System

Abstract

A system is provided.SOLUTION: A system comprising: means for automatically collecting information from social media or other information sources on a network based on a preset keyword when a disaster occurs; means for assessing reliability of the collected information and indicating the reliability in percentage; means for plotting the assessed information on a map and visually displaying a disaster-stricken situation; means for proposing a necessary rescue plan based on the disaster-stricken situation and presenting supplies, human resources, and a transport route necessary for rescue; and means for calculating an optimal physical distribution route based on real-time traffic information and making a transport plan for relief supplies.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] When a disaster occurs, it is necessary to quickly and accurately grasp the situation and plan relief measures. However, collecting information from a wide range of sources and verifying its authenticity takes time, which can delay an appropriate response. In addition, it is not easy to quickly determine the optimal route for delivering relief supplies to the affected area. These problems must be solved. [Means for solving the problem]

[0005] The present invention is a system that includes: means for automatically collecting information based on preset keywords from social media and other information sources on the network when a disaster occurs; means for assessing the reliability of the collected information and indicating the reliability as a percentage; means for plotting the assessed information on a map to visually display the damage situation; means for proposing necessary relief measures based on the damage situation and presenting the supplies, personnel, and transportation routes required for relief; and means for calculating optimal logistics routes based on real-time traffic information and formulating a transportation plan for relief supplies. This system enables fast and efficient information collection and accurate planning of relief measures, preventing the damage from spreading and achieving early recovery.

[0006] "Networked social media" refers to a general platform where users can share information and communicate over the Internet.

[0007] "Automatic means of collecting information" refers to algorithms or programs that retrieve data from the Internet based on specific keywords or conditions without manual intervention.

[0008] "Means for assessing the reliability of collected information and expressing the reliability as a percentage" refers to technology that uses machine learning models, etc. to evaluate the credibility of acquired data and express the results as a percentage.

[0009] "Means of plotting assessed information on a map and visually displaying the damage situation" refers to technology that displays collected data on a map based on geographical location information, visually conveying to users the extent and impact of the damage.

[0010] "Means to propose necessary relief measures based on the disaster situation and present the supplies, personnel, and transportation routes required for relief" refers to a system that plans appropriate relief activities based on collected and evaluated information and proposes the necessary resources and optimal transportation routes for those activities.

[0011] "Means for calculating optimal logistics routes based on real-time traffic information and formulating transportation plans for relief supplies" refers to technology that uses data that reflects current traffic conditions to calculate optimal delivery routes for supplies and plans efficient supply distribution during relief operations. [Brief explanation of the drawings]

[0012] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0013] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0016] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0017] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0018] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0020] [First embodiment]

[0021] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0022] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0023] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0025] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0028] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0030] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0032] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0033] The present invention is a system that supports the rapid and accurate collection of information and the planning of relief measures when a disaster occurs. This system is composed of a server, terminals, and users.

[0034] Information collection

[0035] When a disaster occurs, the server automatically searches social media and other information sources on the network for information containing pre-defined keywords (e.g., "earthquake," "tsunami," "fire," etc.). For this purpose, the server includes a function to set relevant keywords as input fields. For example, the server uses the Twitter API or RSS feeds from news sites to obtain relevant information in real time.

[0036] Information reliability assessment

[0037] To assess the reliability of the collected information, the server uses a pre-trained fact-checking model (e.g., a machine learning algorithm). This model evaluates the reliability of the collected data and displays it as a percentage. For example, the server analyzes a tweet that says, "A magnitude 6 earthquake occurred in X city," and evaluates its reliability as "85%."

[0038] Information Visualization

[0039] The server plots the assessed information on a map and displays it visually, using Google Maps API and OpenStreetMap API to geographically represent the damage situation, allowing users to check the situation in real time through a dashboard.

[0040] For example, if the server determines that a large number of buildings have collapsed in a particular area, it will highlight the area in red and show the user the extent of the damage.

[0041] Proposal for relief measures

[0042] Based on the damage situation, the server refers to past data and pre-prepared scenarios to propose appropriate rescue measures, presenting the necessary supplies, personnel, transport routes, etc., and creating a rescue operation plan.

[0043] For example, if it is determined that medical assistance is needed in a particular area, the server will create a list of "medicines, medical staff" and present it to the user.

[0044] Transport routes and supporting logistics

[0045] The server uses real-time traffic information to calculate optimal routes for relief logistics, including algorithms that use data reflecting current traffic conditions to calculate the optimal delivery route for supplies.

[0046] For example, if a main road is collapsed, the server will calculate a detour route and instruct the user, "Since main road route A is unusable, use route B." The device will then provide the user with appropriate navigation information based on this information.

[0047] This system supports the planning of relief measures by quickly and efficiently collecting information when a disaster occurs, assessing its reliability, and visually displaying it, thereby preventing damage from spreading and enabling a rapid response.

[0048] The processing flow will be explained below.

[0049] Step 1:

[0050] When the server detects that a disaster has occurred, it automatically searches social media and other information sources on the network based on pre-defined keywords (e.g., "earthquake," "tsunami," "fire," etc.) To do this, the server accesses the Twitter API and RSS feeds of news sites to collect relevant posts and articles from these sources.

[0051] Step 2:

[0052] The server stores the collected information in a database, including the text content of each post, the date and time of posting, and information about the poster.

[0053] Step 3:

[0054] The server applies a fact-checking model to the collected information, specifically a pre-trained machine learning algorithm (e.g., a text classification model using RoBERTa), and uses this model to assess the trustworthiness of each post and calculate a confidence score as a percentage.

[0055] Step 4:

[0056] The server stores the assessed reliability of the information again in a database and sets criteria for selecting highly reliable information.

[0057] Step 5:

[0058] The server plots information that meets the reliability criteria on a map based on geographic location information (e.g., place names and GPS data included in the post), using the Google Maps API and OpenStreetMap API to visually display the information.

[0059] Step 6:

[0060] The server visualizes the damage situation on a map and then plans optimal relief measures based on the results, such as identifying the areas with the most damage and listing the necessary supplies, personnel, and transportation routes.

[0061] Step 7:

[0062] The server displays details of rescue measures on a dashboard, allowing users to review this information and take action.

[0063] Step 8:

[0064] The server accesses a traffic information API (e.g., Google Maps Traffic API) to obtain real-time traffic information and checks the latest road conditions, including road closures, congestion information, and detour routes.

[0065] Step 9:

[0066] The server integrates traffic and disaster information to calculate optimal logistics routes and create transportation plans for supplies. For example, if a major road is destroyed, it automatically calculates a detour route and displays the results on the dashboard.

[0067] Step 10:

[0068] The device displays optimal transportation routes and support logistics routes to users in real time, allowing users to safely and efficiently transport relief supplies to their destinations based on this information.

[0069] Step 11:

[0070] The server continuously collects new information, assesses reliability, plots it on the map, and updates rescue plans, allowing for rapid response to changing situations.

[0071] As a result, this system will enable rapid and accurate information collection, reliability evaluation, rescue plan planning, and logistics route optimization in the event of a disaster.

[0072] Example 1

[0073] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0074] When a disaster occurs, it is important to quickly and accurately collect information and plan relief measures, even with conventional technology. However, the reliability and immediacy of the information, as well as the applicability of relief measures, remain issues. There is also room for improvement in technology that accurately evaluates the reliability of collected information and visually displays the damage situation, as well as methods for calculating the optimal delivery route for relief supplies in real time.

[0075] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0076] In this invention, the server includes: means for automatically collecting information based on preset search terms from digital communication media on a network and other data sources when a disaster occurs; means for assessing the reliability of the collected information and displaying the reliability as a numerical value; means for plotting the assessed information on a map to visually display the damage situation; means for proposing necessary rescue measures based on the damage situation and presenting the resources, personnel, and transportation routes required for rescue; means for calculating optimal transportation routes based on real-time traffic information and formulating a transport plan for support resources; means for evaluating the collected data using a generative AI model that has been trained in advance to improve the reliability of the information; and means for displaying the reliability evaluation results of the assessed data on a user dashboard to notify the user. This enables rapid and accurate information collection and the planning of reliable rescue measures.

[0077] "When a disaster occurs" refers to the situation when a natural disaster such as an earthquake, tsunami, or fire occurs.

[0078] "Networked digital communications media" refers to platforms and services for transmitting and retrieving information over the Internet.

[0079] "Pre-set search terms" refer to keywords that are predetermined in anticipation of a disaster occurring.

[0080] "Means for automatically collecting information" refers to a method for automatically obtaining disaster-related data from the network based on set search terms.

[0081] "Means of assessing reliability and expressing the degree of reliability numerically" refers to a method of evaluating the credibility of collected data using machine learning models, etc., and expressing the results numerically.

[0082] "Means of plotting on a map and visually displaying the damage situation" refers to a method of displaying collected information on a map using a geographic information system to visualize the location and extent of the damage.

[0083] "Means of proposing relief measures and presenting the resources, personnel, and transportation routes required for relief" refers to methods of drawing up plans for relief activities based on the disaster situation and indicating the supplies, personnel, and transportation routes required for those activities.

[0084] "Means for calculating optimal transportation routes and formulating plans for transporting relief resources" refers to a method for calculating plans for delivering relief supplies and personnel via optimal routes based on traffic information obtained in real time.

[0085] A "generative AI model" refers to a learning model that uses artificial intelligence technology to generate and extract useful information and patterns from large amounts of data.

[0086] A "user dashboard" refers to an interface that allows users to visually check collected information and analysis results.

[0087] The present invention is a system that supports the rapid and accurate collection of information and the planning of rescue measures when a disaster occurs. This system is composed of a server, terminals, and users. The specific operation of each component of this system will be described below.

[0088] In this system, a server automatically collects information from digital communication media and other data sources on the network during a disaster. To gather disaster-related information, the server uses pre-defined search terms. For example, it uses the Twitter API or RSS feeds from news sites to search for keywords such as "earthquake" or "tsunami," and retrieves related tweets and news articles in real time. This allows for rapid and comprehensive collection of information.

[0089] The server assesses the reliability of the collected information. A pre-trained generative AI model is used to assess reliability. This model analyzes the collected data and indicates its reliability as a percentage. For example, if a tweet stating "A magnitude 6 earthquake has occurred in XX city" is collected, the generative AI model will assess the reliability of the tweet and assign it a reliability of 85%. Information with low reliability is filtered out, and only information with high reliability is advanced to the next processing step.

[0090] The server then plots the information, which has been assessed for reliability, on a map and displays it visually. Using the Google Maps API and OpenStreetMap API, the assessed information is visualized on the map, allowing users to check the damage situation in real time through a dashboard. For example, if the server determines that a large number of buildings have collapsed in a particular area, it will highlight that area in red and display it to the user.

[0091] The server then proposes relief measures based on the damage situation. To create appropriate relief measures, it references past data and pre-prepared scenarios. For example, if it determines that medical assistance is needed in a particular area, the server creates a list of "medicines and medical staff" and displays it to the user. This allows the user to quickly arrange for the necessary resources.

[0092] Furthermore, the server analyzes real-time traffic information and calculates the optimal support logistics route. It uses a database that reflects road traffic conditions and congestion information to create a transportation plan. For example, if a major road has collapsed, it calculates a detour route and instructs the terminal to "use route B as main road route A is unusable." The terminal provides this information to the user and performs appropriate navigation.

[0093] A specific example of how this works is the process of collecting tweets related to the keyword "earthquake" and evaluating their reliability using a fact-checking model. The information collected and evaluated in this way is displayed on a map using the Google Maps API, visually informing users of the affected areas.

[0094] Examples of prompts include:

[0095] Collect information that an "earthquake" has occurred during a disaster and evaluate its reliability.

[0096] Please suggest appropriate rescue measures in case of a fire in XX city.

[0097] Calculate the best route for transporting medical supplies to the disaster area.

[0098] As described above, the present invention is a system that efficiently collects necessary information when a disaster occurs, improves its reliability, and supports the planning of rapid relief measures. This helps prevent damage from spreading and enables early response.

[0099] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0100] Step 1:

[0101] When a disaster occurs, the server automatically collects information from digital communication media and other data sources on the network using pre-set search terms (e.g., "earthquake," "tsunami"), specifically by searching for information by keyword using the Twitter API and RSS feeds of news sites to obtain relevant data. The input required is the search term and API authentication information, and the output is related information (tweets and news articles).

[0102] Step 2:

[0103] The server runs a process to assess the reliability of the collected information. This process uses a pre-trained generative AI model. The input is the information collected in step 1, and the output is a percentage of the reliability. Specifically, the text of the collected tweets and news articles is input into the generative AI model, which analyzes their reliability.

[0104] Step 3:

[0105] The server plots the information whose reliability has been evaluated on a map and displays it visually. Specifically, it uses the Google Maps API or OpenStreetMap API to display information related to the affected area on the map. The reliability information evaluated in step 2 is required as input, and visualized map information is obtained as output. For example, areas where a magnitude 6 earthquake has occurred are highlighted in red and displayed to the user.

[0106] Step 4:

[0107] The server proposes necessary relief measures based on the disaster situation. It refers to past data and pre-prepared scenarios to plan appropriate relief measures. The input requires the disaster information visualized in step 3, and the output presents relief measures (e.g., a list of "medicine, medical staff"). Specifically, if it is determined that medical assistance is needed in the disaster-stricken area, the server creates the necessary list from the database and displays it to the user.

[0108] Step 5:

[0109] The server analyzes real-time traffic information and calculates the optimal relief logistics route. This is done using a database that reflects current traffic information. Real-time traffic data and relief supply information are required as input, and the optimal delivery route is presented as output. Specifically, if a major road has collapsed, a detour route is calculated and an instruction is given to "use route B as main road route A is unusable." The terminal provides this information to the user and performs appropriate navigation.

[0110] Through these steps, the server quickly and accurately collects, evaluates, and visualizes information, and then proposes relief measures and optimizes logistics routes, providing them to users.

[0111] (Application example 1)

[0112] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0113] Current disaster response systems face challenges in quickly and accurately collecting information and formulating relief measures when a disaster occurs. Furthermore, it is difficult to assess the reliability of the collected information, making it difficult to accurately grasp the situation in the affected area in real time. Furthermore, there is a lack of means to quickly provide information that reflects reliability assessments via mobile devices.

[0114] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0115] In this invention, the server includes: means for automatically collecting information based on preset keywords from social media and other information sources on a network when a disaster occurs; means for assessing the reliability of the collected information and indicating the reliability as a percentage; means for plotting the assessed information on a map to visually display the damage situation; means for proposing necessary relief measures based on the damage situation and presenting the supplies, personnel, and transportation routes required for relief; means for calculating optimal logistics routes based on real-time traffic information and formulating a transportation plan for relief supplies; and means for visually displaying information reflecting the reliability assessment for a specific area on a mobile device. This enables rapid and accurate information collection and assessment, visual understanding of the damage situation, and real-time information provision via mobile devices.

[0116] "Networked social media" is a general term for online platforms where users share content such as text, images, and videos over the Internet.

[0117] "Assessing the reliability of information" refers to the process of evaluating the accuracy and veracity of collected information.

[0118] "Indicating the reliability as a percentage" means expressing the reliability of the assessed information as a percentage.

[0119] "A means of plotting on a map and visually displaying the damage situation" is a system that displays collected information as location information on a map, allowing users to intuitively understand the damage situation.

[0120] "Means for proposing relief measures and indicating the supplies, personnel, and transportation routes necessary for relief" refers to a system that presents appropriate relief activities based on the disaster situation and indicates the necessary resources and optimal delivery routes.

[0121] "Means for calculating optimal logistics routes based on real-time traffic information and formulating transportation plans for relief supplies" refers to a method that uses current traffic data to calculate the optimal route for delivering relief supplies and then creates a specific logistics plan based on that.

[0122] "Mobile Device" refers to a portable computing device such as a smartphone or tablet.

[0123] "A means for visibly displaying information on a mobile device that reflects a reliability assessment for a specific area" refers to a function that provides disaster information based on the assessed reliability of the information in an easy-to-understand format on the user's mobile device.

[0124] The present invention relates to a system for supporting rapid and accurate information gathering and rescue planning in the event of a disaster. This system is composed of a server, terminals, and users.

[0125] Information collection

[0126] When a disaster occurs, the server automatically searches social media and other information sources on the network for information containing pre-defined keywords (e.g., "earthquake," "tsunami," "fire," etc.). The server includes a function to set relevant keywords as input fields. Specifically, it obtains relevant information in real time using the Twitter API and RSS feeds from news sites.

[0127] Information reliability assessment

[0128] To assess the reliability of the collected information, the server uses a pre-trained fact-checking model (e.g., a machine learning algorithm) that rates the collected data and indicates its veracity as a percentage.

[0129] Information Visualization

[0130] The server plots the assessed information on a map and displays it visually, using Google Maps API and OpenStreetMap API to geographically represent the damage situation, allowing users to check the situation in real time through a dashboard.

[0131] Proposal for relief measures

[0132] Based on the damage situation, the server refers to past data and pre-prepared scenarios to propose appropriate rescue measures, presenting the necessary supplies, personnel, transport routes, etc., and creating a rescue operation plan.

[0133] Transport routes and supporting logistics

[0134] The server calculates the optimal route for logistics support based on real-time traffic information. This includes an algorithm that uses data reflecting current traffic conditions to calculate the optimal delivery route for supplies, thereby providing appropriate navigation information to users.

[0135] Visualization of information reliability ratings for specific regions

[0136] To visually display information reflecting the trust ratings for specific areas, the system also provides information to mobile devices, specifically through smartphone and tablet apps, delivering this information to users in real time.

[0137] Hardware and software used

[0138] Hardware: smartphones, tablets, servers

[0139] Software: Python, Tweepy, TextBlob, Folium, Twitter API, Google Maps API, OpenStreetMap API

[0140] Specific examples

[0141] For example, if an earthquake occurs, the server will collect tweets containing the word "earthquake," evaluate their reliability, and display them on a map. Based on this information, the server will suggest safe evacuation routes and arrange for the necessary relief supplies.

[0142] Prompt Sentence Examples

[0143] Development of a smartphone app that collects real-time information during disasters, evaluates its reliability, and visualizes it

[0144] Step 1: Collect tweets about the disaster using the Twitter API

[0145] Step 2: Assess the authenticity of the tweet using TextBlob

[0146] Step 3: Visualize your data on a map using Folium

[0147] Thus, in order to implement the present invention, it is important that each element works in an organic manner, that disaster information is processed quickly and efficiently, and that appropriate relief measures are formulated.

[0148] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0149] Step 1:

[0150] When a disaster occurs, the server automatically collects information from social media and other sources on the network based on pre-set keywords (e.g., "earthquake," "tsunami," "fire," etc.). The input is the pre-set keywords and API authentication information, and the output is the information obtained from social media and news sites. The server uses the Twitter API, etc., to obtain tweets and news containing the relevant keywords. This processing makes it possible to collect disaster-related information in real time.

[0151] Step 2:

[0152] The server assesses the reliability of the collected information. The input is the information collected in step 1, and the output is data showing the reliability of each piece of information as a percentage. The server applies a machine learning algorithm to evaluate the reliability of the information and displays the result as a reliability percentage. This process allows users to judge the credibility of disaster-related information.

[0153] Step 3:

[0154] The server plots the assessed information on a map and displays it visually. The input is the information and geographic information whose reliability was assessed in step 2, and the output is a visually displayed map. The server uses the Google Maps API and OpenStreetMap API to generate a map that visually shows the damage situation. This allows users to intuitively understand the extent of damage in each area.

[0155] Step 4:

[0156] Based on the disaster situation, the server proposes the necessary relief measures and presents the supplies, personnel, and transportation routes required for relief. The input is the disaster situation, past data, and scenario data from Step 3, and the output is the proposed relief measures, required resources, and delivery routes. The server refers to past disaster data and rescue scenarios prepared in advance to propose appropriate support measures.

[0157] Step 5:

[0158] The server calculates the optimal logistics route based on real-time traffic information and creates a transportation plan for relief supplies. The input is real-time traffic data, and the output is the optimal transportation route. The server calculates the optimal supply delivery route based on the latest traffic information and presents that route to the user.

[0159] Step 6:

[0160] The server visually displays information reflecting the reliability assessment for a specific area on a mobile device. The input is the reliability assessment and geographic information generated in Steps 2 and 3, and the output is damage information displayed on the mobile device. The server provides information to users in real time via a smartphone or tablet app.

[0161] Through these steps, the present invention enables rapid and accurate information collection and assessment, visual understanding of the damage situation, and real-time information provision via mobile devices.

[0162] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0163] This invention combines a system that supports rapid and accurate information gathering and rescue planning in the event of a disaster with an emotion engine that recognizes the user's emotions. This system is composed of a server, terminals, and users.

