system

Abstract

A system is provided.SOLUTION: A system including a means for collecting and aggregating disaster information in real time from an SNS or a news site, a means for generating an optimal delivery route based on the aggregated information, a means for predicting necessary supplies and the amount thereof from the scale and damage situation of an earthquake, a means for delivering supplies using a drone, and a means for integrally managing all the above means.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] In the event of a disaster, optimization of logistics and rapid support are required. However, responding efficiently and effectively is not easy because multiple factors, such as the collection and consolidation of disaster information, supply delivery, and forecasting of needed supplies, are interrelated. In addition, impassable roads and infrastructure damage often make it difficult to supply supplies using conventional logistics systems. Rather than simply solving these issues individually, a system that manages them in an integrated manner is required. [Means for solving the problem]

[0005] The present invention provides a system including the following means to optimize logistics and provide rapid support in the event of a disaster.

[0006] 1. A means of collecting and aggregating disaster information in real time from social media and news sites

[0007] 2. A method for generating optimal delivery routes based on aggregated information

[0008] 3. A method for predicting the supplies and quantities needed based on the scale of the earthquake and the extent of the damage

[0009] 4. Drone delivery of supplies

[0010] 5. A means to integrate and manage all of the above measures

[0011] This makes it possible to analyze road conditions and traffic information in real time to generate optimal delivery routes, and to use natural language processing technology to analyze collected disaster information and extract important information, enabling relief supplies to be delivered to disaster-stricken areas quickly and efficiently.

[0012] A "disaster information aggregation method" is a method of collecting disaster-related information in real time from social media and news sites and consolidating it in a centralized manner.

[0013] The "delivery route generation means" is a means for calculating and generating the optimal delivery route for supplies to disaster-stricken areas based on the collected disaster information.

[0014] A "materials demand forecasting method" is a method for predicting the types and quantities of materials needed in disaster-stricken areas based on the scale of the earthquake and the extent of the damage.

[0015] "Supply delivery means" refers to the use of drones to deliver supplies to disaster-stricken areas.

[0016] The "system integration management means" is a means for integrating and centrally managing the disaster information collection means, delivery route generation means, material demand forecasting means, and material delivery means.

[0017] "SNS" is an abbreviation for social networking service, which refers to an online platform where users can share and exchange information.

[0018] A "news site" is an information website operated on the Internet by a newspaper company or news organization.

[0019] "Natural language processing" refers to the technology that enables computers to understand and analyze human language.

[0020] "Traffic information" refers to information on road congestion, traffic accidents, construction work, etc., and is used to select the optimal route.

[0021] A "drone" refers to an unmanned aerial vehicle that flies by remote control or automatic operation and transports goods, etc. [Brief explanation of the drawings]

[0022] [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

[0023] 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.

[0024] First, the terms used in the following description will be explained.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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."

[0030] [First embodiment]

[0031] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0032] 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.

[0033] 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).

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0039] 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.

[0040] 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.

[0041] 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.

[0042] 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."

[0043] The present invention provides a system that includes the following four main functions to optimize logistics and provide fast and efficient support during disasters: disaster information collection means, delivery route generation means, supply demand forecasting means, and supply delivery means.

[0044] Disaster information collection method

[0045] overview

[0046] The server collects disaster-related information from social media and news sites in real time and compiles it in a centralized manner. This information serves as a foundation for quickly understanding the situation in the affected areas.

[0047] Natural language explanations

[0048] 1. The server obtains the latest disaster information through the APIs of various social media and news sites at specified intervals.

[0049] 2. The acquired information is analyzed using a natural language processing engine to extract important keywords and phrases.

[0050] 3. Based on the extracted keywords, disaster information is classified by region and stored in a database.

[0051] Specific examples

[0052] When a request to "check the disaster situation in Tokyo" is made from a terminal, the server provides the user with the latest disaster information related to Tokyo from the database.

[0053] Delivery route generation method

[0054] overview

[0055] The server calculates and generates optimal delivery routes to affected areas based on the collected disaster information, enabling fast and efficient delivery of supplies.

[0056] Natural language explanation

[0057] 1. The server collects and analyzes real-time road conditions and traffic information.

