporters, enabling efficient distribution of supplies.

[0913] "Emotion analysis means" refers to a technique or method for analyzing emotions from user input (e.g., text or voice) and adjusting the information provided based on the results.

[0914] "Natural language processing" is a technical field that uses computers to understand, interpret, and manipulate human language, and is particularly used for analyzing text data.

[0915] "Global Positioning System data" is data used to obtain highly accurate positional information of any point on Earth using satellites.

[0916] Specific embodiments for carrying out the present invention will be described below.

[0917] This system consists of three components: a server, terminals, and users. The server plays a central role in collecting data from various information sources and analyzing and classifying it. The terminals are devices that users use to obtain information, check the safety of others, register supplies, and confirm support, and users are the entities that actually use these functions.

[0918] First, the server collects data from multiple sources, such as social networking services (SNS), online news, and official government announcements. The server obtains data from these sources in real time, analyzes it using a natural language processing (NLP) engine (described below), and classifies it by time, region, location, and issuer.

[0919] The NLP engine uses the open source TextBlob and generative AI models using deep learning (such as GPT). Through this analysis, for example, a social media post containing the hashtag "disaster name" is classified as "information from an individual user, Tokyo, October 15, 2023."

[0920] When a user inputs a question through their device, the question is sent to the server. For example, if the user inputs the question, "What is the current situation in Shibuya Ward?", the server searches for relevant information from the database, and the generative AI generates the optimal answer based on the analysis results and provides it to the user. An example of a prompt sentence is, "What is the current situation in Shibuya Ward?" Furthermore, an emotion engine is used to analyze the user's emotions and adjust the way information is presented as necessary. If the user asks a question with an anxious expression or tone, the content is changed to one that gives a sense of security.

[0921] For safety checks, the server obtains communication history, wireless connection information, and Global Positioning System (GPS) data from the telecommunications company's API. For example, when a user enters the name and contact information of "Taro Tanaka" to check the user's safety, the server searches the database and returns information such as "Taro Tanaka was last contacted in front of Shibuya Station at 3:30 PM." If the user appears very worried, the emotion engine provides additional information such as "He may be in a relatively safe location."

[0922] To match supplies, disaster victims register the supplies they need and the quantities they require on the site. For example, they might enter "10 liters of water, 3 blankets." The server stores this information in a database and makes it available for donors to view. When a donor selects supplies available on the site, the server notifies the administrator and instructs them on the appropriate procedures for arranging supplies. Using an emotion engine, the system also provides reassuring messages when donors are donating for the first time.

[0923] In this way, the server and terminals work together to provide prompt and appropriate information and support activities in the event of a disaster. Examples of prompt sentences introduced include user questions such as "What is the current situation in Shibuya Ward?" and "I want to check on the safety of my daughter."

[0924] The above is a specific embodiment for carrying out the present invention, and this system will improve the efficiency of information provision and support activities in the event of a disaster.

[0925] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0926] Step 1:

[0927] The server collects data from multiple sources, specifically social networking services (SNS), online news, official government announcements, etc., and obtains data in real time through APIs. Data from these sources is used as input, and the raw data is stored on the server as output.

[0928] Step 2:

[0929] The server analyzes the collected data and categorizes it by time, region, location, and presenter. Specifically, it processes the data with a natural language processing engine using TextBlob and generative AI models (e.g., GPT). It uses the collected raw data as input and provides data categorized by time, region, location, and presenter as output.

[0930] Step 3:

[0931] The user inputs a question through a terminal. For example, they input "What is the current situation in Shibuya Ward?" on the application screen of a smartphone or PC. The user's question text is used as input, and the question content is sent to the server as output.

[0932] Step 4:

[0933] The server searches for relevant information from the database based on the user's question, and the generative AI generates an appropriate answer based on the analysis results. The user's question and classified data are used as input, and the generated answer text is obtained as output.

[0934] Step 5:

[0935] The server uses an emotion engine to analyze the user's emotions and adjust the information provided. Specifically, it analyzes the user's input text using TextBlob or other emotion analysis tools. The input is the user's question text, and the output is the user's emotion score. For example, if the user asks a question with an anxious expression or tone, the server adjusts the answer to make it more reassuring.

[0936] Step 6:

[0937] The server obtains communication history, wireless connection information, and Global Positioning System (GPS) data from the telecommunications company's API and checks the safety of disaster victims. Location information data from the telecommunications company is used as input, and information on the safety of disaster victims is obtained as output. This provides information such as, "Taro Tanaka was last heard from in front of Shibuya Station at 3:30 PM."

[0938] Step 7:

[0939] Users register information about required supplies through their terminals. For example, they input specific needs such as "10 liters of water, 3 blankets." The input is the information about the needs of disaster victims, and the output is stored on the server.

[0940] Step 8:

[0941] The server matches supporters based on the material needs registered on the site. Specifically, it compares the information on the materials that can be provided selected by the supporter with the information on the needs of the disaster victims to make the optimal match. The input is the information on the material needs of the disaster victims and the information on the materials that can be provided by the supporter, and the matching results are obtained as the output.

[0942] The above is the specific processing flow of this system's program. At each step, the necessary data is input, specific data processing and data calculations are performed, and ultimately useful information and support is provided to the user.

[0943] 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.

[0944] 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.

[0945] 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.

[0946] [Third embodiment]

[0947] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0948] 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.

[0949] 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).

[0950] 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.

[0951] 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.

[0952] 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).

[0953] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0954] 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.

[0955] 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.

[0956] 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.

[0957] 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.

[0958] 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."

[0959] This invention is a "disaster information and support system" for smoothly providing information and carrying out support activities when a disaster occurs. This system collects and organizes information from social media and online news, and provides information in response to user questions. It also utilizes data from telecommunications companies to check the safety and location of disaster victims, and has the function of matching supply needs with supporters.

[0960] System configuration

[0961] 1. Server:

[0962] The server collects and stores data in real time from multiple sources (e.g., social media, online news, official government announcements, etc.). It then analyzes the data using a natural language processing (NLP) engine and categorizes it by time, region, location, and presenter. The results of this analysis are stored in a database and can be searched and provided as needed.

[0963] 2. Terminal:

[0964] The device is used by users to access the site, search for information, register supplies, and confirm support. Examples of such devices include PCs, smartphones, and tablets.

[0965] 3. User:

[0966] Users include those who provide information (e.g., disaster victims, general users) and those who acquire information (e.g., family members, supporters). Users use the site to check safety and register / confirm supplies.

[0967] Program processing

[0968] 1. Data Collection and Analysis:

[0969] Server: Collects data from specified sources and analyzes it using a natural language processing engine. For example, it collects posts related to specific hashtags or keywords through social media APIs and categorizes these posts by date, time, location, and author.

[0970] Example: The server collects and analyzes social media posts containing the hashtag "disaster name." Through this analysis, the posts are classified as "October 15, 2023, Shibuya Ward, Tokyo, information from individual users."

[0971] 2. Question and Answer:

[0972] User: Enters a question on the site (e.g., "What is the current situation in Shibuya Ward?"). This question is sent to the server.

[0973] Server: Analyzes the question and searches the database for relevant information. Based on the analysis results, the generation AI generates an appropriate answer and provides it to the user.

[0974] Example: When a user asks, "What is the current situation in Shibuya Ward?", the server will respond based on the latest news and social media posts with something like, "Traffic restrictions are in place in Shibuya Ward, and the evacuation shelter is at XX Elementary School."

[0975] 3. Safety confirmation:

[0976] Server: Obtains communication history, Wi-Fi connection information, and GPS data from the telecommunications company's API, and checks the last location and safety of victims.

[0977] Users: Enter names and contact information on the site to check on the safety of family and loved ones.

[0978] Server: Based on the input information, searches for communication data and provides the user with the relevant safety information.

[0979] Example: When a user checks the safety of "Taro Tanaka," the server responds with information such as "Taro Tanaka was last contacted in front of Shibuya Station at 15:30."

[0980] 4. Registering material needs and matching donors:

[0981] Victims (users): Enter and register the supplies they need and their quantities on the site (for example, 10 liters of water, 3 blankets).

[0982] Server: Stores registered material needs in a database and makes them available for donors to view.

[0983] Donors (users): Select the supplies they can donate on the site and express their intention to donate.

[0984] Server: Confirms the supporter's selection, notifies the administrator, and instructs the appropriate arrangement procedure.

[0985] Example: A donor views the "List of victims in the Tohoku region" and selects "Provide three blankets to the Tanaka family." After confirmation, the administrator instructs the donor on how and when to deliver the relief supplies.

[0986] In this way, the system of the present invention can provide information quickly and appropriately when a disaster occurs, and efficiently support communication between victims and supporters.

[0987] The processing flow will be explained below.

[0988] Data collection and analysis

[0989] Step 1:

[0990] Server: Periodically sends requests to APIs of social media, online news, and government announcement sites to collect data.

[0991] Step 2:

[0992] Server: Adds collected data to a queue for analysis and passes it to the natural language processing engine.

[0993] Step 3:

[0994] Server: A natural language processing engine analyzes the data and categorizes it by date, time, location, and presenter.

[0995] Step 4:

[0996] Server: The analysis results are stored in a database and indexed for later retrieval.

[0997] Question and Answering

[0998] Step 1:

[0999] User: Enters a question into the site's search box (e.g., "What's the current situation in Shibuya Ward?").

[1000] Step 2:

[1001] Server: Receives questions from users and analyzes the content of the questions using natural language processing.

[1002] Step 3:

[1003] Server: Searches for relevant information from the database and generates appropriate answers using generative AI.

[1004] Step 4:

[1005] Server: Returns the answer to the user's terminal and displays it to the user.

[1006] Confirmation of safety

[1007] Step 1:

[1008] Server: Periodically obtains communication history, Wi-Fi connection information, and GPS data from the telecommunications company's API.

[1009] Step 2:

[1010] Server: Analyzes the acquired data and stores the victim's last location and safety information in a database.

[1011] Step 3:

[1012] User: Enters name and contact information into the safety confirmation form on the site.

[1013] Step 4:

[1014] Server: Searches the database based on the entered information and identifies the relevant safety information.

[1015] Step 5:

[1016] Server: Sends safety information to the user's device so that the user can check it.

[1017] Registering supply needs and matching supporters

[1018] Step 1:

[1019] Victims (users): Enter the supplies they need and their quantities in the supply registration form on the site (e.g., 10 liters of water, 3 blankets).

[1020] Step 2:

[1021] Server: Stores the input material needs information in a database.

[1022] Step 3:

[1023] Donor (user): Access the donation list page on the site and select the items they can donate.

[1024] Step 4:

[1025] Server: Confirms the supporter's selection and notifies the administrator.

[1026] Step 5:

[1027] Administrator (server): Checks the support details and sends instructions to the supporter for arrangements.

[1028] Step 6:

[1029] Supporter (user): Follow instructions, prepare supplies, and provide them to disaster victims.

[1030] The above is a specific processing flow for implementing the present invention. This system supports communication between disaster victims and supporters quickly and efficiently, and ensures the delivery of necessary information and supplies.

[1031] Example 1

[1032] 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."

[1033] When a disaster occurs, it is necessary to quickly and accurately grasp the damage situation, confirm the safety of victims, and provide supplies effectively. However, with conventional systems, the series of processes of information collection and analysis, question and answering, safety confirmation, and supply provision were fragmented, making efficient operation difficult. In addition, a lack of real-time information provision using generative AI models made it difficult to respond quickly.

[1034] 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.

[1035] In this invention, the server includes a means for collecting data from multiple information sources, a means for analyzing the collected data and classifying it by time, region, location, and presenter, a means for inputting user questions as prompts to a generative AI model and generating responses, a means for identifying the safety and location information of disaster victims using data from telecommunications carriers, and a means for matching supporters based on the material needs registered on the site. This enables the prompt and accurate provision of information in the event of a disaster and the smooth implementation of disaster victim support activities.

[1036] "Data collection tools" are tools for extracting and capturing data from multiple sources.

[1037] "Data analysis means" refers to means for analyzing collected data and classifying it based on specific criteria.

[1038] A "generative AI model" is a system that uses artificial intelligence technology to automatically generate responses based on input prompts.