[0164] Information collection

[0165] When a disaster occurs, the server automatically searches social media and other information sources on the network based on pre-defined keywords (e.g., "earthquake," "tsunami," "fire," etc.) To do this, the server accesses the Twitter API and RSS feeds of news sites to collect relevant posts and articles.

[0166] Information reliability assessment

[0167] The server applies a fact-checking model to the collected information, which is pre-trained using a machine learning algorithm (e.g., a text classification model using RoBERTa), and uses this model to assess the trustworthiness of each post, calculating a confidence score as a percentage.

[0168] Information Visualization

[0169] The server plots the assessed information on a map and displays it visually, using Google Maps API and OpenStreetMap API to geographically represent the damage situation, allowing users to check the situation in real time through a dashboard.

[0170] Proposal for relief measures

[0171] Based on the damage situation, the server refers to past data and pre-prepared scenarios to propose appropriate rescue measures. It presents the necessary supplies, personnel, and transportation routes, and creates a rescue operation plan.

[0172] Transport routes and supporting logistics

[0173] The server calculates optimal logistics routes based on real-time traffic information and creates a delivery plan for relief supplies, which includes an algorithm that uses data reflecting the latest road conditions to calculate the optimal delivery route for supplies.

[0174] Adding an Emotion Engine

[0175] emotion recognition

[0176] The server incorporates an emotion engine that analyzes user posts, comments, and voice data to recognize emotions. The emotion engine evaluates user emotions using techniques such as text analysis, voice analysis, and facial expression analysis.

[0177] As a specific example, if a user posts a comment saying "I'm very scared," the emotion engine will analyze the comment and determine that the user is feeling strong anxiety or fear.

[0178] Emotion-based responses

[0179] The server then presents appropriate support messages and countermeasures based on the user's recognized emotions. For example, if the emotion engine determines that the user is in a panic, the server will display a support message such as "Please stay calm and evacuate to a safe place."

[0180] Furthermore, the system can suggest high-priority rescue measures based on user emotional data. For example, if a region where many users are expressing strong anxiety is determined to require immediate psychological support, the system will prioritize dispatching medical staff to that region.

[0181] Overall system flow

[0182] This system enables rapid and efficient information gathering, reliability assessment, visualization of the damage situation, rescue plan proposals, logistics route optimization, and user emotion recognition and support based on that information when a disaster occurs, thereby preventing damage from spreading and enabling a rapid response.

[0183] As a concrete example, when an earthquake occurs, the server collects information using keywords such as "earthquake" and "damage," assesses its reliability, and plots it on a map. At the same time, the emotion engine analyzes user posts, and presents appropriate messages to users who are feeling anxious or scared, providing psychological support. In this way, the entire system can provide support from both the information and emotional perspectives.

[0184] The processing flow will be explained below.

[0185] Step 1:

[0186] When the server detects that a disaster has occurred, it automatically searches social media and other information sources on the network based on pre-defined keywords (e.g., "earthquake," "tsunami," "fire," etc.) by accessing the Twitter API and RSS feeds of news sites to collect relevant posts and articles.

[0187] Step 2:

[0188] The server stores the collected information in a database, which includes the text content of the posts, the date and time of posting, and information about the poster.

[0189] Step 3:

[0190] The server applies a fact-checking model to the collected information, using a pre-trained machine learning algorithm (e.g., a text classification model using RoBERTa) to assess the trustworthiness of each post and calculate a confidence score as a percentage.

[0191] Step 4:

[0192] The server stores the assessed reliability of the information in a database and selects information that meets the reliability criteria. Based on this reliable information, the damage situation can be grasped.

[0193] Step 5:

[0194] The server plots reliable information on a map based on geographic location information (e.g., place names and GPS data included in posts), using the Google Maps API and OpenStreetMap API.

[0195] Step 6:

[0196] The server visually displays the damage situation plotted on a map, allowing users to check the extent and impact of the damage in real time through a dashboard.

[0197] Step 7:

[0198] The server references past data and pre-prepared scenarios to plan relief measures based on the disaster situation, such as listing the supplies, personnel, and transportation routes needed for the most affected areas.

[0199] Step 8:

[0200] The server displays details of the rescue plan on a dashboard, allowing the user to review this information and proceed with the actual rescue operation.

[0201] Step 9:

[0202] The server accesses a traffic information API (e.g., Google Maps Traffic API) to obtain real-time traffic information and collects the latest road conditions, including road closures, congestion information, and detour routes.

[0203] Step 10:

[0204] The server integrates traffic and disaster information to calculate optimal logistics routes and create transportation plans for supplies. For example, if a major road is destroyed, it automatically calculates a detour route and displays the results on the dashboard.

[0205] Step 11:

[0206] The device displays optimal transportation routes and support logistics routes to users in real time, allowing them to safely and efficiently transport relief supplies to their destinations based on this information.

[0207] Step 12:

[0208] The server uses an emotion engine to analyze user posts, comments, and voice data. The emotion engine uses technologies such as text analysis, voice analysis, and facial expression analysis to evaluate the user's emotions.

[0209] Step 13:

[0210] The server then creates appropriate support messages and countermeasures based on the user's emotions recognized by the emotion engine. For example, if many users show strong anxiety, the server determines that psychological support is necessary and displays messages such as "Please stay calm and evacuate to a safe place."

[0211] Step 14:

[0212] The server then uses the emotion data to suggest high-priority rescue measures, such as creating a plan to immediately dispatch medical staff to areas where many users are panicking.

[0213] Step 15:

[0214] The server continuously collects new information, assesses its reliability, plots it on a map, and updates rescue plans, allowing for rapid response to changing situations.

[0215] In this way, this system supports disaster response from both an information and emotional perspective, aiming to minimize damage and achieve rapid recovery.

[0216] Example 2

[0217] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0218] When a disaster occurs, rapid and accurate information gathering, reliability assessment, visualization of the damage situation, relief plan proposals, optimization of relief logistics, and recognition and response of user emotions are required. However, conventional systems cannot comprehensively meet these requirements, and in particular, lack support including emotion recognition, resulting in insufficient psychological care for users. This leads to a decline in the quality of disaster response, and there is a risk of the damage increasing and relief efforts being delayed.

[0219] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0220] In this invention, the server includes: means for automatically collecting information based on preset keywords from social media and other information sources on a network; means for assessing the reliability of the collected information using a machine learning algorithm and displaying the reliability as a percentage; means for plotting the assessed information on a map to visually display the damage situation; means for referring to past data based on the damage situation, proposing necessary relief measures, and presenting necessary supplies, personnel, and transportation routes; means for calculating optimal logistics routes based on real-time traffic information and formulating a transportation plan for relief supplies; and means for analyzing user posts and comments and utilizing an emotion engine that recognizes emotions to present appropriate countermeasures based on user emotion data. This enables rapid and accurate information collection, reliable information evaluation, visual confirmation of the damage situation, proposing effective relief measures, calculating optimal logistics routes, and providing rapid support based on user emotions.

[0221] A "network" is an electronic communication means for sending and receiving information.

[0222] "Social media" is a general term for online platforms that allow users to create and share content.

[0223] "Source" refers to the medium or location that provides data or information.

[0224] "Keywords" are key words or phrases used to search for specific information.

[0225] A "machine learning algorithm" is a computational method that allows a computer to automatically learn and identify patterns based on empirical data.

[0226] "Reliability" is a numerical evaluation of the accuracy and credibility of information.

[0227] A "map" is a flat representation for visually displaying geographic information.

[0228] "Plotting" refers to placing information in a specific location and visually representing it.

[0229] "Historical data" refers to records or information previously collected.

[0230] "Relief measures" refer to specific measures and actions taken to mitigate damage and provide assistance in disasters and emergencies.

[0231] "Supplies" refers to materials and equipment necessary for relief activities.

[0232] "Human resources" refers to individuals or personnel with specific skills or knowledge.

[0233] A "transport route" refers to a route for transporting materials or personnel to a specific location.

[0234] "Real-time traffic information" refers to the latest data on current road conditions and traffic flow.

[0235] A "logistics route" refers to the route for optimal delivery of goods.

[0236] A "transportation plan" refers to detailed procedures and schedules for efficiently transporting supplies.

[0237] "User" refers to any individual or organization that uses this system.

[0238] "Post" means a message or comment posted by a user on social media or online platforms.

[0239] A "comment" refers to a post in which a user expresses their opinion or impression on a particular topic.

[0240] "Emotion engine" refers to technology that analyzes a user's text and voice data to identify their emotional state.

[0241] "Emotional data" refers to information about a user's emotional state.

[0242] "Responses" refer to specific actions or support measures that should be taken in response to a particular situation.

[0243] This invention relates to a system that supports rapid and accurate information gathering and rescue planning in the event of a disaster, and combines it with an emotion engine that recognizes the user's emotions. The system is composed of a server, terminals, and users, each of which plays a specific role.

[0244] Specifically, when a disaster occurs, the server automatically collects information from social media and other sources on the network based on pre-defined keywords (e.g., "earthquake," "tsunami," "fire," etc.) using well-known interfaces such as the Twitter API and RSS feeds from news sites.

[0245] The collected information is evaluated for reliability using a machine learning algorithm (e.g., RoBERTa model), and the reliability of each piece of information is calculated as a percentage. This reliability evaluation uses a pre-trained model, enabling highly accurate information judgment.

[0246] The information with a reliability assessment is then plotted on a map using the Google Maps API and OpenStreetMap API, allowing the server to visually represent the damage situation and users to view the situation in real time on a dashboard on their devices.

[0247] Based on the disaster situation, the server refers to past data and pre-prepared scenarios to propose optimal rescue measures. Specific rescue measures include presenting the necessary supplies, personnel, and transportation routes, thereby realizing efficient rescue operations.

[0248] Based on real-time traffic information, the server calculates the optimal logistics route and creates a transportation plan for relief supplies. This traffic information uses data that reflects the latest road conditions. By incorporating an algorithm to calculate the optimal delivery route for supplies, rapid transportation of supplies is possible.

[0249] Furthermore, the system is equipped with an emotion engine that analyzes user posts, comments, and voice data to recognize emotions. This is done using technologies such as text analysis, voice analysis, and facial expression analysis. For example, if a user posts a comment saying "I'm very scared," the emotion engine will analyze the comment and determine that the user is feeling strong anxiety or fear.

[0250] The server presents appropriate support messages and countermeasures based on the user's recognized emotions. For example, if the emotion engine determines that the user is in a state of panic, it will display a support message such as "Please stay calm and evacuate to a safe place." It also suggests high-priority rescue measures based on the user's emotional data. For example, it may determine that an area where many users are expressing strong anxiety requires immediate psychological support, and prioritize the dispatch of medical staff to that area.

[0251] As a concrete example, when an earthquake occurs, the server collects information using the keywords "earthquake" and "damage," assesses its reliability using a machine learning model, and plots it on a map. At the same time, the emotion engine analyzes user posts, and provides psychological support by displaying appropriate messages to users who are feeling anxious or scared. This entire system can provide support from both an informational and emotional perspective.

[0252] Example prompt for a generative AI model:

[0253] An earthquake has occurred and damage information is being collected. Collect the latest tweets and news articles related to the disaster, evaluate the reliability of the information, recognize emotions from user comments, and suggest countermeasures.

[0254] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0255] Step 1:

[0256] The server collects information from social media and news sites on the network based on pre-set keywords (e.g., "earthquake," "tsunami," "fire," etc.).

[0257] Input: Keywords such as "earthquake," "tsunami," and "fire"

[0258] Output: A list of tweets and news articles containing the keyword

[0259] Operation:

[0260] 1. The server uses the Twitter API to collect tweets containing the keyword.

[0261] 2. The server parses the news site's RSS feed and retrieves the latest articles.

[0262] Step 2:

[0263] The server evaluates the reliability of the collected information using machine learning algorithms.

[0264] Input: Collected tweets and news articles

[0265] Output: Confidence score (percentage) for each piece of information

[0266] Operation:

[0267] 1. The server inputs each collected text data into a machine learning model (e.g., RoBERTa model) and calculates a confidence score.

[0268] 2. The server stores the confidence score in a database.

[0269] Step 3:

[0270] The server plots the information whose reliability has been assessed on a map and displays it.

[0271] Input: Information (tweets or news articles) with assessed credibility and their location

[0272] Output: Damage information plotted on a map

[0273] Operation:

[0274] 1. The server uses the Google Maps API or OpenStreetMap API to plot the location data of the disaster information on a map.

[0275] 2. Users can access the dashboard through their devices and check the status in real time.

[0276] Step 4:

[0277] The server proposes appropriate relief measures based on the disaster situation.

[0278] Input: Disaster information and past rescue data

[0279] Output: Proposed relief plan (necessary supplies, personnel, transport routes)

[0280] Operation:

[0281] 1. The server compares past disaster data with current damage information.

[0282] 2. The server plans the required supplies, personnel, and transportation routes and displays them on the dashboard.

[0283] Step 5:

[0284] The server calculates the optimal logistics route based on real-time traffic information.

[0285] Input: Latest road conditions and traffic data

[0286] Output: Optimal logistics routes and transportation plans for relief supplies

[0287] Operation:

[0288] 1. The server uses a traffic data API (e.g., Google Maps Traffic API) to obtain real-time traffic information.

[0289] 2. The server applies an algorithm to calculate the optimal delivery route and displays the results on a dashboard.

[0290] Step 6:

[0291] The server analyzes users' posts and comments to recognize their emotions.

[0292] Input: User posts and comments (text data)

[0293] Output: User's emotion evaluation result

[0294] Operation:

[0295] 1. When a user posts a comment from their device, the server inputs the text data into the emotion engine.

[0296] 2. The sentiment engine performs text analysis and evaluates the user's sentiment.

[0297] Step 7:

[0298] The server presents appropriate support messages and countermeasures based on the recognized emotions.

[0299] Input: User's emotion evaluation result

[0300] Output: Support message and / or action plan

[0301] Operation:

[0302] 1. After the emotion engine evaluates the user's emotion, the server generates an appropriate message based on the result.

[0303] 2. The server displays support messages such as "Please stay calm and evacuate to a safe place" on the dashboard.

[0304] 3. The server proposes high-priority rescue measures based on the user's emotional data.

[0305] (Application example 2)

[0306] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0307] In modern society, when a disaster occurs, there is a need to quickly and accurately collect information and plan appropriate relief measures. However, many challenges exist, such as confusion during a disaster, a decrease in the reliability of information, and the mental instability of victims. It is also important to provide optimal escape routes and routes for transporting supplies based on traffic conditions and the situation in the affected area, but current systems are unable to adequately address these issues.

[0308] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for automatically collecting information based on preset keywords from social media and other information sources on the network when a disaster occurs; means for assessing the reliability of the collected information and displaying the reliability as a percentage; means for plotting the assessed information on a map to visually display the damage situation; means for proposing necessary relief measures based on the damage situation and presenting the supplies, personnel, and transportation routes required for relief; means for calculating optimal logistics routes based on real-time traffic information and formulating a transportation plan for relief supplies; and means for recognizing the emotions of occupants using a camera and microphone and providing appropriate support messages and responses based on the emotion data. This enables rapid and accurate information collection and reliability assessment, relief measure proposals, calculation of optimal logistics routes, and mental care for occupants.

[0309] "Networked social media" is a general term for platforms used via the Internet for sharing and exchanging information.

[0310] "Source" refers to the medium or device from which information is disseminated.

[0311] "Keywords" are important words or phrases used when searching for specific information.

[0312] "Means for automatically collecting information" refers to a mechanism for automatically acquiring information based on set conditions.

[0313] A "means for assessing trustworthiness" is a method or system for evaluating the veracity or accuracy of collected information.

[0314] A "means of showing reliability as a percentage" is a method of quantifying the reliability of information and displaying it in the form of a percentage.

[0315] "Means of plotting on a map and visually displaying the damage situation" refers to a method of illustrating the situation in the disaster area on a map using a geographic information system.

[0316] "Means for proposing relief measures and presenting the supplies, personnel, and transportation routes required for relief" is a system that plans and proposes appropriate support actions, necessary resources, and routes for transporting them.

[0317] "Means for calculating optimal logistics routes based on real-time traffic information" is a system that calculates the most suitable route for transporting goods efficiently based on the latest traffic data.

[0318] "Means for formulating a transportation plan for relief supplies" refers to a method for creating a specific plan for delivering necessary supplies to the appropriate locations.

[0319] "Means of recognizing emotions using a camera or microphone" refers to technology that analyzes image and audio data to identify a person's emotional state.

[0320] "Means for providing appropriate support messages and responses based on emotional data" is a system that presents necessary messages and actions based on the results of user emotional analysis.

[0321]

[0322] This invention is a system that supports the rapid and accurate collection of information and the planning of relief measures when a disaster occurs, and also integrates an emotion engine for recognizing the user's emotions. This system is composed of a server, terminals, and users.

[0323] Server Features

[0324] When a disaster occurs, the server automatically collects information from social media and other sources on the network based on pre-defined keywords (e.g., "earthquake," "tsunami," "fire," etc.) using the Twitter API and RSS feeds from news sites.

[0325] The collected information is fact-checked on the server, and its reliability is assessed using machine learning algorithms such as RoBERTa, with the reliability being expressed as a percentage.

[0326] The server plots the assessed information on a map using Google Maps API or OpenStreetMap API, visually displaying the damage situation, allowing users to check the situation in real time through a dashboard.

[0327] Based on the damage situation, the server refers to past data and pre-prepared scenarios to propose appropriate relief measures. It presents the necessary supplies, personnel, and transportation routes. It also calculates optimal logistics routes based on real-time traffic information and creates transportation plans for relief supplies.

[0328] Emotion Engine

[0329] The emotion engine is built into the server and recognizes emotions by analyzing user posts, comments, and voice data. Emotion recognition uses technologies such as text analysis, voice analysis, and facial expression analysis. For example, if a user posts a comment saying "I'm very scared," the emotion engine analyzes the comment and determines that the user is feeling strong anxiety or fear.

[0330] The server presents appropriate support messages and countermeasures based on the user's recognized emotions. For example, if the emotion engine determines that the user is in a state of panic, it displays a support message such as "Please stay calm and evacuate to a safe place." It also suggests high-priority rescue measures based on the user's emotional data. If a large number of users are expressing strong anxiety in an area, it will determine that psychological support is necessary and prioritize the dispatch of medical staff to that area.

[0331] Specific examples

[0332] For example, when an earthquake occurs, the server collects information using keywords such as "earthquake" and "damage," assesses the reliability of the information, and plots it on a map. At the same time, the server analyzes user posts using an emotion engine, and displays appropriate messages to users who are feeling anxious or scared, providing psychological support.

[0333] An example of a prompt is as follows:

[0334] Input prompt: "Very scary"

[0335] Evaluation result: Emotional polarity -0.9

[0336] Response message: "Please remain calm and seek safety."

[0337] This allows the entire system to provide support in both informational and emotional terms.

[0338] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0339] Step 1:

[0340] When a disaster occurs, the server automatically collects information from social media and other sources on the network based on pre-defined keywords (e.g., "earthquake," "tsunami," "fire," etc.). In this step, it uses the Twitter API and RSS feeds from news sites to retrieve related posts and news articles. The input is a list of keywords, and the output is a list of collected information.

[0341] Step 2:

[0342] The server uses machine learning algorithms such as RoBERTa to fact-check the collected information and evaluate its reliability. This process takes the collected information as input and outputs the reliability of each piece of information as a percentage. A text classification model is used to calculate the reliability.

[0343] Step 3:

[0344] The server plots the assessed information on a map using the Google Maps API or OpenStreetMap API, visually displaying the damage situation. The input is a list of information whose reliability has been assessed, and the output is the damage situation plotted on a map. This process allows users to check the situation in real time through a dashboard.

[0345] Step 4:

[0346] The server refers to past data and pre-prepared scenarios to propose necessary relief measures based on the disaster situation. In this step, the required supplies, personnel, and transportation routes are presented. The input is the disaster situation plotted on a map, and the output is the proposed relief measures.

[0347] Step 5:

[0348] The server calculates the optimal logistics route based on real-time traffic information and creates a delivery plan for relief supplies. In this step, past route data and current traffic condition data are input and the optimal delivery route is output. A real-time traffic data API is used to collect traffic information.

[0349] Step 6:

[0350] The emotion engine recognizes emotions by analyzing user posts, comments, and voice data. The input is the user's text and voice, and the output is the emotional evaluation result. Emotion recognition uses text analysis, voice analysis, and facial expression analysis. For example, if a user posts "very scary," the text is analyzed and the emotion of fear is evaluated.

[0351] Step 7:

[0352] The server presents appropriate support messages and countermeasures based on the recognized user's emotional data. In this step, the server receives the emotion evaluation results as input and outputs support messages and countermeasures based on them. For example, if the server recognizes that the user is in a panic state, it will provide a message such as "Please stay calm and evacuate to a safe place."