[0058] 2. Based on the analyzed data, an algorithm is run to generate the optimal delivery route.

[0059] 3. Once the optimal route is generated, the user is notified via the terminal.

[0060] Specific examples

[0061] When a user sends a request from their terminal to "deliver goods from point A to point B," the server calculates the optimal delivery route and provides it to the user.

[0062] Material demand forecasting method

[0063] overview

[0064] The server predicts the types and quantities of supplies needed in the affected areas based on the scale of the earthquake and the extent of the damage, making it possible to prepare appropriate supplies in advance.

[0065] Natural language explanation

[0066] 1. The server collects data indicating the scale of the earthquake and the extent of the damage.

[0067] 2. Input the collected data into a machine learning model to predict the types and quantities of supplies needed.

[0068] 3. The prediction results are stored in a database and can be viewed by the user at any time.

[0069] Specific examples

[0070] When a user sends a request from their terminal to "check the supplies needed after an earthquake occurs," the server retrieves a list of predicted supplies and provides it to the user.

[0071] Delivery method (drone delivery)

[0072] overview

[0073] The server provides a means to deliver supplies to disaster areas using drones, making it possible to deliver supplies to areas where roads are impassable.

[0074] Natural language explanation

[0075] 1. The server obtains the location where supplies need to be delivered and the initial position of the drone.

[0076] 2. Calculate the optimal delivery route for the drone and send instructions to the drone management system.

[0077] 3. The drone delivers the goods to the destination and notifies the server that delivery is complete.

[0078] Specific examples

[0079] When a user inputs "Deliver supplies to an area where roads are impassable" into their device, the server calculates the optimal route for the drone and sends it into operation. Once the delivery is complete, the user is notified.

[0080] By integrating these functions, a system will be created to optimize logistics and provide rapid support during disasters.

[0081] The processing flow will be explained below.

[0082] Disaster information collection method

[0083] Processing flow

[0084] Step 1:

[0085] The server sends requests to the APIs of various social networking sites and news sites at specified time intervals to obtain the latest disaster information data.

[0086] Step 2:

[0087] The server temporarily stores the acquired disaster information data in a database.

[0088] Step 3:

[0089] The server inputs the stored data into a natural language processing engine to extract important keywords and phrases.

[0090] Step 4:

[0091] The server categorizes disaster information by region based on the extracted keywords and stores the categorized information in the main database.

[0092] Step 5:

[0093] The user sends a request from the terminal, such as "I would like to check the disaster situation in Tokyo."

[0094] Step 6:

[0095] In response to a request, the server searches the main database for disaster information for the relevant area and provides it to the user.

[0096] Delivery route generation method

[0097] Processing flow

[0098] Step 1:

[0099] The server collects road conditions and traffic information in real time, using image analysis from traffic cameras and data from traffic information APIs.

[0100] Step 2:

[0101] The server analyzes the collected road condition data and filters out information on road disruptions and congestion.

[0102] Step 3:

[0103] The server runs a delivery route generation algorithm to calculate the optimal route, using Dijkstra's algorithm or A algorithm.

[0104] Step 4:

[0105] The user inputs the starting point and destination of the goods from the terminal.

[0106] Step 5:

[0107] The server recalculates the optimal route based on the input information and provides the generated route information to the user.

[0108] Step 6:

[0109] The terminal displays the calculated optimum route on a user interface.

[0110] Material demand forecasting method

[0111] Processing flow

[0112] Step 1:

[0113] The server collects data on the scale and damage caused by earthquakes, specifically from earthquake information APIs and news sites.

[0114] Step 2:

[0115] The server inputs the collected data into a machine learning model to predict demand for goods, using algorithms such as regression analysis and random forests.

[0116] Step 3:

[0117] The server stores the results of the predicted material demand in a database.

[0118] Step 4:

[0119] The user sends a request to the server from the terminal to "check supplies needed after an earthquake occurs."

[0120] Step 5:

[0121] The server retrieves the prediction results from the database and provides them to the user.

[0122] Delivery method (drone delivery)

[0123] Processing flow

[0124] Step 1:

[0125] The server obtains the location where supplies need to be delivered and the drone's initial location information.