[1039] A "prompt" is a question or instruction sentence that is input to a generative AI model.

[1040] "Telecommunications carrier data" refers to various data provided by companies that provide telecommunications services, such as communication history, wireless LAN connection information, and global positioning system data.

[1041] "Safety confirmation means" refers to a method of using telecommunications carrier data to determine the location of victims and whether they are safe.

[1042] The "material needs registration means" is a means for disaster victims to input and register the materials and quantities they need on the site.

[1043] The "supporter matching means" is a means for selecting and matching supporters based on the material needs registered on the site.

[1044] A "user question answering means" is a means for analyzing questions from users and generating and providing appropriate responses using a generative AI model.

[1045] "Natural language processing" is the technology that enables computers to understand, analyze, and generate human language.

[1046] This invention relates to a "disaster information and support system" for smoothly providing information and providing support activities when a disaster occurs. This system collects and analyzes data from multiple sources and provides information in response to user inquiries. It also utilizes data from telecommunications carriers to provide information on the safety and location of disaster victims, and has the function of matching relief supplies with supporters.

[1047] composition

[1048] 1. Server:

[1049] The server collects data in real time from multiple sources, such as social media, online news, and official government announcements, including social media APIs (e.g., Twitter API) and RSS feeds from news sites.

[1050] The collected data is analyzed using natural language processing (NLP) engines (e.g., spaCy, NLTK) that use programming languages ​​and libraries such as Python and TensorFlow. After analysis, the data is categorized by time, region, location, and presenter and stored in an SQL database.

[1051] 2. Terminal:

[1052] Terminals are devices used by users to search for information, register supplies, and confirm assistance. These include computers, smartphones, and tablets.

[1053] 3. User:

[1054] Users include both information providers (disaster victims, general users) and information recipients (family members, supporters). Users enter questions through a website form and receive answers generated by the server using a generative AI model (e.g., OpenAI GPT-3).

[1055] System operation example

[1056] Data collection and analysis

[1057] The server uses the social networking service's API to collect posts containing the hashtag "disaster name." For example, the server sends a query to the Twitter API to retrieve related posts. The collected posts are analyzed using a natural language processing engine and classified into categories such as "October 15, 2023, Shibuya Ward, Tokyo, information from individual users."

[1058] Question and Answering

[1059] A user enters "What is the current situation in Shibuya Ward?" into a form on the website and sends the question to the server. The server analyzes the question and searches for relevant information from a database. The prompt "What is the current situation in Shibuya Ward?" is input into the generative AI model, and the generated answer "Traffic restrictions are in place in Shibuya Ward, and the evacuation shelter is XX Elementary School" is provided to the user.

[1060] Confirmation of safety

[1061] The user enters the name and contact information of a family member and requests a safety check on the site. For example, the user enters the name "Taro Tanaka" and clicks the confirmation button. The server retrieves communication history, WiFi connection information, and GPS data from the carrier's API, and responds to the user with information such as "Taro Tanaka was last contacted in front of Shibuya Station at 3:30 PM."

[1062] Registering supply needs and matching supporters

[1063] Victims (users) register the supplies they need and the quantities they require on the site. For example, they enter 10 liters of water and three blankets. The server stores this information in a database and makes it available for donors to view. Donors (users) select the supplies they can donate and express their willingness to donate. For example, a donor selects "provide three blankets to the Tanaka family." The server confirms the donor's selection, notifies the administrator, and instructs them on the appropriate procedures.

[1064] In this way, it will be possible to provide quick and accurate information and smoothly carry out relief activities when a disaster occurs.

[1065] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1066] Step 1:

[1067] Data collection and storage

[1068] Server: Collects data from multiple sources (social media, online news, official government announcements, etc.). Specifically, the server sends queries to social media APIs (e.g., Twitter API) to retrieve posts related to specific hashtags or keywords. Since the retrieved data is unorganized as is, all data is first stored in temporary storage.

[1069] Input: Specific hashtags or keywords

[1070] Output: Unorganized data (social media posts, news articles, etc.)

[1071] Step 2:

[1072] Data analysis and classification

[1073] Server: The data stored in temporary storage is analyzed using a natural language processing (NLP) engine. Python, TensorFlow, and NLP libraries (e.g., spaCy, NLTK) are used here. The analyzed data is categorized by time, region, location, and presenter. The categorized data is then stored in an SQL database.

[1074] Input: Unorganized data (social media posts, news articles, etc.)

[1075] Output: Categorised data (organised by time, region, location and presenter)

[1076] Specific operation: The NLP engine analyzes the collected social media posts and classifies them as "information from an individual user, Shibuya-ku, Tokyo, October 15, 2023."

[1077] Step 3:

[1078] Receiving questions from users

[1079] User: Enters a question into the input form on the site and clicks the submit button. For example, "What is the current situation in Shibuya Ward?" This question is sent to the server.

[1080] Input: User question (e.g. "What is the current situation in Shibuya Ward?")

[1081] Output: The question data sent to the server

[1082] Specific operation: The user types "What is the current situation in Shibuya Ward?" in the browser and clicks the submit button.

[1083] Step 4:

[1084] Question analysis and answer generation

[1085] Server: Analyzes the received question using a natural language processing engine, searches for relevant information in a database, and generates prompts using a generative AI model (e.g., OpenAI GPT-3) to generate appropriate answers.

[1086] Input: User question data

[1087] Output: Response data from the generative AI model

[1088] Specific operation: When the server sends the prompt message "What is the current situation in Shibuya Ward?" to the generation AI, the generation AI model generates a response saying "Traffic restrictions are in place in Shibuya Ward, and the evacuation shelter is XX Elementary School."

[1089] Step 5:

[1090] Response provision

[1091] Server: Sends data to the terminal to provide the generated response to the user.

[1092] Input: Response data from a generative AI model

[1093] Output: Response data sent to the user device

[1094] Specific operation: The server generates a response, "Traffic restrictions are in place in Shibuya Ward, and the evacuation shelter is XX Elementary School," and sends it to the user.

[1095] Step 6:

[1096] Acceptance of safety confirmation requests

[1097] User: Enter the name and contact information of a family member or close friend into a form on the site and click the confirm button. For example, enter "Taro Tanaka."

[1098] Input: User-entered data (name and contact information)

[1099] Output: Safety confirmation request data sent to the server

[1100] Specific operation: The user enters "Taro Tanaka" in the browser and clicks the confirmation button.

[1101] Step 7:

[1102] Data collection and safety information provision

[1103] Server: Obtains communication history, Wi-Fi connection information, and GPS data from the telecommunications carrier's API, and confirms the victim's last location and safety.

[1104] Input: Safety confirmation request data, data from telecommunications carrier API

[1105] Output: Safety information provided data

[1106] Specific operation: The server sends a query to the telecommunications company's API and returns the safety information it has obtained, "Taro Tanaka was last heard from in front of Shibuya Station at 15:30," to the user.

[1107] Step 8:

[1108] Registering supply needs

[1109] Victims (users): Enter the supplies they need and the quantity on the site, and click the registration button. For example, enter 10 liters of water and 3 blankets.

[1110] Input: Data on disaster victims' material needs

[1111] Output: Material needs data sent to the server

[1112] Specific actions: The victim enters "10 liters of water, 3 blankets" and clicks the registration button.

[1113] Step 9:

[1114] Store and display supply needs

[1115] Server: Stores registered material needs in a database and makes them available for donors to view.

[1116] Input: Material needs data

[1117] Output: Material needs information stored in a database

[1118] Specific operation: The server stores the material needs data in an SQL database and displays it on a web page.

[1119] Step 10:

[1120] Supporter matching

[1121] Donor (user): Selects available items on the site and expresses their intention to donate. For example, they can view the list of victims and select "Donate three blankets to the Tanaka family."

[1122] Input: Data provided by supporter

[1123] Output: Assistance provision data sent to the server

[1124] Specific action: The supporter selects "Provide three blankets to the Tanaka family" and clicks the "Provide" button.

[1125] Step 11:

[1126] Support arrangements

[1127] Server: Confirms the supporter's selection, notifies the administrator, and instructs the appropriate arrangement procedure.

[1128] Input: Assistance provision data

[1129] Output: Notification data to administrator and assistance arrangement information

[1130] Specific operation: The server checks the support provision data, automatically generates and sends a notification email to the administrator, who then arranges for the delivery of the support supplies.

[1131] (Application example 1)

[1132] 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."

[1133] When a disaster occurs, it is extremely important for logistics facility workers to quickly and accurately collect information and confirm the safety of their employees. However, with current systems, it takes time and effort to collect and analyze information, making it difficult for workers and managers to quickly grasp the actual situation at the disaster site. In addition, there is a lack of systems that can efficiently register the needs for supplies needed in the event of a disaster and efficiently match them with supporters. For these reasons, there is a need for a system that can consistently collect information, confirm the safety of employees, and match them with supporters at logistics facilities during a disaster.

[1134] 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.

[1135] In this invention, the server includes a means for collecting data from multiple information sources, a means for analyzing the collected data and classifying it by time, region, location, and presenter, and a means for providing related information from the classified data based on questions from users. This enables information collection, safety confirmation, supply needs registration, and supporter matching at logistics facilities in the event of a disaster.

[1136] "Source" refers to the source from which data is collected, including social media, online news, and official government announcements.

[1137] "Data analysis" refers to the process of classifying collected data by time, region, location, and presenter, and extracting relevant information.

[1138] "User question" refers to information or questions that a user inputs into the system.

[1139] "Telecommunications company data" refers to data provided by telecommunications companies, including communication history, Wi-Fi connection information, GPS data, and location and safety information.

[1140] "Material needs" refers to information about the supplies and quantities needed by disaster victims.

[1141] "Donor matching" refers to the process of connecting donors with disaster victims based on their material needs.

[1142] A "logistics facility" refers to a location or building used to manage the distribution of goods and materials.

[1143] "Server" refers to the primary computer system that responds to user queries, analyzes data, and provides information.

[1144] "Natural language processing" refers to technologies that automate the analysis and classification of text data, and includes generative AI models.

[1145] "Safety confirmation" refers to the process of confirming the safety status and current location of disaster victims.

[1146] A "generative AI model" refers to a type of artificial intelligence that performs natural language processing based on large amounts of data and generates appropriate responses to questions.

[1147] This invention is a system for efficiently collecting information, confirming the safety of people, registering supply needs, and matching supporters at logistics facilities during disasters. This system functions in cooperation with data from a server, user terminals, and telecommunications companies.

[1148] server

[1149] The server collects and stores data in real time from multiple sources (e.g., social media, online news, official government announcements, etc.). It analyzes the data using a natural language processing (NLP) engine (e.g., Spacy, BERT) and categorizes it by time, region, location, and presenter. The results of this analysis are stored in a database and can be searched and provided as needed. The server also uses a generative AI model (e.g., GPT-3) to generate appropriate answers to user questions and provide information in real time.

[1150] Terminal

[1151] At the logistics facility, workers access the system using their smartphones. A dedicated application is installed on the terminals, allowing them to access information and functions necessary in the event of a disaster. Through the terminals, users can input questions and receive responses from the server. They can also register needed supplies and check the contents of supplies provided by supporters.

[1152] User

[1153] Users of this system include workers and managers at logistics facilities. They use the system to collect information, confirm the safety of people, register needs for supplies, and match supporters during disasters. As a specific example of operation, a user can ask the system, "What is the current situation in XX area?" and receive a response from the server such as, "Traffic restrictions in place. Evacuation shelters are located at XX location."

[1154] Hardware and software used

[1155] Hardware: Smartphone (iOS, Android)

[1156] Software: Flask, Django (backend), MySQL (database), Python (request processing), natural language processing engine (Spacy, BERT), generative AI model (GPT-3)

[1157] Data processing and calculation

[1158] The server continuously retrieves data from social media, online news, and telecommunications company APIs, analyzes the data using a natural language processing engine, and extracts and classifies relevant information. Information stored in a cloud database is analyzed and responded to using a generative AI model to respond to user questions in real time. It also integrates and processes communication history, Wi-Fi connection information, and GPS data to check the safety of logistics facility employees.