[0353] Step 8:

[0354] The vehicle's environment (e.g., temperature and lighting) is adjusted based on the user's emotional state. The input is the output of the emotion engine, and the output is the adjusted vehicle environment settings, allowing the occupants to travel with greater peace of mind.

[0355] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0356] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0357] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0358] [Second embodiment]

[0359] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0360] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0361] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0362] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0363] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0364] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0365] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0366] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0367] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0368] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0369] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0370] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0371] The present invention is a system that supports the rapid and accurate collection of information and the planning of relief measures when a disaster occurs. This system is composed of a server, terminals, and users.

[0372] Information collection

[0373] When a disaster occurs, the server automatically searches social media and other information sources on the network for information containing pre-defined keywords (e.g., "earthquake," "tsunami," "fire," etc.). For this purpose, the server includes a function to set relevant keywords as input fields. For example, the server uses the Twitter API or RSS feeds from news sites to obtain relevant information in real time.

[0374] Information reliability assessment

[0375] To assess the reliability of the collected information, the server uses a pre-trained fact-checking model (e.g., a machine learning algorithm). This model evaluates the reliability of the collected data and displays it as a percentage. For example, the server analyzes a tweet that says, "A magnitude 6 earthquake occurred in X city," and evaluates its reliability as "85%."

[0376] Information Visualization

[0377] The server plots the assessed information on a map and displays it visually, using Google Maps API and OpenStreetMap API to geographically represent the damage situation, allowing users to check the situation in real time through a dashboard.

[0378] For example, if the server determines that a large number of buildings have collapsed in a particular area, it will highlight the area in red and show the user the extent of the damage.

[0379] Proposal for relief measures

[0380] Based on the damage situation, the server refers to past data and pre-prepared scenarios to propose appropriate rescue measures, presenting the necessary supplies, personnel, transport routes, etc., and creating a rescue operation plan.

[0381] For example, if it is determined that medical assistance is needed in a particular area, the server will create a list of "medicines, medical staff" and present it to the user.

[0382] Transport routes and supporting logistics

[0383] The server uses real-time traffic information to calculate optimal routes for relief logistics, including algorithms that use data reflecting current traffic conditions to calculate the optimal delivery route for supplies.

[0384] For example, if a main road is collapsed, the server will calculate a detour route and instruct the user, "Since main road route A is unusable, use route B." The device will then provide the user with appropriate navigation information based on this information.

[0385] This system supports the planning of relief measures by quickly and efficiently collecting information when a disaster occurs, assessing its reliability, and visually displaying it, thereby preventing damage from spreading and enabling a rapid response.

[0386] The processing flow will be explained below.

[0387] Step 1:

[0388] When the server detects that a disaster has occurred, it automatically searches social media and other information sources on the network based on pre-defined keywords (e.g., "earthquake," "tsunami," "fire," etc.) To do this, the server accesses the Twitter API and RSS feeds of news sites to collect relevant posts and articles from these sources.

[0389] Step 2:

[0390] The server stores the collected information in a database, including the text content of each post, the date and time of posting, and information about the poster.

[0391] Step 3:

[0392] The server applies a fact-checking model to the collected information, specifically a pre-trained machine learning algorithm (e.g., a text classification model using RoBERTa), and uses this model to assess the trustworthiness of each post and calculate a confidence score as a percentage.

[0393] Step 4:

[0394] The server stores the assessed reliability of the information again in a database and sets criteria for selecting highly reliable information.

[0395] Step 5:

[0396] The server plots information that meets the reliability criteria on a map based on geographic location information (e.g., place names and GPS data included in the post), using the Google Maps API and OpenStreetMap API to visually display the information.

[0397] Step 6:

[0398] The server visualizes the damage situation on a map and then plans optimal relief measures based on the results, such as identifying the areas with the most damage and listing the necessary supplies, personnel, and transportation routes.

[0399] Step 7:

[0400] The server displays details of rescue measures on a dashboard, allowing users to review this information and take action.

[0401] Step 8:

[0402] The server accesses a traffic information API (e.g., Google Maps Traffic API) to obtain real-time traffic information and checks the latest road conditions, including road closures, congestion information, and detour routes.

[0403] Step 9:

[0404] The server integrates traffic and disaster information to calculate optimal logistics routes and create transportation plans for supplies. For example, if a major road is destroyed, it automatically calculates a detour route and displays the results on the dashboard.

[0405] Step 10:

[0406] The device displays optimal transportation routes and support logistics routes to users in real time, allowing users to safely and efficiently transport relief supplies to their destinations based on this information.

[0407] Step 11:

[0408] The server continuously collects new information, assesses reliability, plots it on the map, and updates rescue plans, allowing for rapid response to changing situations.

[0409] As a result, this system will enable rapid and accurate information collection, reliability evaluation, rescue plan planning, and logistics route optimization in the event of a disaster.

[0410] Example 1

[0411] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0412] When a disaster occurs, it is important to quickly and accurately collect information and plan relief measures, even with conventional technology. However, the reliability and immediacy of the information, as well as the applicability of relief measures, remain issues. There is also room for improvement in technology that accurately evaluates the reliability of collected information and visually displays the damage situation, as well as methods for calculating the optimal delivery route for relief supplies in real time.

[0413] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0414] In this invention, the server includes: means for automatically collecting information based on preset search terms from digital communication media on a network and other data sources when a disaster occurs; means for assessing the reliability of the collected information and displaying the reliability as a numerical value; means for plotting the assessed information on a map to visually display the damage situation; means for proposing necessary rescue measures based on the damage situation and presenting the resources, personnel, and transportation routes required for rescue; means for calculating optimal transportation routes based on real-time traffic information and formulating a transport plan for support resources; means for evaluating the collected data using a generative AI model that has been trained in advance to improve the reliability of the information; and means for displaying the reliability evaluation results of the assessed data on a user dashboard to notify the user. This enables rapid and accurate information collection and the planning of reliable rescue measures.

[0415] "When a disaster occurs" refers to the situation when a natural disaster such as an earthquake, tsunami, or fire occurs.

[0416] "Networked digital communications media" refers to platforms and services for transmitting and retrieving information over the Internet.

[0417] "Pre-set search terms" refer to keywords that are predetermined in anticipation of a disaster occurring.

[0418] "Means for automatically collecting information" refers to a method for automatically obtaining disaster-related data from the network based on set search terms.

[0419] "Means of assessing reliability and expressing the degree of reliability numerically" refers to a method of evaluating the credibility of collected data using machine learning models, etc., and expressing the results numerically.

[0420] "Means of plotting on a map and visually displaying the damage situation" refers to a method of displaying collected information on a map using a geographic information system to visualize the location and extent of the damage.

[0421] "Means of proposing relief measures and presenting the resources, personnel, and transportation routes required for relief" refers to methods of drawing up plans for relief activities based on the disaster situation and indicating the supplies, personnel, and transportation routes required for those activities.

[0422] "Means for calculating optimal transportation routes and formulating plans for transporting relief resources" refers to a method for calculating plans for delivering relief supplies and personnel via optimal routes based on traffic information obtained in real time.

[0423] A "generative AI model" refers to a learning model that uses artificial intelligence technology to generate and extract useful information and patterns from large amounts of data.

[0424] A "user dashboard" refers to an interface that allows users to visually check collected information and analysis results.

[0425] The present invention is a system that supports the rapid and accurate collection of information and the planning of rescue measures when a disaster occurs. This system is composed of a server, terminals, and users. The specific operation of each component of this system will be described below.

[0426] In this system, a server automatically collects information from digital communication media and other data sources on the network during a disaster. To gather disaster-related information, the server uses pre-defined search terms. For example, it uses the Twitter API or RSS feeds from news sites to search for keywords such as "earthquake" or "tsunami," and retrieves related tweets and news articles in real time. This allows for rapid and comprehensive collection of information.

[0427] The server assesses the reliability of the collected information. A pre-trained generative AI model is used to assess reliability. This model analyzes the collected data and indicates its reliability as a percentage. For example, if a tweet stating "A magnitude 6 earthquake has occurred in XX city" is collected, the generative AI model will assess the reliability of the tweet and assign it a reliability of 85%. Information with low reliability is filtered out, and only information with high reliability is advanced to the next processing step.

[0428] The server then plots the information, which has been assessed for reliability, on a map and displays it visually. Using the Google Maps API and OpenStreetMap API, the assessed information is visualized on the map, allowing users to check the damage situation in real time through a dashboard. For example, if the server determines that a large number of buildings have collapsed in a particular area, it will highlight that area in red and display it to the user.

[0429] The server then proposes relief measures based on the damage situation. To create appropriate relief measures, it references past data and pre-prepared scenarios. For example, if it determines that medical assistance is needed in a particular area, the server creates a list of "medicines and medical staff" and displays it to the user. This allows the user to quickly arrange for the necessary resources.

[0430] Furthermore, the server analyzes real-time traffic information and calculates the optimal support logistics route. It uses a database that reflects road traffic conditions and congestion information to create a transportation plan. For example, if a major road has collapsed, it calculates a detour route and instructs the terminal to "use route B as main road route A is unusable." The terminal provides this information to the user and performs appropriate navigation.

[0431] A specific example of how this works is the process of collecting tweets related to the keyword "earthquake" and evaluating their reliability using a fact-checking model. The information collected and evaluated in this way is displayed on a map using the Google Maps API, visually informing users of the affected areas.

[0432] Examples of prompts include:

[0433] Collect information that an "earthquake" has occurred during a disaster and evaluate its reliability.

[0434] Please suggest appropriate rescue measures in case of a fire in XX city.

[0435] Calculate the best route for transporting medical supplies to the disaster area.

[0436] As described above, the present invention is a system that efficiently collects necessary information when a disaster occurs, improves its reliability, and supports the planning of rapid relief measures. This helps prevent damage from spreading and enables early response.

[0437] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0438] Step 1:

[0439] When a disaster occurs, the server automatically collects information from digital communication media and other data sources on the network using pre-set search terms (e.g., "earthquake," "tsunami"), specifically by searching for information by keyword using the Twitter API and RSS feeds of news sites to obtain relevant data. The input required is the search term and API authentication information, and the output is related information (tweets and news articles).

[0440] Step 2:

[0441] The server runs a process to assess the reliability of the collected information. This process uses a pre-trained generative AI model. The input is the information collected in step 1, and the output is a percentage of the reliability. Specifically, the text of the collected tweets and news articles is input into the generative AI model, which analyzes their reliability.

[0442] Step 3:

[0443] The server plots the information whose reliability has been evaluated on a map and displays it visually. Specifically, it uses the Google Maps API or OpenStreetMap API to display information related to the affected area on the map. The reliability information evaluated in step 2 is required as input, and visualized map information is obtained as output. For example, areas where a magnitude 6 earthquake has occurred are highlighted in red and displayed to the user.

[0444] Step 4:

[0445] The server proposes necessary relief measures based on the disaster situation. It refers to past data and pre-prepared scenarios to plan appropriate relief measures. The input requires the disaster information visualized in step 3, and the output presents relief measures (e.g., a list of "medicine, medical staff"). Specifically, if it is determined that medical assistance is needed in the disaster-stricken area, the server creates the necessary list from the database and displays it to the user.

[0446] Step 5:

[0447] The server analyzes real-time traffic information and calculates the optimal relief logistics route. This is done using a database that reflects current traffic information. Real-time traffic data and relief supply information are required as input, and the optimal delivery route is presented as output. Specifically, if a major road has collapsed, a detour route is calculated and an instruction is given to "use route B as main road route A is unusable." The terminal provides this information to the user and performs appropriate navigation.

[0448] Through these steps, the server quickly and accurately collects, evaluates, and visualizes information, and then proposes relief measures and optimizes logistics routes, providing them to users.

[0449] (Application example 1)

[0450] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0451] Current disaster response systems face challenges in quickly and accurately collecting information and formulating relief measures when a disaster occurs. Furthermore, it is difficult to assess the reliability of the collected information, making it difficult to accurately grasp the situation in the affected area in real time. Furthermore, there is a lack of means to quickly provide information that reflects reliability assessments via mobile devices.

[0452] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0453] In this invention, the server includes: means for automatically collecting information based on preset keywords from social media and other information sources on a network when a disaster occurs; means for assessing the reliability of the collected information and indicating the reliability as a percentage; means for plotting the assessed information on a map to visually display the damage situation; means for proposing necessary relief measures based on the damage situation and presenting the supplies, personnel, and transportation routes required for relief; means for calculating optimal logistics routes based on real-time traffic information and formulating a transportation plan for relief supplies; and means for visually displaying information reflecting the reliability assessment for a specific area on a mobile device. This enables rapid and accurate information collection and assessment, visual understanding of the damage situation, and real-time information provision via mobile devices.

[0454] "Networked social media" is a general term for online platforms where users share content such as text, images, and videos over the Internet.

[0455] "Assessing the reliability of information" refers to the process of evaluating the accuracy and veracity of collected information.

[0456] "Indicating the reliability as a percentage" means expressing the reliability of the assessed information as a percentage.

[0457] "A means of plotting on a map and visually displaying the damage situation" is a system that displays collected information as location information on a map, allowing users to intuitively understand the damage situation.

[0458] "Means for proposing relief measures and indicating the supplies, personnel, and transportation routes necessary for relief" refers to a system that presents appropriate relief activities based on the disaster situation and indicates the necessary resources and optimal delivery routes.

[0459] "Means for calculating optimal logistics routes based on real-time traffic information and formulating transportation plans for relief supplies" refers to a method that uses current traffic data to calculate the optimal route for delivering relief supplies and then creates a specific logistics plan based on that.

[0460] "Mobile Device" refers to a portable computing device such as a smartphone or tablet.

[0461] "A means for visibly displaying information on a mobile device that reflects a reliability assessment for a specific area" refers to a function that provides disaster information based on the assessed reliability of the information in an easy-to-understand format on the user's mobile device.

[0462] The present invention relates to a system for supporting rapid and accurate information gathering and rescue planning in the event of a disaster. This system is composed of a server, terminals, and users.

[0463] Information collection

[0464] When a disaster occurs, the server automatically searches social media and other information sources on the network for information containing pre-defined keywords (e.g., "earthquake," "tsunami," "fire," etc.). The server includes a function to set relevant keywords as input fields. Specifically, it obtains relevant information in real time using the Twitter API and RSS feeds from news sites.

[0465] Information reliability assessment

[0466] To assess the reliability of the collected information, the server uses a pre-trained fact-checking model (e.g., a machine learning algorithm) that rates the collected data and indicates its veracity as a percentage.

[0467] Information Visualization

[0468] The server plots the assessed information on a map and displays it visually, using Google Maps API and OpenStreetMap API to geographically represent the damage situation, allowing users to check the situation in real time through a dashboard.

[0469] Proposal for relief measures

[0470] Based on the damage situation, the server refers to past data and pre-prepared scenarios to propose appropriate rescue measures, presenting the necessary supplies, personnel, transport routes, etc., and creating a rescue operation plan.

[0471] Transport routes and supporting logistics

[0472] The server calculates the optimal route for logistics support based on real-time traffic information. This includes an algorithm that uses data reflecting current traffic conditions to calculate the optimal delivery route for supplies, thereby providing appropriate navigation information to users.

[0473] Visualization of information reliability ratings for specific regions

[0474] To visually display information reflecting the trust ratings for specific areas, the system also provides information to mobile devices, specifically through smartphone and tablet apps, delivering this information to users in real time.

[0475] Hardware and software used

[0476] Hardware: smartphones, tablets, servers

[0477] Software: Python, Tweepy, TextBlob, Folium, Twitter API, Google Maps API, OpenStreetMap API

[0478] Specific examples

[0479] For example, if an earthquake occurs, the server will collect tweets containing the word "earthquake," evaluate their reliability, and display them on a map. Based on this information, the server will suggest safe evacuation routes and arrange for the necessary relief supplies.

[0480] Prompt Sentence Examples

[0481] Development of a smartphone app that collects real-time information during disasters, evaluates its reliability, and visualizes it

[0482] Step 1: Collect tweets about the disaster using the Twitter API

[0483] Step 2: Assess the authenticity of the tweet using TextBlob

[0484] Step 3: Visualize your data on a map using Folium

[0485] Thus, in order to implement the present invention, it is important that each element works in an organic manner, that disaster information is processed quickly and efficiently, and that appropriate relief measures are formulated.

[0486] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0487] Step 1:

[0488] When a disaster occurs, the server automatically collects information from social media and other sources on the network based on pre-set keywords (e.g., "earthquake," "tsunami," "fire," etc.). The input is the pre-set keywords and API authentication information, and the output is the information obtained from social media and news sites. The server uses the Twitter API, etc., to obtain tweets and news containing the relevant keywords. This processing makes it possible to collect disaster-related information in real time.

[0489] Step 2:

[0490] The server assesses the reliability of the collected information. The input is the information collected in step 1, and the output is data showing the reliability of each piece of information as a percentage. The server applies a machine learning algorithm to evaluate the reliability of the information and displays the result as a reliability percentage. This process allows users to judge the credibility of disaster-related information.

[0491] Step 3:

[0492] The server plots the assessed information on a map and displays it visually. The input is the information and geographic information whose reliability was assessed in step 2, and the output is a visually displayed map. The server uses the Google Maps API and OpenStreetMap API to generate a map that visually shows the damage situation. This allows users to intuitively understand the extent of damage in each area.

[0493] Step 4:

[0494] Based on the disaster situation, the server proposes the necessary relief measures and presents the supplies, personnel, and transportation routes required for relief. The input is the disaster situation, past data, and scenario data from Step 3, and the output is the proposed relief measures, required resources, and delivery routes. The server refers to past disaster data and rescue scenarios prepared in advance to propose appropriate support measures.

[0495] Step 5:

[0496] The server calculates the optimal logistics route based on real-time traffic information and creates a transportation plan for relief supplies. The input is real-time traffic data, and the output is the optimal transportation route. The server calculates the optimal supply delivery route based on the latest traffic information and presents that route to the user.

[0497] Step 6:

[0498] The server visually displays information reflecting the reliability assessment for a specific area on a mobile device. The input is the reliability assessment and geographic information generated in Steps 2 and 3, and the output is damage information displayed on the mobile device. The server provides information to users in real time via a smartphone or tablet app.

[0499] Through these steps, the present invention enables rapid and accurate information collection and assessment, visual understanding of the damage situation, and real-time information provision via mobile devices.

[0500] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0501] This invention combines a system that supports rapid and accurate information gathering and rescue planning in the event of a disaster with an emotion engine that recognizes the user's emotions. This system is composed of a server, terminals, and users.

[0502] Information collection

[0503] When a disaster occurs, the server automatically searches social media and other information sources on the network based on pre-defined keywords (e.g., "earthquake," "tsunami," "fire," etc.) To do this, the server accesses the Twitter API and RSS feeds of news sites to collect relevant posts and articles.

[0504] Information reliability assessment

[0505] The server applies a fact-checking model to the collected information, which is pre-trained using a machine learning algorithm (e.g., a text classification model using RoBERTa), and uses this model to assess the trustworthiness of each post, calculating a confidence score as a percentage.

[0506] Information Visualization

[0507] The server plots the assessed information on a map and displays it visually, using Google Maps API and OpenStreetMap API to geographically represent the damage situation, allowing users to check the situation in real time through a dashboard.

[0508] Proposal for relief measures

[0509] Based on the damage situation, the server refers to past data and pre-prepared scenarios to propose appropriate rescue measures. It presents the necessary supplies, personnel, and transportation routes, and creates a rescue operation plan.

[0510] Transport routes and supporting logistics

[0511] The server calculates optimal logistics routes based on real-time traffic information and creates a delivery plan for relief supplies, which includes an algorithm that uses data reflecting the latest road conditions to calculate the optimal delivery route for supplies.

[0512] Adding an Emotion Engine

[0513] emotion recognition

[0514] The server incorporates an emotion engine that analyzes user posts, comments, and voice data to recognize emotions. The emotion engine evaluates user emotions using techniques such as text analysis, voice analysis, and facial expression analysis.

[0515] As a specific example, if a user posts a comment saying "I'm very scared," the emotion engine will analyze the comment and determine that the user is feeling strong anxiety or fear.

[0516] Emotion-based responses

[0517] The server then presents appropriate support messages and countermeasures based on the user's recognized emotions. For example, if the emotion engine determines that the user is in a panic, the server will display a support message such as "Please stay calm and evacuate to a safe place."

[0518] Furthermore, the system can suggest high-priority rescue measures based on user emotional data. For example, if a region where many users are expressing strong anxiety is determined to require immediate psychological support, the system will prioritize dispatching medical staff to that region.

