system

Abstract

Provide a system. 【Solution means】 Means for acquiring disaster-related information from an information-providing medium, Means for analyzing the acquired information to determine the type, location, and severity of a disaster, Means for visually displaying the analyzed information based on geographical information, Means for selecting highly relevant information based on the user's location information, Means for notifying the user based on the selected information, Means for dynamically updating the geographical information displayed on the user's device, Means for re-analyzing information based on the collected data when data collection is performed, A system including the above.

Description

Technical Field

[0004] , , , ,

[0005] , , , , ,

[0003] , ,

[0001] The technology of the present disclosure relates to a system.

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In recent years, the frequency of natural disasters has been increasing, and there is a demand for rapid and appropriate information collection and provision. However, conventional information provision means lack timeliness and accuracy and are insufficient to support the immediate decision-making required by residents. Also, it is difficult to select information that meets individual needs from a vast amount of information. Therefore, it is necessary to develop a system that provides disaster information with higher accuracy, speed, and in accordance with individual needs.

Means for Solving the Problems

[0005] This invention provides a system that includes means for acquiring disaster-related information from information provision media, and analyzes the acquired information to determine the type, location, and severity of the disaster. Furthermore, it includes means for visually displaying the analyzed information based on geographical information and selecting and notifying users of highly relevant information based on their location information. This enables the rapid and accurate provision of disaster information, thereby supporting residents' decision-making during disasters.

[0006] "Information dissemination media" refers to social networking services (SNS), news websites, and other digital platforms that serve as channels for disseminating disaster-related information.

[0007] "Disaster-related information" refers to information concerning natural disasters and other emergencies, including details such as the type, location, severity, and scope of impact of the disaster.

[0008] "Means of acquisition" refers to the functions of software or hardware used to collect necessary information from information sources.

[0009] "Means of analysis" refers to the process of analyzing the meaning of acquired information and extracting necessary metadata.

[0010] "Geographic information" refers to information about geographical location, including addresses, coordinates, and location data on maps.

[0011] "Means of visual display" refers to methods of illustrating information in a format that is easy for users to understand, primarily on maps.

[0012] "Location information" refers to data that indicates the user's current geographical location, and is based on the user's address or GPS coordinates.

[0013] "Highly relevant information" refers to information that is deemed particularly important based on the user's individual needs and location information.

[0014] "Means of notification" refers to alert systems and messaging functions used to inform users of selected information. [Brief explanation of the drawing]

[0015] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when combined with an emotion engine.

Embodiments for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0019] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] As shown in Figure 1, the 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.

[0026] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0028] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0029] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0035] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0036] This invention is a system for providing rapid information during disasters. It automatically collects and analyzes disaster-related information from information sources to determine the type, location, and severity of the disaster, and immediately notifies users.

[0037] The system begins with the server accessing APIs of information providers to periodically retrieve various disaster information. For example, the server uses APIs from social media and news sites to collect posts and articles written in natural language. This enables real-time information gathering.

[0038] Next, the collected information is analyzed on the server using natural language processing technology. During the analysis, keywords and phrases to identify the disaster are extracted from the text data, and the type and severity of the disaster are determined based on these. For example, if phrases such as "seismic intensity 5," "fire outbreak," or "flood warning" are detected, the corresponding disaster is estimated.

[0039] The analysis results are linked to geographical information and reflected in a visual map. The server uses a Geographic Information System (GIS) to plot this information on the map and prepare it for display in a user-friendly format. This process visually shows the affected areas and the locations of shelters.

[0040] The device filters information based on the user's pre-registered location and regional settings, displaying only highly relevant information. This allows users to receive important information that is relevant to them as a priority. Information tailored to the user's location is selected, and irrelevant information is not displayed.

[0041] When important information is identified, the device immediately sends a push notification to the user, prompting them to check for the new information. For example, if there is a risk of a significant aftershock, an immediate notification will be sent with a specific warning. This notification system allows users to detect danger in real time and take appropriate action.

[0042] Furthermore, the system manages billing based on user usage. Premium users can access additional features and detailed information, and billing for these is automatically handled by the server. This ensures stable service delivery and monetization.

[0043] This invention enables the realization of a system that supports user safety and decision-making during disasters by providing rapid and reliable disaster information.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The server connects to the APIs of information providers and periodically collects disaster-related information. It filters and retrieves necessary data from social media and news sites using specific hashtags and keywords.

[0047] Step 2:

[0048] The server analyzes the collected data. Using natural language processing algorithms, it extracts keywords related to the type and severity of the disaster from the text. This analysis generates metadata such as the type of disaster, location, and time of occurrence.

[0049] Step 3:

[0050] The server uses the analyzed data to prepare for plotting on a map using a geographic information system. Here, it creates coordinate information to clearly identify the location of the disaster and visualize the extent of its impact.

[0051] Step 4:

[0052] The device filters relevant information based on the user's registered information. It selects disaster information relevant to the user based on their set location and areas of interest.

[0053] Step 5:

[0054] The terminal displays the selected information on a map. It illustrates the affected area and places icons indicating important locations such as evacuation shelters as needed.

[0055] Step 6:

[0056] The device sends notifications to the user when important information is updated. It uses push notifications to instantly deliver new information and alerts to the user.

[0057] Step 7:

[0058] The server monitors user usage and manages billing. It generates billing information and processes payments at the appropriate time according to the user's contract plan.

[0059] (Example 1)

[0060] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0061] In recent years, the increasing frequency of natural disasters has created a demand for rapid and accurate information provision, but traditional methods often lack real-time capabilities and accuracy. Furthermore, it is difficult to select relevant information for each user and encourage appropriate action. In addition, proper billing management for service usage remains a challenge.

[0062] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0063] In this invention, the server includes means for acquiring disaster information from information supply organizations, means for analyzing the acquired information to evaluate the type, location, and severity of the disaster, and means for visually presenting the analyzed information based on location information. This enables the provision of reliable disaster information in real time and the provision of customized information for each user. Furthermore, it enables appropriate billing management based on usage.

[0064] "Information supply organizations" refer to external services and systems that provide disaster information, including social media platforms and news media.

[0065] "Disaster information" refers to important data that should be provided to users, including information about the type, location, and severity of natural disasters.

[0066] "Information analysis" refers to the process of processing acquired disaster information and evaluating its type, location, and severity.

[0067] "Location information" refers to data that indicates a geographical location and is used to identify the user's current location or the area where a disaster has occurred.

[0068] "Visual presentation" refers to the process of displaying analyzed information in the form of maps, graphs, and other visual aids to make it easily understandable for users.

[0069] "User" refers to an individual or organization that uses this system to receive disaster information.

[0070] "Billing management" refers to the process of billing users appropriately based on their system usage and generating revenue.

[0071] This invention is a system that enables the rapid and accurate provision of information during disasters. The server automatically collects disaster information from social media and news media via APIs from information supply organizations. Specifically, the server uses APIs from social media platforms to obtain disaster-related posting data. It can also collect recent article information using RSS feeds from news sites.

[0072] The server analyzes the collected information using natural language processing libraries such as "spaCy" and "NLTK." This process extracts important phrases and keywords from the text data and further evaluates the urgency and reliability of the information through sentiment analysis.

[0073] The analyzed information is visually displayed on a map using GIS software such as "ArcGIS" and "QGIS." Visualizing geographic information makes it possible to intuitively understand the location and extent of the disaster.

[0074] The device filters out highly relevant disaster information based on the user's location and pre-configured regional information. This process allows the user to receive only the necessary information while reducing the associated noise.

[0075] Important information is instantly communicated to users via push notifications. As a concrete example, Firebase Cloud Messaging (FCM) is used to provide real-time notifications of critical disaster information, such as earthquake intensity in specific areas.

[0076] Furthermore, this system also includes a function to automatically manage billing for each user. The server charges based on usage and provides premium users with additional features and detailed information. This enables stable service provision and monetization.

[0077] As a concrete example, if an earthquake with a seismic intensity of 5 occurs in the user's area, the server collects and analyzes that information, and the device immediately sends a push notification based on the results filtered according to the location information.

[0078] Examples of prompt statements are as follows:

[0079] "Design a program that collects information about earthquakes with a seismic intensity of 5 and notifies users in a designated area. Describe in detail the necessary APIs, natural language processing techniques, and specific processing steps using GIS software."

[0080] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0081] Step 1:

[0082] The server accesses APIs of information providers to collect disaster information. The input is requests to the API, and the output is data of posts and articles related to the disaster. Specifically, the server periodically calls the API to retrieve text data from social media and news sources.

[0083] Step 2:

[0084] The server analyzes the collected text data using a natural language processing library. The input is the collected text data, and the output is data including extracted keywords, disaster type, location, and severity. Specifically, the server uses the "spaCy" library to extract specific phrases and keywords from the text and evaluate the urgency of the information by performing sentiment analysis.

[0085] Step 3:

[0086] The server plots the analysis results on a map using GIS software. The input is the analyzed geographic information data, and the output is a map visualizing the disaster situation. Specifically, the server uses the "ArcGIS" tool to map the extracted point information and show the affected area and the locations of evacuation shelters.

[0087] Step 4:

[0088] The terminal filters highly relevant information based on the location information registered by the user. The input is mapped disaster information and the user's location information, and the output is filtered relevant information. Specifically, the terminal selects only disaster information related to the user's specified area, and displays only the information the user needs.

[0089] Step 5:

[0090] The device sends important information to the user as a push notification. The input is filtered important information, and the output is a notification message to the user. Specifically, the device uses "Firebase Cloud Messaging" to notify the user of disaster information in real time in the form of an alert.

[0091] Step 6:

[0092] The server manages billing based on user usage. Inputs are user usage data and subscription information, while output is billing data. Specifically, the server analyzes user data processing volume monthly and automatically bills based on that analysis.

[0093] (Application Example 1)

[0094] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0095] In the event of a disaster, a system is needed that provides accurate and relevant information in real time, enabling local residents and social infrastructure to take swift and safe actions. This invention aims to solve this problem by rapidly acquiring and analyzing data from multiple sources and efficiently transmitting the necessary information to users. Conventional systems had the potential for delays in information acquisition and erroneous decisions based on inaccurate information, so there was a need for a means to improve this.

[0096] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0097] In this invention, the server includes means for acquiring disaster-related information from an information provision medium, means for analyzing the acquired information to determine the type, location, and severity of the disaster, and means for visually displaying the analyzed information based on geographic information. This enables users to take quick and appropriate evacuation actions based on geographic information that is updated in real time.

[0098] An "information provision medium" refers to a platform or interface used to provide data, including disaster-related information.

[0099] "Means of acquisition" refers to the methods and technologies for receiving data from information provision media and incorporating it into a system.

[0100] "Means of analysis" refer to technologies that process acquired data, understand its content concretely, and convert it into information useful to users.

[0101] "Geographic information" refers to information that includes data related to specific locations or regions, enabling location-based decision-making.

[0102] "Means of visual display" refers to technologies that use visual elements such as maps and graphs to visually represent information in an easy-to-understand manner.

[0103] "User location information" refers to data about the current location of each individual user of the system.

[0104] "Methods for selecting highly relevant information" refer to technologies for selecting information that is of high importance and necessity to the user from the information that has been acquired.

[0105] "Means of notification" refer to approaches and technologies used to inform users of selected information and encourage their awareness and actions.

[0106] "Methods for dynamically updating" refer to technologies that immediately reflect newly acquired information and analysis results in geographic information and displayed content.

[0107] "Methods for reanalysis" refer to techniques for re-analyzing information based on the latest data and providing timely and accurate information.

[0108] The system for implementing this invention consists mainly of a server and terminals. The server accesses the API of an information provision medium and acquires disaster-related information in real time. The hardware used for this is a standard server computer, and the software incorporates a script that controls API access. The data is first analyzed using natural language processing technology. Python and NLP libraries (e.g., SpaCy) are used for the analysis, and data processing is performed to determine the type and severity of the information.

[0109] The analyzed data is plotted on a map using a Geographic Information System (GIS) and displayed in an easy-to-understand visual format. Leaflet.js is used as the software for this purpose. Specifically, the acquired and analyzed data is overlaid on the map in an intuitively understandable form. The device selects highly relevant information based on the user's location and visualizes it on the smartphone. Relevant information is immediately sent to the user as a push notification, supporting user actions at the appropriate time.

[0110] For example, if a "river flood warning" is issued during heavy rain, users will be notified immediately. The device displays real-time updated map information, allowing users to check the nearest evacuation shelters and dangerous areas. Furthermore, if the collected data is new, it is re-analyzed to always maintain the most up-to-date information.

[0111] An example of a prompt to be input into the generation AI model would be: "Assess the potential disaster risks to a specific area using the following information: flood advisories, strong wind warnings, and evacuation shelter location data. Generate a warning message based on detailed disaster type and location information." The warning message generated based on this prompt will be used as part of the information provided to the user.

[0112] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0113] Step 1:

[0114] The server accesses the API of an information provision medium to retrieve disaster-related data. The input is the response data from the API, which the server receives and prepares for analysis. The output is the received raw data. The retrieved data plays a crucial role in subsequent processing.

[0115] Step 2:

[0116] The server performs natural language processing on the acquired data to analyze the type, location, and severity of the disaster. The input for this step is the raw data acquired in step 1, and keywords and important phrases are extracted from the text using an NLP library. The output is the analyzed information, which identifies the type and severity of the disaster.