[1159] Specific examples (prompt sentence examples)

[1160] When a user asks, "What is the current situation in district X?", the question is sent to the server, which then uses a generative AI model to create an answer based on the latest news and social media posts, such as "Traffic restrictions are in place in district X, and evacuation shelters are located at X location."

[1161] The present invention enables logistics facilities to quickly and efficiently collect and provide information in the event of a disaster, confirm the safety of people, register material needs, and match supporters.

[1162] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1163] Step 1:

[1164] Information Collection and Storage

[1165] Input: Social media, online news, official government announcements, and other sources

[1166] Output: Raw data collected

[1167] The server collects data in real time from social media APIs, news site RSS feeds, and official government announcement sites, and stores the collected raw data in a database.

[1168] Step 2:

[1169] Data analysis and classification

[1170] Input: Raw data collected

[1171] Output: Parsed and classified data

[1172] The server analyzes the collected raw data using a natural language processing (NLP) engine (e.g., Spacy, BERT) and categorizes it by time, region, location, and presenter. The analyzed data is stored in a database and made searchable.

[1173] Step 3:

[1174] Accepting user questions

[1175] Input: User question

[1176] Output: Question

[1177] The terminal provides an interface for users to input questions. The user uses a smartphone to input a question such as "What is the current situation in the X area?" This question is then sent to the server.

[1178] Step 4:

[1179] Question analysis and response generation

[1180] Input: User question

[1181] Output: The generated response

[1182] The server analyzes the question received from the user, searches for relevant information from the database, and uses a generative AI model (e.g., GPT-3) to generate an appropriate response based on the relevant information.

[1183] Step 5:

[1184] Providing a response

[1185] Input: Generated response

[1186] Output: Display the answer to the user

[1187] The server generates a response and sends it to the device, which then displays it on the user's smartphone. For example, if a user asks, "What is the current situation in district X?", the device displays, "Traffic restrictions are in place in district X, and the evacuation shelter is at location X."

[1188] Step 6:

[1189] Confirmation of safety

[1190] Input: User safety confirmation request, name, contact information

[1191] Output: Safety information

[1192] The server obtains information on the last location and safety of disaster victims based on communication history, Wi-Fi connection information, and GPS data provided by the telecommunications company, allowing users to check the safety of their family and colleagues.

[1193] Step 7:

[1194] Registering supply needs

[1195] Input: Information on supply needs from disaster victims (users)

[1196] Output: List of material needs

[1197] The terminal provides an interface where disaster victims can input the supplies and quantities they need, and sends the registered information to a server, which stores the information in a database and makes it available to supporters.

[1198] Step 8:

[1199] Donors' declaration of intent to donate supplies

[1200] Input: Information on supplies provided by supporters (users)

[1201] Output: Notification of matched relief supplies and relief arrangements

[1202] Donors use their terminals to select registered material needs and express their willingness to donate. The server verifies this information and notifies the administrator. The administrator then instructs the donors on how and when to deliver the supplies.

[1203] The above is the processing flow of the "Disaster Information and Support System" at logistics facilities.

[1204] 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.

[1205] This invention is a "disaster information and support system" for smoothly providing information and providing support activities when a disaster occurs. This system collects and organizes information from social media and online news, and provides information in response to user questions. It also utilizes data from telecommunications companies to check the safety of disaster victims, provide location information, and match material needs with supporters. Furthermore, this invention incorporates an emotion engine that recognizes the user's emotions, and can adjust the information provided based on the user's emotions.

[1206] System configuration

[1207] 1. Server:

[1208] The server collects and stores data in real time from multiple sources (e.g., social media, online news, official government announcements, etc.). It then analyzes the data using a natural language processing (NLP) engine and categorizes it by time, region, location, and issuer. The results of this analysis are stored in a database and can be searched and provided as needed. It also uses data from telecommunications companies to confirm the safety of victims and identify their locations.

[1209] 2. Terminal:

[1210] The device is used by users to access the site, search for information, register supplies, and confirm support. Examples of such devices include PCs, smartphones, and tablets.

[1211] 3. User:

[1212] Users include those who provide information (e.g., disaster victims, general users) and those who acquire information (e.g., family members, supporters). Users use the site to check safety and register / confirm supplies.

[1213] 4. Emotion Engine:

[1214] The emotion engine analyzes emotions from text and voice input by the user and adjusts the information provided based on those emotions. For example, if the user is feeling anxious, it will provide more reassuring information.

[1215] Program processing

[1216] 1. Data Collection and Analysis:

[1217] Server: Collects data from specified sources and analyzes it using a natural language processing engine. For example, it collects posts related to specific hashtags or keywords through social media APIs and categorizes these posts by date, time, location, and author.

[1218] Example: The server collects and analyzes social media posts containing the hashtag "disaster name." Through this analysis, the posts are classified as "October 15, 2023, Shibuya Ward, Tokyo, information from individual users."

[1219] 2. Question and Answer:

[1220] User: Enters a question on the site (e.g., "What is the current situation in Shibuya Ward?"). This question is sent to the server.

[1221] Server: Analyzes the question and searches the database for relevant information. Based on the analysis results, the generation AI generates an appropriate answer and provides it to the user. It also uses an emotion engine to recognize the user's emotions and adjust the information provided as needed.

[1222] Example: When a user asks, "What is the current situation in Shibuya Ward?", the server will respond based on the latest news and social media posts with, for example, "Traffic restrictions are in place in Shibuya Ward, and the evacuation shelter is at X Elementary School." If the user asks the question with an anxious expression or tone, the server will adjust the response to something more reassuring, such as, "Many evacuation shelters have now been opened in Shibuya Ward, and there are many places where you can safely evacuate."

[1223] 3. Safety confirmation:

[1224] Server: Obtains communication history, Wi-Fi connection information, and GPS data from the telecommunications company's API, and checks the last location and safety of victims.

[1225] Users: Enter names and contact information on the site to check on the safety of family and loved ones.

[1226] Server: Searches the database based on the input information and provides the relevant safety information to the user. It also adjusts the way the information is provided using an emotion engine.

[1227] Example: When a user checks the safety of "Taro Tanaka," the server responds with information like, "Taro Tanaka was last heard from in front of Shibuya Station at 3:30 PM." If the user seems very worried, the server might add, "Taro Tanaka has been heard from recently and may be in a relatively safe location."

[1228] 4. Registering material needs and matching donors:

[1229] Victims (users): Enter the required supplies and their quantities in the supply registration form on the site and register (e.g., 10 liters of water, 3 blankets).

[1230] Server: Stores the inputted material needs in a database and makes them available for donors to view.

[1231] Donor (user): Access the donation list page on the site and select the items they can donate.

[1232] Server: Confirms the supporter's selection, notifies the administrator, and instructs the appropriate arrangement procedure. It also uses an emotion engine to provide appropriate communication tools.

[1233] Example: A donor views the "List of victims in the Tohoku region" and selects "Provide three blankets to the Tanaka family." After confirmation, the administrator instructs the donor on how and when to deliver the relief supplies. If this is the first time the donor is providing relief, the emotion engine is used to simultaneously provide a message such as, "Thank you for your first donation. We will explain the procedure so that you can feel at ease."

[1234] In this way, the system of the present invention can provide information quickly and appropriately when a disaster occurs, and efficiently support communication between victims and supporters. By incorporating an emotion engine, it becomes possible to provide information and responses according to the user's emotions, realizing support that gives a greater sense of security.

[1235] The processing flow will be explained below.

[1236] Data collection and analysis

[1237] Step 1:

[1238] Server: Periodically sends requests to APIs of social media, online news, and government announcement sites to collect data.

[1239] Step 2:

[1240] Server: Adds collected data to a queue for analysis and passes it to the natural language processing engine.

[1241] Step 3:

[1242] Server: A natural language processing engine analyzes the data and categorizes it by date, time, location, and presenter.

[1243] Step 4:

[1244] Server: The analysis results are stored in a database and indexed for later retrieval.

[1245] Question and Answering

[1246] Step 1:

[1247] User: Enters a question into the site's search box (e.g., "What's the current situation in Shibuya Ward?").

[1248] Step 2:

[1249] Server: Receives questions from users and analyzes the content of the questions using natural language processing.

[1250] Step 3:

[1251] Server: Searches for relevant information from the database and generates appropriate answers using generative AI.

[1252] Step 4:

[1253] Server: Uses an emotion engine to analyze emotions from the user's input and tone.

[1254] Step 5:

[1255] Server: Adjusts the generated answer based on the user's emotions. For example, if the user is feeling anxious, adds reassuring information.

[1256] Step 6:

[1257] Server: Returns the adjusted answer to the user's terminal and displays it to the user.

[1258] Confirmation of safety

[1259] Step 1:

[1260] Server: Periodically obtains communication history, Wi-Fi connection information, and GPS data from the telecommunications company's API.

[1261] Step 2:

[1262] Server: Analyzes the acquired data and stores the victim's last location and safety information in a database.

[1263] Step 3:

[1264] User: Enters name and contact information into the safety confirmation form on the site.

[1265] Step 4:

[1266] Server: Searches the database based on the entered information and identifies the relevant safety information.

[1267] Step 5:

[1268] Server: Sends safety information to the user's device so that the user can check it.

[1269] Step 6:

[1270] Server: Uses the emotion engine to tailor how safety information is provided. If the user is very worried, provide additional reassuring information.

[1271] Registering supply needs and matching supporters

[1272] Step 1:

[1273] Victims (users): Enter the supplies they need and their quantities in the supply registration form on the site (e.g., 10 liters of water, 3 blankets).

[1274] Step 2:

[1275] Server: Stores the input material needs information in a database.

[1276] Step 3:

[1277] Donor (user): Access the donation list page on the site and select the items they can donate.

[1278] Step 4:

[1279] Server: Confirms the supporter's selection and notifies the administrator.

[1280] Step 5:

[1281] Administrator (server): Checks the support details and sends instructions to the supporter for arrangements.

[1282] Step 6:

[1283] Server: Uses the emotion engine to provide appropriate communication to supporters. For example, for supporters providing support for the first time, a message containing instructions on how to provide support will be sent to put them at ease.

[1284] Step 7:

[1285] Supporter (user): Follow instructions, prepare supplies, and provide them to disaster victims.

[1286] In this way, the system of the present invention can provide information quickly and appropriately when a disaster occurs, and efficiently support communication between victims and supporters. By incorporating an emotion engine, it becomes possible to provide information and responses according to the user's emotions, realizing support that gives a greater sense of security.

[1287] Example 2

[1288] 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."

[1289] In the event of a disaster, it is necessary to provide victims, their families, and supporters with fast and accurate information. However, because information is scattered and vast, it is difficult to quickly obtain the necessary information. It is also difficult to smoothly confirm the safety of victims and carry out procedures for providing material support. Furthermore, there is a lack of emotionally sensitive information provided to users who feel excessive stress and anxiety during a disaster. Effective means to solve these problems are desired.

[1290] 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.

[1291] In this invention, the server includes means for collecting data from multiple information sources, means for analyzing the collected data using natural language processing and classifying it by time, region, location, and presenter, means for providing relevant information from the classified data based on questions from users and adjusting the content of the information using an emotion engine, means for identifying the safety and location information of disaster victims using data from communication service providers, and means for matching supporters based on material needs registered on the site and providing appropriate communication to the supporters using the emotion engine.This enables the provision of quick and accurate information, safety confirmation, smooth procedures for material support, and the provision of information that takes emotions into consideration in the event of a disaster.

[1292] "Sources" refer to external data providers from which data is collected, such as social media, online news, and official government announcements.

[1293] "Natural language processing" is a technology that enables computers to understand, analyze, and generate human language.

[1294] An "emotion engine" is a software engine that analyzes emotions from text and voice input by the user and adjusts the information and responses provided based on those emotions.

[1295] "Telecommunications service provider" refers to a company or organization that provides telecommunications services through a telecommunications network.

[1296] "Safety confirmation" refers to the act of collecting and providing information to confirm the safety and current location of disaster victims.

[1297] "Material needs" refers to the types and quantities of supplies and items needed by disaster victims.

[1298] "Supporters" refers to people and organizations whose role is to provide supplies and services to disaster victims during a disaster.