[0519] Overall system flow

[0520] This system enables rapid and efficient information gathering, reliability assessment, visualization of the damage situation, rescue plan proposals, logistics route optimization, and user emotion recognition and support based on that information when a disaster occurs, thereby preventing damage from spreading and enabling a rapid response.

[0521] As a concrete example, when an earthquake occurs, the server collects information using keywords such as "earthquake" and "damage," assesses its reliability, and plots it on a map. At the same time, the emotion engine analyzes user posts, and presents appropriate messages to users who are feeling anxious or scared, providing psychological support. In this way, the entire system can provide support from both the information and emotional perspectives.

[0522] The processing flow will be explained below.

[0523] Step 1:

[0524] When the server detects that a disaster has occurred, it automatically searches social media and other information sources on the network based on pre-defined keywords (e.g., "earthquake," "tsunami," "fire," etc.) by accessing the Twitter API and RSS feeds of news sites to collect relevant posts and articles.

[0525] Step 2:

[0526] The server stores the collected information in a database, which includes the text content of the posts, the date and time of posting, and information about the poster.

[0527] Step 3:

[0528] The server applies a fact-checking model to the collected information, using a pre-trained machine learning algorithm (e.g., a text classification model using RoBERTa) to assess the trustworthiness of each post and calculate a confidence score as a percentage.

[0529] Step 4:

[0530] The server stores the assessed reliability of the information in a database and selects information that meets the reliability criteria. Based on this reliable information, the damage situation can be grasped.

[0531] Step 5:

[0532] The server plots reliable information on a map based on geographic location information (e.g., place names and GPS data included in posts), using the Google Maps API and OpenStreetMap API.

[0533] Step 6:

[0534] The server visually displays the damage situation plotted on a map, allowing users to check the extent and impact of the damage in real time through a dashboard.

[0535] Step 7:

[0536] The server references past data and pre-prepared scenarios to plan relief measures based on the disaster situation, such as listing the supplies, personnel, and transportation routes needed for the most affected areas.

[0537] Step 8:

[0538] The server displays details of the rescue plan on a dashboard, allowing the user to review this information and proceed with the actual rescue operation.

[0539] Step 9:

[0540] The server accesses a traffic information API (e.g., Google Maps Traffic API) to obtain real-time traffic information and collects the latest road conditions, including road closures, congestion information, and detour routes.

[0541] Step 10:

[0542] The server integrates traffic and disaster information to calculate optimal logistics routes and create transportation plans for supplies. For example, if a major road is destroyed, it automatically calculates a detour route and displays the results on the dashboard.

[0543] Step 11:

[0544] The device displays optimal transportation routes and support logistics routes to users in real time, allowing them to safely and efficiently transport relief supplies to their destinations based on this information.

[0545] Step 12:

[0546] The server uses an emotion engine to analyze user posts, comments, and voice data. The emotion engine uses technologies such as text analysis, voice analysis, and facial expression analysis to evaluate the user's emotions.

[0547] Step 13:

[0548] The server then creates appropriate support messages and countermeasures based on the user's emotions recognized by the emotion engine. For example, if many users show strong anxiety, the server determines that psychological support is necessary and displays messages such as "Please stay calm and evacuate to a safe place."

[0549] Step 14:

[0550] The server then uses the emotion data to suggest high-priority rescue measures, such as creating a plan to immediately dispatch medical staff to areas where many users are panicking.

[0551] Step 15:

[0552] The server continuously collects new information, assesses its reliability, plots it on a map, and updates rescue plans, allowing for rapid response to changing situations.

[0553] In this way, this system supports disaster response from both an information and emotional perspective, aiming to minimize damage and achieve rapid recovery.

[0554] Example 2

[0555] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0556] When a disaster occurs, rapid and accurate information gathering, reliability assessment, visualization of the damage situation, relief plan proposals, optimization of relief logistics, and recognition and response of user emotions are required. However, conventional systems cannot comprehensively meet these requirements, and in particular, lack support including emotion recognition, resulting in insufficient psychological care for users. This leads to a decline in the quality of disaster response, and there is a risk of the damage increasing and relief efforts being delayed.

[0557] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0558] In this invention, the server includes: means for automatically collecting information based on preset keywords from social media and other information sources on a network; means for assessing the reliability of the collected information using a machine learning algorithm and displaying the reliability as a percentage; means for plotting the assessed information on a map to visually display the damage situation; means for referring to past data based on the damage situation, proposing necessary relief measures, and presenting necessary supplies, personnel, and transportation routes; means for calculating optimal logistics routes based on real-time traffic information and formulating a transportation plan for relief supplies; and means for analyzing user posts and comments and utilizing an emotion engine that recognizes emotions to present appropriate countermeasures based on user emotion data. This enables rapid and accurate information collection, reliable information evaluation, visual confirmation of the damage situation, proposing effective relief measures, calculating optimal logistics routes, and providing rapid support based on user emotions.

[0559] A "network" is an electronic communication means for sending and receiving information.

[0560] "Social media" is a general term for online platforms that allow users to create and share content.

[0561] "Source" refers to the medium or location that provides data or information.

[0562] "Keywords" are key words or phrases used to search for specific information.

[0563] A "machine learning algorithm" is a computational method that allows a computer to automatically learn and identify patterns based on empirical data.

[0564] "Reliability" is a numerical evaluation of the accuracy and credibility of information.

[0565] A "map" is a flat representation for visually displaying geographic information.

[0566] "Plotting" refers to placing information in a specific location and visually representing it.

[0567] "Historical data" refers to records or information previously collected.

[0568] "Relief measures" refer to specific measures and actions taken to mitigate damage and provide assistance in disasters and emergencies.

[0569] "Supplies" refers to materials and equipment necessary for relief activities.

[0570] "Human resources" refers to individuals or personnel with specific skills or knowledge.

[0571] A "transport route" refers to a route for transporting materials or personnel to a specific location.

[0572] "Real-time traffic information" refers to the latest data on current road conditions and traffic flow.

[0573] A "logistics route" refers to the route for optimal delivery of goods.

[0574] A "transportation plan" refers to detailed procedures and schedules for efficiently transporting supplies.

[0575] "User" refers to any individual or organization that uses this system.

[0576] "Post" means a message or comment posted by a user on social media or online platforms.

[0577] A "comment" refers to a post in which a user expresses their opinion or impression on a particular topic.

[0578] "Emotion engine" refers to technology that analyzes a user's text and voice data to identify their emotional state.

[0579] "Emotional data" refers to information about a user's emotional state.

[0580] "Responses" refer to specific actions or support measures that should be taken in response to a particular situation.

[0581] This invention relates to a system that supports rapid and accurate information gathering and rescue planning in the event of a disaster, and combines it with an emotion engine that recognizes the user's emotions. The system is composed of a server, terminals, and users, each of which plays a specific role.

[0582] Specifically, when a disaster occurs, the server automatically collects information from social media and other sources on the network based on pre-defined keywords (e.g., "earthquake," "tsunami," "fire," etc.) using well-known interfaces such as the Twitter API and RSS feeds from news sites.

[0583] The collected information is evaluated for reliability using a machine learning algorithm (e.g., RoBERTa model), and the reliability of each piece of information is calculated as a percentage. This reliability evaluation uses a pre-trained model, enabling highly accurate information judgment.

[0584] The information with a reliability assessment is then plotted on a map using the Google Maps API and OpenStreetMap API, allowing the server to visually represent the damage situation and users to view the situation in real time on a dashboard on their devices.

[0585] Based on the disaster situation, the server refers to past data and pre-prepared scenarios to propose optimal rescue measures. Specific rescue measures include presenting the necessary supplies, personnel, and transportation routes, thereby realizing efficient rescue operations.

[0586] Based on real-time traffic information, the server calculates the optimal logistics route and creates a transportation plan for relief supplies. This traffic information uses data that reflects the latest road conditions. By incorporating an algorithm to calculate the optimal delivery route for supplies, rapid transportation of supplies is possible.

[0587] Furthermore, the system is equipped with an emotion engine that analyzes user posts, comments, and voice data to recognize emotions. This is done using technologies such as text analysis, voice analysis, and facial expression analysis. For example, if a user posts a comment saying "I'm very scared," the emotion engine will analyze the comment and determine that the user is feeling strong anxiety or fear.

[0588] The server presents appropriate support messages and countermeasures based on the user's recognized emotions. For example, if the emotion engine determines that the user is in a state of panic, it will display a support message such as "Please stay calm and evacuate to a safe place." It also suggests high-priority rescue measures based on the user's emotional data. For example, it may determine that an area where many users are expressing strong anxiety requires immediate psychological support, and prioritize the dispatch of medical staff to that area.

[0589] As a concrete example, when an earthquake occurs, the server collects information using the keywords "earthquake" and "damage," assesses its reliability using a machine learning model, and plots it on a map. At the same time, the emotion engine analyzes user posts, and provides psychological support by displaying appropriate messages to users who are feeling anxious or scared. This entire system can provide support from both an informational and emotional perspective.

[0590] Example prompt for a generative AI model:

[0591] An earthquake has occurred and damage information is being collected. Collect the latest tweets and news articles related to the disaster, evaluate the reliability of the information, recognize emotions from user comments, and suggest countermeasures.

[0592] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0593] Step 1:

[0594] The server collects information from social media and news sites on the network based on pre-set keywords (e.g., "earthquake," "tsunami," "fire," etc.).

[0595] Input: Keywords such as "earthquake," "tsunami," and "fire"

[0596] Output: A list of tweets and news articles containing the keyword

[0597] Operation:

[0598] 1. The server uses the Twitter API to collect tweets containing the keyword.

[0599] 2. The server parses the news site's RSS feed and retrieves the latest articles.

[0600] Step 2:

[0601] The server evaluates the reliability of the collected information using machine learning algorithms.

[0602] Input: Collected tweets and news articles

[0603] Output: Confidence score (percentage) for each piece of information

[0604] Operation:

[0605] 1. The server inputs each collected text data into a machine learning model (e.g., RoBERTa model) and calculates a confidence score.

[0606] 2. The server stores the confidence score in a database.

[0607] Step 3:

[0608] The server plots the information whose reliability has been assessed on a map and displays it.

[0609] Input: Information (tweets or news articles) with assessed credibility and their location

[0610] Output: Damage information plotted on a map

[0611] Operation:

[0612] 1. The server uses the Google Maps API or OpenStreetMap API to plot the location data of the disaster information on a map.

[0613] 2. Users can access the dashboard through their devices and check the status in real time.

[0614] Step 4:

[0615] The server proposes appropriate relief measures based on the disaster situation.

[0616] Input: Disaster information and past rescue data

[0617] Output: Proposed relief plan (necessary supplies, personnel, transport routes)

[0618] Operation:

[0619] 1. The server compares past disaster data with current damage information.

[0620] 2. The server plans the required supplies, personnel, and transportation routes and displays them on the dashboard.

[0621] Step 5:

[0622] The server calculates the optimal logistics route based on real-time traffic information.

[0623] Input: Latest road conditions and traffic data

[0624] Output: Optimal logistics routes and transportation plans for relief supplies

[0625] Operation:

[0626] 1. The server uses a traffic data API (e.g., Google Maps Traffic API) to obtain real-time traffic information.

[0627] 2. The server applies an algorithm to calculate the optimal delivery route and displays the results on a dashboard.

[0628] Step 6:

[0629] The server analyzes users' posts and comments to recognize their emotions.

[0630] Input: User posts and comments (text data)

[0631] Output: User's emotion evaluation result

[0632] Operation:

[0633] 1. When a user posts a comment from their device, the server inputs the text data into the emotion engine.

[0634] 2. The sentiment engine performs text analysis and evaluates the user's sentiment.

[0635] Step 7:

[0636] The server presents appropriate support messages and countermeasures based on the recognized emotions.

[0637] Input: User's emotion evaluation result

[0638] Output: Support message and / or action plan

[0639] Operation:

[0640] 1. After the emotion engine evaluates the user's emotion, the server generates an appropriate message based on the result.

[0641] 2. The server displays support messages such as "Please stay calm and evacuate to a safe place" on the dashboard.

[0642] 3. The server proposes high-priority rescue measures based on the user's emotional data.

[0643] (Application example 2)

[0644] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0645] In modern society, when a disaster occurs, there is a need to quickly and accurately collect information and plan appropriate relief measures. However, many challenges exist, such as confusion during a disaster, a decrease in the reliability of information, and the mental instability of victims. It is also important to provide optimal escape routes and routes for transporting supplies based on traffic conditions and the situation in the affected area, but current systems are unable to adequately address these issues.

[0646] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for automatically collecting information based on preset keywords from social media and other information sources on the network when a disaster occurs; means for assessing the reliability of the collected information and displaying the reliability as a percentage; means for plotting the assessed information on a map to visually display the damage situation; means for proposing necessary relief measures based on the damage situation and presenting the supplies, personnel, and transportation routes required for relief; means for calculating optimal logistics routes based on real-time traffic information and formulating a transportation plan for relief supplies; and means for recognizing the emotions of occupants using a camera and microphone and providing appropriate support messages and responses based on the emotion data. This enables rapid and accurate information collection and reliability assessment, relief measure proposals, calculation of optimal logistics routes, and mental care for occupants.

[0647] "Networked social media" is a general term for platforms used via the Internet for sharing and exchanging information.

[0648] "Source" refers to the medium or device from which information is disseminated.

[0649] "Keywords" are important words or phrases used when searching for specific information.

[0650] "Means for automatically collecting information" refers to a mechanism for automatically acquiring information based on set conditions.

[0651] A "means for assessing trustworthiness" is a method or system for evaluating the veracity or accuracy of collected information.

[0652] A "means of showing reliability as a percentage" is a method of quantifying the reliability of information and displaying it in the form of a percentage.

[0653] "Means of plotting on a map and visually displaying the damage situation" refers to a method of illustrating the situation in the disaster area on a map using a geographic information system.

[0654] "Means for proposing relief measures and presenting the supplies, personnel, and transportation routes required for relief" is a system that plans and proposes appropriate support actions, necessary resources, and routes for transporting them.

[0655] "Means for calculating optimal logistics routes based on real-time traffic information" is a system that calculates the most suitable route for transporting goods efficiently based on the latest traffic data.

[0656] "Means for formulating a transportation plan for relief supplies" refers to a method for creating a specific plan for delivering necessary supplies to the appropriate locations.

[0657] "Means of recognizing emotions using a camera or microphone" refers to technology that analyzes image and audio data to identify a person's emotional state.

[0658] "Means for providing appropriate support messages and responses based on emotional data" is a system that presents necessary messages and actions based on the results of user emotional analysis.

[0659]

[0660] This invention is a system that supports the rapid and accurate collection of information and the planning of relief measures when a disaster occurs, and also integrates an emotion engine for recognizing the user's emotions. This system is composed of a server, terminals, and users.

[0661] Server Features

[0662] When a disaster occurs, the server automatically collects information from social media and other sources on the network based on pre-defined keywords (e.g., "earthquake," "tsunami," "fire," etc.) using the Twitter API and RSS feeds from news sites.

[0663] The collected information is fact-checked on the server, and its reliability is assessed using machine learning algorithms such as RoBERTa, with the reliability being expressed as a percentage.

[0664] The server plots the assessed information on a map using Google Maps API or OpenStreetMap API, visually displaying the damage situation, allowing users to check the situation in real time through a dashboard.

[0665] Based on the damage situation, the server refers to past data and pre-prepared scenarios to propose appropriate relief measures. It presents the necessary supplies, personnel, and transportation routes. It also calculates optimal logistics routes based on real-time traffic information and creates transportation plans for relief supplies.

[0666] Emotion Engine

[0667] The emotion engine is built into the server and recognizes emotions by analyzing user posts, comments, and voice data. Emotion recognition uses technologies such as text analysis, voice analysis, and facial expression analysis. For example, if a user posts a comment saying "I'm very scared," the emotion engine analyzes the comment and determines that the user is feeling strong anxiety or fear.

[0668] The server presents appropriate support messages and countermeasures based on the user's recognized emotions. For example, if the emotion engine determines that the user is in a state of panic, it displays a support message such as "Please stay calm and evacuate to a safe place." It also suggests high-priority rescue measures based on the user's emotional data. If a large number of users are expressing strong anxiety in an area, it will determine that psychological support is necessary and prioritize the dispatch of medical staff to that area.

[0669] Specific examples

[0670] For example, when an earthquake occurs, the server collects information using keywords such as "earthquake" and "damage," assesses the reliability of the information, and plots it on a map. At the same time, the server analyzes user posts using an emotion engine, and displays appropriate messages to users who are feeling anxious or scared, providing psychological support.

[0671] An example of a prompt is as follows:

[0672] Input prompt: "Very scary"

[0673] Evaluation result: Emotional polarity -0.9

[0674] Response message: "Please remain calm and seek safety."

[0675] This allows the entire system to provide support in both informational and emotional terms.

[0676] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0677] Step 1:

[0678] When a disaster occurs, the server automatically collects information from social media and other sources on the network based on pre-defined keywords (e.g., "earthquake," "tsunami," "fire," etc.). In this step, it uses the Twitter API and RSS feeds from news sites to retrieve related posts and news articles. The input is a list of keywords, and the output is a list of collected information.

[0679] Step 2:

[0680] The server uses machine learning algorithms such as RoBERTa to fact-check the collected information and evaluate its reliability. This process takes the collected information as input and outputs the reliability of each piece of information as a percentage. A text classification model is used to calculate the reliability.

[0681] Step 3:

[0682] The server plots the assessed information on a map using the Google Maps API or OpenStreetMap API, visually displaying the damage situation. The input is a list of information whose reliability has been assessed, and the output is the damage situation plotted on a map. This process allows users to check the situation in real time through a dashboard.

[0683] Step 4:

[0684] The server refers to past data and pre-prepared scenarios to propose necessary relief measures based on the disaster situation. In this step, the required supplies, personnel, and transportation routes are presented. The input is the disaster situation plotted on a map, and the output is the proposed relief measures.

[0685] Step 5:

[0686] The server calculates the optimal logistics route based on real-time traffic information and creates a delivery plan for relief supplies. In this step, past route data and current traffic condition data are input and the optimal delivery route is output. A real-time traffic data API is used to collect traffic information.

[0687] Step 6:

[0688] The emotion engine recognizes emotions by analyzing user posts, comments, and voice data. The input is the user's text and voice, and the output is the emotional evaluation result. Emotion recognition uses text analysis, voice analysis, and facial expression analysis. For example, if a user posts "very scary," the text is analyzed and the emotion of fear is evaluated.

[0689] Step 7:

[0690] The server presents appropriate support messages and countermeasures based on the recognized user's emotional data. In this step, the server receives the emotion evaluation results as input and outputs support messages and countermeasures based on them. For example, if the server recognizes that the user is in a panic state, it will provide a message such as "Please stay calm and evacuate to a safe place."

[0691] Step 8:

[0692] The vehicle's environment (e.g., temperature and lighting) is adjusted based on the user's emotional state. The input is the output of the emotion engine, and the output is the adjusted vehicle environment settings, allowing the occupants to travel with greater peace of mind.

[0693] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0694] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0695] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0696] [Third embodiment]

[0697] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0698] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0699] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0700] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0701] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0702] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0703] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0704] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0705] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0706] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0707] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0708] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0709] The present invention is a system that supports the rapid and accurate collection of information and the planning of relief measures when a disaster occurs. This system is composed of a server, terminals, and users.

[0710] Information collection

[0711] When a disaster occurs, the server automatically searches social media and other information sources on the network for information containing pre-defined keywords (e.g., "earthquake," "tsunami," "fire," etc.). For this purpose, the server includes a function to set relevant keywords as input fields. For example, the server uses the Twitter API or RSS feeds from news sites to obtain relevant information in real time.

[0712] Information reliability assessment

[0713] To assess the reliability of the collected information, the server uses a pre-trained fact-checking model (e.g., a machine learning algorithm). This model evaluates the reliability of the collected data and displays it as a percentage. For example, the server analyzes a tweet that says, "A magnitude 6 earthquake occurred in X city," and evaluates its reliability as "85%."

[0714] Information Visualization

[0715] The server plots the assessed information on a map and displays it visually, using Google Maps API and OpenStreetMap API to geographically represent the damage situation, allowing users to check the situation in real time through a dashboard.

[0716] For example, if the server determines that a large number of buildings have collapsed in a particular area, it will highlight the area in red and show the user the extent of the damage.

[0717] Proposal for relief measures

[0718] Based on the damage situation, the server refers to past data and pre-prepared scenarios to propose appropriate rescue measures, presenting the necessary supplies, personnel, transport routes, etc., and creating a rescue operation plan.

[0719] For example, if it is determined that medical assistance is needed in a particular area, the server will create a list of "medicines, medical staff" and present it to the user.