[0117] Step 3:

[0118] The server inputs the analyzed information into a Geographic Information System (GIS) and visualizes it on a map. The input for this step is the analysis results from step 2. The output is visualized map data, providing disaster information in an easy-to-understand format for users. Libraries such as Leaflet.js are used to display the extent of the disaster's impact and the locations of evacuation shelters on the map.

[0119] Step 4:

[0120] The device obtains the user's location information and filters it for the most relevant information. The input is the user's location information stored on the device and the map data from step 3. Based on this information, the device selects the most important notifications for the user. The output is the selected information, which is presented to the user on the device.

[0121] Step 5:

[0122] The device sends a push notification to the user based on the selected information. The input for this step is the information selected in step 4. The output is a notification to the user, and the device displays warnings and alerts to the user in real time.

[0123] Step 6:

[0124] The server performs reanalysis based on newly acquired data and user feedback. The inputs for this step are new data and user feedback. The server reanalyzes the data and prepares information that reflects the latest situation. The output is the updated analysis results, maintaining the accuracy of the information provided to users throughout the system.

[0125] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0126] This invention is a system that provides necessary information quickly during disasters and delivers information while taking into account the user's emotional state. In particular, it is characterized by the provision of information optimized according to the user's mental state by combining it with an emotion engine.

[0127] The system begins with a server collecting disaster-related information from information sources. The collected information is then analyzed by the server using natural language processing technology to determine the type, location, and severity of the disaster. The results of this analysis are then plotted on a map using a GIS (Geographic Information System).

[0128] At this stage, the device selects highly relevant information based on the user's location data. This selected information is then ready to be provided to the user.

[0129] Next, the emotion engine operates on the device to recognize the user's current emotional state. Emotion recognition is inferred from the user interface's operation history, selections, and user input patterns. This information, along with the user's emotional history, is sent to the server, where appropriate actions are considered.

[0130] The server adjusts the way and content of information provided based on the emotional state obtained from the emotion engine. For example, if a user is showing signs of anxiety, more detailed evacuation information and safety check guides will be provided. On the other hand, users who are relatively calm will be provided with information that focuses on summaries.

[0131] This adjusted information is notified to users through their devices, allowing for real-time follow-up. When there are important updates, notifications are sent in an emotionally sensitive manner to enhance user confidence.

[0132] Furthermore, the system accumulates users' emotional history, which can be used to improve the accuracy of future information provision. This ensures that users continuously receive information optimized for their needs.

[0133] This system goes beyond simply providing information; it enables disaster response support that is sensitive to the user's emotions, contributing to reducing the psychological burden on users and ensuring their safety.

[0134] The following describes the processing flow.

[0135] Step 1:

[0136] The server connects to APIs of information sources to periodically collect disaster-related information. These sources include social media and news sites, and the server filters the data using specific hashtags and keywords.

[0137] Step 2:

[0138] The server analyzes the collected information. Using natural language processing, it extracts keywords related to the type, location, and severity of the disaster to identify the disaster information. This analysis generates the necessary metadata.

[0139] Step 3:

[0140] The server uses GIS to plot the analyzed disaster information on a map. It processes coordinate information to visually display the disaster area and its impact on a map.

[0141] Step 4:

[0142] The device selects highly relevant information based on the user's pre-registered location data. This ensures that users receive only disaster information that is important to them.

[0143] Step 5:

[0144] The device recognizes the user's emotional state through the user interface. The emotion recognition engine analyzes the user's operation history and input patterns to determine their current emotion.

[0145] Step 6:

[0146] The server analyzes user emotion information obtained from the emotion engine. Based on this, it adjusts how disaster information is provided and selects appropriate information according to the user's emotions.

[0147] Step 7:

[0148] The device will notify users of carefully selected disaster information. By providing information in an emotionally sensitive manner, it aims to reduce user anxiety and guide them to take necessary actions.

[0149] Step 8:

[0150] The server stores the user's emotional history in a database. This stored data is then used to optimize future information delivery based on the user's tendencies.

[0151] This processing flow enables the system to provide users with emotionally resonant disaster information.

[0152] (Example 2)

[0153] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0154] Conventional disaster information systems provided information uniformly without considering the emotional state of users, which sometimes failed to alleviate their mental burden. Furthermore, the selection of appropriate information delivery methods was often inadequate, making it difficult for users to obtain the information they needed quickly and appropriately. Additionally, there was a lack of methods to utilize individual emotional histories to improve the accuracy of information provision.

[0155] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0156] In this invention, the server includes means for collecting disaster information from an information acquisition device, means for analyzing the collected information to determine the type, location, and severity of the disaster, and means for visualizing the analysis results based on spatial data. This makes it possible to provide information that takes into account the emotional state of the user, enabling timely notification of important information and reduction of mental burden. Furthermore, by utilizing individual emotional history, the accuracy of the provided content can be continuously improved.

[0157] An "information acquisition device" is a device used to collect disaster information from external sources.

[0158] "Analysis" is the process of processing collected information to determine the type, location, and severity of a disaster.

[0159] "Spatial data" refers to data used to visualize information based on geographical information.

[0160] "User" refers to an individual or group that uses the system.

[0161] "Location data" refers to geographical information that indicates the user's current location.

[0162] An "emotion analysis device" is a device used to recognize the emotional state of a user.

[0163] "Information provision method" refers to the method of determining what format the analyzed information will be provided to users.

[0164] "Emotional state" refers to the user's psychological state, and information provision is adjusted based on this.

[0165] "Notification" refers to the act of informing users of the adjusted information.

[0166] "Emotional history" refers to a record of a user's past emotions.

[0167] A system implementing this invention efficiently provides disaster information through the interaction of a server, terminal, and user, and enables appropriate responses according to the user's emotional state.

[0168] The server uses information acquisition devices to collect disaster information from multiple sources. These include news sites, social media, and government disaster information pages. On the server, the Python requests library is used, and necessary information is retrieved using BeautifulSoup. This information is analyzed to determine the type of disaster, its location, and its severity. The natural language processing library NLTK is used for the analysis. In addition, the disaster information is converted into spatial data using GeoPandas and visualized on a map.

[0169] The terminal uses the user's location information to compare it with geographic information data obtained from the server. In this process, the terminal uses GPS functionality to determine the user's current location. Based on this, it reads the user's emotional state in order to select disaster information relevant to the user and adjust the method of information delivery. The emotion analysis device implements a machine learning model using TENSORFLOW®, which infers the emotional state from the user's input patterns and operation history.

[0170] Users receive information tailored to their needs via their devices, enabling them to respond quickly and appropriately. Important information is communicated in a way that is sensitive to the user's feelings, providing reassuring and clear instructions. For example, if a user expresses anxiety, detailed information such as, "The nearest evacuation center is XX. Here are the directions," is provided.

[0171] An example of a prompt message to utilize this system is: "Present information about the current disaster situation and customize the notification content based on the user's current emotional state. If the user is anxious, provide specific safety guidelines; if calm, provide summary information." Based on this, the AI ​​model will provide the most appropriate information.

[0172] This invention aims to reduce the psychological burden during disasters and contribute to ensuring user safety through the smooth provision of information.

[0173] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0174] Step 1:

[0175] The server collects disaster information from external sources. URLs of news sites, social media, and government disaster information pages are provided as input. The Python requests library is used to retrieve HTML data from these sites, and BeautifulSoup is used to scrape the necessary information and output it. The collected data is saved in string format for subsequent analysis.

[0176] Step 2:

[0177] The server analyzes the collected information using natural language processing technology. Disaster information is provided as input in string format. The NLTK library is used to tokenize the text data. Based on the tokenized data, key phrases are extracted to determine the type, location, and severity of the disaster. The analysis results are output in associative array format.

[0178] Step 3:

[0179] The server visualizes the analysis results based on map information. The analysis results are provided as input in the form of an associative array. Using GeoPandas, the disaster information is converted into geographic data, generating GIS data as output. The GIS data is saved for plotting on a map and used for visual verification.

[0180] Step 4:

[0181] The device obtains the user's location information via a GPS module. The user's current location data is provided as input. Mapping software (e.g., folium) running on the device then overlays relevant disaster information onto a map. The output is a map image showing the user's current location and related information superimposed.

[0182] Step 5:

[0183] The sentiment analyzer, which operates on the terminal, recognizes the user's emotional state. The user's operation history and input pattern data are provided as input. A machine learning model using TensorFlow infers the emotional state (anxiety, calmness, etc.) from this data. The recognized emotional state is output as sentiment data, as it influences how subsequent information is provided.

[0184] Step 6:

[0185] The server adjusts the information delivery method based on the recognized emotional state. Emotional data and GIS data are provided as input. If the emotional state is anxious, detailed evacuation information and action guidelines are provided; if the emotional state is calm, summary information is provided. The adjusted information is output in a customized text or visual data format.

[0186] Step 7:

[0187] The device notifies the user of adjusted information. Customized information data is provided as input. Using the notification function, important updates and emotionally sensitive information are sent to the user in real time. Output is presented to the user as an alarm sound, an alert screen, or explanatory text.

[0188] This series of steps allows users to receive accurate and timely information tailored to their emotional state at any given time.

[0189] (Application Example 2)

[0190] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0191] During disasters, there is a need to provide users with personalized, rapid, and appropriate information. However, general information systems fail to consider users' emotional states, making it difficult to alleviate their anxiety and confusion. Furthermore, there is the problem of information overload or insufficiency hindering swift responses and evacuation actions.

[0192] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0193] In this invention, the server includes means for acquiring disaster-related data from an information source, means for analyzing the acquired data to determine the nature, location, and urgency of the disaster, means for visually presenting the analyzed data based on geographical information, means for selecting highly relevant data based on the user's location data, and means for analyzing the user's emotional state and adjusting the content provided according to that emotional state. This enables the provision of information tailored to the user's emotions and rapid evacuation support.

[0194] An "information source" is a system or medium that provides the source for obtaining disaster-related data.

[0195] "Disaster-related data" refers to data that includes information about the nature, location, and urgency of a disaster.

[0196] "Analysis" is the process performed to determine the characteristics of a disaster from the acquired data.

[0197] "Geographic information" refers to map data and location data that contain information related to a specific place.

[0198] "To present visually" means to express information in a way that is easy to understand visually.

[0199] "User location data" refers to information that indicates the user's geographical location.

[0200] "Highly relevant data" refers to data that is of high priority and directly relevant to a particular user.

[0201] "Emotional state" is an indicator that shows the user's emotional state and psychological response.

[0202] "Adjusting the content provided" means changing the way information is presented and the content of that information to suit the user's emotional state.

[0203] This invention is a system that provides personalized information to users quickly during disasters and adjusts the information according to their emotional state. The system mainly consists of a server and terminals.

[0204] The server acquires disaster-related data from information sources and analyzes that data to determine the nature, location, and urgency of the disaster. Specifically, it uses a natural language processing engine for data analysis and presents the data visually using a Geographic Information System (GIS). This makes it possible to instantly reflect important disaster-related information.

[0205] The device acquires the user's location data and selects highly relevant information from the data transmitted from the server. Furthermore, an emotion engine runs on the device to analyze the user's emotional state, inferring it based on the user's operation history and input patterns. As a result, the server adjusts the content provided based on the user's emotional state and delivers optimized information to the user.

[0206] As a concrete example, when an earthquake occurs, the server analyzes various data and visually provides residents in the affected area with information on emergency evacuation routes and safe shelters. Furthermore, if a user indicates anxiety on their device, they will receive more detailed reassurance information and guidance via push notifications. In this process, it is also possible to use a generative AI model to create appropriate prompts for the information the user is seeking.

[0207] An example of a prompt message would be, "Please tell me more about how to provide information that takes into account emotional states in a real-time evacuation guidance app during disasters." This would serve as a guide for the system to provide appropriate information.

[0208] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0209] Step 1:

[0210] The server acquires disaster-related data from information sources. Specifically, it accesses open data on the internet and dedicated disaster information sources, and sends the collected data to the server. At this point, the input is raw data from the information sources, and the output is unprocessed disaster-related data stored on the server.

[0211] Step 2:

[0212] The server analyzes the acquired data to determine the nature, location, and urgency of the disaster. A natural language processing engine is used for data analysis, classifying each data point through keyword analysis and other methods. The input is the raw data obtained in step 1, and the output is analyzed data labeled with disaster characteristics. Specifically, it performs text analysis and statistical modeling.

[0213] Step 3:

[0214] The server visually presents the analyzed data based on geographical information. Using GIS, it marks the location of disasters on a map. The input is the analyzed data obtained in step 2, and the output is visualized geographical information. Specifically, this involves data overlaying onto a map and generating interactive maps.

[0215] Step 4:

[0216] The terminal acquires the user's location data and selects highly relevant information from the data sent from the server. The input is the terminal's location information and the geographical visualization data from step 3, and the output is filtered information relevant to the user. Specifically, it uses distance calculation and filtering algorithms.

[0217] Step 5:

[0218] An emotion engine runs on the device to analyze the user's emotional state, inferring it based on the user's operation history and input patterns. The input is the user's operation data within the app, and the output is the inferred emotional state. Specifically, this is an inference of a machine learning model.