[1299] "Matching" refers to the process of connecting the needs of disaster victims with the resources available to supporters.

[1300] "Data classification" refers to the process of organizing and dividing collected data by different criteria such as time, region, location, and presenter.

[1301] A "database" refers to a system that organizes and stores collected and analyzed data so that it can be searched and retrieved as needed.

[1302] "Global Positioning System Data" refers to data used to measure specific locations on Earth using satellites.

[1303] "Wireless communication network connection information" refers to information about the WiFi network or cell tower to which a mobile device is connected.

[1304] This invention is a "disaster information and support system" for smoothly providing information and carrying out support activities when a disaster occurs. This system collects data from multiple sources, such as social media and online news, and analyzes and classifies it to provide users with appropriate information.

[1305] 1. Data Collection

[1306] Server: The server collects data from sources such as social media, online news, and official government announcements. It collects posts containing specific hashtags or keywords through the APIs of the social media platforms used.

[1307] Example: A server collects all Twitter posts containing the hashtag "Disaster Breaking News" and stores this data.

[1308] 2. Data analysis and classification

[1309] Server: The server analyzes the collected data using natural language processing (NLP) techniques and categorizes the data by time, region, location, and presenter.

[1310] Software used: General NLP engine

[1311] Example: The server analyzes collected Twitter posts and classifies them as "information from an individual user, Shibuya-ku, Tokyo, October 15, 2023."

[1312] 3. Question and Answering

[1313] User: A user types a question into a search box on the site (e.g., "What's the current situation in Shibuya Ward?").

[1314] Server: The server receives the question, searches for relevant information from a database, and responds. Generative AI generates appropriate answers, and an emotion engine is used to tailor the information according to the user's emotions.

[1315] Example: When a user asks, "What is the current situation in Shibuya Ward?", the server responds, "Traffic restrictions are currently in place in Shibuya Ward. An evacuation shelter has been opened at X Elementary School." Furthermore, if the emotion engine detects that the user is anxious, it adds reassuring information, such as, "There are many safe places to evacuate to in Shibuya Ward."

[1316] 4. Safety confirmation

[1317] User: Users enter the names and contact information of family members and acquaintances on the site to check on their safety.

[1318] Server: The server uses the communication service provider's API to obtain communication history and GPS data, and checks the last location and safety information of the victims. It uses an emotion engine to adjust how the information is provided.

[1319] Example: When a user checks the safety of "Taro Tanaka," the server responds with information such as, "Taro Tanaka was last contacted in front of Shibuya Station at 3:30 PM." If the user feels uneasy, the server provides additional reassuring information such as, "Taro Tanaka has been in contact recently and is likely in a safe location."

[1320] 5. Registering supply needs and matching supporters

[1321] Victims (users): Victims enter the supplies they need and their quantities in the site's supply registration form (e.g., "10 liters of water, 3 blankets").

[1322] Server: The entered information is saved in a database and made available for supporters to view.

[1323] Donors (users): Donors access the donation list page on the site and select the items they can donate.

[1324] Server: Confirms the supporter's selection, notifies the administrator, and instructs appropriate arrangements. Uses the emotion engine to provide supporters with appropriate communication tools.

[1325] Example: A donor views the "List of victims in the Tohoku region" and selects "Provide three blankets to the Tanaka family." The server notifies the administrator and instructs them to arrange for delivery. Also, for first-time donors, a message is displayed saying, "Thank you for your first donation. We will explain the donation procedure so you can feel at ease."

[1326] By combining these functions, the system of the present invention can provide prompt and appropriate information in the event of a disaster, confirm the safety of people, facilitate smooth procedures for providing material support, and provide information that takes emotions into consideration.

[1327] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1328] Step 1: Data collection

[1329] Server: The server collects data from multiple sources, such as social media, online news, and official government announcements. Specifically, it uses social media APIs to retrieve posts containing specific hashtags or keywords.

[1330] Input: A specific hashtag or keyword (e.g., "disaster breaking news")

[1331] Output: Collected post data (e.g. Twitter posts)

[1332] Specific operation: The server collects all Twitter posts containing the hashtag "Disaster Breaking News" and stores this data.

[1333] Step 2: Data analysis and classification

[1334] Server: The server analyzes the collected data using a natural language processing engine (e.g., a general NLP engine) and categorizes the data by time, region, location, and presenter. The analyzed data is stored in a database.

[1335] Input: Collected post data (e.g., Twitter posts)

[1336] Output: Classified data (e.g., "Information from an individual user, Shibuya Ward, Tokyo, October 15, 2023")

[1337] Specific operation: The server analyzes the collected Twitter posts and classifies them as "information from an individual user in Shibuya Ward, Tokyo, on October 15, 2023." This classification result is stored in a database.

[1338] Step 3: Question and Answer

[1339] User: A user types a question into a search box on the site (e.g., "What's the current situation in Shibuya Ward?").

[1340] Server: The server receives the question, searches for relevant information from a database, uses a generative AI model to generate an appropriate answer, and uses an emotion engine to tailor the information according to the user's emotions.

[1341] Input: User question (e.g. "What is the current situation in Shibuya Ward?")

[1342] Output: Generated answer (e.g. "Traffic restrictions are in place in Shibuya Ward. An evacuation shelter has been opened at XX Elementary School.")

[1343] Specific operation: The server analyzes the user's question and searches the database for relevant information. The generation AI generates a response such as, "Traffic restrictions are in place in Shibuya Ward. An evacuation shelter has been opened at X-X Elementary School." Furthermore, if the emotion engine detects the user's feelings of anxiety, it adds, "There are many safe places to evacuate to in Shibuya Ward."

[1344] Step 4: Safety confirmation

[1345] User: Users enter the names and contact information of family members and acquaintances on the site to check on their safety.

[1346] Server: The server uses the communication service provider's API to obtain communication history and GPS data, and checks the last location and safety information of the victims. It uses an emotion engine to adjust how the information is provided.

[1347] Input: Names and contact information of family members or acquaintances (e.g., "Taro Tanaka")

[1348] Output: Safety information (e.g. "Taro Tanaka was last heard from in front of Shibuya Station at 15:30")

[1349] Specific operation: Based on the name and contact information of "Taro Tanaka" entered by the user, the server uses the communication service provider's API to obtain communication history and GPS data. This provides information such as "Taro Tanaka was last contacted in front of Shibuya Station at 3:30 PM." For users who feel uneasy, the server provides additional information to reassure them, such as "Taro Tanaka has been contacted recently and is likely in a safe location."

[1350] Step 5: Register your supply needs

[1351] Victims (users): Victims enter the supplies they need and their quantities in the site's supply registration form (e.g., "10 liters of water, 3 blankets").

[1352] Server: The entered information is saved in a database and made available for supporters to view.

[1353] Input: The supplies you need and their quantities (e.g., "10 liters of water, 3 blankets")

[1354] Output: Registered supply information (e.g., "10 liters of water, 3 blankets")

[1355] Specific operation: When a victim registers "10 liters of water, 3 blankets" on the site, the server saves this in the database and allows supporters to proceed and view it.

[1356] Step 6: Supporter Matching

[1357] Donors (users): Donors access the donation list page on the site and select the items they can donate.

[1358] Server: Confirms the supporter's selection, notifies the administrator, and instructs appropriate arrangements. Uses the emotion engine to provide supporters with appropriate communication tools.

[1359] Input: The items that donors can provide (e.g., "3 blankets")

[1360] Output: Instructions for providing assistance (e.g., "Provide three blankets to the Tanaka family")

[1361] Specific operation: A donor views the "List of victims in the Tohoku region" and selects "Provide three blankets to the Tanaka family." The server notifies the administrator and instructs them to arrange for delivery. For first-time donors, the server also displays a message saying, "Thank you for your first donation. We will explain the donation procedure so you can feel at ease."

[1362] (Application example 2)

[1363] 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."

[1364] When a disaster occurs, there is a need for a system that can provide information quickly and appropriately and facilitate smooth communication between victims and supporters. Current systems have issues with obtaining information in real time and providing information that reflects emotions, as well as issues with smoothly confirming the safety of victims and matching supplies. There is a need for a system that can solve these issues and support more effective support activities.

[1365] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data from multiple information sources, means for analyzing the collected data and classifying it by time, region, location, and presenter, means for providing related information from the classified data based on questions from users, means for identifying the safety and location information of disaster victims using data from telecommunications companies, means for matching supporters based on material needs registered on the site, and means for analyzing user emotions and providing information according to the results. This makes it possible to provide information and support activities quickly and appropriately when a disaster occurs.

[1366] "Sources" are the origins of information provided by various digital media and platforms (e.g., social networking services, online news, official government announcements, etc.).

[1367] "Data collection methods" are the mechanisms and techniques used to obtain necessary data from various sources and incorporate it into the system.

[1368] "Data analysis tools" are techniques and methods for analyzing collected data and categorizing it based on specific criteria (e.g., time, region, location, presenter, etc.).

[1369] The "user question answering means" is a system or function for accepting questions from users and searching for and providing related information based on those questions.

[1370] "Safety confirmation means" refers to technology or methods for confirming the safety and location of disaster victims using data from telecommunications companies (e.g., communication history, wireless connection information, global positioning system data).

[1371] "Supply matching tools" are systems and functions that connect the supply needs registered on the site with supporters, enabling efficient distribution of supplies.

[1372] "Emotion analysis means" refers to a technique or method for analyzing emotions from user input (e.g., text or voice) and adjusting the information provided based on the results.

[1373] "Natural language processing" is a technical field that uses computers to understand, interpret, and manipulate human language, and is particularly used for analyzing text data.

[1374] "Global Positioning System data" is data used to obtain highly accurate positional information of any point on Earth using satellites.

[1375] Specific embodiments for carrying out the present invention will be described below.

[1376] This system consists of three components: a server, terminals, and users. The server plays a central role in collecting data from various information sources and analyzing and classifying it. The terminals are devices that users use to obtain information, check the safety of others, register supplies, and confirm support, and users are the entities that actually use these functions.

[1377] First, the server collects data from multiple sources, such as social networking services (SNS), online news, and official government announcements. The server obtains data from these sources in real time, analyzes it using a natural language processing (NLP) engine (described below), and classifies it by time, region, location, and issuer.

[1378] The NLP engine uses the open source TextBlob and generative AI models using deep learning (such as GPT). Through this analysis, for example, a social media post containing the hashtag "disaster name" is classified as "information from an individual user, Tokyo, October 15, 2023."

[1379] When a user inputs a question through their device, the question is sent to the server. For example, if the user inputs the question, "What is the current situation in Shibuya Ward?", the server searches for relevant information from the database, and the generative AI generates the optimal answer based on the analysis results and provides it to the user. An example of a prompt sentence is, "What is the current situation in Shibuya Ward?" Furthermore, an emotion engine is used to analyze the user's emotions and adjust the way information is presented as necessary. If the user asks a question with an anxious expression or tone, the content is changed to one that gives a sense of security.

[1380] For safety checks, the server obtains communication history, wireless connection information, and Global Positioning System (GPS) data from the telecommunications company's API. For example, when a user enters the name and contact information of "Taro Tanaka" to check the user's safety, the server searches the database and returns information such as "Taro Tanaka was last contacted in front of Shibuya Station at 3:30 PM." If the user appears very worried, the emotion engine provides additional information such as "He may be in a relatively safe location."

[1381] To match supplies, disaster victims register the supplies they need and the quantities they require on the site. For example, they might enter "10 liters of water, 3 blankets." The server stores this information in a database and makes it available for donors to view. When a donor selects supplies available on the site, the server notifies the administrator and instructs them on the appropriate procedures for arranging supplies. Using an emotion engine, the system also provides reassuring messages when donors are donating for the first time.

[1382] In this way, the server and terminals work together to provide prompt and appropriate information and support activities in the event of a disaster. Examples of prompt sentences introduced include user questions such as "What is the current situation in Shibuya Ward?" and "I want to check on the safety of my daughter."

[1383] The above is a specific embodiment for carrying out the present invention, and this system will improve the efficiency of information provision and support activities in the event of a disaster.

[1384] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1385] Step 1:

[1386] The server collects data from multiple sources, specifically social networking services (SNS), online news, official government announcements, etc., and obtains data in real time through APIs. Data from these sources is used as input, and the raw data is stored on the server as output.