[0720] Transport routes and supporting logistics

[0721] The server uses real-time traffic information to calculate optimal routes for relief logistics, including algorithms that use data reflecting current traffic conditions to calculate the optimal delivery route for supplies.

[0722] For example, if a main road is collapsed, the server will calculate a detour route and instruct the user, "Since main road route A is unusable, use route B." The device will then provide the user with appropriate navigation information based on this information.

[0723] This system supports the planning of relief measures by quickly and efficiently collecting information when a disaster occurs, assessing its reliability, and visually displaying it, thereby preventing damage from spreading and enabling a rapid response.

[0724] The processing flow will be explained below.

[0725] Step 1:

[0726] When the server detects that a disaster has occurred, it automatically searches social media and other information sources on the network based on pre-defined keywords (e.g., "earthquake," "tsunami," "fire," etc.) To do this, the server accesses the Twitter API and RSS feeds of news sites to collect relevant posts and articles from these sources.

[0727] Step 2:

[0728] The server stores the collected information in a database, including the text content of each post, the date and time of posting, and information about the poster.

[0729] Step 3:

[0730] The server applies a fact-checking model to the collected information, specifically a pre-trained machine learning algorithm (e.g., a text classification model using RoBERTa), and uses this model to assess the trustworthiness of each post and calculate a confidence score as a percentage.

[0731] Step 4:

[0732] The server stores the assessed reliability of the information again in a database and sets criteria for selecting highly reliable information.

[0733] Step 5:

[0734] The server plots information that meets the reliability criteria on a map based on geographic location information (e.g., place names and GPS data included in the post), using the Google Maps API and OpenStreetMap API to visually display the information.

[0735] Step 6:

[0736] The server visualizes the damage situation on a map and then plans optimal relief measures based on the results, such as identifying the areas with the most damage and listing the necessary supplies, personnel, and transportation routes.

[0737] Step 7:

[0738] The server displays details of rescue measures on a dashboard, allowing users to review this information and take action.

[0739] Step 8:

[0740] The server accesses a traffic information API (e.g., Google Maps Traffic API) to obtain real-time traffic information and checks the latest road conditions, including road closures, congestion information, and detour routes.

[0741] Step 9:

[0742] The server integrates traffic and disaster information to calculate optimal logistics routes and create transportation plans for supplies. For example, if a major road is destroyed, it automatically calculates a detour route and displays the results on the dashboard.

[0743] Step 10:

[0744] The device displays optimal transportation routes and support logistics routes to users in real time, allowing users to safely and efficiently transport relief supplies to their destinations based on this information.

[0745] Step 11:

[0746] The server continuously collects new information, assesses reliability, plots it on the map, and updates rescue plans, allowing for rapid response to changing situations.

[0747] As a result, this system will enable rapid and accurate information collection, reliability evaluation, rescue plan planning, and logistics route optimization in the event of a disaster.

[0748] Example 1

[0749] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0750] When a disaster occurs, it is important to quickly and accurately collect information and plan relief measures, even with conventional technology. However, the reliability and immediacy of the information, as well as the applicability of relief measures, remain issues. There is also room for improvement in technology that accurately evaluates the reliability of collected information and visually displays the damage situation, as well as methods for calculating the optimal delivery route for relief supplies in real time.

[0751] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0752] In this invention, the server includes: means for automatically collecting information based on preset search terms from digital communication media on a network and other data sources when a disaster occurs; means for assessing the reliability of the collected information and displaying the reliability as a numerical value; means for plotting the assessed information on a map to visually display the damage situation; means for proposing necessary rescue measures based on the damage situation and presenting the resources, personnel, and transportation routes required for rescue; means for calculating optimal transportation routes based on real-time traffic information and formulating a transport plan for support resources; means for evaluating the collected data using a generative AI model that has been trained in advance to improve the reliability of the information; and means for displaying the reliability evaluation results of the assessed data on a user dashboard to notify the user. This enables rapid and accurate information collection and the planning of reliable rescue measures.

[0753] "When a disaster occurs" refers to the situation when a natural disaster such as an earthquake, tsunami, or fire occurs.

[0754] "Networked digital communications media" refers to platforms and services for transmitting and retrieving information over the Internet.

[0755] "Pre-set search terms" refer to keywords that are predetermined in anticipation of a disaster occurring.

[0756] "Means for automatically collecting information" refers to a method for automatically obtaining disaster-related data from the network based on set search terms.

[0757] "Means of assessing reliability and expressing the degree of reliability numerically" refers to a method of evaluating the credibility of collected data using machine learning models, etc., and expressing the results numerically.

[0758] "Means of plotting on a map and visually displaying the damage situation" refers to a method of displaying collected information on a map using a geographic information system to visualize the location and extent of the damage.

[0759] "Means of proposing relief measures and presenting the resources, personnel, and transportation routes required for relief" refers to methods of drawing up plans for relief activities based on the disaster situation and indicating the supplies, personnel, and transportation routes required for those activities.

[0760] "Means for calculating optimal transportation routes and formulating plans for transporting relief resources" refers to a method for calculating plans for delivering relief supplies and personnel via optimal routes based on traffic information obtained in real time.

[0761] A "generative AI model" refers to a learning model that uses artificial intelligence technology to generate and extract useful information and patterns from large amounts of data.

[0762] A "user dashboard" refers to an interface that allows users to visually check collected information and analysis results.

[0763] The present invention is a system that supports the rapid and accurate collection of information and the planning of rescue measures when a disaster occurs. This system is composed of a server, terminals, and users. The specific operation of each component of this system will be described below.

[0764] In this system, a server automatically collects information from digital communication media and other data sources on the network during a disaster. To gather disaster-related information, the server uses pre-defined search terms. For example, it uses the Twitter API or RSS feeds from news sites to search for keywords such as "earthquake" or "tsunami," and retrieves related tweets and news articles in real time. This allows for rapid and comprehensive collection of information.

[0765] The server assesses the reliability of the collected information. A pre-trained generative AI model is used to assess reliability. This model analyzes the collected data and indicates its reliability as a percentage. For example, if a tweet stating "A magnitude 6 earthquake has occurred in XX city" is collected, the generative AI model will assess the reliability of the tweet and assign it a reliability of 85%. Information with low reliability is filtered out, and only information with high reliability is advanced to the next processing step.

[0766] The server then plots the information, which has been assessed for reliability, on a map and displays it visually. Using the Google Maps API and OpenStreetMap API, the assessed information is visualized on the map, allowing users to check the damage situation in real time through a dashboard. For example, if the server determines that a large number of buildings have collapsed in a particular area, it will highlight that area in red and display it to the user.

[0767] The server then proposes relief measures based on the damage situation. To create appropriate relief measures, it references past data and pre-prepared scenarios. For example, if it determines that medical assistance is needed in a particular area, the server creates a list of "medicines and medical staff" and displays it to the user. This allows the user to quickly arrange for the necessary resources.

[0768] Furthermore, the server analyzes real-time traffic information and calculates the optimal support logistics route. It uses a database that reflects road traffic conditions and congestion information to create a transportation plan. For example, if a major road has collapsed, it calculates a detour route and instructs the terminal to "use route B as main road route A is unusable." The terminal provides this information to the user and performs appropriate navigation.

[0769] A specific example of how this works is the process of collecting tweets related to the keyword "earthquake" and evaluating their reliability using a fact-checking model. The information collected and evaluated in this way is displayed on a map using the Google Maps API, visually informing users of the affected areas.

[0770] Examples of prompts include:

[0771] Collect information that an "earthquake" has occurred during a disaster and evaluate its reliability.

[0772] Please suggest appropriate rescue measures in case of a fire in XX city.

[0773] Calculate the best route for transporting medical supplies to the disaster area.

[0774] As described above, the present invention is a system that efficiently collects necessary information when a disaster occurs, improves its reliability, and supports the planning of rapid relief measures. This helps prevent damage from spreading and enables early response.

[0775] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0776] Step 1:

[0777] When a disaster occurs, the server automatically collects information from digital communication media and other data sources on the network using pre-set search terms (e.g., "earthquake," "tsunami"), specifically by searching for information by keyword using the Twitter API and RSS feeds of news sites to obtain relevant data. The input required is the search term and API authentication information, and the output is related information (tweets and news articles).

[0778] Step 2:

[0779] The server runs a process to assess the reliability of the collected information. This process uses a pre-trained generative AI model. The input is the information collected in step 1, and the output is a percentage of the reliability. Specifically, the text of the collected tweets and news articles is input into the generative AI model, which analyzes their reliability.

[0780] Step 3:

[0781] The server plots the information whose reliability has been evaluated on a map and displays it visually. Specifically, it uses the Google Maps API or OpenStreetMap API to display information related to the affected area on the map. The reliability information evaluated in step 2 is required as input, and visualized map information is obtained as output. For example, areas where a magnitude 6 earthquake has occurred are highlighted in red and displayed to the user.

[0782] Step 4:

[0783] The server proposes necessary relief measures based on the disaster situation. It refers to past data and pre-prepared scenarios to plan appropriate relief measures. The input requires the disaster information visualized in step 3, and the output presents relief measures (e.g., a list of "medicine, medical staff"). Specifically, if it is determined that medical assistance is needed in the disaster-stricken area, the server creates the necessary list from the database and displays it to the user.

[0784] Step 5:

[0785] The server analyzes real-time traffic information and calculates the optimal relief logistics route. This is done using a database that reflects current traffic information. Real-time traffic data and relief supply information are required as input, and the optimal delivery route is presented as output. Specifically, if a major road has collapsed, a detour route is calculated and an instruction is given to "use route B as main road route A is unusable." The terminal provides this information to the user and performs appropriate navigation.

[0786] Through these steps, the server quickly and accurately collects, evaluates, and visualizes information, and then proposes relief measures and optimizes logistics routes, providing them to users.

[0787] (Application example 1)

[0788] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0789] Current disaster response systems face challenges in quickly and accurately collecting information and formulating relief measures when a disaster occurs. Furthermore, it is difficult to assess the reliability of the collected information, making it difficult to accurately grasp the situation in the affected area in real time. Furthermore, there is a lack of means to quickly provide information that reflects reliability assessments via mobile devices.

[0790] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0791] In this invention, the server includes: means for automatically collecting information based on preset keywords from social media and other information sources on a network when a disaster occurs; means for assessing the reliability of the collected information and indicating the reliability as a percentage; means for plotting the assessed information on a map to visually display the damage situation; means for proposing necessary relief measures based on the damage situation and presenting the supplies, personnel, and transportation routes required for relief; means for calculating optimal logistics routes based on real-time traffic information and formulating a transportation plan for relief supplies; and means for visually displaying information reflecting the reliability assessment for a specific area on a mobile device. This enables rapid and accurate information collection and assessment, visual understanding of the damage situation, and real-time information provision via mobile devices.

[0792] "Networked social media" is a general term for online platforms where users share content such as text, images, and videos over the Internet.

[0793] "Assessing the reliability of information" refers to the process of evaluating the accuracy and veracity of collected information.

[0794] "Indicating the reliability as a percentage" means expressing the reliability of the assessed information as a percentage.

[0795] "A means of plotting on a map and visually displaying the damage situation" is a system that displays collected information as location information on a map, allowing users to intuitively understand the damage situation.

[0796] "Means for proposing relief measures and indicating the supplies, personnel, and transportation routes necessary for relief" refers to a system that presents appropriate relief activities based on the disaster situation and indicates the necessary resources and optimal delivery routes.

[0797] "Means for calculating optimal logistics routes based on real-time traffic information and formulating transportation plans for relief supplies" refers to a method that uses current traffic data to calculate the optimal route for delivering relief supplies and then creates a specific logistics plan based on that.

[0798] "Mobile Device" refers to a portable computing device such as a smartphone or tablet.

[0799] "A means for visibly displaying information on a mobile device that reflects a reliability assessment for a specific area" refers to a function that provides disaster information based on the assessed reliability of the information in an easy-to-understand format on the user's mobile device.

[0800] The present invention relates to a system for supporting rapid and accurate information gathering and rescue planning in the event of a disaster. This system is composed of a server, terminals, and users.

[0801] Information collection

[0802] When a disaster occurs, the server automatically searches social media and other information sources on the network for information containing pre-defined keywords (e.g., "earthquake," "tsunami," "fire," etc.). The server includes a function to set relevant keywords as input fields. Specifically, it obtains relevant information in real time using the Twitter API and RSS feeds from news sites.

[0803] Information reliability assessment

[0804] To assess the reliability of the collected information, the server uses a pre-trained fact-checking model (e.g., a machine learning algorithm) that rates the collected data and indicates its veracity as a percentage.

[0805] Information Visualization

[0806] The server plots the assessed information on a map and displays it visually, using Google Maps API and OpenStreetMap API to geographically represent the damage situation, allowing users to check the situation in real time through a dashboard.

[0807] Proposal for relief measures

[0808] Based on the damage situation, the server refers to past data and pre-prepared scenarios to propose appropriate rescue measures, presenting the necessary supplies, personnel, transport routes, etc., and creating a rescue operation plan.

[0809] Transport routes and supporting logistics

[0810] The server calculates the optimal route for logistics support based on real-time traffic information. This includes an algorithm that uses data reflecting current traffic conditions to calculate the optimal delivery route for supplies, thereby providing appropriate navigation information to users.

[0811] Visualization of information reliability ratings for specific regions

[0812] To visually display information reflecting the trust ratings for specific areas, the system also provides information to mobile devices, specifically through smartphone and tablet apps, delivering this information to users in real time.

[0813] Hardware and software used

[0814] Hardware: smartphones, tablets, servers

[0815] Software: Python, Tweepy, TextBlob, Folium, Twitter API, Google Maps API, OpenStreetMap API

[0816] Specific examples

[0817] For example, if an earthquake occurs, the server will collect tweets containing the word "earthquake," evaluate their reliability, and display them on a map. Based on this information, the server will suggest safe evacuation routes and arrange for the necessary relief supplies.

[0818] Prompt Sentence Examples

[0819] Development of a smartphone app that collects real-time information during disasters, evaluates its reliability, and visualizes it

[0820] Step 1: Collect tweets about the disaster using the Twitter API

[0821] Step 2: Assess the authenticity of the tweet using TextBlob

[0822] Step 3: Visualize your data on a map using Folium

[0823] Thus, in order to implement the present invention, it is important that each element works in an organic manner, that disaster information is processed quickly and efficiently, and that appropriate relief measures are formulated.

[0824] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0825] Step 1:

[0826] When a disaster occurs, the server automatically collects information from social media and other sources on the network based on pre-set keywords (e.g., "earthquake," "tsunami," "fire," etc.). The input is the pre-set keywords and API authentication information, and the output is the information obtained from social media and news sites. The server uses the Twitter API, etc., to obtain tweets and news containing the relevant keywords. This processing makes it possible to collect disaster-related information in real time.

[0827] Step 2:

[0828] The server assesses the reliability of the collected information. The input is the information collected in step 1, and the output is data showing the reliability of each piece of information as a percentage. The server applies a machine learning algorithm to evaluate the reliability of the information and displays the result as a reliability percentage. This process allows users to judge the credibility of disaster-related information.

[0829] Step 3:

[0830] The server plots the assessed information on a map and displays it visually. The input is the information and geographic information whose reliability was assessed in step 2, and the output is a visually displayed map. The server uses the Google Maps API and OpenStreetMap API to generate a map that visually shows the damage situation. This allows users to intuitively understand the extent of damage in each area.

[0831] Step 4:

[0832] Based on the disaster situation, the server proposes the necessary relief measures and presents the supplies, personnel, and transportation routes required for relief. The input is the disaster situation, past data, and scenario data from Step 3, and the output is the proposed relief measures, required resources, and delivery routes. The server refers to past disaster data and rescue scenarios prepared in advance to propose appropriate support measures.

[0833] Step 5:

[0834] The server calculates the optimal logistics route based on real-time traffic information and creates a transportation plan for relief supplies. The input is real-time traffic data, and the output is the optimal transportation route. The server calculates the optimal supply delivery route based on the latest traffic information and presents that route to the user.

[0835] Step 6:

[0836] The server visually displays information reflecting the reliability assessment for a specific area on a mobile device. The input is the reliability assessment and geographic information generated in Steps 2 and 3, and the output is damage information displayed on the mobile device. The server provides information to users in real time via a smartphone or tablet app.

[0837] Through these steps, the present invention enables rapid and accurate information collection and assessment, visual understanding of the damage situation, and real-time information provision via mobile devices.

[0838] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0839] This invention combines a system that supports rapid and accurate information gathering and rescue planning in the event of a disaster with an emotion engine that recognizes the user's emotions. This system is composed of a server, terminals, and users.

[0840] Information collection

[0841] When a disaster occurs, the server automatically searches social media and other information sources on the network based on pre-defined keywords (e.g., "earthquake," "tsunami," "fire," etc.) To do this, the server accesses the Twitter API and RSS feeds of news sites to collect relevant posts and articles.

[0842] Information reliability assessment

[0843] The server applies a fact-checking model to the collected information, which is pre-trained using a machine learning algorithm (e.g., a text classification model using RoBERTa), and uses this model to assess the trustworthiness of each post, calculating a confidence score as a percentage.

[0844] Information Visualization

[0845] The server plots the assessed information on a map and displays it visually, using Google Maps API and OpenStreetMap API to geographically represent the damage situation, allowing users to check the situation in real time through a dashboard.

[0846] Proposal for relief measures

[0847] Based on the damage situation, the server refers to past data and pre-prepared scenarios to propose appropriate rescue measures. It presents the necessary supplies, personnel, and transportation routes, and creates a rescue operation plan.

[0848] Transport routes and supporting logistics

[0849] The server calculates optimal logistics routes based on real-time traffic information and creates a delivery plan for relief supplies, which includes an algorithm that uses data reflecting the latest road conditions to calculate the optimal delivery route for supplies.

[0850] Adding an Emotion Engine

[0851] emotion recognition

[0852] The server incorporates an emotion engine that analyzes user posts, comments, and voice data to recognize emotions. The emotion engine evaluates user emotions using techniques such as text analysis, voice analysis, and facial expression analysis.

[0853] As a specific example, if a user posts a comment saying "I'm very scared," the emotion engine will analyze the comment and determine that the user is feeling strong anxiety or fear.

[0854] Emotion-based responses

[0855] The server then presents appropriate support messages and countermeasures based on the user's recognized emotions. For example, if the emotion engine determines that the user is in a panic, the server will display a support message such as "Please stay calm and evacuate to a safe place."

[0856] Furthermore, the system can suggest high-priority rescue measures based on user emotional data. For example, if a region where many users are expressing strong anxiety is determined to require immediate psychological support, the system will prioritize dispatching medical staff to that region.

[0857] Overall system flow

[0858] This system enables rapid and efficient information gathering, reliability assessment, visualization of the damage situation, rescue plan proposals, logistics route optimization, and user emotion recognition and support based on that information when a disaster occurs, thereby preventing damage from spreading and enabling a rapid response.

[0859] As a concrete example, when an earthquake occurs, the server collects information using keywords such as "earthquake" and "damage," assesses its reliability, and plots it on a map. At the same time, the emotion engine analyzes user posts, and presents appropriate messages to users who are feeling anxious or scared, providing psychological support. In this way, the entire system can provide support from both the information and emotional perspectives.

[0860] The processing flow will be explained below.

[0861] Step 1:

[0862] When the server detects that a disaster has occurred, it automatically searches social media and other information sources on the network based on pre-defined keywords (e.g., "earthquake," "tsunami," "fire," etc.) by accessing the Twitter API and RSS feeds of news sites to collect relevant posts and articles.

[0863] Step 2:

[0864] The server stores the collected information in a database, which includes the text content of the posts, the date and time of posting, and information about the poster.

[0865] Step 3:

[0866] The server applies a fact-checking model to the collected information, using a pre-trained machine learning algorithm (e.g., a text classification model using RoBERTa) to assess the trustworthiness of each post and calculate a confidence score as a percentage.

[0867] Step 4:

[0868] The server stores the assessed reliability of the information in a database and selects information that meets the reliability criteria. Based on this reliable information, the damage situation can be grasped.

[0869] Step 5:

[0870] The server plots reliable information on a map based on geographic location information (e.g., place names and GPS data included in posts), using the Google Maps API and OpenStreetMap API.

[0871] Step 6:

[0872] The server visually displays the damage situation plotted on a map, allowing users to check the extent and impact of the damage in real time through a dashboard.

[0873] Step 7:

[0874] The server references past data and pre-prepared scenarios to plan relief measures based on the disaster situation, such as listing the supplies, personnel, and transportation routes needed for the most affected areas.

[0875] Step 8:

[0876] The server displays details of the rescue plan on a dashboard, allowing the user to review this information and proceed with the actual rescue operation.

[0877] Step 9:

[0878] The server accesses a traffic information API (e.g., Google Maps Traffic API) to obtain real-time traffic information and collects the latest road conditions, including road closures, congestion information, and detour routes.