[0219] Step 6:

[0220] The server adjusts the content provided based on the user's emotional state, delivering optimized information to the user. The input is the emotional state obtained in step 5 and the refined information from step 4, and the output is emotionally sensitive information. Specifically, it performs tasks such as prioritizing information and selecting prompts.

[0221] Step 7:

[0222] The user receives information in real time via their device and follows instructions as needed. The input is the adjusted information from step 6, and the output is the user's actions and responses. Specific actions include using the app's notification and guidance features.

[0223] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0224] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include those described above. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions shown by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0225] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0226] [Second Embodiment]

[0227] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0228] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0229] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0230] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0231] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0232] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0233] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0234] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0235] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0236] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0237] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0238] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0239] This invention is a system for providing rapid information during disasters. It automatically collects and analyzes disaster-related information from information sources to determine the type, location, and severity of the disaster, and immediately notifies users.

[0240] The system begins with the server accessing APIs of information providers to periodically retrieve various disaster information. For example, the server uses APIs from social media and news sites to collect posts and articles written in natural language. This enables real-time information gathering.

[0241] Next, the collected information is analyzed on the server using natural language processing technology. During the analysis, keywords and phrases to identify the disaster are extracted from the text data, and the type and severity of the disaster are determined based on these. For example, if phrases such as "seismic intensity 5," "fire outbreak," or "flood warning" are detected, the corresponding disaster is estimated.

[0242] The analysis results are linked to geographical information and reflected in a visual map. The server uses a Geographic Information System (GIS) to plot this information on the map and prepare it for display in a user-friendly format. This process visually shows the affected areas and the locations of shelters.

[0243] The device filters information based on the user's pre-registered location and regional settings, displaying only highly relevant information. This allows users to receive important information that is relevant to them as a priority. Information tailored to the user's location is selected, and irrelevant information is not displayed.

[0244] When important information is identified, the device immediately sends a push notification to the user, prompting them to check for the new information. For example, if there is a risk of a significant aftershock, an immediate notification will be sent with a specific warning. This notification system allows users to detect danger in real time and take appropriate action.

[0245] Furthermore, the system manages billing based on user usage. Premium users can access additional features and detailed information, and billing for these is automatically handled by the server. This ensures stable service delivery and monetization.

[0246] This invention enables the realization of a system that supports user safety and decision-making during disasters by providing rapid and reliable disaster information.

[0247] The following describes the processing flow.

[0248] Step 1:

[0249] The server connects to the APIs of information providers and periodically collects disaster-related information. It filters and retrieves necessary data from social media and news sites using specific hashtags and keywords.

[0250] Step 2:

[0251] The server analyzes the collected data. Using natural language processing algorithms, it extracts keywords related to the type and severity of the disaster from the text. This analysis generates metadata such as the type of disaster, location, and time of occurrence.

[0252] Step 3:

[0253] The server uses the analyzed data to prepare for plotting on a map using a geographic information system. Here, it creates coordinate information to clearly identify the location of the disaster and visualize the extent of its impact.

[0254] Step 4:

[0255] The device filters relevant information based on the user's registered information. It selects disaster information relevant to the user based on their set location and areas of interest.

[0256] Step 5:

[0257] The terminal displays the selected information on a map. It illustrates the affected area and places icons indicating important locations such as evacuation shelters as needed.

[0258] Step 6:

[0259] The device sends notifications to the user when important information is updated. It uses push notifications to instantly deliver new information and alerts to the user.

[0260] Step 7:

[0261] The server monitors user usage and manages billing. It generates billing information and processes payments at the appropriate time according to the user's contract plan.

[0262] (Example 1)

[0263] Next, we will describe Example 1. 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."

[0264] In recent years, the increasing frequency of natural disasters has created a demand for rapid and accurate information provision, but traditional methods often lack real-time capabilities and accuracy. Furthermore, it is difficult to select relevant information for each user and encourage appropriate action. In addition, proper billing management for service usage remains a challenge.

[0265] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0266] In this invention, the server includes means for acquiring disaster information from information supply organizations, means for analyzing the acquired information to evaluate the type, location, and severity of the disaster, and means for visually presenting the analyzed information based on location information. This enables the provision of reliable disaster information in real time and the provision of customized information for each user. Furthermore, it enables appropriate billing management based on usage.

[0267] "Information supply organizations" refer to external services and systems that provide disaster information, including social media platforms and news media.

[0268] "Disaster information" refers to important data that should be provided to users, including information about the type, location, and severity of natural disasters.

[0269] "Information analysis" refers to the process of processing acquired disaster information and evaluating its type, location, and severity.

[0270] "Location information" refers to data that indicates a geographical location and is used to identify the user's current location or the area where a disaster has occurred.

[0271] "Visual presentation" refers to the process of displaying analyzed information in the form of maps, graphs, and other visual aids to make it easily understandable for users.

[0272] "User" refers to an individual or organization that uses this system to receive disaster information.

[0273] "Billing management" refers to the process of billing users appropriately based on their system usage and generating revenue.

[0274] This invention is a system that enables the rapid and accurate provision of information during disasters. The server automatically collects disaster information from social media and news media via APIs from information supply organizations. Specifically, the server uses APIs from social media platforms to obtain disaster-related posting data. It can also collect recent article information using RSS feeds from news sites.

[0275] The server analyzes the collected information using natural language processing libraries such as "spaCy" and "NLTK." This process extracts important phrases and keywords from the text data and further evaluates the urgency and reliability of the information through sentiment analysis.

[0276] The analyzed information is visually displayed on a map using GIS software such as "ArcGIS" and "QGIS." Visualizing geographic information makes it possible to intuitively understand the location and extent of the disaster.

[0277] The terminal filters only highly relevant disaster information based on the user's location information and pre-set area information. Through this process, the user can receive only the necessary information and reduce the accompanying noise.

[0278] Important information is immediately transmitted to the user through push notifications. As a specific example, Firebase Cloud Messaging (FCM) is used to notify users in real-time of major disaster information such as the seismic intensity in a specific area.

[0279] Furthermore, this system also has a function to automatically manage billing for each user. The server implements billing according to the usage situation and provides additional functions and detailed information to premium users. This enables stable service provision and monetization.

[0280] As a specific example, when an earthquake of seismic intensity 5 occurs in the area where the user is located, the server collects and analyzes the information, and immediately sends a push notification based on the result filtered by the terminal based on the location information.

[0281] Examples of prompt sentences are as follows:

[0282] "Please design a program to collect information about an earthquake of seismic intensity 5 and notify users in the specified area. Please explain in detail the specific processing procedures using the necessary APIs, natural language processing technologies, and GIS software."

[0283] The flow of the specific processing in Example 1 will be described using FIG. 11.

[0284] Step 1:

[0285] The server accesses the API of the information supply institution to collect disaster information. The input is a request to the API, and the output is data of posts and articles related to disasters. As a specific operation, the server periodically calls the API to obtain text data from SNS and news.

[0286] Step 2:

[0287] The server analyzes the collected text data using a natural language processing library. The input is the collected text data, and the output is data including the extracted keywords, types of disasters, locations, and severities. As a specific operation, the server uses the "spaCy" library to extract specific phrases and keywords from the text and performs sentiment analysis to evaluate the urgency of the information.

[0288] Step 3:

[0289] The server plots the analysis results on a map using GIS software. The input is the analyzed geographical information data, and the output is a map visualizing the disaster situation. As a specific operation, the server uses the "ArcGIS" tool to map the extracted location information and show the affected area and the locations of shelters.

[0290] Step 4:

[0291] The terminal filters highly relevant information based on the location information registered by the user. The input is the mapped disaster information and the user's location information, and the output is the filtered relevant information. As a specific operation, the terminal selects only the disaster information related to the designated area of the user, and only the information necessary for the user is displayed.

[0292] Step 5:

[0293] The terminal sends important information to the user as a push notification. The input is the filtered important information, and the output is a notification message to the user. As a specific operation, the terminal uses "Firebase Cloud Messaging" to notify the user of disaster information in real time in the form of an alert.

[0294] Step 6:

[0295] The server manages billing based on user usage. Inputs are user usage data and subscription information, while output is billing data. Specifically, the server analyzes user data processing volume monthly and automatically bills based on that analysis.

[0296] (Application Example 1)

[0297] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0298] In the event of a disaster, a system is needed that provides accurate and relevant information in real time, enabling local residents and social infrastructure to take swift and safe actions. This invention aims to solve this problem by rapidly acquiring and analyzing data from multiple sources and efficiently transmitting the necessary information to users. Conventional systems had the potential for delays in information acquisition and erroneous decisions based on inaccurate information, so there was a need for a means to improve this.

[0299] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0300] In this invention, the server includes means for acquiring disaster-related information from an information provision medium, means for analyzing the acquired information to determine the type, location, and severity of the disaster, and means for visually displaying the analyzed information based on geographic information. This enables users to take quick and appropriate evacuation actions based on geographic information that is updated in real time.

[0301] An "information provision medium" refers to a platform or interface used to provide data, including disaster-related information.

[0302] "Means of acquisition" refers to the methods and technologies for receiving data from information provision media and incorporating it into a system.

[0303] The "means for analysis" is a technology for processing the acquired data, specifically understanding its content, and converting it into useful information for the user.

[0304] "Geographic information" is information that includes data related to specific locations or regions and enables location-based judgments.

[0305] The "means for visually displaying" is a technology for visually representing information using visual elements such as maps and graphs to display the information clearly.

[0306] "User location information" is data related to the location where each individual user using the system is currently located.

[0307] The "means for selecting highly relevant information" is a technology for selecting information with high importance or necessity for the user from the acquired information.

[0308] The "means for notifying" is an approach or technology for informing the user of the selected information and prompting awareness and action.

[0309] The "means for dynamically updating" is a technology for immediately reflecting newly acquired information or analysis results in geographic information and display content.

[0310] The "means for re-analyzing" is a technology for analyzing information again based on the latest data and providing timely and accurate information.

[0311] The system for implementing this invention consists mainly of a server and terminals. The server accesses the API of an information provision medium and acquires disaster-related information in real time. The hardware used for this is a standard server computer, and the software incorporates a script that controls API access. The data is first analyzed using natural language processing technology. Python and NLP libraries (e.g., SpaCy) are used for the analysis, and data processing is performed to determine the type and severity of the information.

[0312] The analyzed data is plotted on a map using a Geographic Information System (GIS) and displayed in an easy-to-understand visual format. Leaflet.js is used as the software for this purpose. Specifically, the acquired and analyzed data is overlaid on the map in an intuitively understandable form. The device selects highly relevant information based on the user's location and visualizes it on the smartphone. Relevant information is immediately sent to the user as a push notification, supporting user actions at the appropriate time.

[0313] For example, if a "river flood warning" is issued during heavy rain, users will be notified immediately. The device displays real-time updated map information, allowing users to check the nearest evacuation shelters and dangerous areas. Furthermore, if the collected data is new, it is re-analyzed to always maintain the most up-to-date information.

[0314] An example of a prompt to be input into the generation AI model would be: "Assess the potential disaster risks to a specific area using the following information: flood advisories, strong wind warnings, and evacuation shelter location data. Generate a warning message based on detailed disaster type and location information." The warning message generated based on this prompt will be used as part of the information provided to the user.

[0315] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0316] Step 1:

[0317] The server accesses the API of an information provision medium to retrieve disaster-related data. The input is the response data from the API, which the server receives and prepares for analysis. The output is the received raw data. The retrieved data plays a crucial role in subsequent processing.

[0318] Step 2:

[0319] The server performs natural language processing on the acquired data to analyze the type, location, and severity of the disaster. The input for this step is the raw data acquired in step 1, and keywords and important phrases are extracted from the text using an NLP library. The output is the analyzed information, which identifies the type and severity of the disaster.

[0320] Step 3:

[0321] The server inputs the analyzed information into a Geographic Information System (GIS) and visualizes it on a map. The input for this step is the analysis results from step 2. The output is visualized map data, providing disaster information in an easy-to-understand format for users. Libraries such as Leaflet.js are used to display the extent of the disaster's impact and the locations of evacuation shelters on the map.

[0322] Step 4:

[0323] The device obtains the user's location information and filters it for the most relevant information. The input is the user's location information stored on the device and the map data from step 3. Based on this information, the device selects the most important notifications for the user. The output is the selected information, which is presented to the user on the device.

[0324] Step 5:

[0325] The device sends a push notification to the user based on the selected information. The input for this step is the information selected in step 4. The output is a notification to the user, and the device displays warnings and alerts to the user in real time.

[0326] Step 6:

[0327] The server performs reanalysis based on newly acquired data and user feedback. The inputs for this step are new data and user feedback. The server reanalyzes the data and prepares information that reflects the latest situation. The output is the updated analysis results, maintaining the accuracy of the information provided to users throughout the system.

[0328] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0329] This invention is a system that provides necessary information quickly during disasters and delivers information while taking into account the user's emotional state. In particular, it is characterized by the provision of information optimized according to the user's mental state by combining it with an emotion engine.

[0330] The system begins with a server collecting disaster-related information from information sources. The collected information is then analyzed by the server using natural language processing technology to determine the type, location, and severity of the disaster. The results of this analysis are then plotted on a map using a GIS (Geographic Information System).

[0331] At this stage, the device selects highly relevant information based on the user's location data. This selected information is then ready to be provided to the user.