[0126] Step 2:

[0127] The server calculates the optimal delivery route for the drone, using algorithms such as the Bellman-Ford algorithm.

[0128] Step 3:

[0129] The server sends the calculated route information to the drone management system.

[0130] Step 4:

[0131] The drone follows the instructed route and delivers the goods to their destination.

[0132] Step 5:

[0133] The drone reaches its destination and delivers the goods.

[0134] Step 6:

[0135] The drone notifies the server that delivery is complete.

[0136] Step 7:

[0137] The server records the delivery completion information in a database and notifies the user.

[0138] Example 1

[0139] 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."

[0140] When disasters such as earthquakes and fires occur, the challenge is to quickly and accurately collect information and deliver appropriate relief supplies to affected areas. Effective logistics is particularly difficult when roads are impassable or information is in disarray. Existing systems are prone to delays and false reports at each stage of information collection, analysis, and supply delivery, making it difficult to provide efficient relief.

[0141] 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.

[0142] In this invention, the server includes a means for collecting disaster information in real time from information sources such as social media and news sites, a means for analyzing the collected disaster information using natural language processing technology and extracting important information, and a means for generating optimal delivery routes based on the extracted information, thereby enabling a fast and efficient disaster response and optimization of logistics.

[0143] "SNS" stands for Social Networking Service, a platform for users to share information and interact online.

[0144] A "news site" is a website that provides news coverage of current events and happenings on the Internet.

[0145] "Disaster information" refers to information about natural disasters such as earthquakes, typhoons, and fires, as well as man-made disasters.

[0146] "Real-time" refers to data acquisition and processing occurring almost simultaneously with real time.

[0147] "Natural language processing technology" is a technology for analyzing and processing human language using a computer, and is used to understand the meaning and intent of text.

[0148] The "optimal delivery route" refers to the most efficient and safe route for delivering goods, taking into account time, distance, and cost.

[0149] The "magnitude of an earthquake" is an indicator of the amount of energy released and the extent of its impact when an earthquake occurs.

[0150] "Damage situation" is information that indicates the extent of human and material damage when a disaster occurs.

[0151] An "unmanned aerial vehicle" is a flying machine that flies remotely or autonomously and is used for transporting goods, etc.

[0152] A "database" is a computer system for efficiently storing, searching, and managing large amounts of data.

[0153] "Traffic information" refers to information that indicates the status of transportation routes such as roads and railways, and includes information on traffic congestion and road closures.

[0154] The present invention is a system for optimizing logistics in the event of a disaster and providing prompt and efficient support. This system operates in cooperation with three parties: a server, a terminal, and a user.

[0155] Server Roles

[0156] Information collection and analysis

[0157] The server collects disaster information in real time from sources such as social media and news sites. This information is collected using, for example, the Twitter API and RSS feeds from various news sites. The collected information is analyzed using a natural language processing engine (e.g., spaCy, BERT) to extract important keywords and phrases. This analysis process identifies important information such as "evacuation shelters," "water outages," and "traffic disruptions."

[0158] Data Classification and Retention

[0159] The extracted important information is classified by region and stored in a database (e.g., MongoDB, MySQL®), which allows the server to grasp the situation in real time and provide a basis for taking necessary measures.

[0160] Generate delivery routes

[0161] The server runs an algorithm (e.g., the Dijkstra algorithm) to generate optimal delivery routes based on collected disaster information and real-time road conditions. Specifically, it uses Google® Maps API and HERE Maps API to collect traffic information and calculates the shortest and safest route based on this information.

[0162] Forecasting demand for goods

[0163] The server collects data on the scale of the earthquake and the extent of the damage, and inputs this data into a machine learning model (e.g., TENSORFLOW (registered trademark), Scikit-learn) to predict the types and quantities of supplies needed. For example, if a large earthquake occurs, it is expected that demand for food, water, medicine, etc. will increase.

[0164] Drone delivery of supplies

[0165] The server acquires information on the drone's initial position and the location where delivery is required, and calculates the optimal delivery route. The calculated route is sent to the drone management system, which instructs the unmanned aerial vehicle to deliver the goods to the destination. Once the delivery is complete, the server receives the information and notifies the user.