[0879] Step 10:

[0880] The server integrates traffic and disaster information to calculate optimal logistics routes and create transportation plans for supplies. For example, if a major road is destroyed, it automatically calculates a detour route and displays the results on the dashboard.

[0881] Step 11:

[0882] The device displays optimal transportation routes and support logistics routes to users in real time, allowing them to safely and efficiently transport relief supplies to their destinations based on this information.

[0883] Step 12:

[0884] The server uses an emotion engine to analyze user posts, comments, and voice data. The emotion engine uses technologies such as text analysis, voice analysis, and facial expression analysis to evaluate the user's emotions.

[0885] Step 13:

[0886] The server then creates appropriate support messages and countermeasures based on the user's emotions recognized by the emotion engine. For example, if many users show strong anxiety, the server determines that psychological support is necessary and displays messages such as "Please stay calm and evacuate to a safe place."

[0887] Step 14:

[0888] The server then uses the emotion data to suggest high-priority rescue measures, such as creating a plan to immediately dispatch medical staff to areas where many users are panicking.

[0889] Step 15:

[0890] The server continuously collects new information, assesses its reliability, plots it on a map, and updates rescue plans, allowing for rapid response to changing situations.

[0891] In this way, this system supports disaster response from both an information and emotional perspective, aiming to minimize damage and achieve rapid recovery.

[0892] Example 2

[0893] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0894] When a disaster occurs, rapid and accurate information gathering, reliability assessment, visualization of the damage situation, relief plan proposals, optimization of relief logistics, and recognition and response of user emotions are required. However, conventional systems cannot comprehensively meet these requirements, and in particular, lack support including emotion recognition, resulting in insufficient psychological care for users. This leads to a decline in the quality of disaster response, and there is a risk of the damage increasing and relief efforts being delayed.

[0895] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0896] In this invention, the server includes: means for automatically collecting information based on preset keywords from social media and other information sources on a network; means for assessing the reliability of the collected information using a machine learning algorithm and displaying the reliability as a percentage; means for plotting the assessed information on a map to visually display the damage situation; means for referring to past data based on the damage situation, proposing necessary relief measures, and presenting necessary supplies, personnel, and transportation routes; means for calculating optimal logistics routes based on real-time traffic information and formulating a transportation plan for relief supplies; and means for analyzing user posts and comments and utilizing an emotion engine that recognizes emotions to present appropriate countermeasures based on user emotion data. This enables rapid and accurate information collection, reliable information evaluation, visual confirmation of the damage situation, proposing effective relief measures, calculating optimal logistics routes, and providing rapid support based on user emotions.

[0897] A "network" is an electronic communication means for sending and receiving information.

[0898] "Social media" is a general term for online platforms that allow users to create and share content.

[0899] "Source" refers to the medium or location that provides data or information.

[0900] "Keywords" are key words or phrases used to search for specific information.

[0901] A "machine learning algorithm" is a computational method that allows a computer to automatically learn and identify patterns based on empirical data.

[0902] "Reliability" is a numerical evaluation of the accuracy and credibility of information.

[0903] A "map" is a flat representation for visually displaying geographic information.

[0904] "Plotting" refers to placing information in a specific location and visually representing it.

[0905] "Historical data" refers to records or information previously collected.

[0906] "Relief measures" refer to specific measures and actions taken to mitigate damage and provide assistance in disasters and emergencies.

[0907] "Supplies" refers to materials and equipment necessary for relief activities.

[0908] "Human resources" refers to individuals or personnel with specific skills or knowledge.

[0909] A "transport route" refers to a route for transporting materials or personnel to a specific location.

[0910] "Real-time traffic information" refers to the latest data on current road conditions and traffic flow.

[0911] A "logistics route" refers to the route for optimal delivery of goods.

[0912] A "transportation plan" refers to detailed procedures and schedules for efficiently transporting supplies.

[0913] "User" refers to any individual or organization that uses this system.

[0914] "Post" means a message or comment posted by a user on social media or online platforms.

[0915] A "comment" refers to a post in which a user expresses their opinion or impression on a particular topic.

[0916] "Emotion engine" refers to technology that analyzes a user's text and voice data to identify their emotional state.

[0917] "Emotional data" refers to information about a user's emotional state.

[0918] "Responses" refer to specific actions or support measures that should be taken in response to a particular situation.

[0919] This invention relates to a system that supports rapid and accurate information gathering and rescue planning in the event of a disaster, and combines it with an emotion engine that recognizes the user's emotions. The system is composed of a server, terminals, and users, each of which plays a specific role.

[0920] Specifically, when a disaster occurs, the server automatically collects information from social media and other sources on the network based on pre-defined keywords (e.g., "earthquake," "tsunami," "fire," etc.) using well-known interfaces such as the Twitter API and RSS feeds from news sites.

[0921] The collected information is evaluated for reliability using a machine learning algorithm (e.g., RoBERTa model), and the reliability of each piece of information is calculated as a percentage. This reliability evaluation uses a pre-trained model, enabling highly accurate information judgment.

[0922] The information with a reliability assessment is then plotted on a map using the Google Maps API and OpenStreetMap API, allowing the server to visually represent the damage situation and users to view the situation in real time on a dashboard on their devices.

[0923] Based on the disaster situation, the server refers to past data and pre-prepared scenarios to propose optimal rescue measures. Specific rescue measures include presenting the necessary supplies, personnel, and transportation routes, thereby realizing efficient rescue operations.

[0924] Based on real-time traffic information, the server calculates the optimal logistics route and creates a transportation plan for relief supplies. This traffic information uses data that reflects the latest road conditions. By incorporating an algorithm to calculate the optimal delivery route for supplies, rapid transportation of supplies is possible.

[0925] Furthermore, the system is equipped with an emotion engine that analyzes user posts, comments, and voice data to recognize emotions. This is done using technologies such as text analysis, voice analysis, and facial expression analysis. For example, if a user posts a comment saying "I'm very scared," the emotion engine will analyze the comment and determine that the user is feeling strong anxiety or fear.

[0926] The server presents appropriate support messages and countermeasures based on the user's recognized emotions. For example, if the emotion engine determines that the user is in a state of panic, it will display a support message such as "Please stay calm and evacuate to a safe place." It also suggests high-priority rescue measures based on the user's emotional data. For example, it may determine that an area where many users are expressing strong anxiety requires immediate psychological support, and prioritize the dispatch of medical staff to that area.

[0927] As a concrete example, when an earthquake occurs, the server collects information using the keywords "earthquake" and "damage," assesses its reliability using a machine learning model, and plots it on a map. At the same time, the emotion engine analyzes user posts, and provides psychological support by displaying appropriate messages to users who are feeling anxious or scared. This entire system can provide support from both an informational and emotional perspective.

[0928] Example prompt for a generative AI model:

[0929] An earthquake has occurred and damage information is being collected. Collect the latest tweets and news articles related to the disaster, evaluate the reliability of the information, recognize emotions from user comments, and suggest countermeasures.

[0930] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0931] Step 1:

[0932] The server collects information from social media and news sites on the network based on pre-set keywords (e.g., "earthquake," "tsunami," "fire," etc.).

[0933] Input: Keywords such as "earthquake," "tsunami," and "fire"

[0934] Output: A list of tweets and news articles containing the keyword

[0935] Operation:

[0936] 1. The server uses the Twitter API to collect tweets containing the keyword.

[0937] 2. The server parses the news site's RSS feed and retrieves the latest articles.

[0938] Step 2:

[0939] The server evaluates the reliability of the collected information using machine learning algorithms.

[0940] Input: Collected tweets and news articles

[0941] Output: Confidence score (percentage) for each piece of information

[0942] Operation:

[0943] 1. The server inputs each collected text data into a machine learning model (e.g., RoBERTa model) and calculates a confidence score.

[0944] 2. The server stores the confidence score in a database.

[0945] Step 3:

[0946] The server plots the information whose reliability has been assessed on a map and displays it.

[0947] Input: Information (tweets or news articles) with assessed credibility and their location

[0948] Output: Damage information plotted on a map

[0949] Operation:

[0950] 1. The server uses the Google Maps API or OpenStreetMap API to plot the location data of the disaster information on a map.

[0951] 2. Users can access the dashboard through their devices and check the status in real time.

[0952] Step 4:

[0953] The server proposes appropriate relief measures based on the disaster situation.

[0954] Input: Disaster information and past rescue data

[0955] Output: Proposed relief plan (necessary supplies, personnel, transport routes)

[0956] Operation:

[0957] 1. The server compares past disaster data with current damage information.

[0958] 2. The server plans the required supplies, personnel, and transportation routes and displays them on the dashboard.

[0959] Step 5:

[0960] The server calculates the optimal logistics route based on real-time traffic information.

[0961] Input: Latest road conditions and traffic data

[0962] Output: Optimal logistics routes and transportation plans for relief supplies

[0963] Operation:

[0964] 1. The server uses a traffic data API (e.g., Google Maps Traffic API) to obtain real-time traffic information.

[0965] 2. The server applies an algorithm to calculate the optimal delivery route and displays the results on a dashboard.

[0966] Step 6:

[0967] The server analyzes users' posts and comments to recognize their emotions.

[0968] Input: User posts and comments (text data)

[0969] Output: User's emotion evaluation result

[0970] Operation:

[0971] 1. When a user posts a comment from their device, the server inputs the text data into the emotion engine.

[0972] 2. The sentiment engine performs text analysis and evaluates the user's sentiment.

[0973] Step 7:

[0974] The server presents appropriate support messages and countermeasures based on the recognized emotions.

[0975] Input: User's emotion evaluation result

[0976] Output: Support message and / or action plan

[0977] Operation:

[0978] 1. After the emotion engine evaluates the user's emotion, the server generates an appropriate message based on the result.

[0979] 2. The server displays support messages such as "Please stay calm and evacuate to a safe place" on the dashboard.

[0980] 3. The server proposes high-priority rescue measures based on the user's emotional data.

[0981] (Application example 2)

[0982] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0983] In modern society, when a disaster occurs, there is a need to quickly and accurately collect information and plan appropriate relief measures. However, many challenges exist, such as confusion during a disaster, a decrease in the reliability of information, and the mental instability of victims. It is also important to provide optimal escape routes and routes for transporting supplies based on traffic conditions and the situation in the affected area, but current systems are unable to adequately address these issues.

[0984] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for automatically collecting information based on preset keywords from social media and other information sources on the network when a disaster occurs; means for assessing the reliability of the collected information and displaying the reliability as a percentage; means for plotting the assessed information on a map to visually display the damage situation; means for proposing necessary relief measures based on the damage situation and presenting the supplies, personnel, and transportation routes required for relief; means for calculating optimal logistics routes based on real-time traffic information and formulating a transportation plan for relief supplies; and means for recognizing the emotions of occupants using a camera and microphone and providing appropriate support messages and responses based on the emotion data. This enables rapid and accurate information collection and reliability assessment, relief measure proposals, calculation of optimal logistics routes, and mental care for occupants.

[0985] "Networked social media" is a general term for platforms used via the Internet for sharing and exchanging information.

[0986] "Source" refers to the medium or device from which information is disseminated.

[0987] "Keywords" are important words or phrases used when searching for specific information.

[0988] "Means for automatically collecting information" refers to a mechanism for automatically acquiring information based on set conditions.

[0989] A "means for assessing trustworthiness" is a method or system for evaluating the veracity or accuracy of collected information.

[0990] A "means of showing reliability as a percentage" is a method of quantifying the reliability of information and displaying it in the form of a percentage.

[0991] "Means of plotting on a map and visually displaying the damage situation" refers to a method of illustrating the situation in the disaster area on a map using a geographic information system.

[0992] "Means for proposing relief measures and presenting the supplies, personnel, and transportation routes required for relief" is a system that plans and proposes appropriate support actions, necessary resources, and routes for transporting them.

[0993] "Means for calculating optimal logistics routes based on real-time traffic information" is a system that calculates the most suitable route for transporting goods efficiently based on the latest traffic data.

[0994] "Means for formulating a transportation plan for relief supplies" refers to a method for creating a specific plan for delivering necessary supplies to the appropriate locations.

[0995] "Means of recognizing emotions using a camera or microphone" refers to technology that analyzes image and audio data to identify a person's emotional state.

[0996] "Means for providing appropriate support messages and responses based on emotional data" is a system that presents necessary messages and actions based on the results of user emotional analysis.

[0997]

[0998] This invention is a system that supports the rapid and accurate collection of information and the planning of relief measures when a disaster occurs, and also integrates an emotion engine for recognizing the user's emotions. This system is composed of a server, terminals, and users.

[0999] Server Features

[1000] When a disaster occurs, the server automatically collects information from social media and other sources on the network based on pre-defined keywords (e.g., "earthquake," "tsunami," "fire," etc.) using the Twitter API and RSS feeds from news sites.

[1001] The collected information is fact-checked on the server, and its reliability is assessed using machine learning algorithms such as RoBERTa, with the reliability being expressed as a percentage.

[1002] The server plots the assessed information on a map using Google Maps API or OpenStreetMap API, visually displaying the damage situation, allowing users to check the situation in real time through a dashboard.

[1003] Based on the damage situation, the server refers to past data and pre-prepared scenarios to propose appropriate relief measures. It presents the necessary supplies, personnel, and transportation routes. It also calculates optimal logistics routes based on real-time traffic information and creates transportation plans for relief supplies.

[1004] Emotion Engine

[1005] The emotion engine is built into the server and recognizes emotions by analyzing user posts, comments, and voice data. Emotion recognition uses technologies such as text analysis, voice analysis, and facial expression analysis. For example, if a user posts a comment saying "I'm very scared," the emotion engine analyzes the comment and determines that the user is feeling strong anxiety or fear.

[1006] The server presents appropriate support messages and countermeasures based on the user's recognized emotions. For example, if the emotion engine determines that the user is in a state of panic, it displays a support message such as "Please stay calm and evacuate to a safe place." It also suggests high-priority rescue measures based on the user's emotional data. If a large number of users are expressing strong anxiety in an area, it will determine that psychological support is necessary and prioritize the dispatch of medical staff to that area.

[1007] Specific examples

[1008] For example, when an earthquake occurs, the server collects information using keywords such as "earthquake" and "damage," assesses the reliability of the information, and plots it on a map. At the same time, the server analyzes user posts using an emotion engine, and displays appropriate messages to users who are feeling anxious or scared, providing psychological support.

[1009] An example of a prompt is as follows:

[1010] Input prompt: "Very scary"

[1011] Evaluation result: Emotional polarity -0.9

[1012] Response message: "Please remain calm and seek safety."

[1013] This allows the entire system to provide support in both informational and emotional terms.

[1014] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1015] Step 1:

[1016] When a disaster occurs, the server automatically collects information from social media and other sources on the network based on pre-defined keywords (e.g., "earthquake," "tsunami," "fire," etc.). In this step, it uses the Twitter API and RSS feeds from news sites to retrieve related posts and news articles. The input is a list of keywords, and the output is a list of collected information.

[1017] Step 2:

[1018] The server uses machine learning algorithms such as RoBERTa to fact-check the collected information and evaluate its reliability. This process takes the collected information as input and outputs the reliability of each piece of information as a percentage. A text classification model is used to calculate the reliability.

[1019] Step 3:

[1020] The server plots the assessed information on a map using the Google Maps API or OpenStreetMap API, visually displaying the damage situation. The input is a list of information whose reliability has been assessed, and the output is the damage situation plotted on a map. This process allows users to check the situation in real time through a dashboard.

[1021] Step 4:

[1022] The server refers to past data and pre-prepared scenarios to propose necessary relief measures based on the disaster situation. In this step, the required supplies, personnel, and transportation routes are presented. The input is the disaster situation plotted on a map, and the output is the proposed relief measures.

[1023] Step 5:

[1024] The server calculates the optimal logistics route based on real-time traffic information and creates a delivery plan for relief supplies. In this step, past route data and current traffic condition data are input and the optimal delivery route is output. A real-time traffic data API is used to collect traffic information.

[1025] Step 6:

[1026] The emotion engine recognizes emotions by analyzing user posts, comments, and voice data. The input is the user's text and voice, and the output is the emotional evaluation result. Emotion recognition uses text analysis, voice analysis, and facial expression analysis. For example, if a user posts "very scary," the text is analyzed and the emotion of fear is evaluated.

[1027] Step 7:

[1028] The server presents appropriate support messages and countermeasures based on the recognized user's emotional data. In this step, the server receives the emotion evaluation results as input and outputs support messages and countermeasures based on them. For example, if the server recognizes that the user is in a panic state, it will provide a message such as "Please stay calm and evacuate to a safe place."

[1029] Step 8:

[1030] The vehicle's environment (e.g., temperature and lighting) is adjusted based on the user's emotional state. The input is the output of the emotion engine, and the output is the adjusted vehicle environment settings, allowing the occupants to travel with greater peace of mind.

[1031] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1032] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1033] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1034] [Fourth embodiment]

[1035] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1036] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1037] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1038] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1039] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1040] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1041] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1042] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1043] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1044] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1045] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1046] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1047] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1048] The present invention is a system that supports the rapid and accurate collection of information and the planning of relief measures when a disaster occurs. This system is composed of a server, terminals, and users.

[1049] Information collection

[1050] When a disaster occurs, the server automatically searches social media and other information sources on the network for information containing pre-defined keywords (e.g., "earthquake," "tsunami," "fire," etc.). For this purpose, the server includes a function to set relevant keywords as input fields. For example, the server uses the Twitter API or RSS feeds from news sites to obtain relevant information in real time.

[1051] Information reliability assessment

[1052] To assess the reliability of the collected information, the server uses a pre-trained fact-checking model (e.g., a machine learning algorithm). This model evaluates the reliability of the collected data and displays it as a percentage. For example, the server analyzes a tweet that says, "A magnitude 6 earthquake occurred in X city," and evaluates its reliability as "85%."

[1053] Information Visualization

[1054] The server plots the assessed information on a map and displays it visually, using Google Maps API and OpenStreetMap API to geographically represent the damage situation, allowing users to check the situation in real time through a dashboard.

[1055] For example, if the server determines that a large number of buildings have collapsed in a particular area, it will highlight the area in red and show the user the extent of the damage.

[1056] Proposal for relief measures

[1057] Based on the damage situation, the server refers to past data and pre-prepared scenarios to propose appropriate rescue measures, presenting the necessary supplies, personnel, transport routes, etc., and creating a rescue operation plan.

[1058] For example, if it is determined that medical assistance is needed in a particular area, the server will create a list of "medicines, medical staff" and present it to the user.

[1059] Transport routes and supporting logistics

[1060] The server uses real-time traffic information to calculate optimal routes for relief logistics, including algorithms that use data reflecting current traffic conditions to calculate the optimal delivery route for supplies.

[1061] For example, if a main road is collapsed, the server will calculate a detour route and instruct the user, "Since main road route A is unusable, use route B." The device will then provide the user with appropriate navigation information based on this information.

[1062] This system supports the planning of relief measures by quickly and efficiently collecting information when a disaster occurs, assessing its reliability, and visually displaying it, thereby preventing damage from spreading and enabling a rapid response.

[1063] The processing flow will be explained below.

[1064] Step 1:

[1065] When the server detects that a disaster has occurred, it automatically searches social media and other information sources on the network based on pre-defined keywords (e.g., "earthquake," "tsunami," "fire," etc.) To do this, the server accesses the Twitter API and RSS feeds of news sites to collect relevant posts and articles from these sources.

[1066] Step 2:

[1067] The server stores the collected information in a database, including the text content of each post, the date and time of posting, and information about the poster.

[1068] Step 3:

[1069] The server applies a fact-checking model to the collected information, specifically a pre-trained machine learning algorithm (e.g., a text classification model using RoBERTa), and uses this model to assess the trustworthiness of each post and calculate a confidence score as a percentage.

[1070] Step 4:

[1071] The server stores the assessed reliability of the information again in a database and sets criteria for selecting highly reliable information.

[1072] Step 5:

[1073] The server plots information that meets the reliability criteria on a map based on geographic location information (e.g., place names and GPS data included in the post), using the Google Maps API and OpenStreetMap API to visually display the information.

[1074] Step 6:

[1075] The server visualizes the damage situation on a map and then plans optimal relief measures based on the results, such as identifying the areas with the most damage and listing the necessary supplies, personnel, and transportation routes.

[1076] Step 7:

[1077] The server displays details of rescue measures on a dashboard, allowing users to review this information and take action.

[1078] Step 8:

[1079] The server accesses a traffic information API (e.g., Google Maps Traffic API) to obtain real-time traffic information and checks the latest road conditions, including road closures, congestion information, and detour routes.