[0332] Next, the emotion engine operates on the device to recognize the user's current emotional state. Emotion recognition is inferred from the user interface's operation history, selections, and user input patterns. This information, along with the user's emotional history, is sent to the server, where appropriate actions are considered.

[0333] The server adjusts the way and content of information provided based on the emotional state obtained from the emotion engine. For example, if a user is showing signs of anxiety, more detailed evacuation information and safety check guides will be provided. On the other hand, users who are relatively calm will be provided with information that focuses on summaries.

[0334] This adjusted information is notified to users through their devices, allowing for real-time follow-up. When there are important updates, notifications are sent in an emotionally sensitive manner to enhance user confidence.

[0335] Furthermore, the system accumulates users' emotional history, which can be used to improve the accuracy of future information provision. This ensures that users continuously receive information optimized for their needs.

[0336] This system goes beyond simply providing information; it enables disaster response support that is sensitive to the user's emotions, contributing to reducing the psychological burden on users and ensuring their safety.

[0337] The following describes the processing flow.

[0338] Step 1:

[0339] The server connects to APIs of information sources to periodically collect disaster-related information. These sources include social media and news sites, and the server filters the data using specific hashtags and keywords.

[0340] Step 2:

[0341] The server analyzes the collected information. Using natural language processing, it extracts keywords related to the type, location, and severity of the disaster to identify the disaster information. This analysis generates the necessary metadata.

[0342] Step 3:

[0343] The server uses GIS to plot the analyzed disaster information on a map. It processes coordinate information to visually display the disaster area and its impact on a map.

[0344] Step 4:

[0345] The device selects highly relevant information based on the user's pre-registered location data. This ensures that users receive only disaster information that is important to them.

[0346] Step 5:

[0347] The device recognizes the user's emotional state through the user interface. The emotion recognition engine analyzes the user's operation history and input patterns to determine their current emotion.

[0348] Step 6:

[0349] The server analyzes user emotion information obtained from the emotion engine. Based on this, it adjusts how disaster information is provided and selects appropriate information according to the user's emotions.

[0350] Step 7:

[0351] The device will notify users of carefully selected disaster information. By providing information in an emotionally sensitive manner, it aims to reduce user anxiety and guide them to take necessary actions.

[0352] Step 8:

[0353] The server stores the user's emotional history in a database. This stored data is then used to optimize future information delivery based on the user's tendencies.

[0354] This processing flow enables the system to provide users with emotionally resonant disaster information.

[0355] (Example 2)

[0356] Next, we will describe Example 2. 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".

[0357] Conventional disaster information systems provided information uniformly without considering the emotional state of users, which sometimes failed to alleviate their mental burden. Furthermore, the selection of appropriate information delivery methods was often inadequate, making it difficult for users to obtain the information they needed quickly and appropriately. Additionally, there was a lack of methods to utilize individual emotional histories to improve the accuracy of information provision.

[0358] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0359] In this invention, the server includes means for collecting disaster information from an information acquisition device, means for analyzing the collected information to determine the type, location, and severity of the disaster, and means for visualizing the analysis results based on spatial data. This makes it possible to provide information that takes into account the emotional state of the user, enabling timely notification of important information and reduction of mental burden. Furthermore, by utilizing individual emotional history, the accuracy of the provided content can be continuously improved.

[0360] An "information acquisition device" is a device used to collect disaster information from external sources.

[0361] "Analysis" is the process of processing collected information to determine the type, location, and severity of a disaster.

[0362] "Spatial data" refers to data used to visualize information based on geographical information.

[0363] "User" refers to an individual or group that uses the system.

[0364] "Location data" refers to geographical information that indicates the user's current location.

[0365] An "emotion analysis device" is a device used to recognize the emotional state of a user.

[0366] "Information provision method" refers to the method of determining what format the analyzed information will be provided to users.

[0367] "Emotional state" refers to the user's psychological state, and information provision is adjusted based on this.

[0368] "Notification" refers to the act of informing users of the adjusted information.

[0369] "Emotional history" refers to a record of a user's past emotions.

[0370] A system implementing this invention efficiently provides disaster information through the interaction of a server, terminal, and user, and enables appropriate responses according to the user's emotional state.

[0371] The server uses information acquisition devices to collect disaster information from multiple sources. These include news sites, social media, and government disaster information pages. On the server, the Python requests library is used, and necessary information is retrieved using BeautifulSoup. This information is analyzed to determine the type of disaster, its location, and its severity. The natural language processing library NLTK is used for the analysis. In addition, the disaster information is converted into spatial data using GeoPandas and visualized on a map.

[0372] The device uses the user's location information to compare it with geographic data obtained from the server. In this process, the device uses GPS to determine the user's current location. Based on this, it reads the user's emotional state in order to select disaster information relevant to the user and adjust the method of information delivery. The emotion analysis device implements a machine learning model using TensorFlow, which infers the emotional state from the user's input patterns and operation history.

[0373] Users receive information tailored to their needs via their devices, enabling them to respond quickly and appropriately. Important information is communicated in a way that is sensitive to the user's feelings, providing reassuring and clear instructions. For example, if a user expresses anxiety, detailed information such as, "The nearest evacuation center is XX. Here are the directions," is provided.

[0374] An example of a prompt message to utilize this system is: "Present information about the current disaster situation and customize the notification content based on the user's current emotional state. If the user is anxious, provide specific safety guidelines; if calm, provide summary information." Based on this, the AI ​​model will provide the most appropriate information.

[0375] This invention aims to reduce the psychological burden during disasters and contribute to ensuring user safety through the smooth provision of information.

[0376] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0377] Step 1:

[0378] The server collects disaster information from external sources. URLs of news sites, social media, and government disaster information pages are provided as input. The Python requests library is used to retrieve HTML data from these sites, and BeautifulSoup is used to scrape the necessary information and output it. The collected data is saved in string format for subsequent analysis.

[0379] Step 2:

[0380] The server analyzes the collected information using natural language processing technology. Disaster information is provided as input in string format. The NLTK library is used to tokenize the text data. Based on the tokenized data, key phrases are extracted to determine the type, location, and severity of the disaster. The analysis results are output in associative array format.

[0381] Step 3:

[0382] The server visualizes the analysis results based on map information. The analysis results are provided as input in the form of an associative array. Using GeoPandas, the disaster information is converted into geographic data, generating GIS data as output. The GIS data is saved for plotting on a map and used for visual verification.

[0383] Step 4:

[0384] The device obtains the user's location information via a GPS module. The user's current location data is provided as input. Mapping software (e.g., folium) running on the device then overlays relevant disaster information onto a map. The output is a map image showing the user's current location and related information superimposed.

[0385] Step 5:

[0386] The sentiment analyzer, which operates on the terminal, recognizes the user's emotional state. The user's operation history and input pattern data are provided as input. A machine learning model using TensorFlow infers the emotional state (anxiety, calmness, etc.) from this data. The recognized emotional state is output as sentiment data, as it influences how subsequent information is provided.

[0387] Step 6:

[0388] The server adjusts the information delivery method based on the recognized emotional state. Emotional data and GIS data are provided as input. If the emotional state is anxious, detailed evacuation information and action guidelines are provided; if the emotional state is calm, summary information is provided. The adjusted information is output in a customized text or visual data format.

[0389] Step 7:

[0390] The device notifies the user of adjusted information. Customized information data is provided as input. Using the notification function, important updates and emotionally sensitive information are sent to the user in real time. Output is presented to the user as an alarm sound, an alert screen, or explanatory text.

[0391] This series of steps allows users to receive accurate and timely information tailored to their emotional state at any given time.

[0392] (Application Example 2)

[0393] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0394] During disasters, there is a need to provide users with personalized, rapid, and appropriate information. However, general information systems fail to consider users' emotional states, making it difficult to alleviate their anxiety and confusion. Furthermore, there is the problem of information overload or insufficiency hindering swift responses and evacuation actions.

[0395] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0396] In this invention, the server includes means for acquiring disaster-related data from an information source, means for analyzing the acquired data to determine the nature, location, and urgency of the disaster, means for visually presenting the analyzed data based on geographical information, means for selecting highly relevant data based on the user's location data, and means for analyzing the user's emotional state and adjusting the content provided according to that emotional state. This enables the provision of information tailored to the user's emotions and rapid evacuation support.

[0397] An "information source" is a system or medium that provides the source for obtaining disaster-related data.

[0398] "Disaster-related data" refers to data that includes information about the nature, location, and urgency of a disaster.

[0399] "Analysis" is the process performed to determine the characteristics of a disaster from the acquired data.

[0400] "Geographic information" refers to map data and location data that contain information related to a specific place.

[0401] "To present visually" means to express information in a way that is easy to understand visually.

[0402] "User location data" refers to information that indicates the user's geographical location.

[0403] "Highly relevant data" refers to data that is of high priority and directly relevant to a particular user.

[0404] "Emotional state" is an indicator that shows the user's emotional state and psychological response.

[0405] "Adjusting the content provided" means changing the way information is presented and the content of that information to suit the user's emotional state.

[0406] This invention is a system that provides personalized information to users quickly during disasters and adjusts the information according to their emotional state. The system mainly consists of a server and terminals.

[0407] The server acquires disaster-related data from information sources and analyzes that data to determine the nature, location, and urgency of the disaster. Specifically, it uses a natural language processing engine for data analysis and presents the data visually using a Geographic Information System (GIS). This makes it possible to instantly reflect important disaster-related information.

[0408] The device acquires the user's location data and selects highly relevant information from the data transmitted from the server. Furthermore, an emotion engine runs on the device to analyze the user's emotional state, inferring it based on the user's operation history and input patterns. As a result, the server adjusts the content provided based on the user's emotional state and delivers optimized information to the user.

[0409] As a concrete example, when an earthquake occurs, the server analyzes various data and visually provides residents in the affected area with information on emergency evacuation routes and safe shelters. Furthermore, if a user indicates anxiety on their device, they will receive more detailed reassurance information and guidance via push notifications. In this process, it is also possible to use a generative AI model to create appropriate prompts for the information the user is seeking.

[0410] An example of a prompt message would be, "Please tell me more about how to provide information that takes into account emotional states in a real-time evacuation guidance app during disasters." This would serve as a guide for the system to provide appropriate information.

[0411] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0412] Step 1:

[0413] The server acquires disaster-related data from information sources. Specifically, it accesses open data on the internet and dedicated disaster information sources, and sends the collected data to the server. At this point, the input is raw data from the information sources, and the output is unprocessed disaster-related data stored on the server.

[0414] Step 2:

[0415] The server analyzes the acquired data to determine the nature, location, and urgency of the disaster. A natural language processing engine is used for data analysis, classifying each data point through keyword analysis and other methods. The input is the raw data obtained in step 1, and the output is analyzed data labeled with disaster characteristics. Specifically, it performs text analysis and statistical modeling.

[0416] Step 3:

[0417] The server visually presents the analyzed data based on geographical information. Using GIS, it marks the location of disasters on a map. The input is the analyzed data obtained in step 2, and the output is visualized geographical information. Specifically, this involves data overlaying onto a map and generating interactive maps.

[0418] Step 4:

[0419] The terminal acquires the user's location data and selects highly relevant information from the data sent from the server. The input is the terminal's location information and the geographical visualization data from step 3, and the output is filtered information relevant to the user. Specifically, it uses distance calculation and filtering algorithms.

[0420] Step 5:

[0421] An emotion engine runs on the device to analyze the user's emotional state, inferring it based on the user's operation history and input patterns. The input is the user's operation data within the app, and the output is the inferred emotional state. Specifically, this is an inference of a machine learning model.

[0422] Step 6:

[0423] The server adjusts the content provided based on the user's emotional state, delivering optimized information to the user. The input is the emotional state obtained in step 5 and the refined information from step 4, and the output is emotionally sensitive information. Specifically, it performs tasks such as prioritizing information and selecting prompts.

[0424] Step 7:

[0425] The user receives information in real time via their device and follows instructions as needed. The input is the adjusted information from step 6, and the output is the user's actions and responses. Specific actions include using the app's notification and guidance features.

[0426] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0427] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include those described above. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions shown by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0428] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0429] [Third Embodiment]

[0430] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0431] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0432] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0433] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0434] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0435] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0436] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0437] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0438] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0439] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0440] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0441] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0442] This invention is a system for providing rapid information during disasters. It automatically collects and analyzes disaster-related information from information sources to determine the type, location, and severity of the disaster, and immediately notifies users.

[0443] The system begins with the server accessing APIs of information providers to periodically retrieve various disaster information. For example, the server uses APIs from social media and news sites to collect posts and articles written in natural language. This enables real-time information gathering.

[0444] Next, the collected information is analyzed on the server using natural language processing technology. During the analysis, keywords and phrases to identify the disaster are extracted from the text data, and the type and severity of the disaster are determined based on these. For example, if phrases such as "seismic intensity 5," "fire outbreak," or "flood warning" are detected, the corresponding disaster is estimated.

[0445] The analysis results are linked to geographical information and reflected in a visual map. The server uses a Geographic Information System (GIS) to plot this information on the map and prepare it for display in a user-friendly format. This process visually shows the affected areas and the locations of shelters.