[1387] Step 2:

[1388] The server analyzes the collected data and categorizes it by time, region, location, and presenter. Specifically, it processes the data with a natural language processing engine using TextBlob and generative AI models (e.g., GPT). It uses the collected raw data as input and provides data categorized by time, region, location, and presenter as output.

[1389] Step 3:

[1390] The user inputs a question through a terminal. For example, they input "What is the current situation in Shibuya Ward?" on the application screen of a smartphone or PC. The user's question text is used as input, and the question content is sent to the server as output.

[1391] Step 4:

[1392] The server searches for relevant information from the database based on the user's question, and the generative AI generates an appropriate answer based on the analysis results. The user's question and classified data are used as input, and the generated answer text is obtained as output.

[1393] Step 5:

[1394] The server uses an emotion engine to analyze the user's emotions and adjust the information provided. Specifically, it analyzes the user's input text using TextBlob or other emotion analysis tools. The input is the user's question text, and the output is the user's emotion score. For example, if the user asks a question with an anxious expression or tone, the server adjusts the answer to make it more reassuring.

[1395] Step 6:

[1396] The server obtains communication history, wireless connection information, and Global Positioning System (GPS) data from the telecommunications company's API and checks the safety of disaster victims. Location information data from the telecommunications company is used as input, and information on the safety of disaster victims is obtained as output. This provides information such as, "Taro Tanaka was last heard from in front of Shibuya Station at 3:30 PM."

[1397] Step 7:

[1398] Users register information about required supplies through their terminals. For example, they input specific needs such as "10 liters of water, 3 blankets." The input is the information about the needs of disaster victims, and the output is stored on the server.

[1399] Step 8:

[1400] The server matches supporters based on the material needs registered on the site. Specifically, it compares the information on the materials that can be provided selected by the supporter with the information on the needs of the disaster victims to make the optimal match. The input is the information on the material needs of the disaster victims and the information on the materials that can be provided by the supporter, and the matching results are obtained as the output.

[1401] The above is the specific processing flow of this system's program. At each step, the necessary data is input, specific data processing and data calculations are performed, and ultimately useful information and support is provided to the user.

[1402] 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.

[1403] 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.

[1404] 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.

[1405] [Fourth embodiment]

[1406] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1407] 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.

[1408] 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).

[1409] 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.

[1410] 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.

[1411] 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).

[1412] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1413] 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.

[1414] 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.

[1415] 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.

[1416] 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.

[1417] 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.

[1418] 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."

[1419] This invention is a "disaster information and support system" for smoothly providing information and carrying out support activities when a disaster occurs. This system collects and organizes information from social media and online news, and provides information in response to user questions. It also utilizes data from telecommunications companies to check the safety and location of disaster victims, and has the function of matching supply needs with supporters.

[1420] System configuration

[1421] 1. Server:

[1422] The server collects and stores data in real time from multiple sources (e.g., social media, online news, official government announcements, etc.). It then analyzes the data using a natural language processing (NLP) engine and categorizes it by time, region, location, and presenter. The results of this analysis are stored in a database and can be searched and provided as needed.

[1423] 2. Terminal:

[1424] The device is used by users to access the site, search for information, register supplies, and confirm support. Examples of such devices include PCs, smartphones, and tablets.

[1425] 3. User:

[1426] Users include those who provide information (e.g., disaster victims, general users) and those who acquire information (e.g., family members, supporters). Users use the site to check safety and register / confirm supplies.

[1427] Program processing

[1428] 1. Data Collection and Analysis:

[1429] Server: Collects data from specified sources and analyzes it using a natural language processing engine. For example, it collects posts related to specific hashtags or keywords through social media APIs and categorizes these posts by date, time, location, and author.

[1430] Example: The server collects and analyzes social media posts containing the hashtag "disaster name." Through this analysis, the posts are classified as "October 15, 2023, Shibuya Ward, Tokyo, information from individual users."

[1431] 2. Question and Answer:

[1432] User: Enters a question on the site (e.g., "What is the current situation in Shibuya Ward?"). This question is sent to the server.

[1433] Server: Analyzes the question and searches the database for relevant information. Based on the analysis results, the generation AI generates an appropriate answer and provides it to the user.

[1434] Example: When a user asks, "What is the current situation in Shibuya Ward?", the server will respond based on the latest news and social media posts with something like, "Traffic restrictions are in place in Shibuya Ward, and the evacuation shelter is at XX Elementary School."

[1435] 3. Safety confirmation:

[1436] Server: Obtains communication history, Wi-Fi connection information, and GPS data from the telecommunications company's API, and checks the last location and safety of victims.

[1437] Users: Enter names and contact information on the site to check on the safety of family and loved ones.

[1438] Server: Based on the input information, searches for communication data and provides the user with the relevant safety information.

[1439] Example: When a user checks the safety of "Taro Tanaka," the server responds with information such as "Taro Tanaka was last contacted in front of Shibuya Station at 15:30."

[1440] 4. Registering material needs and matching donors:

[1441] Victims (users): Enter and register the supplies they need and their quantities on the site (for example, 10 liters of water, 3 blankets).

[1442] Server: Stores registered material needs in a database and makes them available for donors to view.

[1443] Donors (users): Select the supplies they can donate on the site and express their intention to donate.

[1444] Server: Confirms the supporter's selection, notifies the administrator, and instructs the appropriate arrangement procedure.

[1445] Example: A donor views the "List of victims in the Tohoku region" and selects "Provide three blankets to the Tanaka family." After confirmation, the administrator instructs the donor on how and when to deliver the relief supplies.

[1446] In this way, the system of the present invention can provide information quickly and appropriately when a disaster occurs, and efficiently support communication between victims and supporters.

[1447] The processing flow will be explained below.

[1448] Data collection and analysis

[1449] Step 1:

[1450] Server: Periodically sends requests to APIs of social media, online news, and government announcement sites to collect data.

[1451] Step 2:

[1452] Server: Adds collected data to a queue for analysis and passes it to the natural language processing engine.

[1453] Step 3:

[1454] Server: A natural language processing engine analyzes the data and categorizes it by date, time, location, and presenter.

[1455] Step 4:

[1456] Server: The analysis results are stored in a database and indexed for later retrieval.

[1457] Question and Answering

[1458] Step 1:

[1459] User: Enters a question into the site's search box (e.g., "What's the current situation in Shibuya Ward?").

[1460] Step 2:

[1461] Server: Receives questions from users and analyzes the content of the questions using natural language processing.

[1462] Step 3:

[1463] Server: Searches for relevant information from the database and generates appropriate answers using generative AI.

[1464] Step 4:

[1465] Server: Returns the answer to the user's terminal and displays it to the user.

[1466] Confirmation of safety

[1467] Step 1:

[1468] Server: Periodically obtains communication history, Wi-Fi connection information, and GPS data from the telecommunications company's API.

[1469] Step 2:

[1470] Server: Analyzes the acquired data and stores the victim's last location and safety information in a database.

[1471] Step 3:

[1472] User: Enters name and contact information into the safety confirmation form on the site.

[1473] Step 4:

[1474] Server: Searches the database based on the entered information and identifies the relevant safety information.

[1475] Step 5:

[1476] Server: Sends safety information to the user's device so that the user can check it.

[1477] Registering supply needs and matching supporters

[1478] Step 1:

[1479] Victims (users): Enter the supplies they need and their quantities in the supply registration form on the site (e.g., 10 liters of water, 3 blankets).

[1480] Step 2:

[1481] Server: Stores the input material needs information in a database.

[1482] Step 3:

[1483] Donor (user): Access the donation list page on the site and select the items they can donate.

[1484] Step 4:

[1485] Server: Confirms the supporter's selection and notifies the administrator.

[1486] Step 5:

[1487] Administrator (server): Checks the support details and sends instructions to the supporter for arrangements.

[1488] Step 6:

[1489] Supporter (user): Follow instructions, prepare supplies, and provide them to disaster victims.

[1490] The above is a specific processing flow for implementing the present invention. This system supports communication between disaster victims and supporters quickly and efficiently, and ensures the delivery of necessary information and supplies.

[1491] Example 1

[1492] 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."

[1493] When a disaster occurs, it is necessary to quickly and accurately grasp the damage situation, confirm the safety of victims, and provide supplies effectively. However, with conventional systems, the series of processes of information collection and analysis, question and answering, safety confirmation, and supply provision were fragmented, making efficient operation difficult. In addition, a lack of real-time information provision using generative AI models made it difficult to respond quickly.

[1494] 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.

[1495] In this invention, the server includes a means for collecting data from multiple information sources, a means for analyzing the collected data and classifying it by time, region, location, and presenter, a means for inputting user questions as prompts to a generative AI model and generating responses, a means for identifying the safety and location information of disaster victims using data from telecommunications carriers, and a means for matching supporters based on the material needs registered on the site. This enables the prompt and accurate provision of information in the event of a disaster and the smooth implementation of disaster victim support activities.

[1496] "Data collection tools" are tools for extracting and capturing data from multiple sources.

[1497] "Data analysis means" refers to means for analyzing collected data and classifying it based on specific criteria.

[1498] A "generative AI model" is a system that uses artificial intelligence technology to automatically generate responses based on input prompts.

[1499] A "prompt" is a question or instruction sentence that is input to a generative AI model.

[1500] "Telecommunications carrier data" refers to various data provided by companies that provide telecommunications services, such as communication history, wireless LAN connection information, and global positioning system data.

[1501] "Safety confirmation means" refers to a method of using telecommunications carrier data to determine the location of victims and whether they are safe.

[1502] The "material needs registration means" is a means for disaster victims to input and register the materials and quantities they need on the site.

[1503] The "supporter matching means" is a means for selecting and matching supporters based on the material needs registered on the site.

[1504] A "user question answering means" is a means for analyzing questions from users and generating and providing appropriate responses using a generative AI model.

[1505] "Natural language processing" is the technology that enables computers to understand, analyze, and generate human language.

[1506] This invention relates to a "disaster information and support system" for smoothly providing information and providing support activities when a disaster occurs. This system collects and analyzes data from multiple sources and provides information in response to user inquiries. It also utilizes data from telecommunications carriers to provide information on the safety and location of disaster victims, and has the function of matching relief supplies with supporters.

[1507] composition

[1508] 1. Server:

[1509] The server collects data in real time from multiple sources, such as social media, online news, and official government announcements, including social media APIs (e.g., Twitter API) and RSS feeds from news sites.

[1510] The collected data is analyzed using natural language processing (NLP) engines (e.g., spaCy, NLTK) that use programming languages ​​and libraries such as Python and TensorFlow. After analysis, the data is categorized by time, region, location, and presenter and stored in an SQL database.

[1511] 2. Terminal:

[1512] Terminals are devices used by users to search for information, register supplies, and confirm assistance. These include computers, smartphones, and tablets.

[1513] 3. User:

[1514] Users include both information providers (disaster victims, general users) and information recipients (family members, supporters). Users enter questions through a website form and receive answers generated by the server using a generative AI model (e.g., OpenAI GPT-3).

[1515] System operation example

[1516] Data collection and analysis

[1517] The server uses the social networking service's API to collect posts containing the hashtag "disaster name." For example, the server sends a query to the Twitter API to retrieve related posts. The collected posts are analyzed using a natural language processing engine and classified into categories such as "October 15, 2023, Shibuya Ward, Tokyo, information from individual users."

[1518] Question and Answering

[1519] A user enters "What is the current situation in Shibuya Ward?" into a form on the website and sends the question to the server. The server analyzes the question and searches for relevant information from a database. The prompt "What is the current situation in Shibuya Ward?" is input into the generative AI model, and the generated answer "Traffic restrictions are in place in Shibuya Ward, and the evacuation shelter is XX Elementary School" is provided to the user.

[1520] Confirmation of safety

[1521] The user enters the name and contact information of a family member and requests a safety check on the site. For example, the user enters the name "Taro Tanaka" and clicks the confirmation button. The server retrieves communication history, WiFi connection information, and GPS data from the carrier's API, and responds to the user with information such as "Taro Tanaka was last contacted in front of Shibuya Station at 3:30 PM."