[1080] Step 9:

[1081] The server integrates traffic and disaster information to calculate optimal logistics routes and create transportation plans for supplies. For example, if a major road is destroyed, it automatically calculates a detour route and displays the results on the dashboard.

[1082] Step 10:

[1083] The device displays optimal transportation routes and support logistics routes to users in real time, allowing users to safely and efficiently transport relief supplies to their destinations based on this information.

[1084] Step 11:

[1085] The server continuously collects new information, assesses reliability, plots it on the map, and updates rescue plans, allowing for rapid response to changing situations.

[1086] As a result, this system will enable rapid and accurate information collection, reliability evaluation, rescue plan planning, and logistics route optimization in the event of a disaster.

[1087] Example 1

[1088] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1089] When a disaster occurs, it is important to quickly and accurately collect information and plan relief measures, even with conventional technology. However, the reliability and immediacy of the information, as well as the applicability of relief measures, remain issues. There is also room for improvement in technology that accurately evaluates the reliability of collected information and visually displays the damage situation, as well as methods for calculating the optimal delivery route for relief supplies in real time.

[1090] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1091] In this invention, the server includes: means for automatically collecting information based on preset search terms from digital communication media on a network and other data sources when a disaster occurs; means for assessing the reliability of the collected information and displaying the reliability as a numerical value; means for plotting the assessed information on a map to visually display the damage situation; means for proposing necessary rescue measures based on the damage situation and presenting the resources, personnel, and transportation routes required for rescue; means for calculating optimal transportation routes based on real-time traffic information and formulating a transport plan for support resources; means for evaluating the collected data using a generative AI model that has been trained in advance to improve the reliability of the information; and means for displaying the reliability evaluation results of the assessed data on a user dashboard to notify the user. This enables rapid and accurate information collection and the planning of reliable rescue measures.

[1092] "When a disaster occurs" refers to the situation when a natural disaster such as an earthquake, tsunami, or fire occurs.

[1093] "Networked digital communications media" refers to platforms and services for transmitting and retrieving information over the Internet.

[1094] "Pre-set search terms" refer to keywords that are predetermined in anticipation of a disaster occurring.

[1095] "Means for automatically collecting information" refers to a method for automatically obtaining disaster-related data from the network based on set search terms.

[1096] "Means of assessing reliability and expressing the degree of reliability numerically" refers to a method of evaluating the credibility of collected data using machine learning models, etc., and expressing the results numerically.

[1097] "Means of plotting on a map and visually displaying the damage situation" refers to a method of displaying collected information on a map using a geographic information system to visualize the location and extent of the damage.

[1098] "Means of proposing relief measures and presenting the resources, personnel, and transportation routes required for relief" refers to methods of drawing up plans for relief activities based on the disaster situation and indicating the supplies, personnel, and transportation routes required for those activities.

[1099] "Means for calculating optimal transportation routes and formulating plans for transporting relief resources" refers to a method for calculating plans for delivering relief supplies and personnel via optimal routes based on traffic information obtained in real time.

[1100] A "generative AI model" refers to a learning model that uses artificial intelligence technology to generate and extract useful information and patterns from large amounts of data.

[1101] A "user dashboard" refers to an interface that allows users to visually check collected information and analysis results.

[1102] The present invention is a system that supports the rapid and accurate collection of information and the planning of rescue measures when a disaster occurs. This system is composed of a server, terminals, and users. The specific operation of each component of this system will be described below.

[1103] In this system, a server automatically collects information from digital communication media and other data sources on the network during a disaster. To gather disaster-related information, the server uses pre-defined search terms. For example, it uses the Twitter API or RSS feeds from news sites to search for keywords such as "earthquake" or "tsunami," and retrieves related tweets and news articles in real time. This allows for rapid and comprehensive collection of information.

[1104] The server assesses the reliability of the collected information. A pre-trained generative AI model is used to assess reliability. This model analyzes the collected data and indicates its reliability as a percentage. For example, if a tweet stating "A magnitude 6 earthquake has occurred in XX city" is collected, the generative AI model will assess the reliability of the tweet and assign it a reliability of 85%. Information with low reliability is filtered out, and only information with high reliability is advanced to the next processing step.

[1105] The server then plots the information, which has been assessed for reliability, on a map and displays it visually. Using the Google Maps API and OpenStreetMap API, the assessed information is visualized on the map, allowing users to check the damage situation in real time through a dashboard. For example, if the server determines that a large number of buildings have collapsed in a particular area, it will highlight that area in red and display it to the user.

[1106] The server then proposes relief measures based on the damage situation. To create appropriate relief measures, it references past data and pre-prepared scenarios. For example, if it determines that medical assistance is needed in a particular area, the server creates a list of "medicines and medical staff" and displays it to the user. This allows the user to quickly arrange for the necessary resources.

[1107] Furthermore, the server analyzes real-time traffic information and calculates the optimal support logistics route. It uses a database that reflects road traffic conditions and congestion information to create a transportation plan. For example, if a major road has collapsed, it calculates a detour route and instructs the terminal to "use route B as main road route A is unusable." The terminal provides this information to the user and performs appropriate navigation.

[1108] A specific example of how this works is the process of collecting tweets related to the keyword "earthquake" and evaluating their reliability using a fact-checking model. The information collected and evaluated in this way is displayed on a map using the Google Maps API, visually informing users of the affected areas.

[1109] Examples of prompts include:

[1110] Collect information that an "earthquake" has occurred during a disaster and evaluate its reliability.

[1111] Please suggest appropriate rescue measures in case of a fire in XX city.

[1112] Calculate the best route for transporting medical supplies to the disaster area.

[1113] As described above, the present invention is a system that efficiently collects necessary information when a disaster occurs, improves its reliability, and supports the planning of rapid relief measures. This helps prevent damage from spreading and enables early response.

[1114] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1115] Step 1:

[1116] When a disaster occurs, the server automatically collects information from digital communication media and other data sources on the network using pre-set search terms (e.g., "earthquake," "tsunami"), specifically by searching for information by keyword using the Twitter API and RSS feeds of news sites to obtain relevant data. The input required is the search term and API authentication information, and the output is related information (tweets and news articles).

[1117] Step 2:

[1118] The server runs a process to assess the reliability of the collected information. This process uses a pre-trained generative AI model. The input is the information collected in step 1, and the output is a percentage of the reliability. Specifically, the text of the collected tweets and news articles is input into the generative AI model, which analyzes their reliability.

[1119] Step 3:

[1120] The server plots the information whose reliability has been evaluated on a map and displays it visually. Specifically, it uses the Google Maps API or OpenStreetMap API to display information related to the affected area on the map. The reliability information evaluated in step 2 is required as input, and visualized map information is obtained as output. For example, areas where a magnitude 6 earthquake has occurred are highlighted in red and displayed to the user.

[1121] Step 4:

[1122] The server proposes necessary relief measures based on the disaster situation. It refers to past data and pre-prepared scenarios to plan appropriate relief measures. The input requires the disaster information visualized in step 3, and the output presents relief measures (e.g., a list of "medicine, medical staff"). Specifically, if it is determined that medical assistance is needed in the disaster-stricken area, the server creates the necessary list from the database and displays it to the user.

[1123] Step 5:

[1124] The server analyzes real-time traffic information and calculates the optimal relief logistics route. This is done using a database that reflects current traffic information. Real-time traffic data and relief supply information are required as input, and the optimal delivery route is presented as output. Specifically, if a major road has collapsed, a detour route is calculated and an instruction is given to "use route B as main road route A is unusable." The terminal provides this information to the user and performs appropriate navigation.

[1125] Through these steps, the server quickly and accurately collects, evaluates, and visualizes information, and then proposes relief measures and optimizes logistics routes, providing them to users.

[1126] (Application example 1)

[1127] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1128] Current disaster response systems face challenges in quickly and accurately collecting information and formulating relief measures when a disaster occurs. Furthermore, it is difficult to assess the reliability of the collected information, making it difficult to accurately grasp the situation in the affected area in real time. Furthermore, there is a lack of means to quickly provide information that reflects reliability assessments via mobile devices.

[1129] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1130] In this invention, the server includes: means for automatically collecting information based on preset keywords from social media and other information sources on a network when a disaster occurs; means for assessing the reliability of the collected information and indicating the reliability as a percentage; means for plotting the assessed information on a map to visually display the damage situation; means for proposing necessary relief measures based on the damage situation and presenting the supplies, personnel, and transportation routes required for relief; means for calculating optimal logistics routes based on real-time traffic information and formulating a transportation plan for relief supplies; and means for visually displaying information reflecting the reliability assessment for a specific area on a mobile device. This enables rapid and accurate information collection and assessment, visual understanding of the damage situation, and real-time information provision via mobile devices.

[1131] "Networked social media" is a general term for online platforms where users share content such as text, images, and videos over the Internet.

[1132] "Assessing the reliability of information" refers to the process of evaluating the accuracy and veracity of collected information.

[1133] "Indicating the reliability as a percentage" means expressing the reliability of the assessed information as a percentage.

[1134] "A means of plotting on a map and visually displaying the damage situation" is a system that displays collected information as location information on a map, allowing users to intuitively understand the damage situation.

[1135] "Means for proposing relief measures and indicating the supplies, personnel, and transportation routes necessary for relief" refers to a system that presents appropriate relief activities based on the disaster situation and indicates the necessary resources and optimal delivery routes.

[1136] "Means for calculating optimal logistics routes based on real-time traffic information and formulating transportation plans for relief supplies" refers to a method that uses current traffic data to calculate the optimal route for delivering relief supplies and then creates a specific logistics plan based on that.

[1137] "Mobile Device" refers to a portable computing device such as a smartphone or tablet.

[1138] "A means for visibly displaying information on a mobile device that reflects a reliability assessment for a specific area" refers to a function that provides disaster information based on the assessed reliability of the information in an easy-to-understand format on the user's mobile device.

[1139] The present invention relates to a system for supporting rapid and accurate information gathering and rescue planning in the event of a disaster. This system is composed of a server, terminals, and users.

[1140] Information collection

[1141] When a disaster occurs, the server automatically searches social media and other information sources on the network for information containing pre-defined keywords (e.g., "earthquake," "tsunami," "fire," etc.). The server includes a function to set relevant keywords as input fields. Specifically, it obtains relevant information in real time using the Twitter API and RSS feeds from news sites.

[1142] Information reliability assessment

[1143] To assess the reliability of the collected information, the server uses a pre-trained fact-checking model (e.g., a machine learning algorithm) that rates the collected data and indicates its veracity as a percentage.

[1144] Information Visualization

[1145] The server plots the assessed information on a map and displays it visually, using Google Maps API and OpenStreetMap API to geographically represent the damage situation, allowing users to check the situation in real time through a dashboard.

[1146] Proposal for relief measures

[1147] Based on the damage situation, the server refers to past data and pre-prepared scenarios to propose appropriate rescue measures, presenting the necessary supplies, personnel, transport routes, etc., and creating a rescue operation plan.

[1148] Transport routes and supporting logistics

[1149] The server calculates the optimal route for logistics support based on real-time traffic information. This includes an algorithm that uses data reflecting current traffic conditions to calculate the optimal delivery route for supplies, thereby providing appropriate navigation information to users.

[1150] Visualization of information reliability ratings for specific regions

[1151] To visually display information reflecting the trust ratings for specific areas, the system also provides information to mobile devices, specifically through smartphone and tablet apps, delivering this information to users in real time.

[1152] Hardware and software used

[1153] Hardware: smartphones, tablets, servers

[1154] Software: Python, Tweepy, TextBlob, Folium, Twitter API, Google Maps API, OpenStreetMap API

[1155] Specific examples

[1156] For example, if an earthquake occurs, the server will collect tweets containing the word "earthquake," evaluate their reliability, and display them on a map. Based on this information, the server will suggest safe evacuation routes and arrange for the necessary relief supplies.

[1157] Prompt Sentence Examples

[1158] Development of a smartphone app that collects real-time information during disasters, evaluates its reliability, and visualizes it

[1159] Step 1: Collect tweets about the disaster using the Twitter API

[1160] Step 2: Assess the authenticity of the tweet using TextBlob

[1161] Step 3: Visualize your data on a map using Folium

[1162] Thus, in order to implement the present invention, it is important that each element works in an organic manner, that disaster information is processed quickly and efficiently, and that appropriate relief measures are formulated.

[1163] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1164] Step 1:

[1165] When a disaster occurs, the server automatically collects information from social media and other sources on the network based on pre-set keywords (e.g., "earthquake," "tsunami," "fire," etc.). The input is the pre-set keywords and API authentication information, and the output is the information obtained from social media and news sites. The server uses the Twitter API, etc., to obtain tweets and news containing the relevant keywords. This processing makes it possible to collect disaster-related information in real time.

[1166] Step 2:

[1167] The server assesses the reliability of the collected information. The input is the information collected in step 1, and the output is data showing the reliability of each piece of information as a percentage. The server applies a machine learning algorithm to evaluate the reliability of the information and displays the result as a reliability percentage. This process allows users to judge the credibility of disaster-related information.

[1168] Step 3:

[1169] The server plots the assessed information on a map and displays it visually. The input is the information and geographic information whose reliability was assessed in step 2, and the output is a visually displayed map. The server uses the Google Maps API and OpenStreetMap API to generate a map that visually shows the damage situation. This allows users to intuitively understand the extent of damage in each area.

[1170] Step 4:

[1171] Based on the disaster situation, the server proposes the necessary relief measures and presents the supplies, personnel, and transportation routes required for relief. The input is the disaster situation, past data, and scenario data from Step 3, and the output is the proposed relief measures, required resources, and delivery routes. The server refers to past disaster data and rescue scenarios prepared in advance to propose appropriate support measures.

[1172] Step 5:

[1173] The server calculates the optimal logistics route based on real-time traffic information and creates a transportation plan for relief supplies. The input is real-time traffic data, and the output is the optimal transportation route. The server calculates the optimal supply delivery route based on the latest traffic information and presents that route to the user.

[1174] Step 6:

[1175] The server visually displays information reflecting the reliability assessment for a specific area on a mobile device. The input is the reliability assessment and geographic information generated in Steps 2 and 3, and the output is damage information displayed on the mobile device. The server provides information to users in real time via a smartphone or tablet app.

[1176] Through these steps, the present invention enables rapid and accurate information collection and assessment, visual understanding of the damage situation, and real-time information provision via mobile devices.

[1177] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1178] This invention combines a system that supports rapid and accurate information gathering and rescue planning in the event of a disaster with an emotion engine that recognizes the user's emotions. This system is composed of a server, terminals, and users.

[1179] Information collection

[1180] When a disaster occurs, the server automatically searches social media and other information sources on the network based on pre-defined keywords (e.g., "earthquake," "tsunami," "fire," etc.) To do this, the server accesses the Twitter API and RSS feeds of news sites to collect relevant posts and articles.

[1181] Information reliability assessment

[1182] The server applies a fact-checking model to the collected information, which is pre-trained using a machine learning algorithm (e.g., a text classification model using RoBERTa), and uses this model to assess the trustworthiness of each post, calculating a confidence score as a percentage.

[1183] Information Visualization

[1184] The server plots the assessed information on a map and displays it visually, using Google Maps API and OpenStreetMap API to geographically represent the damage situation, allowing users to check the situation in real time through a dashboard.

[1185] Proposal for relief measures

[1186] Based on the damage situation, the server refers to past data and pre-prepared scenarios to propose appropriate rescue measures. It presents the necessary supplies, personnel, and transportation routes, and creates a rescue operation plan.

[1187] Transport routes and supporting logistics

[1188] The server calculates optimal logistics routes based on real-time traffic information and creates a delivery plan for relief supplies, which includes an algorithm that uses data reflecting the latest road conditions to calculate the optimal delivery route for supplies.

[1189] Adding an Emotion Engine

[1190] emotion recognition

[1191] The server incorporates an emotion engine that analyzes user posts, comments, and voice data to recognize emotions. The emotion engine evaluates user emotions using techniques such as text analysis, voice analysis, and facial expression analysis.

[1192] As a specific example, if a user posts a comment saying "I'm very scared," the emotion engine will analyze the comment and determine that the user is feeling strong anxiety or fear.

[1193] Emotion-based responses

[1194] The server then presents appropriate support messages and countermeasures based on the user's recognized emotions. For example, if the emotion engine determines that the user is in a panic, the server will display a support message such as "Please stay calm and evacuate to a safe place."

[1195] Furthermore, the system can suggest high-priority rescue measures based on user emotional data. For example, if a region where many users are expressing strong anxiety is determined to require immediate psychological support, the system will prioritize dispatching medical staff to that region.

[1196] Overall system flow

[1197] This system enables rapid and efficient information gathering, reliability assessment, visualization of the damage situation, rescue plan proposals, logistics route optimization, and user emotion recognition and support based on that information when a disaster occurs, thereby preventing damage from spreading and enabling a rapid response.

[1198] As a concrete example, when an earthquake occurs, the server collects information using keywords such as "earthquake" and "damage," assesses its reliability, and plots it on a map. At the same time, the emotion engine analyzes user posts, and presents appropriate messages to users who are feeling anxious or scared, providing psychological support. In this way, the entire system can provide support from both the information and emotional perspectives.

[1199] The processing flow will be explained below.

[1200] Step 1:

[1201] When the server detects that a disaster has occurred, it automatically searches social media and other information sources on the network based on pre-defined keywords (e.g., "earthquake," "tsunami," "fire," etc.) by accessing the Twitter API and RSS feeds of news sites to collect relevant posts and articles.

[1202] Step 2:

[1203] The server stores the collected information in a database, which includes the text content of the posts, the date and time of posting, and information about the poster.

[1204] Step 3:

[1205] The server applies a fact-checking model to the collected information, using a pre-trained machine learning algorithm (e.g., a text classification model using RoBERTa) to assess the trustworthiness of each post and calculate a confidence score as a percentage.

[1206] Step 4:

[1207] The server stores the assessed reliability of the information in a database and selects information that meets the reliability criteria. Based on this reliable information, the damage situation can be grasped.

[1208] Step 5:

[1209] The server plots reliable information on a map based on geographic location information (e.g., place names and GPS data included in posts), using the Google Maps API and OpenStreetMap API.

[1210] Step 6:

[1211] The server visually displays the damage situation plotted on a map, allowing users to check the extent and impact of the damage in real time through a dashboard.

[1212] Step 7:

[1213] The server references past data and pre-prepared scenarios to plan relief measures based on the disaster situation, such as listing the supplies, personnel, and transportation routes needed for the most affected areas.

[1214] Step 8:

[1215] The server displays details of the rescue plan on a dashboard, allowing the user to review this information and proceed with the actual rescue operation.

[1216] Step 9:

[1217] The server accesses a traffic information API (e.g., Google Maps Traffic API) to obtain real-time traffic information and collects the latest road conditions, including road closures, congestion information, and detour routes.

[1218] Step 10:

[1219] The server integrates traffic and disaster information to calculate optimal logistics routes and create transportation plans for supplies. For example, if a major road is destroyed, it automatically calculates a detour route and displays the results on the dashboard.

[1220] Step 11:

[1221] The device displays optimal transportation routes and support logistics routes to users in real time, allowing them to safely and efficiently transport relief supplies to their destinations based on this information.

[1222] Step 12:

[1223] The server uses an emotion engine to analyze user posts, comments, and voice data. The emotion engine uses technologies such as text analysis, voice analysis, and facial expression analysis to evaluate the user's emotions.

[1224] Step 13:

[1225] The server then creates appropriate support messages and countermeasures based on the user's emotions recognized by the emotion engine. For example, if many users show strong anxiety, the server determines that psychological support is necessary and displays messages such as "Please stay calm and evacuate to a safe place."

[1226] Step 14:

[1227] The server then uses the emotion data to suggest high-priority rescue measures, such as creating a plan to immediately dispatch medical staff to areas where many users are panicking.

[1228] Step 15:

[1229] The server continuously collects new information, assesses its reliability, plots it on a map, and updates rescue plans, allowing for rapid response to changing situations.

[1230] In this way, this system supports disaster response from both an information and emotional perspective, aiming to minimize damage and achieve rapid recovery.

[1231] Example 2

[1232] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1233] When a disaster occurs, rapid and accurate information gathering, reliability assessment, visualization of the damage situation, relief plan proposals, optimization of relief logistics, and recognition and response of user emotions are required. However, conventional systems cannot comprehensively meet these requirements, and in particular, lack support including emotion recognition, resulting in insufficient psychological care for users. This leads to a decline in the quality of disaster response, and there is a risk of the damage increasing and relief efforts being delayed.