[0446] The device filters information based on the user's pre-registered location and regional settings, displaying only highly relevant information. This allows users to receive important information that is relevant to them as a priority. Information tailored to the user's location is selected, and irrelevant information is not displayed.

[0447] When important information is identified, the device immediately sends a push notification to the user, prompting them to check for the new information. For example, if there is a risk of a significant aftershock, an immediate notification will be sent with a specific warning. This notification system allows users to detect danger in real time and take appropriate action.

[0448] Furthermore, the system manages billing based on user usage. Premium users can access additional features and detailed information, and billing for these is automatically handled by the server. This ensures stable service delivery and monetization.

[0449] This invention enables the realization of a system that supports user safety and decision-making during disasters by providing rapid and reliable disaster information.

[0450] The following describes the processing flow.

[0451] Step 1:

[0452] The server connects to the APIs of information providers and periodically collects disaster-related information. It filters and retrieves necessary data from social media and news sites using specific hashtags and keywords.

[0453] Step 2:

[0454] The server analyzes the collected data. Using natural language processing algorithms, it extracts keywords related to the type and severity of the disaster from the text. This analysis generates metadata such as the type of disaster, location, and time of occurrence.

[0455] Step 3:

[0456] The server uses the analyzed data to prepare for plotting on a map using a geographic information system. Here, it creates coordinate information to clearly identify the location of the disaster and visualize the extent of its impact.

[0457] Step 4:

[0458] The device filters relevant information based on the user's registered information. It selects disaster information relevant to the user based on their set location and areas of interest.

[0459] Step 5:

[0460] The terminal displays the selected information on a map. It illustrates the affected area and places icons indicating important locations such as evacuation shelters as needed.

[0461] Step 6:

[0462] The device sends notifications to the user when important information is updated. It uses push notifications to instantly deliver new information and alerts to the user.

[0463] Step 7:

[0464] The server monitors user usage and manages billing. It generates billing information and processes payments at the appropriate time according to the user's contract plan.

[0465] (Example 1)

[0466] Next, we will describe Example 1. 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."

[0467] In recent years, the increasing frequency of natural disasters has created a demand for rapid and accurate information provision, but traditional methods often lack real-time capabilities and accuracy. Furthermore, it is difficult to select relevant information for each user and encourage appropriate action. In addition, proper billing management for service usage remains a challenge.

[0468] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0469] In this invention, the server includes means for acquiring disaster information from information supply organizations, means for analyzing the acquired information to evaluate the type, location, and severity of the disaster, and means for visually presenting the analyzed information based on location information. This enables the provision of reliable disaster information in real time and the provision of customized information for each user. Furthermore, it enables appropriate billing management based on usage.

[0470] "Information supply organizations" refer to external services and systems that provide disaster information, including social media platforms and news media.

[0471] "Disaster information" refers to important data that should be provided to users, including information about the type, location, and severity of natural disasters.

[0472] "Information analysis" refers to the process of processing acquired disaster information and evaluating its type, location, and severity.

[0473] "Location information" refers to data that indicates a geographical location and is used to identify the user's current location or the area where a disaster has occurred.

[0474] "Visual presentation" refers to the process of displaying analyzed information in the form of maps, graphs, and other visual aids to make it easily understandable for users.

[0475] "User" refers to an individual or organization that uses this system to receive disaster information.

[0476] "Billing management" refers to the process of billing users appropriately based on their system usage and generating revenue.

[0477] This invention is a system that enables the rapid and accurate provision of information during disasters. The server automatically collects disaster information from social media and news media via APIs from information supply organizations. Specifically, the server uses APIs from social media platforms to obtain disaster-related posting data. It can also collect recent article information using RSS feeds from news sites.

[0478] The server analyzes the collected information using natural language processing libraries such as "spaCy" and "NLTK." This process extracts important phrases and keywords from the text data and further evaluates the urgency and reliability of the information through sentiment analysis.

[0479] The analyzed information is visually displayed on a map using GIS software such as "ArcGIS" and "QGIS." Visualizing geographic information makes it possible to intuitively understand the location and extent of the disaster.

[0480] The device filters out highly relevant disaster information based on the user's location and pre-configured regional information. This process allows the user to receive only the necessary information while reducing the associated noise.

[0481] Important information is instantly communicated to users via push notifications. As a concrete example, Firebase Cloud Messaging (FCM) is used to provide real-time notifications of critical disaster information, such as earthquake intensity in specific areas.

[0482] Furthermore, this system also includes a function to automatically manage billing for each user. The server charges based on usage and provides premium users with additional features and detailed information. This enables stable service provision and monetization.

[0483] As a concrete example, if an earthquake with a seismic intensity of 5 occurs in the user's area, the server collects and analyzes that information, and the device immediately sends a push notification based on the results filtered according to the location information.

[0484] Examples of prompt statements are as follows:

[0485] "Design a program that collects information about earthquakes with a seismic intensity of 5 and notifies users in a designated area. Describe in detail the necessary APIs, natural language processing techniques, and specific processing steps using GIS software."

[0486] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0487] Step 1:

[0488] The server accesses APIs of information providers to collect disaster information. The input is requests to the API, and the output is data of posts and articles related to the disaster. Specifically, the server periodically calls the API to retrieve text data from social media and news sources.

[0489] Step 2:

[0490] The server analyzes the collected text data using a natural language processing library. The input is the collected text data, and the output is data including extracted keywords, disaster type, location, and severity. Specifically, the server uses the "spaCy" library to extract specific phrases and keywords from the text and evaluate the urgency of the information by performing sentiment analysis.

[0491] Step 3:

[0492] The server plots the analysis results on a map using GIS software. The input is the analyzed geographic information data, and the output is a map visualizing the disaster situation. Specifically, the server uses the "ArcGIS" tool to map the extracted point information and show the affected area and the locations of evacuation shelters.

[0493] Step 4:

[0494] The terminal filters highly relevant information based on the location information registered by the user. The input is mapped disaster information and the user's location information, and the output is filtered relevant information. Specifically, the terminal selects only disaster information related to the user's specified area, and displays only the information the user needs.

[0495] Step 5:

[0496] The device sends important information to the user as a push notification. The input is filtered important information, and the output is a notification message to the user. Specifically, the device uses "Firebase Cloud Messaging" to notify the user of disaster information in real time in the form of an alert.

[0497] Step 6:

[0498] The server manages billing based on user usage. Inputs are user usage data and subscription information, while output is billing data. Specifically, the server analyzes user data processing volume monthly and automatically bills based on that analysis.

[0499] (Application Example 1)

[0500] Next, we will explain Application Example 1. In the following explanation, 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."

[0501] In the event of a disaster, a system is needed that provides accurate and relevant information in real time, enabling local residents and social infrastructure to take swift and safe actions. This invention aims to solve this problem by rapidly acquiring and analyzing data from multiple sources and efficiently transmitting the necessary information to users. Conventional systems had the potential for delays in information acquisition and erroneous decisions based on inaccurate information, so there was a need for a means to improve this.

[0502] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0503] In this invention, the server includes means for acquiring disaster-related information from an information provision medium, means for analyzing the acquired information to determine the type, location, and severity of the disaster, and means for visually displaying the analyzed information based on geographic information. This enables users to take quick and appropriate evacuation actions based on geographic information that is updated in real time.

[0504] An "information provision medium" refers to a platform or interface used to provide data, including disaster-related information.

[0505] "Means of acquisition" refers to the methods and technologies for receiving data from information provision media and incorporating it into a system.

[0506] "Means of analysis" refer to technologies that process acquired data, understand its content concretely, and convert it into information useful to users.

[0507] "Geographic information" refers to information that includes data related to specific locations or regions, enabling location-based decision-making.

[0508] "Means of visual display" refers to technologies that use visual elements such as maps and graphs to visually represent information in an easy-to-understand manner.

[0509] "User location information" refers to data about the current location of each individual user of the system.

[0510] "Methods for selecting highly relevant information" refer to technologies for selecting information that is of high importance and necessity to the user from the information that has been acquired.

[0511] "Means of notification" refer to approaches and technologies used to inform users of selected information and encourage their awareness and actions.

[0512] "Methods for dynamically updating" refer to technologies that immediately reflect newly acquired information and analysis results in geographic information and displayed content.

[0513] "Methods for reanalysis" refer to techniques for re-analyzing information based on the latest data and providing timely and accurate information.

[0514] The system for implementing this invention consists mainly of a server and terminals. The server accesses the API of an information provision medium and acquires disaster-related information in real time. The hardware used for this is a standard server computer, and the software incorporates a script that controls API access. The data is first analyzed using natural language processing technology. Python and NLP libraries (e.g., SpaCy) are used for the analysis, and data processing is performed to determine the type and severity of the information.

[0515] The analyzed data is plotted on a map using a Geographic Information System (GIS) and displayed in an easy-to-understand visual format. Leaflet.js is used as the software for this purpose. Specifically, the acquired and analyzed data is overlaid on the map in an intuitively understandable form. The device selects highly relevant information based on the user's location and visualizes it on the smartphone. Relevant information is immediately sent to the user as a push notification, supporting user actions at the appropriate time.

[0516] For example, if a "river flood warning" is issued during heavy rain, users will be notified immediately. The device displays real-time updated map information, allowing users to check the nearest evacuation shelters and dangerous areas. Furthermore, if the collected data is new, it is re-analyzed to always maintain the most up-to-date information.

[0517] An example of a prompt to be input into the generation AI model would be: "Assess the potential disaster risks to a specific area using the following information: flood advisories, strong wind warnings, and evacuation shelter location data. Generate a warning message based on detailed disaster type and location information." The warning message generated based on this prompt will be used as part of the information provided to the user.

[0518] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0519] Step 1:

[0520] The server accesses the API of an information provision medium to retrieve disaster-related data. The input is the response data from the API, which the server receives and prepares for analysis. The output is the received raw data. The retrieved data plays a crucial role in subsequent processing.

[0521] Step 2:

[0522] The server performs natural language processing on the acquired data to analyze the type, location, and severity of the disaster. The input for this step is the raw data acquired in step 1, and keywords and important phrases are extracted from the text using an NLP library. The output is the analyzed information, which identifies the type and severity of the disaster.

[0523] Step 3:

[0524] The server inputs the analyzed information into a Geographic Information System (GIS) and visualizes it on a map. The input for this step is the analysis results from step 2. The output is visualized map data, providing disaster information in an easy-to-understand format for users. Libraries such as Leaflet.js are used to display the extent of the disaster's impact and the locations of evacuation shelters on the map.

[0525] Step 4:

[0526] The device obtains the user's location information and filters it for the most relevant information. The input is the user's location information stored on the device and the map data from step 3. Based on this information, the device selects the most important notifications for the user. The output is the selected information, which is presented to the user on the device.

[0527] Step 5:

[0528] The device sends a push notification to the user based on the selected information. The input for this step is the information selected in step 4. The output is a notification to the user, and the device displays warnings and alerts to the user in real time.

[0529] Step 6:

[0530] The server performs reanalysis based on newly acquired data and user feedback. The inputs for this step are new data and user feedback. The server reanalyzes the data and prepares information that reflects the latest situation. The output is the updated analysis results, maintaining the accuracy of the information provided to users throughout the system.

[0531] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0532] This invention is a system that provides necessary information quickly during disasters and delivers information while taking into account the user's emotional state. In particular, it is characterized by the provision of information optimized according to the user's mental state by combining it with an emotion engine.

[0533] The system begins with a server collecting disaster-related information from information sources. The collected information is then analyzed by the server using natural language processing technology to determine the type, location, and severity of the disaster. The results of this analysis are then plotted on a map using a GIS (Geographic Information System).

[0534] At this stage, the device selects highly relevant information based on the user's location data. This selected information is then ready to be provided to the user.

[0535] Next, the emotion engine operates on the device to recognize the user's current emotional state. Emotion recognition is inferred from the user interface's operation history, selections, and user input patterns. This information, along with the user's emotional history, is sent to the server, where appropriate actions are considered.

[0536] The server adjusts the way and content of information provided based on the emotional state obtained from the emotion engine. For example, if a user is showing signs of anxiety, more detailed evacuation information and safety check guides will be provided. On the other hand, users who are relatively calm will be provided with information that focuses on summaries.

[0537] This adjusted information is notified to users through their devices, allowing for real-time follow-up. When there are important updates, notifications are sent in an emotionally sensitive manner to enhance user confidence.

[0538] Furthermore, the system accumulates users' emotional history, which can be used to improve the accuracy of future information provision. This ensures that users continuously receive information optimized for their needs.

[0539] This system goes beyond simply providing information; it enables disaster response support that is sensitive to the user's emotions, contributing to reducing the psychological burden on users and ensuring their safety.

[0540] The following describes the processing flow.

[0541] Step 1:

[0542] The server connects to APIs of information sources to periodically collect disaster-related information. These sources include social media and news sites, and the server filters the data using specific hashtags and keywords.

[0543] Step 2:

[0544] The server analyzes the collected information. Using natural language processing, it extracts keywords related to the type, location, and severity of the disaster to identify the disaster information. This analysis generates the necessary metadata.

[0545] Step 3:

[0546] The server uses GIS to plot the analyzed disaster information on a map. It processes coordinate information to visually display the disaster area and its impact on a map.

[0547] Step 4:

[0548] The device selects highly relevant information based on the user's pre-registered location data. This ensures that users receive only disaster information that is important to them.