[1522] Registering supply needs and matching supporters

[1523] Victims (users) register the supplies they need and the quantities they require on the site. For example, they enter 10 liters of water and three blankets. The server stores this information in a database and makes it available for donors to view. Donors (users) select the supplies they can donate and express their willingness to donate. For example, a donor selects "provide three blankets to the Tanaka family." The server confirms the donor's selection, notifies the administrator, and instructs them on the appropriate procedures.

[1524] In this way, it will be possible to provide quick and accurate information and smoothly carry out relief activities when a disaster occurs.

[1525] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1526] Step 1:

[1527] Data collection and storage

[1528] Server: Collects data from multiple sources (social media, online news, official government announcements, etc.). Specifically, the server sends queries to social media APIs (e.g., Twitter API) to retrieve posts related to specific hashtags or keywords. Since the retrieved data is unorganized as is, all data is first stored in temporary storage.

[1529] Input: Specific hashtags or keywords

[1530] Output: Unorganized data (social media posts, news articles, etc.)

[1531] Step 2:

[1532] Data analysis and classification

[1533] Server: The data stored in temporary storage is analyzed using a natural language processing (NLP) engine. Python, TensorFlow, and NLP libraries (e.g., spaCy, NLTK) are used here. The analyzed data is categorized by time, region, location, and presenter. The categorized data is then stored in an SQL database.

[1534] Input: Unorganized data (social media posts, news articles, etc.)

[1535] Output: Categorised data (organised by time, region, location and presenter)

[1536] Specific operation: The NLP engine analyzes the collected social media posts and classifies them as "information from an individual user, Shibuya-ku, Tokyo, October 15, 2023."

[1537] Step 3:

[1538] Receiving questions from users

[1539] User: Enters a question into the input form on the site and clicks the submit button. For example, "What is the current situation in Shibuya Ward?" This question is sent to the server.

[1540] Input: User question (e.g. "What is the current situation in Shibuya Ward?")

[1541] Output: The question data sent to the server

[1542] Specific operation: The user types "What is the current situation in Shibuya Ward?" in the browser and clicks the submit button.

[1543] Step 4:

[1544] Question analysis and answer generation

[1545] Server: Analyzes the received question using a natural language processing engine, searches for relevant information in a database, and generates prompts using a generative AI model (e.g., OpenAI GPT-3) to generate appropriate answers.

[1546] Input: User question data

[1547] Output: Response data from the generative AI model

[1548] Specific operation: When the server sends the prompt message "What is the current situation in Shibuya Ward?" to the generation AI, the generation AI model generates a response saying "Traffic restrictions are in place in Shibuya Ward, and the evacuation shelter is XX Elementary School."

[1549] Step 5:

[1550] Response provision

[1551] Server: Sends data to the terminal to provide the generated response to the user.

[1552] Input: Response data from a generative AI model

[1553] Output: Response data sent to the user device

[1554] Specific operation: The server generates a response, "Traffic restrictions are in place in Shibuya Ward, and the evacuation shelter is XX Elementary School," and sends it to the user.

[1555] Step 6:

[1556] Acceptance of safety confirmation requests

[1557] User: Enter the name and contact information of a family member or close friend into a form on the site and click the confirm button. For example, enter "Taro Tanaka."

[1558] Input: User-entered data (name and contact information)

[1559] Output: Safety confirmation request data sent to the server

[1560] Specific operation: The user enters "Taro Tanaka" in the browser and clicks the confirmation button.

[1561] Step 7:

[1562] Data collection and safety information provision

[1563] Server: Obtains communication history, Wi-Fi connection information, and GPS data from the telecommunications carrier's API, and confirms the victim's last location and safety.

[1564] Input: Safety confirmation request data, data from telecommunications carrier API

[1565] Output: Safety information provided data

[1566] Specific operation: The server sends a query to the telecommunications company's API and returns the safety information it has obtained, "Taro Tanaka was last heard from in front of Shibuya Station at 15:30," to the user.

[1567] Step 8:

[1568] Registering supply needs

[1569] Victims (users): Enter the supplies they need and the quantity on the site, and click the registration button. For example, enter 10 liters of water and 3 blankets.

[1570] Input: Data on disaster victims' material needs

[1571] Output: Material needs data sent to the server

[1572] Specific actions: The victim enters "10 liters of water, 3 blankets" and clicks the registration button.

[1573] Step 9:

[1574] Store and display supply needs

[1575] Server: Stores registered material needs in a database and makes them available for donors to view.

[1576] Input: Material needs data

[1577] Output: Material needs information stored in a database

[1578] Specific operation: The server stores the material needs data in an SQL database and displays it on a web page.

[1579] Step 10:

[1580] Supporter matching

[1581] Donor (user): Selects available items on the site and expresses their intention to donate. For example, they can view the list of victims and select "Donate three blankets to the Tanaka family."

[1582] Input: Data provided by supporter

[1583] Output: Assistance provision data sent to the server

[1584] Specific action: The supporter selects "Provide three blankets to the Tanaka family" and clicks the "Provide" button.

[1585] Step 11:

[1586] Support arrangements

[1587] Server: Confirms the supporter's selection, notifies the administrator, and instructs the appropriate arrangement procedure.

[1588] Input: Assistance provision data

[1589] Output: Notification data to administrator and assistance arrangement information

[1590] Specific operation: The server checks the support provision data, automatically generates and sends a notification email to the administrator, who then arranges for the delivery of the support supplies.

[1591] (Application example 1)

[1592] 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."

[1593] When a disaster occurs, it is extremely important for logistics facility workers to quickly and accurately collect information and confirm the safety of their employees. However, with current systems, it takes time and effort to collect and analyze information, making it difficult for workers and managers to quickly grasp the actual situation at the disaster site. In addition, there is a lack of systems that can efficiently register the needs for supplies needed in the event of a disaster and efficiently match them with supporters. For these reasons, there is a need for a system that can consistently collect information, confirm the safety of employees, and match them with supporters at logistics facilities during a disaster.

[1594] 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.

[1595] In this invention, the server includes a means for collecting data from multiple information sources, a means for analyzing the collected data and classifying it by time, region, location, and presenter, and a means for providing related information from the classified data based on questions from users. This enables information collection, safety confirmation, supply needs registration, and supporter matching at logistics facilities in the event of a disaster.

[1596] "Source" refers to the source from which data is collected, including social media, online news, and official government announcements.

[1597] "Data analysis" refers to the process of classifying collected data by time, region, location, and presenter, and extracting relevant information.

[1598] "User question" refers to information or questions that a user inputs into the system.

[1599] "Telecommunications company data" refers to data provided by telecommunications companies, including communication history, Wi-Fi connection information, GPS data, and location and safety information.

[1600] "Material needs" refers to information about the supplies and quantities needed by disaster victims.

[1601] "Donor matching" refers to the process of connecting donors with disaster victims based on their material needs.

[1602] A "logistics facility" refers to a location or building used to manage the distribution of goods and materials.

[1603] "Server" refers to the primary computer system that responds to user queries, analyzes data, and provides information.

[1604] "Natural language processing" refers to technologies that automate the analysis and classification of text data, and includes generative AI models.

[1605] "Safety confirmation" refers to the process of confirming the safety status and current location of disaster victims.

[1606] A "generative AI model" refers to a type of artificial intelligence that performs natural language processing based on large amounts of data and generates appropriate responses to questions.

[1607] This invention is a system for efficiently collecting information, confirming the safety of people, registering supply needs, and matching supporters at logistics facilities during disasters. This system functions in cooperation with data from a server, user terminals, and telecommunications companies.

[1608] server

[1609] The server collects and stores data in real time from multiple sources (e.g., social media, online news, official government announcements, etc.). It analyzes the data using a natural language processing (NLP) engine (e.g., Spacy, BERT) and categorizes it by time, region, location, and presenter. The results of this analysis are stored in a database and can be searched and provided as needed. The server also uses a generative AI model (e.g., GPT-3) to generate appropriate answers to user questions and provide information in real time.

[1610] Terminal

[1611] At the logistics facility, workers access the system using their smartphones. A dedicated application is installed on the terminals, allowing them to access information and functions necessary in the event of a disaster. Through the terminals, users can input questions and receive responses from the server. They can also register needed supplies and check the contents of supplies provided by supporters.

[1612] User

[1613] Users of this system include workers and managers at logistics facilities. They use the system to collect information, confirm the safety of people, register needs for supplies, and match supporters during disasters. As a specific example of operation, a user can ask the system, "What is the current situation in XX area?" and receive a response from the server such as, "Traffic restrictions in place. Evacuation shelters are located at XX location."

[1614] Hardware and software used

[1615] Hardware: Smartphone (iOS, Android)

[1616] Software: Flask, Django (backend), MySQL (database), Python (request processing), natural language processing engine (Spacy, BERT), generative AI model (GPT-3)

[1617] Data processing and calculation

[1618] The server continuously retrieves data from social media, online news, and telecommunications company APIs, analyzes the data using a natural language processing engine, and extracts and classifies relevant information. Information stored in a cloud database is analyzed and responded to using a generative AI model to respond to user questions in real time. It also integrates and processes communication history, Wi-Fi connection information, and GPS data to check the safety of logistics facility employees.

[1619] Specific examples (prompt sentence examples)

[1620] When a user asks, "What is the current situation in district X?", the question is sent to the server, which then uses a generative AI model to create an answer based on the latest news and social media posts, such as "Traffic restrictions are in place in district X, and evacuation shelters are located at X location."

[1621] The present invention enables logistics facilities to quickly and efficiently collect and provide information in the event of a disaster, confirm the safety of people, register material needs, and match supporters.

[1622] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1623] Step 1:

[1624] Information Collection and Storage

[1625] Input: Social media, online news, official government announcements, and other sources

[1626] Output: Raw data collected

[1627] The server collects data in real time from social media APIs, news site RSS feeds, and official government announcement sites, and stores the collected raw data in a database.

[1628] Step 2:

[1629] Data analysis and classification

[1630] Input: Raw data collected

[1631] Output: Parsed and classified data

[1632] The server analyzes the collected raw data using a natural language processing (NLP) engine (e.g., Spacy, BERT) and categorizes it by time, region, location, and presenter. The analyzed data is stored in a database and made searchable.

[1633] Step 3:

[1634] Accepting user questions

[1635] Input: User question

[1636] Output: Question

[1637] The terminal provides an interface for users to input questions. The user uses a smartphone to input a question such as "What is the current situation in the X area?" This question is then sent to the server.

[1638] Step 4:

[1639] Question analysis and response generation

[1640] Input: User question

[1641] Output: The generated response

[1642] The server analyzes the question received from the user, searches for relevant information from the database, and uses a generative AI model (e.g., GPT-3) to generate an appropriate response based on the relevant information.

[1643] Step 5:

[1644] Providing a response

[1645] Input: Generated response

[1646] Output: Display the answer to the user

[1647] The server generates a response and sends it to the device, which then displays it on the user's smartphone. For example, if a user asks, "What is the current situation in district X?", the device displays, "Traffic restrictions are in place in district X, and the evacuation shelter is at location X."

[1648] Step 6:

[1649] Confirmation of safety

[1650] Input: User safety confirmation request, name, contact information

[1651] Output: Safety information

[1652] The server obtains information on the last location and safety of disaster victims based on communication history, Wi-Fi connection information, and GPS data provided by the telecommunications company, allowing users to check the safety of their family and colleagues.

[1653] Step 7:

[1654] Registering supply needs

[1655] Input: Information on supply needs from disaster victims (users)

[1656] Output: List of material needs

[1657] The terminal provides an interface where disaster victims can input the supplies and quantities they need, and sends the registered information to a server, which stores the information in a database and makes it available for supporters to view.

[1658] Step 8:

[1659] Donors' declaration of intent to donate supplies

[1660] Input: Information on supplies provided by supporters (users)

[1661] Output: Notification of matched relief supplies and relief arrangements

[1662] Donors use their terminals to select registered material needs and express their willingness to donate. The server verifies this information and notifies the administrator. The administrator then instructs the donors on how and when to deliver the supplies.

[1663] The above is the processing flow of the "Disaster Information and Support System" at logistics facilities.