[1234] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1235] In this invention, the server includes: means for automatically collecting information based on preset keywords from social media and other information sources on a network; means for assessing the reliability of the collected information using a machine learning algorithm and displaying the reliability as a percentage; means for plotting the assessed information on a map to visually display the damage situation; means for referring to past data based on the damage situation, proposing necessary relief measures, and presenting necessary supplies, personnel, and transportation routes; means for calculating optimal logistics routes based on real-time traffic information and formulating a transportation plan for relief supplies; and means for analyzing user posts and comments and utilizing an emotion engine that recognizes emotions to present appropriate countermeasures based on user emotion data. This enables rapid and accurate information collection, reliable information evaluation, visual confirmation of the damage situation, proposing effective relief measures, calculating optimal logistics routes, and providing rapid support based on user emotions.

[1236] A "network" is an electronic communication means for sending and receiving information.

[1237] "Social media" is a general term for online platforms that allow users to create and share content.

[1238] "Source" refers to the medium or location that provides data or information.

[1239] "Keywords" are key words or phrases used to search for specific information.

[1240] A "machine learning algorithm" is a computational method that allows a computer to automatically learn and identify patterns based on empirical data.

[1241] "Reliability" is a numerical evaluation of the accuracy and credibility of information.

[1242] A "map" is a flat representation for visually displaying geographic information.

[1243] "Plotting" refers to placing information in a specific location and visually representing it.

[1244] "Historical data" refers to records or information previously collected.

[1245] "Relief measures" refer to specific measures and actions taken to mitigate damage and provide assistance in disasters and emergencies.

[1246] "Supplies" refers to materials and equipment necessary for relief activities.

[1247] "Human resources" refers to individuals or personnel with specific skills or knowledge.

[1248] A "transport route" refers to a route for transporting materials or personnel to a specific location.

[1249] "Real-time traffic information" refers to the latest data on current road conditions and traffic flow.

[1250] A "logistics route" refers to the route for optimal delivery of goods.

[1251] A "transportation plan" refers to detailed procedures and schedules for efficiently transporting supplies.

[1252] "User" refers to any individual or organization that uses this system.

[1253] "Post" means a message or comment posted by a user on social media or online platforms.

[1254] A "comment" refers to a post in which a user expresses their opinion or impression on a particular topic.

[1255] "Emotion engine" refers to technology that analyzes a user's text and voice data to identify their emotional state.

[1256] "Emotional data" refers to information about a user's emotional state.

[1257] "Responses" refer to specific actions or support measures that should be taken in response to a particular situation.

[1258] This invention relates to a system that supports rapid and accurate information gathering and rescue planning in the event of a disaster, and combines it with an emotion engine that recognizes the user's emotions. The system is composed of a server, terminals, and users, each of which plays a specific role.

[1259] Specifically, when a disaster occurs, the server automatically collects information from social media and other sources on the network based on pre-defined keywords (e.g., "earthquake," "tsunami," "fire," etc.) using well-known interfaces such as the Twitter API and RSS feeds from news sites.

[1260] The collected information is evaluated for reliability using a machine learning algorithm (e.g., RoBERTa model), and the reliability of each piece of information is calculated as a percentage. This reliability evaluation uses a pre-trained model, enabling highly accurate information judgment.

[1261] The information with a reliability assessment is then plotted on a map using the Google Maps API and OpenStreetMap API, allowing the server to visually represent the damage situation and users to view the situation in real time on a dashboard on their devices.

[1262] Based on the disaster situation, the server refers to past data and pre-prepared scenarios to propose optimal rescue measures. Specific rescue measures include presenting the necessary supplies, personnel, and transportation routes, thereby realizing efficient rescue operations.

[1263] Based on real-time traffic information, the server calculates the optimal logistics route and creates a transportation plan for relief supplies. This traffic information uses data that reflects the latest road conditions. By incorporating an algorithm to calculate the optimal delivery route for supplies, rapid transportation of supplies is possible.

[1264] Furthermore, the system is equipped with an emotion engine that analyzes user posts, comments, and voice data to recognize emotions. This is done using technologies such as text analysis, voice analysis, and facial expression analysis. For example, if a user posts a comment saying "I'm very scared," the emotion engine will analyze the comment and determine that the user is feeling strong anxiety or fear.

[1265] The server presents appropriate support messages and countermeasures based on the user's recognized emotions. For example, if the emotion engine determines that the user is in a state of panic, it will display a support message such as "Please stay calm and evacuate to a safe place." It also suggests high-priority rescue measures based on the user's emotional data. For example, it may determine that an area where many users are expressing strong anxiety requires immediate psychological support, and prioritize the dispatch of medical staff to that area.

[1266] As a concrete example, when an earthquake occurs, the server collects information using the keywords "earthquake" and "damage," assesses its reliability using a machine learning model, and plots it on a map. At the same time, the emotion engine analyzes user posts, and provides psychological support by displaying appropriate messages to users who are feeling anxious or scared. This entire system can provide support from both an informational and emotional perspective.

[1267] Example prompt for a generative AI model:

[1268] An earthquake has occurred and damage information is being collected. Collect the latest tweets and news articles related to the disaster, evaluate the reliability of the information, recognize emotions from user comments, and suggest countermeasures.

[1269] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1270] Step 1:

[1271] The server collects information from social media and news sites on the network based on pre-set keywords (e.g., "earthquake," "tsunami," "fire," etc.).

[1272] Input: Keywords such as "earthquake," "tsunami," and "fire"

[1273] Output: A list of tweets and news articles containing the keyword

[1274] Operation:

[1275] 1. The server uses the Twitter API to collect tweets containing the keyword.

[1276] 2. The server parses the news site's RSS feed and retrieves the latest articles.

[1277] Step 2:

[1278] The server evaluates the reliability of the collected information using machine learning algorithms.

[1279] Input: Collected tweets and news articles

[1280] Output: Confidence score (percentage) for each piece of information

[1281] Operation:

[1282] 1. The server inputs each collected text data into a machine learning model (e.g., RoBERTa model) and calculates a confidence score.

[1283] 2. The server stores the confidence score in a database.

[1284] Step 3:

[1285] The server plots the information whose reliability has been assessed on a map and displays it.

[1286] Input: Information (tweets or news articles) with assessed credibility and their location

[1287] Output: Damage information plotted on a map

[1288] Operation:

[1289] 1. The server uses the Google Maps API or OpenStreetMap API to plot the location data of the disaster information on a map.

[1290] 2. Users can access the dashboard through their devices and check the status in real time.

[1291] Step 4:

[1292] The server proposes appropriate relief measures based on the disaster situation.

[1293] Input: Disaster information and past rescue data

[1294] Output: Proposed relief plan (necessary supplies, personnel, transport routes)

[1295] Operation:

[1296] 1. The server compares past disaster data with current damage information.

[1297] 2. The server plans the required supplies, personnel, and transportation routes and displays them on the dashboard.

[1298] Step 5:

[1299] The server calculates the optimal logistics route based on real-time traffic information.

[1300] Input: Latest road conditions and traffic data

[1301] Output: Optimal logistics routes and transportation plans for relief supplies

[1302] Operation:

[1303] 1. The server uses a traffic data API (e.g., Google Maps Traffic API) to obtain real-time traffic information.

[1304] 2. The server applies an algorithm to calculate the optimal delivery route and displays the results on a dashboard.

[1305] Step 6:

[1306] The server analyzes users' posts and comments to recognize their emotions.

[1307] Input: User posts and comments (text data)

[1308] Output: User's emotion evaluation result

[1309] Operation:

[1310] 1. When a user posts a comment from their device, the server inputs the text data into the emotion engine.

[1311] 2. The sentiment engine performs text analysis and evaluates the user's sentiment.

[1312] Step 7:

[1313] The server presents appropriate support messages and countermeasures based on the recognized emotions.

[1314] Input: User's emotion evaluation result

[1315] Output: Support message and / or action plan

[1316] Operation:

[1317] 1. After the emotion engine evaluates the user's emotion, the server generates an appropriate message based on the result.

[1318] 2. The server displays support messages such as "Please stay calm and evacuate to a safe place" on the dashboard.

[1319] 3. The server proposes high-priority rescue measures based on the user's emotional data.

[1320] (Application example 2)

[1321] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1322] In modern society, when a disaster occurs, there is a need to quickly and accurately collect information and plan appropriate relief measures. However, many challenges exist, such as confusion during a disaster, a decrease in the reliability of information, and the mental instability of victims. It is also important to provide optimal escape routes and routes for transporting supplies based on traffic conditions and the situation in the affected area, but current systems are unable to adequately address these issues.

[1323] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for automatically collecting information based on preset keywords from social media and other information sources on the network when a disaster occurs; means for assessing the reliability of the collected information and displaying the reliability as a percentage; means for plotting the assessed information on a map to visually display the damage situation; means for proposing necessary relief measures based on the damage situation and presenting the supplies, personnel, and transportation routes required for relief; means for calculating optimal logistics routes based on real-time traffic information and formulating a transportation plan for relief supplies; and means for recognizing the emotions of occupants using a camera and microphone and providing appropriate support messages and responses based on the emotion data. This enables rapid and accurate information collection and reliability assessment, relief measure proposals, calculation of optimal logistics routes, and mental care for occupants.

[1324] "Networked social media" is a general term for platforms used via the Internet for sharing and exchanging information.

[1325] "Source" refers to the medium or device from which information is disseminated.

[1326] "Keywords" are important words or phrases used when searching for specific information.

[1327] "Means for automatically collecting information" refers to a mechanism for automatically acquiring information based on set conditions.

[1328] A "means for assessing trustworthiness" is a method or system for evaluating the veracity or accuracy of collected information.

[1329] A "means of showing reliability as a percentage" is a method of quantifying the reliability of information and displaying it in the form of a percentage.

[1330] "Means of plotting on a map and visually displaying the damage situation" refers to a method of illustrating the situation in the disaster area on a map using a geographic information system.

[1331] "Means for proposing relief measures and presenting the supplies, personnel, and transportation routes required for relief" is a system that plans and proposes appropriate support actions, necessary resources, and routes for transporting them.

[1332] "Means for calculating optimal logistics routes based on real-time traffic information" is a system that calculates the most suitable route for transporting goods efficiently based on the latest traffic data.

[1333] "Means for formulating a transportation plan for relief supplies" refers to a method for creating a specific plan for delivering necessary supplies to the appropriate locations.

[1334] "Means of recognizing emotions using a camera or microphone" refers to technology that analyzes image and audio data to identify a person's emotional state.

[1335] "Means for providing appropriate support messages and responses based on emotional data" is a system that presents necessary messages and actions based on the results of user emotional analysis.

[1336]

[1337] This invention is a system that supports the rapid and accurate collection of information and the planning of relief measures when a disaster occurs, and also integrates an emotion engine for recognizing the user's emotions. This system is composed of a server, terminals, and users.

[1338] Server Features

[1339] When a disaster occurs, the server automatically collects information from social media and other sources on the network based on pre-defined keywords (e.g., "earthquake," "tsunami," "fire," etc.) using the Twitter API and RSS feeds from news sites.

[1340] The collected information is fact-checked on the server, and its reliability is assessed using machine learning algorithms such as RoBERTa, with the reliability being expressed as a percentage.

[1341] The server plots the assessed information on a map using Google Maps API or OpenStreetMap API, visually displaying the damage situation, allowing users to check the situation in real time through a dashboard.

[1342] Based on the damage situation, the server refers to past data and pre-prepared scenarios to propose appropriate relief measures. It presents the necessary supplies, personnel, and transportation routes. It also calculates optimal logistics routes based on real-time traffic information and creates transportation plans for relief supplies.

[1343] Emotion Engine

[1344] The emotion engine is built into the server and recognizes emotions by analyzing user posts, comments, and voice data. Emotion recognition uses technologies such as text analysis, voice analysis, and facial expression analysis. For example, if a user posts a comment saying "I'm very scared," the emotion engine analyzes the comment and determines that the user is feeling strong anxiety or fear.

[1345] The server presents appropriate support messages and countermeasures based on the user's recognized emotions. For example, if the emotion engine determines that the user is in a state of panic, it displays a support message such as "Please stay calm and evacuate to a safe place." It also suggests high-priority rescue measures based on the user's emotional data. If a large number of users are expressing strong anxiety in an area, it will determine that psychological support is necessary and prioritize the dispatch of medical staff to that area.

[1346] Specific examples

[1347] For example, when an earthquake occurs, the server collects information using keywords such as "earthquake" and "damage," assesses the reliability of the information, and plots it on a map. At the same time, the server analyzes user posts using an emotion engine, and displays appropriate messages to users who are feeling anxious or scared, providing psychological support.

[1348] An example of a prompt is as follows:

[1349] Input prompt: "Very scary"

[1350] Evaluation result: Emotional polarity -0.9

[1351] Response message: "Please remain calm and seek safety."

[1352] This allows the entire system to provide support in both informational and emotional terms.

[1353] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1354] Step 1:

[1355] When a disaster occurs, the server automatically collects information from social media and other sources on the network based on pre-defined keywords (e.g., "earthquake," "tsunami," "fire," etc.). In this step, it uses the Twitter API and RSS feeds from news sites to retrieve related posts and news articles. The input is a list of keywords, and the output is a list of collected information.

[1356] Step 2:

[1357] The server uses machine learning algorithms such as RoBERTa to fact-check the collected information and evaluate its reliability. This process takes the collected information as input and outputs the reliability of each piece of information as a percentage. A text classification model is used to calculate the reliability.

[1358] Step 3:

[1359] The server plots the assessed information on a map using the Google Maps API or OpenStreetMap API, visually displaying the damage situation. The input is a list of information whose reliability has been assessed, and the output is the damage situation plotted on a map. This process allows users to check the situation in real time through a dashboard.

[1360] Step 4:

[1361] The server refers to past data and pre-prepared scenarios to propose necessary relief measures based on the disaster situation. In this step, the required supplies, personnel, and transportation routes are presented. The input is the disaster situation plotted on a map, and the output is the proposed relief measures.

[1362] Step 5:

[1363] The server calculates the optimal logistics route based on real-time traffic information and creates a delivery plan for relief supplies. In this step, past route data and current traffic condition data are input and the optimal delivery route is output. A real-time traffic data API is used to collect traffic information.

[1364] Step 6:

[1365] The emotion engine recognizes emotions by analyzing user posts, comments, and voice data. The input is the user's text and voice, and the output is the emotional evaluation result. Emotion recognition uses text analysis, voice analysis, and facial expression analysis. For example, if a user posts "very scary," the text is analyzed and the emotion of fear is evaluated.

[1366] Step 7:

[1367] The server presents appropriate support messages and countermeasures based on the recognized user's emotional data. In this step, the server receives the emotion evaluation results as input and outputs support messages and countermeasures based on them. For example, if the server recognizes that the user is in a panic state, it will provide a message such as "Please stay calm and evacuate to a safe place."

[1368] Step 8:

[1369] The vehicle's environment (e.g., temperature and lighting) is adjusted based on the user's emotional state. The input is the output of the emotion engine, and the output is the adjusted vehicle environment settings, allowing the occupants to travel with greater peace of mind.

[1370] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1371] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1372] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1373] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1374] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1375] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1376] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1377] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1378] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1379] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1380] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1381] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1382] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1383] 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.

[1384] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1385] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1386] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1387] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1388] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1389] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1390] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1391] The following is further disclosed regarding the above embodiment.

[1392] (Claim 1)

[1393] In the event of a disaster, a means of automatically collecting information from social media and other sources on the network based on pre-defined keywords;

[1394] A means to assess the reliability of the collected information and indicate the reliability as a percentage;

[1395] A means for plotting the assessed information on a map and visually displaying the damage situation;

[1396] A means to propose necessary relief measures based on the disaster situation and to indicate the supplies, personnel, and transportation routes required for relief;

[1397] A means of calculating optimal logistics routes based on real-time traffic information and formulating transportation plans for relief supplies;

[1398] A system including:

[1399] (Claim 2)

[1400] 10. The system of claim 1, further comprising means for cross-referencing the collected information with other reliable sources to verify its authenticity.

[1401] (Claim 3)

[1402] 2. The system according to claim 1, further comprising means for providing the user with access routes and conditions of disaster areas in real time.

[1403] "Example 1"

[1404] (Claim 1)

[1405] A means for automatically collecting information based on pre-defined search terms from digital communication media and other data sources on a network in the event of a disaster;

[1406] A means of assessing the reliability of collected information and expressing the reliability numerically;

[1407] A means for plotting the assessed information on a map and visually displaying the damage situation;

[1408] A means to propose necessary relief measures based on the disaster situation and to present the resources, personnel, and transportation routes required for relief;

[1409] A means for calculating an optimal transportation route based on real-time traffic information and formulating a transportation plan for support resources;

[1410] A means of evaluating the collected data using a pre-trained generative AI model to improve the reliability of the information; and

[1411] a means for displaying the reliability evaluation result of the assessed data on a user dashboard to notify the user;

[1412] A system including:

[1413] (Claim 2)

[1414] 10. The system of claim 1, further comprising means for cross-referencing the collected information with other reliable sources to verify its authenticity.

[1415] (Claim 3)

[1416] 2. The system according to claim 1, further comprising means for providing the user with access routes and conditions of disaster areas in real time.

[1417] "Application Example 1"

[1418] (Claim 1)

[1419] In the event of a disaster, a means of automatically collecting information from social media and other sources on the network based on pre-defined keywords;

[1420] A means to assess the reliability of the collected information and indicate the reliability as a percentage;

[1421] A means for plotting the assessed information on a map and visually displaying the damage situation;

[1422] A means to propose necessary relief measures based on the disaster situation and to indicate the supplies, personnel, and transportation routes required for relief;

[1423] A means of calculating optimal logistics routes based on real-time traffic information and formulating transportation plans for relief supplies;

[1424] means for visually displaying on a mobile device information reflecting the trust rating for a particular region;

[1425] A system including:

[1426] (Claim 2)

[1427] 10. The system of claim 1, further comprising means for cross-referencing the collected information with other reliable sources to verify its authenticity.

[1428] (Claim 3)

[1429] 10. The system of claim 1, further comprising means for providing an interface to a mobile device for viewing real-time disaster information and reliability assessments on a map.

[1430] "Example 2: Combining Emotion Engines"

[1431] (Claim 1)

[1432] A means of automatically collecting information from social media and other sources on the network based on pre-defined keywords;

[1433] A means to assess the reliability of collected information using machine learning algorithms and indicate the reliability as a percentage;

[1434] A means for plotting the assessed information on a map and visually displaying the damage situation;

[1435] A means to refer to past data based on the disaster situation, propose necessary relief measures, and indicate the necessary supplies, personnel, and transportation routes.

[1436] A means of calculating optimal logistics routes based on real-time traffic information and formulating transportation plans for relief supplies;

[1437] A means of analyzing user posts and comments, utilizing an emotion engine that recognizes emotions, and presenting appropriate countermeasures based on the user's emotional data;

[1438] A system including:

[1439] (Claim 2)

[1440] 10. The system of claim 1, further comprising means for cross-referencing the collected information with other reliable sources to verify its authenticity.

[1441] (Claim 3)

[1442] 2. The system according to claim 1, further comprising means for providing the user with access routes and conditions of disaster areas in real time.

[1443] "Application example 2 when combining emotion engines"

[1444] (Claim 1)

[1445] In the event of a disaster, a means of automatically collecting information from social media and other sources on the network based on pre-defined keywords;

[1446] A means to assess the reliability of the collected information and indicate the reliability as a percentage;

[1447] A means for plotting the assessed information on a map and visually displaying the damage situation;

[1448] A means to propose necessary relief measures based on the disaster situation and to indicate the supplies, personnel, and transportation routes required for relief;

[1449] A means of calculating optimal logistics routes based on real-time traffic information and formulating transportation plans for relief supplies;

[1450] A means for recognizing the emotions of occupants using a camera or microphone and providing appropriate support messages and responses based on the emotion data;

[1451] A system including:

[1452] (Claim 2)

[1453] 10. The system of claim 1, further comprising means for cross-referencing the collected information with other reliable sources to verify its authenticity.

[1454] (Claim 3)

[1455] 10. The system of claim 1, further comprising means for providing a user with access routes and conditions in a disaster area in real time, and means for adjusting the vehicle (e.g., adjusting the temperature) based on the emotional state of the occupants. [Explanation of symbols]

[1456] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. In the event of a disaster, a means of automatically collecting information from social media and other sources on the network based on pre-defined keywords; A means to assess the reliability of the collected information and indicate the reliability as a percentage; A means for plotting the assessed information on a map and visually displaying the damage situation; A means to propose necessary relief measures based on the disaster situation and to indicate the supplies, personnel, and transportation routes required for relief; A means of calculating optimal logistics routes based on real-time traffic information and formulating transportation plans for relief supplies; A system including:

2. 10. The system of claim 1, further comprising means for cross-referencing the collected information with other reliable sources to verify its authenticity.

3. The system according to claim 1, further comprising means for providing a user with access routes and conditions of disaster areas in real time.

Images