[0549] Step 5:

[0550] The device recognizes the user's emotional state through the user interface. The emotion recognition engine analyzes the user's operation history and input patterns to determine their current emotion.

[0551] Step 6:

[0552] The server analyzes user emotion information obtained from the emotion engine. Based on this, it adjusts how disaster information is provided and selects appropriate information according to the user's emotions.

[0553] Step 7:

[0554] The device will notify users of carefully selected disaster information. By providing information in an emotionally sensitive manner, it aims to reduce user anxiety and guide them to take necessary actions.

[0555] Step 8:

[0556] The server stores the user's emotional history in a database. This stored data is then used to optimize future information delivery based on the user's tendencies.

[0557] This processing flow enables the system to provide users with emotionally resonant disaster information.

[0558] (Example 2)

[0559] Next, we will describe Example 2. 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."

[0560] Conventional disaster information systems provided information uniformly without considering the emotional state of users, which sometimes failed to alleviate their mental burden. Furthermore, the selection of appropriate information delivery methods was often inadequate, making it difficult for users to obtain the information they needed quickly and appropriately. Additionally, there was a lack of methods to utilize individual emotional histories to improve the accuracy of information provision.

[0561] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0562] In this invention, the server includes means for collecting disaster information from an information acquisition device, means for analyzing the collected information to determine the type, location, and severity of the disaster, and means for visualizing the analysis results based on spatial data. This makes it possible to provide information that takes into account the emotional state of the user, enabling timely notification of important information and reduction of mental burden. Furthermore, by utilizing individual emotional history, the accuracy of the provided content can be continuously improved.

[0563] An "information acquisition device" is a device used to collect disaster information from external sources.

[0564] "Analysis" is the process of processing collected information to determine the type, location, and severity of a disaster.

[0565] "Spatial data" refers to data used to visualize information based on geographical information.

[0566] "User" refers to an individual or group that uses the system.

[0567] "Location data" refers to geographical information that indicates the user's current location.

[0568] An "emotion analysis device" is a device used to recognize the emotional state of a user.

[0569] "Information provision method" refers to the method of determining what format the analyzed information will be provided to users.

[0570] "Emotional state" refers to the user's psychological state, and information provision is adjusted based on this.

[0571] "Notification" refers to the act of informing users of the adjusted information.

[0572] "Emotional history" refers to a record of a user's past emotions.

[0573] A system implementing this invention efficiently provides disaster information through the interaction of a server, terminal, and user, and enables appropriate responses according to the user's emotional state.

[0574] The server uses information acquisition devices to collect disaster information from multiple sources. These include news sites, social media, and government disaster information pages. On the server, the Python requests library is used, and necessary information is retrieved using BeautifulSoup. This information is analyzed to determine the type of disaster, its location, and its severity. The natural language processing library NLTK is used for the analysis. In addition, the disaster information is converted into spatial data using GeoPandas and visualized on a map.

[0575] The device uses the user's location information to compare it with geographic data obtained from the server. In this process, the device uses GPS to determine the user's current location. Based on this, it reads the user's emotional state in order to select disaster information relevant to the user and adjust the method of information delivery. The emotion analysis device implements a machine learning model using TensorFlow, which infers the emotional state from the user's input patterns and operation history.

[0576] Users receive information tailored to their needs via their devices, enabling them to respond quickly and appropriately. Important information is communicated in a way that is sensitive to the user's feelings, providing reassuring and clear instructions. For example, if a user expresses anxiety, detailed information such as, "The nearest evacuation center is XX. Here are the directions," is provided.

[0577] An example of a prompt message to utilize this system is: "Present information about the current disaster situation and customize the notification content based on the user's current emotional state. If the user is anxious, provide specific safety guidelines; if calm, provide summary information." Based on this, the AI ​​model will provide the most appropriate information.

[0578] This invention aims to reduce the psychological burden during disasters and contribute to ensuring user safety through the smooth provision of information.

[0579] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0580] Step 1:

[0581] The server collects disaster information from external sources. URLs of news sites, social media, and government disaster information pages are provided as input. The Python requests library is used to retrieve HTML data from these sites, and BeautifulSoup is used to scrape the necessary information and output it. The collected data is saved in string format for subsequent analysis.

[0582] Step 2:

[0583] The server analyzes the collected information using natural language processing technology. Disaster information is provided as input in string format. The NLTK library is used to tokenize the text data. Based on the tokenized data, key phrases are extracted to determine the type, location, and severity of the disaster. The analysis results are output in associative array format.

[0584] Step 3:

[0585] The server visualizes the analysis results based on map information. The analysis results are provided as input in the form of an associative array. Using GeoPandas, the disaster information is converted into geographic data, generating GIS data as output. The GIS data is saved for plotting on a map and used for visual verification.

[0586] Step 4:

[0587] The device obtains the user's location information via a GPS module. The user's current location data is provided as input. Mapping software (e.g., folium) running on the device then overlays relevant disaster information onto a map. The output is a map image showing the user's current location and related information superimposed.

[0588] Step 5:

[0589] The sentiment analyzer, which operates on the terminal, recognizes the user's emotional state. The user's operation history and input pattern data are provided as input. A machine learning model using TensorFlow infers the emotional state (anxiety, calmness, etc.) from this data. The recognized emotional state is output as sentiment data, as it influences how subsequent information is provided.

[0590] Step 6:

[0591] The server adjusts the information delivery method based on the recognized emotional state. Emotional data and GIS data are provided as input. If the emotional state is anxious, detailed evacuation information and action guidelines are provided; if the emotional state is calm, summary information is provided. The adjusted information is output in a customized text or visual data format.

[0592] Step 7:

[0593] The device notifies the user of adjusted information. Customized information data is provided as input. Using the notification function, important updates and emotionally sensitive information are sent to the user in real time. Output is presented to the user as an alarm sound, an alert screen, or explanatory text.

[0594] This series of steps allows users to receive accurate and timely information tailored to their emotional state at any given time.

[0595] (Application Example 2)

[0596] Next, we will explain application example 2. In the following explanation, 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."

[0597] During disasters, there is a need to provide users with personalized, rapid, and appropriate information. However, general information systems fail to consider users' emotional states, making it difficult to alleviate their anxiety and confusion. Furthermore, there is the problem of information overload or insufficiency hindering swift responses and evacuation actions.

[0598] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0599] In this invention, the server includes means for acquiring disaster-related data from an information source, means for analyzing the acquired data to determine the nature, location, and urgency of the disaster, means for visually presenting the analyzed data based on geographical information, means for selecting highly relevant data based on the user's location data, and means for analyzing the user's emotional state and adjusting the content provided according to that emotional state. This enables the provision of information tailored to the user's emotions and rapid evacuation support.

[0600] An "information source" is a system or medium that provides the source for obtaining disaster-related data.

[0601] "Disaster-related data" refers to data that includes information about the nature, location, and urgency of a disaster.

[0602] "Analysis" is the process performed to determine the characteristics of a disaster from the acquired data.

[0603] "Geographic information" refers to map data and location data that contain information related to a specific place.

[0604] "To present visually" means to express information in a way that is easy to understand visually.

[0605] "User location data" refers to information that indicates the user's geographical location.

[0606] "Highly relevant data" refers to data that is of high priority and directly relevant to a particular user.

[0607] "Emotional state" is an indicator that shows the user's emotional state and psychological response.

[0608] "Adjusting the content provided" means changing the way information is presented and the content of that information to suit the user's emotional state.

[0609] This invention is a system that provides personalized information to users quickly during disasters and adjusts the information according to their emotional state. The system mainly consists of a server and terminals.

[0610] The server acquires disaster-related data from information sources and analyzes that data to determine the nature, location, and urgency of the disaster. Specifically, it uses a natural language processing engine for data analysis and presents the data visually using a Geographic Information System (GIS). This makes it possible to instantly reflect important disaster-related information.

[0611] The device acquires the user's location data and selects highly relevant information from the data transmitted from the server. Furthermore, an emotion engine runs on the device to analyze the user's emotional state, inferring it based on the user's operation history and input patterns. As a result, the server adjusts the content provided based on the user's emotional state and delivers optimized information to the user.

[0612] As a concrete example, when an earthquake occurs, the server analyzes various data and visually provides residents in the affected area with information on emergency evacuation routes and safe shelters. Furthermore, if a user indicates anxiety on their device, they will receive more detailed reassurance information and guidance via push notifications. In this process, it is also possible to use a generative AI model to create appropriate prompts for the information the user is seeking.

[0613] An example of a prompt message would be, "Please tell me more about how to provide information that takes into account emotional states in a real-time evacuation guidance app during disasters." This would serve as a guide for the system to provide appropriate information.

[0614] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0615] Step 1:

[0616] The server acquires disaster-related data from information sources. Specifically, it accesses open data on the internet and dedicated disaster information sources, and sends the collected data to the server. At this point, the input is raw data from the information sources, and the output is unprocessed disaster-related data stored on the server.

[0617] Step 2:

[0618] The server analyzes the acquired data to determine the nature, location, and urgency of the disaster. A natural language processing engine is used for data analysis, classifying each data point through keyword analysis and other methods. The input is the raw data obtained in step 1, and the output is analyzed data labeled with disaster characteristics. Specifically, it performs text analysis and statistical modeling.

[0619] Step 3:

[0620] The server visually presents the analyzed data based on geographical information. Using GIS, it marks the location of disasters on a map. The input is the analyzed data obtained in step 2, and the output is visualized geographical information. Specifically, this involves data overlaying onto a map and generating interactive maps.

[0621] Step 4:

[0622] The terminal acquires the user's location data and selects highly relevant information from the data sent from the server. The input is the terminal's location information and the geographical visualization data from step 3, and the output is filtered information relevant to the user. Specifically, it uses distance calculation and filtering algorithms.

[0623] Step 5:

[0624] An emotion engine runs on the device to analyze the user's emotional state, inferring it based on the user's operation history and input patterns. The input is the user's operation data within the app, and the output is the inferred emotional state. Specifically, this is an inference of a machine learning model.

[0625] Step 6:

[0626] The server adjusts the content provided based on the user's emotional state, delivering optimized information to the user. The input is the emotional state obtained in step 5 and the refined information from step 4, and the output is emotionally sensitive information. Specifically, it performs tasks such as prioritizing information and selecting prompts.

[0627] Step 7:

[0628] The user receives information in real time via their device and follows instructions as needed. The input is the adjusted information from step 6, and the output is the user's actions and responses. Specific actions include using the app's notification and guidance features.

[0629] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0630] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include those described above. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions shown by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0631] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0632] [Fourth Embodiment]

[0633] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0634] As shown in Figure 7, the 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.

[0635] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0636] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0637] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0638] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0639] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0640] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0641] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0642] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0643] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0644] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0645] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0646] This invention is a system for providing rapid information during disasters. It automatically collects and analyzes disaster-related information from information sources to determine the type, location, and severity of the disaster, and immediately notifies users.

[0647] The system begins with the server accessing APIs of information providers to periodically retrieve various disaster information. For example, the server uses APIs from social media and news sites to collect posts and articles written in natural language. This enables real-time information gathering.

[0648] Next, the collected information is analyzed on the server using natural language processing technology. During the analysis, keywords and phrases to identify the disaster are extracted from the text data, and the type and severity of the disaster are determined based on these. For example, if phrases such as "seismic intensity 5," "fire outbreak," or "flood warning" are detected, the corresponding disaster is estimated.

[0649] The analysis results are linked to geographical information and reflected in a visual map. The server uses a Geographic Information System (GIS) to plot this information on the map and prepare it for display in a user-friendly format. This process visually shows the affected areas and the locations of shelters.

[0650] The device filters information based on the user's pre-registered location and regional settings, displaying only highly relevant information. This allows users to receive important information that is relevant to them as a priority. Information tailored to the user's location is selected, and irrelevant information is not displayed.

[0651] When important information is identified, the device immediately sends a push notification to the user, prompting them to check for the new information. For example, if there is a risk of a significant aftershock, an immediate notification will be sent with a specific warning. This notification system allows users to detect danger in real time and take appropriate action.

[0652] Furthermore, the system manages billing based on user usage. Premium users can access additional features and detailed information, and billing for these is automatically handled by the server. This ensures stable service delivery and monetization.

[0653] This invention enables the realization of a system that supports user safety and decision-making during disasters by providing rapid and reliable disaster information.

[0654] The following describes the processing flow.

[0655] Step 1:

[0656] The server connects to the APIs of information providers and periodically collects disaster-related information. It filters and retrieves necessary data from social media and news sites using specific hashtags and keywords.

[0657] Step 2:

[0658] The server analyzes the collected data. Using natural language processing algorithms, it extracts keywords related to the type and severity of the disaster from the text. This analysis generates metadata such as the type of disaster, location, and time of occurrence.

[0659] Step 3:

[0660] The server uses the analyzed data to prepare for plotting on a map using a geographic information system. Here, it creates coordinate information to clearly identify the location of the disaster and visualize the extent of its impact.

[0661] Step 4:

[0662] The device filters relevant information based on the user's registered information. It selects disaster information relevant to the user based on their set location and areas of interest.

[0663] Step 5:

[0664] The terminal displays the selected information on a map. It illustrates the affected area and places icons indicating important locations such as evacuation shelters as needed.