[1664] 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.

[1665] This invention is a "disaster information and support system" for smoothly providing information and providing support activities when a disaster occurs. This system collects and organizes information from social media and online news, and provides information in response to user questions. It also utilizes data from telecommunications companies to check the safety of disaster victims, provide location information, and match material needs with supporters. Furthermore, this invention incorporates an emotion engine that recognizes the user's emotions, and can adjust the information provided based on the user's emotions.

[1666] System configuration

[1667] 1. Server:

[1668] The server collects and stores data in real time from multiple sources (e.g., social media, online news, official government announcements, etc.). It then analyzes the data using a natural language processing (NLP) engine and categorizes it by time, region, location, and issuer. The results of this analysis are stored in a database and can be searched and provided as needed. It also uses data from telecommunications companies to confirm the safety of victims and identify their locations.

[1669] 2. Terminal:

[1670] The device is used by users to access the site, search for information, register supplies, and confirm support. Examples of such devices include PCs, smartphones, and tablets.

[1671] 3. User:

[1672] Users include those who provide information (e.g., disaster victims, general users) and those who acquire information (e.g., family members, supporters). Users use the site to check safety and register / confirm supplies.

[1673] 4. Emotion Engine:

[1674] The emotion engine analyzes emotions from text and voice input by the user and adjusts the information provided based on those emotions. For example, if the user is feeling anxious, it will provide more reassuring information.

[1675] Program processing

[1676] 1. Data Collection and Analysis:

[1677] Server: Collects data from specified sources and analyzes it using a natural language processing engine. For example, it collects posts related to specific hashtags or keywords through social media APIs and categorizes these posts by date, time, location, and author.

[1678] Example: The server collects and analyzes social media posts containing the hashtag "disaster name." Through this analysis, the posts are classified as "October 15, 2023, Shibuya Ward, Tokyo, information from individual users."

[1679] 2. Question and Answer:

[1680] User: Enters a question on the site (e.g., "What is the current situation in Shibuya Ward?"). This question is sent to the server.

[1681] Server: Analyzes the question and searches the database for relevant information. Based on the analysis results, the generation AI generates an appropriate answer and provides it to the user. It also uses an emotion engine to recognize the user's emotions and adjust the information provided as needed.

[1682] Example: When a user asks, "What is the current situation in Shibuya Ward?", the server will respond based on the latest news and social media posts with, for example, "Traffic restrictions are in place in Shibuya Ward, and the evacuation shelter is at X Elementary School." If the user asks the question with an anxious expression or tone, the server will adjust the response to something more reassuring, such as, "Many evacuation shelters have now been opened in Shibuya Ward, and there are many places where you can safely evacuate."

[1683] 3. Safety confirmation:

[1684] Server: Obtains communication history, Wi-Fi connection information, and GPS data from the telecommunications company's API, and checks the last location and safety of victims.

[1685] Users: Enter names and contact information on the site to check on the safety of family and loved ones.

[1686] Server: Searches the database based on the input information and provides the relevant safety information to the user. It also adjusts the way the information is provided using an emotion engine.

[1687] Example: When a user checks the safety of "Taro Tanaka," the server responds with information like, "Taro Tanaka was last heard from in front of Shibuya Station at 3:30 PM." If the user seems very worried, the server might add, "Taro Tanaka has been heard from recently and may be in a relatively safe location."

[1688] 4. Registering material needs and matching donors:

[1689] Victims (users): Enter the required supplies and their quantities in the supply registration form on the site and register (e.g., 10 liters of water, 3 blankets).

[1690] Server: Stores the inputted material needs in a database and makes them available for donors to view.

[1691] Donor (user): Access the donation list page on the site and select the items they can donate.

[1692] Server: Confirms the supporter's selection, notifies the administrator, and instructs the appropriate arrangement procedure. It also uses an emotion engine to provide appropriate communication tools.

[1693] Example: A donor views the "List of victims in the Tohoku region" and selects "Provide three blankets to the Tanaka family." After confirmation, the administrator instructs the donor on how and when to deliver the relief supplies. If this is the first time the donor is providing relief, the emotion engine is used to simultaneously provide a message such as, "Thank you for your first donation. We will explain the procedure so that you can feel at ease."

[1694] In this way, the system of the present invention can provide information quickly and appropriately when a disaster occurs, and efficiently support communication between victims and supporters. By incorporating an emotion engine, it becomes possible to provide information and responses according to the user's emotions, realizing support that gives a greater sense of security.

[1695] The processing flow will be explained below.

[1696] Data collection and analysis

[1697] Step 1:

[1698] Server: Periodically sends requests to APIs of social media, online news, and government announcement sites to collect data.

[1699] Step 2:

[1700] Server: Adds collected data to a queue for analysis and passes it to the natural language processing engine.

[1701] Step 3:

[1702] Server: A natural language processing engine analyzes the data and categorizes it by date, time, location, and presenter.

[1703] Step 4:

[1704] Server: The analysis results are stored in a database and indexed for later retrieval.

[1705] Question and Answering

[1706] Step 1:

[1707] User: Enters a question into the site's search box (e.g., "What's the current situation in Shibuya Ward?").

[1708] Step 2:

[1709] Server: Receives questions from users and analyzes the content of the questions using natural language processing.

[1710] Step 3:

[1711] Server: Searches for relevant information from the database and generates appropriate answers using generative AI.

[1712] Step 4:

[1713] Server: Uses an emotion engine to analyze emotions from the user's input and tone.

[1714] Step 5:

[1715] Server: Adjusts the generated answer based on the user's emotions. For example, if the user is feeling anxious, adds reassuring information.

[1716] Step 6:

[1717] Server: Returns the adjusted answer to the user's terminal and displays it to the user.

[1718] Confirmation of safety

[1719] Step 1:

[1720] Server: Periodically obtains communication history, Wi-Fi connection information, and GPS data from the telecommunications company's API.

[1721] Step 2:

[1722] Server: Analyzes the acquired data and stores the victim's last location and safety information in a database.

[1723] Step 3:

[1724] User: Enters name and contact information into the safety confirmation form on the site.

[1725] Step 4:

[1726] Server: Searches the database based on the entered information and identifies the relevant safety information.

[1727] Step 5:

[1728] Server: Sends safety information to the user's device so that the user can check it.

[1729] Step 6:

[1730] Server: Uses the emotion engine to tailor how safety information is provided. If the user is very worried, provide additional reassuring information.

[1731] Registering supply needs and matching supporters

[1732] Step 1:

[1733] Victims (users): Enter the supplies they need and their quantities in the supply registration form on the site (e.g., 10 liters of water, 3 blankets).

[1734] Step 2:

[1735] Server: Stores the input material needs information in a database.

[1736] Step 3:

[1737] Donor (user): Access the donation list page on the site and select the items they can donate.

[1738] Step 4:

[1739] Server: Confirms the supporter's selection and notifies the administrator.

[1740] Step 5:

[1741] Administrator (server): Checks the support details and sends instructions to the supporter for arrangements.

[1742] Step 6:

[1743] Server: Uses the emotion engine to provide appropriate communication to supporters. For example, for supporters providing support for the first time, a message containing instructions on how to provide support will be sent to put them at ease.

[1744] Step 7:

[1745] Supporter (user): Follow instructions, prepare supplies, and provide them to disaster victims.

[1746] In this way, the system of the present invention can provide information quickly and appropriately when a disaster occurs, and efficiently support communication between victims and supporters. By incorporating an emotion engine, it becomes possible to provide information and responses according to the user's emotions, realizing support that gives a greater sense of security.

[1747] Example 2

[1748] 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."

[1749] In the event of a disaster, it is necessary to provide victims, their families, and supporters with fast and accurate information. However, because information is scattered and vast, it is difficult to quickly obtain the necessary information. It is also difficult to smoothly confirm the safety of victims and carry out procedures for providing material support. Furthermore, there is a lack of emotionally sensitive information provided to users who feel excessive stress and anxiety during a disaster. Effective means to solve these problems are desired.

[1750] 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.

[1751] In this invention, the server includes means for collecting data from multiple information sources, means for analyzing the collected data using natural language processing and classifying it by time, region, location, and presenter, means for providing relevant information from the classified data based on questions from users and adjusting the content of the information using an emotion engine, means for identifying the safety and location information of disaster victims using data from communication service providers, and means for matching supporters based on material needs registered on the site and providing appropriate communication to the supporters using the emotion engine.This enables the provision of quick and accurate information, safety confirmation, smooth procedures for material support, and the provision of information that takes emotions into consideration in the event of a disaster.

[1752] "Sources" refer to external data providers from which data is collected, such as social media, online news, and official government announcements.

[1753] "Natural language processing" is a technology that enables computers to understand, analyze, and generate human language.

[1754] An "emotion engine" is a software engine that analyzes emotions from text and voice input by the user and adjusts the information and responses provided based on those emotions.

[1755] "Telecommunications service provider" refers to a company or organization that provides telecommunications services through a telecommunications network.

[1756] "Safety confirmation" refers to the act of collecting and providing information to confirm the safety and current location of disaster victims.

[1757] "Material needs" refers to the types and quantities of supplies and items needed by disaster victims.

[1758] "Supporters" refers to people and organizations whose role is to provide supplies and services to disaster victims during a disaster.

[1759] "Matching" refers to the process of connecting the needs of disaster victims with the resources available to supporters.

[1760] "Data classification" refers to the process of organizing and dividing collected data by different criteria such as time, region, location, and presenter.

[1761] A "database" refers to a system that organizes and stores collected and analyzed data so that it can be searched and retrieved as needed.

[1762] "Global Positioning System Data" refers to data used to measure specific locations on Earth using satellites.

[1763] "Wireless communication network connection information" refers to information about the WiFi network or cell tower to which a mobile device is connected.

[1764] This invention is a "disaster information and support system" for smoothly providing information and carrying out support activities when a disaster occurs. This system collects data from multiple sources, such as social media and online news, and analyzes and classifies it to provide users with appropriate information.

[1765] 1. Data Collection

[1766] Server: The server collects data from sources such as social media, online news, and official government announcements. It collects posts containing specific hashtags or keywords through the APIs of the social media platforms used.

[1767] Example: A server collects all Twitter posts containing the hashtag "Disaster Breaking News" and stores this data.

[1768] 2. Data analysis and classification

[1769] Server: The server analyzes the collected data using natural language processing (NLP) techniques and categorizes the data by time, region, location, and presenter.

[1770] Software used: General NLP engine

[1771] Example: The server analyzes collected Twitter posts and classifies them as "information from an individual user, Shibuya-ku, Tokyo, October 15, 2023."

[1772] 3. Question and Answering

[1773] User: A user types a question into a search box on the site (e.g., "What's the current situation in Shibuya Ward?").

[1774] Server: The server receives the question, searches for relevant information from a database, and responds. Generative AI generates appropriate answers, and an emotion engine is used to tailor the information according to the user's emotions.

[1775] Example: When a user asks, "What is the current situation in Shibuya Ward?", the server responds, "Traffic restrictions are currently in place in Shibuya Ward. An evacuation shelter has been opened at X Elementary School." Furthermore, if the emotion engine detects that the user is anxious, it adds reassuring information, such as, "There are many safe places to evacuate to in Shibuya Ward."

[1776] 4. Safety confirmation

[1777] User: Users enter the names and contact information of family members and acquaintances on the site to check on their safety.

[1778] Server: The server uses the communication service provider's API to obtain communication history and GPS data, and checks the last location and safety information of the victims. It uses an emotion engine to adjust how the information is provided.

[1779] Example: When a user checks the safety of "Taro Tanaka," the server responds with information such as, "Taro Tanaka was last contacted in front of Shibuya Station at 3:30 PM." If the user feels uneasy, the server provides additional reassuring information such as, "Taro Tanaka has been in contact recently and is likely in a safe location."

[1780] 5. Registering supply needs and matching supporters

[1781] Victims (users): Victims enter the supplies they need and their quantities in the site's supply registration form (e.g., "10 liters of water, 3 blankets").

[1782] Server: The entered information is saved in a database and made available for supporters to view.

[1783] Donors (users): Donors access the donation list page on the site and select the items they can donate.