[0166] Device Role

[0167] The terminal provides an interface for users to access the system, through which they can check disaster information and make delivery requests.

[0168] User Roles

[0169] Users send requests to the server via their terminals, such as "Check the disaster situation in Tokyo," "Deliver supplies from point A to point B," "Check supplies needed after an earthquake occurs," and "Deliver supplies to areas where roads are impassable." The server receives these requests, performs the necessary processing, and provides the results to the user.

[0170] Specific examples

[0171] Example prompt sentence:

[0172] "To optimize logistics during disasters, collect disaster information from social media and news sites, generate optimal delivery routes, and deliver supplies to affected areas."

[0173] These explanations clarify the specific embodiments of the present invention. A system is constructed that centrally manages a series of processes, from collecting and analyzing disaster information, creating optimal delivery routes, predicting demand for supplies, and delivering supplies by drone. This enables a rapid and efficient response in the event of a disaster.

[0174] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0175] Program processing steps and detailed explanation

[0176] Disaster information collection method

[0177] Step 1: Gather information

[0178] The server obtains the latest disaster information through the APIs of social media and news sites at specified intervals.

[0179] Input: Data obtained from APIs of various social media and news sites (e.g., Twitter tweets, news articles)

[0180] Specific operation: The server uses the Twitter API key to collect tweets with keywords such as "earthquake," "evacuation," and "support," and retrieves the latest articles from the news site's RSS feed.

[0181] Output: Raw data (text data)

[0182] Step 2: Natural Language Processing Analysis

[0183] The server inputs the collected text data into a natural language processing technology engine (e.g., spaCy, BERT) to extract important keywords and phrases.

[0184] Input: Raw data acquired

[0185] Specific operation: The server uses a natural language processing engine to analyze the text data and uses tokenization, stemming, and entity recognition to identify important information such as "shelters," "water outages," and "traffic disruptions."

[0186] Output: Extracted important keywords and phrases

[0187] Step 3: Classify and store data

[0188] Based on the extracted keywords, the server classifies disaster information by region and stores it in a database.

[0189] Input: Extracted important keywords and phrases

[0190] Specific operation: The server classifies information based on place names such as "Tokyo" and "Osaka" and stores it in a database such as MongoDB or MySQL.

[0191] Output: Database entries for disaster information categorized by region

[0192] Delivery route generation method

[0193] Step 1: Collect road conditions

[0194] The server collects real-time road conditions and traffic information using the Google Maps API and HERE Maps API.

[0195] Input: Real-time road condition data

[0196] Specific operation: The server collects information such as traffic congestion and road closures through the API and plots it on a map.

[0197] Output: Latest traffic information dataset

[0198] Step 2: Data analysis

[0199] The server analyzes the collected data and runs an algorithm (e.g., Dijkstra algorithm) to generate optimal delivery routes.

[0200] Input: Latest traffic information dataset

[0201] Specific operation: The server calculates the distance and time between each delivery point, evaluates multiple routes, and identifies the shortest and safest route.

[0202] Output: Optimal delivery route information

[0203] Step 3: Notification of results

[0204] Once the optimal route has been generated, the server notifies the user via the terminal.

[0205] Input: Optimal delivery route information

[0206] Specific operation: The server sends the generated route data in JSON format to the terminal and notifies the user.

[0207] Output: Route information provided to the user

[0208] Material demand forecasting method

[0209] Step 1: Data collection

[0210] The server collects data from the USGS and the Japan Meteorological Agency indicating the scale of the earthquake and the extent of the damage.

[0211] Input: Earthquake magnitude and damage data

[0212] Specific operation: The server obtains data such as the earthquake's epicenter, magnitude, and scale of damage through the API.

[0213] Output: Earthquake and damage dataset

[0214] Step 2: Input to the machine learning model

[0215] The server inputs the collected data into a machine learning model (e.g., TensorFlow, Scikit-learn) to predict the type and quantity of supplies needed.

[0216] Input: Earthquake and damage dataset

[0217] How it works: The server uses data from past disasters to use machine learning models to predict demand for food, water, medicine, etc.

[0218] Output: List of predicted supplies

[0219] Step 3: Save the prediction results

[0220] The server stores the prediction results in a database so that users can check them at any time.