[0665] Step 6:

[0666] The device sends notifications to the user when important information is updated. It uses push notifications to instantly deliver new information and alerts to the user.

[0667] Step 7:

[0668] The server monitors user usage and manages billing. It generates billing information and processes payments at the appropriate time according to the user's contract plan.

[0669] (Example 1)

[0670] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0671] In recent years, the increasing frequency of natural disasters has created a demand for rapid and accurate information provision, but traditional methods often lack real-time capabilities and accuracy. Furthermore, it is difficult to select relevant information for each user and encourage appropriate action. In addition, proper billing management for service usage remains a challenge.

[0672] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0673] In this invention, the server includes means for acquiring disaster information from information supply organizations, means for analyzing the acquired information to evaluate the type, location, and severity of the disaster, and means for visually presenting the analyzed information based on location information. This enables the provision of reliable disaster information in real time and the provision of customized information for each user. Furthermore, it enables appropriate billing management based on usage.

[0674] "Information supply organizations" refer to external services and systems that provide disaster information, including social media platforms and news media.

[0675] "Disaster information" refers to important data that should be provided to users, including information about the type, location, and severity of natural disasters.

[0676] "Information analysis" refers to the process of processing acquired disaster information and evaluating its type, location, and severity.

[0677] "Location information" refers to data that indicates a geographical location and is used to identify the user's current location or the area where a disaster has occurred.

[0678] "Visual presentation" refers to the process of displaying analyzed information in the form of maps, graphs, and other visual aids to make it easily understandable for users.

[0679] "User" refers to an individual or organization that uses this system to receive disaster information.

[0680] "Billing management" refers to the process of billing users appropriately based on their system usage and generating revenue.

[0681] This invention is a system that enables the rapid and accurate provision of information during disasters. The server automatically collects disaster information from social media and news media via APIs from information supply organizations. Specifically, the server uses APIs from social media platforms to obtain disaster-related posting data. It can also collect recent article information using RSS feeds from news sites.

[0682] The server analyzes the collected information using natural language processing libraries such as "spaCy" and "NLTK." This process extracts important phrases and keywords from the text data and further evaluates the urgency and reliability of the information through sentiment analysis.

[0683] The analyzed information is visually displayed on a map using GIS software such as "ArcGIS" and "QGIS." Visualizing geographic information makes it possible to intuitively understand the location and extent of the disaster.

[0684] The device filters out highly relevant disaster information based on the user's location and pre-configured regional information. This process allows the user to receive only the necessary information while reducing the associated noise.

[0685] Important information is instantly communicated to users via push notifications. As a concrete example, Firebase Cloud Messaging (FCM) is used to provide real-time notifications of critical disaster information, such as earthquake intensity in specific areas.

[0686] Furthermore, this system also includes a function to automatically manage billing for each user. The server charges based on usage and provides premium users with additional features and detailed information. This enables stable service provision and monetization.

[0687] As a concrete example, if an earthquake with a seismic intensity of 5 occurs in the user's area, the server collects and analyzes that information, and the device immediately sends a push notification based on the results filtered according to the location information.

[0688] Examples of prompt statements are as follows:

[0689] "Design a program that collects information about earthquakes with a seismic intensity of 5 and notifies users in a designated area. Describe in detail the necessary APIs, natural language processing techniques, and specific processing steps using GIS software."

[0690] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0691] Step 1:

[0692] The server accesses APIs of information providers to collect disaster information. The input is requests to the API, and the output is data of posts and articles related to the disaster. Specifically, the server periodically calls the API to retrieve text data from social media and news sources.

[0693] Step 2:

[0694] The server analyzes the collected text data using a natural language processing library. The input is the collected text data, and the output is data including extracted keywords, disaster type, location, and severity. Specifically, the server uses the "spaCy" library to extract specific phrases and keywords from the text and evaluate the urgency of the information by performing sentiment analysis.

[0695] Step 3:

[0696] The server plots the analysis results on a map using GIS software. The input is the analyzed geographic information data, and the output is a map visualizing the disaster situation. Specifically, the server uses the "ArcGIS" tool to map the extracted point information and show the affected area and the locations of evacuation shelters.

[0697] Step 4:

[0698] The terminal filters highly relevant information based on the location information registered by the user. The input is mapped disaster information and the user's location information, and the output is filtered relevant information. Specifically, the terminal selects only disaster information related to the user's specified area, and displays only the information the user needs.

[0699] Step 5:

[0700] The device sends important information to the user as a push notification. The input is filtered important information, and the output is a notification message to the user. Specifically, the device uses "Firebase Cloud Messaging" to notify the user of disaster information in real time in the form of an alert.

[0701] Step 6:

[0702] The server manages billing based on user usage. Inputs are user usage data and subscription information, while output is billing data. Specifically, the server analyzes user data processing volume monthly and automatically bills based on that analysis.

[0703] (Application Example 1)

[0704] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0705] In the event of a disaster, a system is needed that provides accurate and relevant information in real time, enabling local residents and social infrastructure to take swift and safe actions. This invention aims to solve this problem by rapidly acquiring and analyzing data from multiple sources and efficiently transmitting the necessary information to users. Conventional systems had the potential for delays in information acquisition and erroneous decisions based on inaccurate information, so there was a need for a means to improve this.

[0706] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0707] In this invention, the server includes means for acquiring disaster-related information from an information provision medium, means for analyzing the acquired information to determine the type, location, and severity of the disaster, and means for visually displaying the analyzed information based on geographic information. This enables users to take quick and appropriate evacuation actions based on geographic information that is updated in real time.

[0708] An "information provision medium" refers to a platform or interface used to provide data, including disaster-related information.

[0709] "Means of acquisition" refers to the methods and technologies for receiving data from information provision media and incorporating it into a system.

[0710] "Means of analysis" refer to technologies that process acquired data, understand its content concretely, and convert it into information useful to users.

[0711] "Geographic information" refers to information that includes data related to specific locations or regions, enabling location-based decision-making.

[0712] "Means of visual display" refers to technologies that use visual elements such as maps and graphs to visually represent information in an easy-to-understand manner.

[0713] "User location information" refers to data about the current location of each individual user of the system.

[0714] "Methods for selecting highly relevant information" refer to technologies for selecting information that is of high importance and necessity to the user from the information that has been acquired.

[0715] "Means of notification" refer to approaches and technologies used to inform users of selected information and encourage their awareness and actions.

[0716] "Methods for dynamically updating" refer to technologies that immediately reflect newly acquired information and analysis results in geographic information and displayed content.

[0717] "Methods for reanalysis" refer to techniques for re-analyzing information based on the latest data and providing timely and accurate information.

[0718] The system for implementing this invention consists mainly of a server and terminals. The server accesses the API of an information provision medium and acquires disaster-related information in real time. The hardware used for this is a standard server computer, and the software incorporates a script that controls API access. The data is first analyzed using natural language processing technology. Python and NLP libraries (e.g., SpaCy) are used for the analysis, and data processing is performed to determine the type and severity of the information.

[0719] The analyzed data is plotted on a map using a Geographic Information System (GIS) and displayed in an easy-to-understand visual format. Leaflet.js is used as the software for this purpose. Specifically, the acquired and analyzed data is overlaid on the map in an intuitively understandable form. The device selects highly relevant information based on the user's location and visualizes it on the smartphone. Relevant information is immediately sent to the user as a push notification, supporting user actions at the appropriate time.

[0720] For example, if a "river flood warning" is issued during heavy rain, users will be notified immediately. The device displays real-time updated map information, allowing users to check the nearest evacuation shelters and dangerous areas. Furthermore, if the collected data is new, it is re-analyzed to always maintain the most up-to-date information.

[0721] An example of a prompt to be input into the generation AI model would be: "Assess the potential disaster risks to a specific area using the following information: flood advisories, strong wind warnings, and evacuation shelter location data. Generate a warning message based on detailed disaster type and location information." The warning message generated based on this prompt will be used as part of the information provided to the user.

[0722] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0723] Step 1:

[0724] The server accesses the API of an information provision medium to retrieve disaster-related data. The input is the response data from the API, which the server receives and prepares for analysis. The output is the received raw data. The retrieved data plays a crucial role in subsequent processing.

[0725] Step 2:

[0726] The server performs natural language processing on the acquired data to analyze the type, location, and severity of the disaster. The input for this step is the raw data acquired in step 1, and keywords and important phrases are extracted from the text using an NLP library. The output is the analyzed information, which identifies the type and severity of the disaster.

[0727] Step 3:

[0728] The server inputs the analyzed information into a Geographic Information System (GIS) and visualizes it on a map. The input for this step is the analysis results from step 2. The output is visualized map data, providing disaster information in an easy-to-understand format for users. Libraries such as Leaflet.js are used to display the extent of the disaster's impact and the locations of evacuation shelters on the map.

[0729] Step 4:

[0730] The device obtains the user's location information and filters it for the most relevant information. The input is the user's location information stored on the device and the map data from step 3. Based on this information, the device selects the most important notifications for the user. The output is the selected information, which is presented to the user on the device.

[0731] Step 5:

[0732] The device sends a push notification to the user based on the selected information. The input for this step is the information selected in step 4. The output is a notification to the user, and the device displays warnings and alerts to the user in real time.

[0733] Step 6:

[0734] The server performs reanalysis based on newly acquired data and user feedback. The inputs for this step are new data and user feedback. The server reanalyzes the data and prepares information that reflects the latest situation. The output is the updated analysis results, maintaining the accuracy of the information provided to users throughout the system.

[0735] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0736] This invention is a system that provides necessary information quickly during disasters and delivers information while taking into account the user's emotional state. In particular, it is characterized by the provision of information optimized according to the user's mental state by combining it with an emotion engine.

[0737] The system begins with a server collecting disaster-related information from information sources. The collected information is then analyzed by the server using natural language processing technology to determine the type, location, and severity of the disaster. The results of this analysis are then plotted on a map using a GIS (Geographic Information System).

[0738] At this stage, the device selects highly relevant information based on the user's location data. This selected information is then ready to be provided to the user.

[0739] Next, the emotion engine operates on the device to recognize the user's current emotional state. Emotion recognition is inferred from the user interface's operation history, selections, and user input patterns. This information, along with the user's emotional history, is sent to the server, where appropriate actions are considered.

[0740] The server adjusts the way and content of information provided based on the emotional state obtained from the emotion engine. For example, if a user is showing signs of anxiety, more detailed evacuation information and safety check guides will be provided. On the other hand, users who are relatively calm will be provided with information that focuses on summaries.

[0741] This adjusted information is notified to users through their devices, allowing for real-time follow-up. When there are important updates, notifications are sent in an emotionally sensitive manner to enhance user confidence.

[0742] Furthermore, the system accumulates users' emotional history, which can be used to improve the accuracy of future information provision. This ensures that users continuously receive information optimized for their needs.

[0743] This system goes beyond simply providing information; it enables disaster response support that is sensitive to the user's emotions, contributing to reducing the psychological burden on users and ensuring their safety.

[0744] The following describes the processing flow.

[0745] Step 1:

[0746] The server connects to APIs of information sources to periodically collect disaster-related information. These sources include social media and news sites, and the server filters the data using specific hashtags and keywords.

[0747] Step 2:

[0748] The server analyzes the collected information. Using natural language processing, it extracts keywords related to the type, location, and severity of the disaster to identify the disaster information. This analysis generates the necessary metadata.

[0749] Step 3:

[0750] The server uses GIS to plot the analyzed disaster information on a map. It processes coordinate information to visually display the disaster area and its impact on a map.

[0751] Step 4:

[0752] The device selects highly relevant information based on the user's pre-registered location data. This ensures that users receive only disaster information that is important to them.

[0753] Step 5:

[0754] The device recognizes the user's emotional state through the user interface. The emotion recognition engine analyzes the user's operation history and input patterns to determine their current emotion.

[0755] Step 6:

[0756] The server analyzes user emotion information obtained from the emotion engine. Based on this, it adjusts how disaster information is provided and selects appropriate information according to the user's emotions.

[0757] Step 7:

[0758] The device will notify users of carefully selected disaster information. By providing information in an emotionally sensitive manner, it aims to reduce user anxiety and guide them to take necessary actions.

[0759] Step 8:

[0760] The server stores the user's emotional history in a database. This stored data is then used to optimize future information delivery based on the user's tendencies.

[0761] This processing flow enables the system to provide users with emotionally resonant disaster information.

[0762] (Example 2)

[0763] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0764] Conventional disaster information systems provided information uniformly without considering the emotional state of users, which sometimes failed to alleviate their mental burden. Furthermore, the selection of appropriate information delivery methods was often inadequate, making it difficult for users to obtain the information they needed quickly and appropriately. Additionally, there was a lack of methods to utilize individual emotional histories to improve the accuracy of information provision.

[0765] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0766] In this invention, the server includes means for collecting disaster information from an information acquisition device, means for analyzing the collected information to determine the type, location, and severity of the disaster, and means for visualizing the analysis results based on spatial data. This makes it possible to provide information that takes into account the emotional state of the user, enabling timely notification of important information and reduction of mental burden. Furthermore, by utilizing individual emotional history, the accuracy of the provided content can be continuously improved.

[0767] An "information acquisition device" is a device used to collect disaster information from external sources.