[1784] Server: Confirms the supporter's selection, notifies the administrator, and instructs appropriate arrangements. Uses the emotion engine to provide supporters with appropriate communication tools.

[1785] Example: A donor views the "List of victims in the Tohoku region" and selects "Provide three blankets to the Tanaka family." The server notifies the administrator and instructs them to arrange for delivery. Also, for first-time donors, a message is displayed saying, "Thank you for your first donation. We will explain the donation procedure so you can feel at ease."

[1786] By combining these functions, the system of the present invention can provide prompt and appropriate information in the event of a disaster, confirm the safety of people, facilitate smooth procedures for providing material support, and provide information that takes emotions into consideration.

[1787] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1788] Step 1: Data collection

[1789] Server: The server collects data from multiple sources, such as social media, online news, and official government announcements. Specifically, it uses social media APIs to retrieve posts containing specific hashtags or keywords.

[1790] Input: A specific hashtag or keyword (e.g., "disaster breaking news")

[1791] Output: Collected post data (e.g. Twitter posts)

[1792] Specific operation: The server collects all Twitter posts containing the hashtag "Disaster Breaking News" and stores this data.

[1793] Step 2: Data analysis and classification

[1794] Server: The server analyzes the collected data using a natural language processing engine (e.g., a general NLP engine) and categorizes the data by time, region, location, and presenter. The analyzed data is stored in a database.

[1795] Input: Collected post data (e.g., Twitter posts)

[1796] Output: Classified data (e.g., "Information from an individual user, Shibuya Ward, Tokyo, October 15, 2023")

[1797] Specific operation: The server analyzes the collected Twitter posts and classifies them as "information from an individual user in Shibuya Ward, Tokyo, on October 15, 2023." This classification result is stored in a database.

[1798] Step 3: Question and Answer

[1799] User: A user types a question into a search box on the site (e.g., "What's the current situation in Shibuya Ward?").

[1800] Server: The server receives the question, searches for relevant information from a database, uses a generative AI model to generate an appropriate answer, and uses an emotion engine to tailor the information according to the user's emotions.

[1801] Input: User question (e.g. "What is the current situation in Shibuya Ward?")

[1802] Output: Generated answer (e.g. "Traffic restrictions are in place in Shibuya Ward. An evacuation shelter has been opened at XX Elementary School.")

[1803] Specific operation: The server analyzes the user's question and searches the database for relevant information. The generation AI generates a response such as, "Traffic restrictions are in place in Shibuya Ward. An evacuation shelter has been opened at X-X Elementary School." Furthermore, if the emotion engine detects the user's feelings of anxiety, it adds, "There are many safe places to evacuate to in Shibuya Ward."

[1804] Step 4: Safety confirmation

[1805] User: Users enter the names and contact information of family members and acquaintances on the site to check on their safety.

[1806] Server: The server uses the communication service provider's API to obtain communication history and GPS data, and checks the last location and safety information of the victims. It uses an emotion engine to adjust how the information is provided.

[1807] Input: Names and contact information of family members or acquaintances (e.g., "Taro Tanaka")

[1808] Output: Safety information (e.g. "Taro Tanaka was last heard from in front of Shibuya Station at 15:30")

[1809] Specific operation: Based on the name and contact information of "Taro Tanaka" entered by the user, the server uses the communication service provider's API to obtain communication history and GPS data. This provides information such as "Taro Tanaka was last contacted in front of Shibuya Station at 3:30 PM." For users who feel uneasy, the server provides additional information to reassure them, such as "Taro Tanaka has been in communication recently and is likely in a safe location."

[1810] Step 5: Register your supply needs

[1811] Victims (users): Victims enter the supplies they need and their quantities in the site's supply registration form (e.g., "10 liters of water, 3 blankets").

[1812] Server: The entered information is saved in a database and made available for supporters to view.

[1813] Input: The supplies you need and their quantities (e.g., "10 liters of water, 3 blankets")

[1814] Output: Registered supply information (e.g., "10 liters of water, 3 blankets")

[1815] Specific operation: When a victim registers "10 liters of water, 3 blankets" on the site, the server saves this in the database and allows supporters to proceed and view it.

[1816] Step 6: Supporter Matching

[1817] Donors (users): Donors access the donation list page on the site and select the items they can donate.

[1818] Server: Confirms the supporter's selection, notifies the administrator, and instructs appropriate arrangements. Uses the emotion engine to provide supporters with appropriate communication tools.

[1819] Input: The items that donors can provide (e.g., "3 blankets")

[1820] Output: Instructions for providing assistance (e.g., "Provide three blankets to the Tanaka family")

[1821] Specific operation: A donor views the "List of victims in the Tohoku region" and selects "Provide three blankets to the Tanaka family." The server notifies the administrator and instructs them to arrange for delivery. For first-time donors, the server also displays a message saying, "Thank you for your first donation. We will explain the donation procedure so you can feel at ease."

[1822] (Application example 2)

[1823] 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."

[1824] When a disaster occurs, there is a need for a system that can provide information quickly and appropriately and facilitate smooth communication between victims and supporters. Current systems have issues with obtaining information in real time and providing information that reflects emotions, as well as issues with smoothly confirming the safety of victims and matching supplies. There is a need for a system that can solve these issues and support more effective support activities.

[1825] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data from multiple information sources, means for analyzing the collected data and classifying it by time, region, location, and presenter, means for providing related information from the classified data based on questions from users, means for identifying the safety and location information of disaster victims using data from telecommunications companies, means for matching supporters based on material needs registered on the site, and means for analyzing user emotions and providing information according to the results. This makes it possible to provide information and support activities quickly and appropriately when a disaster occurs.

[1826] "Sources" are the origins of information provided by various digital media and platforms (e.g., social networking services, online news, official government announcements, etc.).

[1827] "Data collection methods" are the mechanisms and techniques used to obtain necessary data from various sources and incorporate it into the system.

[1828] "Data analysis tools" are techniques and methods for analyzing collected data and categorizing it based on specific criteria (e.g., time, region, location, presenter, etc.).

[1829] The "user question answering means" is a system or function for accepting questions from users and searching for and providing related information based on those questions.

[1830] "Safety confirmation means" refers to technology or methods for confirming the safety and location of disaster victims using data from telecommunications companies (e.g., communication history, wireless connection information, global positioning system data).

[1831] "Supply matching tools" are systems and functions that connect the supply needs registered on the site with supporters, enabling efficient distribution of supplies.

[1832] "Emotion analysis means" refers to a technique or method for analyzing emotions from user input (e.g., text or voice) and adjusting the information provided based on the results.

[1833] "Natural language processing" is a technical field that uses computers to understand, interpret, and manipulate human language, and is particularly used for analyzing text data.

[1834] "Global Positioning System data" is data used to obtain highly accurate positional information of any point on Earth using satellites.

[1835] Specific embodiments for carrying out the present invention will be described below.

[1836] This system consists of three components: a server, terminals, and users. The server plays a central role in collecting data from various information sources and analyzing and classifying it. The terminals are devices that users use to obtain information, check the safety of others, register supplies, and confirm support, and users are the entities that actually use these functions.

[1837] First, the server collects data from multiple sources, such as social networking services (SNS), online news, and official government announcements. The server obtains data from these sources in real time, analyzes it using a natural language processing (NLP) engine (described below), and classifies it by time, region, location, and issuer.

[1838] The NLP engine uses the open source TextBlob and generative AI models using deep learning (such as GPT). Through this analysis, for example, a social media post containing the hashtag "disaster name" is classified as "information from an individual user, Tokyo, October 15, 2023."

[1839] When a user inputs a question through their device, the question is sent to the server. For example, if the user inputs the question, "What is the current situation in Shibuya Ward?", the server searches for relevant information from the database, and the generative AI generates the optimal answer based on the analysis results and provides it to the user. An example of a prompt sentence is, "What is the current situation in Shibuya Ward?" Furthermore, an emotion engine is used to analyze the user's emotions and adjust the way information is presented as necessary. If the user asks a question with an anxious expression or tone, the content is changed to one that gives a sense of security.

[1840] For safety checks, the server obtains communication history, wireless connection information, and Global Positioning System (GPS) data from the telecommunications company's API. For example, when a user enters the name and contact information of "Taro Tanaka" to check the user's safety, the server searches the database and returns information such as "Taro Tanaka was last contacted in front of Shibuya Station at 3:30 PM." If the user appears very worried, the emotion engine provides additional information such as "He may be in a relatively safe location."

[1841] To match supplies, disaster victims register the supplies they need and the quantities they require on the site. For example, they might enter "10 liters of water, 3 blankets." The server stores this information in a database and makes it available for donors to view. When a donor selects supplies available on the site, the server notifies the administrator and instructs them on the appropriate procedures for arranging supplies. Using an emotion engine, the system also provides reassuring messages when donors are donating for the first time.

[1842] In this way, the server and terminals work together to provide prompt and appropriate information and support activities in the event of a disaster. Examples of prompt sentences introduced include user questions such as "What is the current situation in Shibuya Ward?" and "I want to check on the safety of my daughter."

[1843] The above is a specific embodiment for carrying out the present invention, and this system will improve the efficiency of information provision and support activities in the event of a disaster.

[1844] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1845] Step 1:

[1846] The server collects data from multiple sources, specifically social networking services (SNS), online news, official government announcements, etc., and obtains data in real time through APIs. Data from these sources is used as input, and the raw data is stored on the server as output.

[1847] Step 2:

[1848] The server analyzes the collected data and categorizes it by time, region, location, and presenter. Specifically, it processes the data with a natural language processing engine using TextBlob and generative AI models (e.g., GPT). It uses the collected raw data as input and provides data categorized by time, region, location, and presenter as output.

[1849] Step 3:

[1850] The user inputs a question through a terminal. For example, they input "What is the current situation in Shibuya Ward?" on the application screen of a smartphone or PC. The user's question text is used as input, and the question content is sent to the server as output.

[1851] Step 4:

[1852] The server searches for relevant information from the database based on the user's question, and the generative AI generates an appropriate answer based on the analysis results. The user's question and classified data are used as input, and the generated answer text is obtained as output.

[1853] Step 5:

[1854] The server uses an emotion engine to analyze the user's emotions and adjust the information provided. Specifically, it analyzes the user's input text using TextBlob or other emotion analysis tools. The input is the user's question text, and the output is the user's emotion score. For example, if the user asks a question with an anxious expression or tone, the server adjusts the answer to make it more reassuring.

[1855] Step 6:

[1856] The server obtains communication history, wireless connection information, and Global Positioning System (GPS) data from the telecommunications company's API and checks the safety of disaster victims. Location information data from the telecommunications company is used as input, and information on the safety of disaster victims is obtained as output. This provides information such as, "Taro Tanaka was last heard from in front of Shibuya Station at 3:30 PM."

[1857] Step 7:

[1858] Users register information about required supplies through their terminals. For example, they input specific needs such as "10 liters of water, 3 blankets." The input is the information about the needs of disaster victims, and the output is stored on the server.

[1859] Step 8:

[1860] The server matches supporters based on the material needs registered on the site. Specifically, it compares the information on the materials that can be provided selected by the supporter with the information on the needs of the disaster victims to make the optimal match. The input is the information on the material needs of the disaster victims and the information on the materials that can be provided by the supporter, and the matching results are obtained as the output.

[1861] The above is the specific processing flow of this system's program. At each step, the necessary data is input, specific data processing and data calculations are performed, and ultimately useful information and support is provided to the user.

[1862] 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.

[1863] 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.

[1864] 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.

[1865] 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.

[1866] 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.

[1867] 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.

[1868] 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).

[1869] 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.

[1870] 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."

[1871] 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.

[1872] 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).

[1873] 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 gene...

Claims

1. a means of collecting data from multiple sources; A means of analyzing the collected data and categorizing it by time, region, location, and presenter; means for providing relevant information from the classified data based on a query from a user; A means of identifying the safety and location of victims using data from telecommunications companies; A means of matching donors based on material needs registered on the site, and A system including:

2. 10. The system of claim 1, further comprising means for analyzing the collected data using natural language processing.

3. The system according to claim 1, further comprising means for identifying the location information of the disaster victim using communication history, WiFi connection information, and GPS data.

Images