[0768] "Analysis" is the process of processing collected information to determine the type, location, and severity of a disaster.

[0769] "Spatial data" refers to data used to visualize information based on geographical information.

[0770] "User" refers to an individual or group that uses the system.

[0771] "Location data" refers to geographical information that indicates the user's current location.

[0772] An "emotion analysis device" is a device used to recognize the emotional state of a user.

[0773] "Information provision method" refers to the method of determining what format the analyzed information will be provided to users.

[0774] "Emotional state" refers to the user's psychological state, and information provision is adjusted based on this.

[0775] "Notification" refers to the act of informing users of the adjusted information.

[0776] "Emotional history" refers to a record of a user's past emotions.

[0777] A system implementing this invention efficiently provides disaster information through the interaction of a server, terminal, and user, and enables appropriate responses according to the user's emotional state.

[0778] The server uses information acquisition devices to collect disaster information from multiple sources. These include news sites, social media, and government disaster information pages. On the server, the Python requests library is used, and necessary information is retrieved using BeautifulSoup. This information is analyzed to determine the type of disaster, its location, and its severity. The natural language processing library NLTK is used for the analysis. In addition, the disaster information is converted into spatial data using GeoPandas and visualized on a map.

[0779] The device uses the user's location information to compare it with geographic data obtained from the server. In this process, the device uses GPS to determine the user's current location. Based on this, it reads the user's emotional state in order to select disaster information relevant to the user and adjust the method of information delivery. The emotion analysis device implements a machine learning model using TensorFlow, which infers the emotional state from the user's input patterns and operation history.

[0780] Users receive information tailored to their needs via their devices, enabling them to respond quickly and appropriately. Important information is communicated in a way that is sensitive to the user's feelings, providing reassuring and clear instructions. For example, if a user expresses anxiety, detailed information such as, "The nearest evacuation center is XX. Here are the directions," is provided.

[0781] An example of a prompt message to utilize this system is: "Present information about the current disaster situation and customize the notification content based on the user's current emotional state. If the user is anxious, provide specific safety guidelines; if calm, provide summary information." Based on this, the AI ​​model will provide the most appropriate information.

[0782] This invention aims to reduce the psychological burden during disasters and contribute to ensuring user safety through the smooth provision of information.

[0783] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0784] Step 1:

[0785] The server collects disaster information from external sources. URLs of news sites, social media, and government disaster information pages are provided as input. The Python requests library is used to retrieve HTML data from these sites, and BeautifulSoup is used to scrape the necessary information and output it. The collected data is saved in string format for subsequent analysis.

[0786] Step 2:

[0787] The server analyzes the collected information using natural language processing technology. Disaster information is provided as input in string format. The NLTK library is used to tokenize the text data. Based on the tokenized data, key phrases are extracted to determine the type, location, and severity of the disaster. The analysis results are output in associative array format.

[0788] Step 3:

[0789] The server visualizes the analysis results based on map information. The analysis results are provided as input in the form of an associative array. Using GeoPandas, the disaster information is converted into geographic data, generating GIS data as output. The GIS data is saved for plotting on a map and used for visual verification.

[0790] Step 4:

[0791] The device obtains the user's location information via a GPS module. The user's current location data is provided as input. Mapping software (e.g., folium) running on the device then overlays relevant disaster information onto a map. The output is a map image showing the user's current location and related information superimposed.

[0792] Step 5:

[0793] The sentiment analyzer, which operates on the terminal, recognizes the user's emotional state. The user's operation history and input pattern data are provided as input. A machine learning model using TensorFlow infers the emotional state (anxiety, calmness, etc.) from this data. The recognized emotional state is output as sentiment data, as it influences how subsequent information is provided.

[0794] Step 6:

[0795] The server adjusts the information delivery method based on the recognized emotional state. Emotional data and GIS data are provided as input. If the emotional state is anxious, detailed evacuation information and action guidelines are provided; if the emotional state is calm, summary information is provided. The adjusted information is output in a customized text or visual data format.

[0796] Step 7:

[0797] The device notifies the user of adjusted information. Customized information data is provided as input. Using the notification function, important updates and emotionally sensitive information are sent to the user in real time. Output is presented to the user as an alarm sound, an alert screen, or explanatory text.

[0798] This series of steps allows users to receive accurate and timely information tailored to their emotional state at any given time.

[0799] (Application Example 2)

[0800] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0801] During disasters, there is a need to provide users with personalized, rapid, and appropriate information. However, general information systems fail to consider users' emotional states, making it difficult to alleviate their anxiety and confusion. Furthermore, there is the problem of information overload or insufficiency hindering swift responses and evacuation actions.

[0802] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0803] In this invention, the server includes means for acquiring disaster-related data from an information source, means for analyzing the acquired data to determine the nature, location, and urgency of the disaster, means for visually presenting the analyzed data based on geographical information, means for selecting highly relevant data based on the user's location data, and means for analyzing the user's emotional state and adjusting the content provided according to that emotional state. This enables the provision of information tailored to the user's emotions and rapid evacuation support.

[0804] An "information source" is a system or medium that provides the source for obtaining disaster-related data.

[0805] "Disaster-related data" refers to data that includes information about the nature, location, and urgency of a disaster.

[0806] "Analysis" is the process performed to determine the characteristics of a disaster from the acquired data.

[0807] "Geographic information" refers to map data and location data that contain information related to a specific place.

[0808] "To present visually" means to express information in a way that is easy to understand visually.

[0809] "User location data" refers to information that indicates the user's geographical location.

[0810] "Highly relevant data" refers to data that is of high priority and directly relevant to a particular user.

[0811] "Emotional state" is an indicator that shows the user's emotional state and psychological response.

[0812] "Adjusting the content provided" means changing the way information is presented and the content of that information to suit the user's emotional state.

[0813] This invention is a system that provides personalized information to users quickly during disasters and adjusts the information according to their emotional state. The system mainly consists of a server and terminals.

[0814] The server acquires disaster-related data from information sources and analyzes that data to determine the nature, location, and urgency of the disaster. Specifically, it uses a natural language processing engine for data analysis and presents the data visually using a Geographic Information System (GIS). This makes it possible to instantly reflect important disaster-related information.

[0815] The device acquires the user's location data and selects highly relevant information from the data transmitted from the server. Furthermore, an emotion engine runs on the device to analyze the user's emotional state, inferring it based on the user's operation history and input patterns. As a result, the server adjusts the content provided based on the user's emotional state and delivers optimized information to the user.

[0816] As a concrete example, when an earthquake occurs, the server analyzes various data and visually provides residents in the affected area with information on emergency evacuation routes and safe shelters. Furthermore, if a user indicates anxiety on their device, they will receive more detailed reassurance information and guidance via push notifications. In this process, it is also possible to use a generative AI model to create appropriate prompts for the information the user is seeking.

[0817] An example of a prompt message would be, "Please tell me more about how to provide information that takes into account emotional states in a real-time evacuation guidance app during disasters." This would serve as a guide for the system to provide appropriate information.

[0818] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0819] Step 1:

[0820] The server acquires disaster-related data from information sources. Specifically, it accesses open data on the internet and dedicated disaster information sources, and sends the collected data to the server. At this point, the input is raw data from the information sources, and the output is unprocessed disaster-related data stored on the server.

[0821] Step 2:

[0822] The server analyzes the acquired data to determine the nature, location, and urgency of the disaster. A natural language processing engine is used for data analysis, classifying each data point through keyword analysis and other methods. The input is the raw data obtained in step 1, and the output is analyzed data labeled with disaster characteristics. Specifically, it performs text analysis and statistical modeling.

[0823] Step 3:

[0824] The server visually presents the analyzed data based on geographical information. Using GIS, it marks the location of disasters on a map. The input is the analyzed data obtained in step 2, and the output is visualized geographical information. Specifically, this involves data overlaying onto a map and generating interactive maps.

[0825] Step 4:

[0826] The terminal acquires the user's location data and selects highly relevant information from the data sent from the server. The input is the terminal's location information and the geographical visualization data from step 3, and the output is filtered information relevant to the user. Specifically, it uses distance calculation and filtering algorithms.

[0827] Step 5:

[0828] An emotion engine runs on the device to analyze the user's emotional state, inferring it based on the user's operation history and input patterns. The input is the user's operation data within the app, and the output is the inferred emotional state. Specifically, this is an inference of a machine learning model.

[0829] Step 6:

[0830] The server adjusts the content provided based on the user's emotional state, delivering optimized information to the user. The input is the emotional state obtained in step 5 and the refined information from step 4, and the output is emotionally sensitive information. Specifically, it performs tasks such as prioritizing information and selecting prompts.

[0831] Step 7:

[0832] The user receives information in real time via their device and follows instructions as needed. The input is the adjusted information from step 6, and the output is the user's actions and responses. Specific actions include using the app's notification and guidance features.

[0833] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0834] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include those described above. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions shown by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0835] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0836] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0837] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0838] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0839] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0840] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0841] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0842] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0843] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0844] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0845] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0846] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0847] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0848] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0849] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0850] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0851] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0852] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0853] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0854] The following is further disclosed regarding the embodiments described above.

[0855] (Claim 1)

[0856] Means of obtaining disaster-related information from information provision media,

[0857] A means of analyzing acquired information to determine the type, location, and severity of the disaster,

[0858] A means of visually displaying the analyzed information based on geographic information,

[0859] A means of selecting highly relevant information based on the user's location information,

[0860] A means of notifying users based on selected information,

[0861] A system that includes this.

[0862] (Claim 2)

[0863] The system according to claim 1, further comprising means for evaluating the reliability of information obtained from an information provision medium.

[0864] (Claim 3)

[0865] The system according to claim 1, further comprising means for processing charges based on the user's usage status.

[0866] "Example 1"

[0867] (Claim 1)

[0868] Means of obtaining disaster information from information supply organizations,

[0869] A means of analyzing acquired information to assess the type, location, and severity of the disaster,

[0870] A means of visually presenting the analyzed information based on location information,

[0871] A means of selecting relevant information based on the user's location data,

[0872] A means of notifying users based on selected information,

[0873] A means of charging based on system usage,

[0874] A system that includes this.

[0875] (Claim 2)

[0876] The system according to claim 1, further comprising means for evaluating the reliability of information obtained from an information supply organization.

[0877] (Claim 3)

[0878] The system according to claim 1, further comprising means for performing billing processing based on the user's usage trends.

[0879] "Application Example 1"

[0880] (Claim 1)

[0881] Means of obtaining disaster-related information from information provision media,

[0882] A means of analyzing acquired information to determine the type, location, and severity of the disaster,

[0883] A means of visually displaying the analyzed information based on geographic information,

[0884] A means of selecting highly relevant information based on the user's location information,

[0885] A means of notifying users based on selected information,

[0886] A means for dynamically updating geographic information displayed on the user's device,

[0887] When data collection is performed, a means of reanalyzing the information based on the collected data,

[0888] A system that includes this.

[0889] (Claim 2)

[0890] The system according to claim 1, further comprising means for evaluating the reliability of information obtained from an information provision medium.

[0891] (Claim 3)

[0892] The system according to claim 1, further comprising means for processing charges based on the user's usage status.

[0893] "Example 2 of combining an emotion engine"

[0894] (Claim 1)

[0895] A means of collecting disaster information from an information acquisition device,

[0896] A means of analyzing collected information to determine the type, location, and severity of the disaster,

[0897] A means of visualizing the analysis results based on spatial data,

[0898] A means of selecting highly relevant information based on the user's location data,

[0899] A means of recognizing the user's emotional state using an emotion analysis device,

[0900] Means for adjusting the method of providing information based on recognized emotional states,

[0901] A means of notifying users of the adjusted information,

[0902] A system that includes this.

[0903] (Claim 2)

[0904] The system according to claim 1, further comprising means for presenting acquired disaster information in a format corresponding to emotional state.

[0905] (Claim 3)

[0906] The system according to claim 1, further comprising means for accumulating the emotional history of users to improve the accuracy of information provision.

[0907] "Application example 2 when combining with an emotional engine"

[0908] (Claim 1)

[0909] Means for obtaining disaster-related data from information sources,

[0910] A means of analyzing acquired data to determine the nature, location, and urgency of the disaster,

[0911] A means of visually presenting the analyzed data based on geographical information,

[0912] A means of selecting highly relevant data based on the user's location data,

[0913] A means of notifying users based on selected data,

[0914] A means of analyzing the emotional state of users and adjusting the content of services provided according to that emotional state,

[0915] A system that includes this.

[0916] (Claim 2)

[0917] The system according to claim 1, further comprising means for evaluating the reliability of data obtained from an information source.

[0918] (Claim 3)

[0919] The system according to claim 1, further comprising means for processing charges based on the user's usage status. [Explanation of symbols]

[0920] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means of obtaining disaster-related information from information provision media, A means of analyzing acquired information to determine the type, location, and severity of the disaster, A means of visually displaying the analyzed information based on geographic information, A means of selecting highly relevant information based on the user's location information, A means of notifying users based on selected information, A means for dynamically updating geographic information displayed on the user's device, When data collection is performed, a means of reanalyzing the information based on the collected data, A system that includes this.

2. The system according to claim 1, further comprising means for evaluating the reliability of information obtained from an information provision medium.

3. The system according to claim 1, further comprising means for processing charges based on the user's usage status.

Images