[0221] Input: Forecasted supplies list

[0222] Specific operation: The server updates the prediction results in real time and displays them in the database and on the dashboard.

[0223] Output: Stored supply forecast data

[0224] Delivery method (drone delivery)

[0225] Step 1: Obtaining delivery points and drone positions

[0226] The server uses GPS data to obtain the location where supplies need to be delivered and the drone's initial position.

[0227] Input: Delivery point and initial drone position data

[0228] Specific operation: The server collects the latitude and longitude information of the required delivery point, as well as the drone's current location information.

[0229] Output: Geolocation dataset

[0230] Step 2: Route calculation

[0231] The server calculates the optimal delivery route for the drone and sends instructions to the drone management system.

[0232] Input: Geolocation dataset

[0233] How it works: The server uses a 3D mapping algorithm to calculate a route that avoids obstacles and takes into account wind direction and weather conditions.

[0234] Output: Optimal drone delivery route

[0235] Step 3: Delivery notification

[0236] The server notifies the user once the drone has delivered the goods to the destination and received notification that delivery has been completed.

[0237] Input: Delivery completion notification from drone

[0238] Specific operation: The server monitors the delivery status in real time, and after delivery is completed, it records the status and notifies the user via email or app.

[0239] Output: Delivery completion notification to user

[0240] Through the above processing steps, the system of the present invention realizes rapid and efficient disaster response and optimization of logistics.

[0241] (Application example 1)

[0242] 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."

[0243] Logistics during disasters is a key element for providing fast and efficient support to disaster-stricken areas. However, traditional logistics systems often lack real-time information and fragmented information, making it difficult to generate optimal delivery routes and forecast supply demand. Furthermore, when roads were impassable, delivery of supplies could be significantly delayed. Furthermore, logistics center staff and managers lacked the means to monitor the situation in real time and respond quickly. To resolve these situations, a more integrated management system is needed.

[0244] 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.

[0245] In this invention, the server includes a means for collecting and aggregating disaster information from social media and news sites in real time, a means for generating optimal delivery routes based on the aggregated information, a means for predicting the supplies needed and their quantities based on the scale of the earthquake and the extent of the damage, a means for logistics center staff and managers to monitor the situation in real time via smartphone and take swift action, a means for delivering supplies using drones, and a means for integrating and managing all of the above means, thereby enabling optimized logistics and rapid support during disasters.

[0246] "SNS" is an abbreviation for social networking service, an online platform for users to share information and communicate.

[0247] A "news site" is a website that provides news articles over the Internet.

[0248] "Real-time" refers to the immediacy with which data and information are collected, analyzed, and displayed immediately.

[0249] "Disaster information" refers to information that indicates the status and impact of natural disasters such as earthquakes and floods.

[0250] A "logistics center" is a facility where supplies are stored, sorted, and prepared for delivery.

[0251] A "smartphone" is a mobile phone device with advanced computing power and connectivity.

[0252] "Staff" refers to employees working in an organization or facility.

[0253] A "manager" is a position that manages and supervises an organization or team.

[0254] A "delivery route" refers to the optimal route for transporting goods, calculated to minimize time and distance.

[0255] "Earthquake magnitude" is a numerical indicator that shows the amount of energy an earthquake generates.

[0256] "Damage status" is information indicating the damage and state of damage caused by a disaster.

[0257] "Supplies" refers to support items such as food, water, medicine, and cold weather gear that are needed in the event of a disaster.

[0258] "Demand forecasting" is the act of predicting how much material will be needed in the future.

[0259] A "drone" is an unmanned aircraft that can be remotely controlled and fly autonomously.

[0260] "Integrated management" refers to the integration and centralized management of multiple functions and methods.

[0261] The present invention relates to a system for optimizing logistics at a logistics center during a disaster and providing prompt and efficient support. The system has the following main functions:

[0262] 1. Disaster information collection method

[0263] The server collects and aggregates disaster information in real time from social media and news sites. For example, it uses the APIs of social media sites and RSS feeds from news sites. The collected information is analyzed within the server using a natural language processing engine to extract important keywords and phrases. This allows the situation in the affected areas to be quickly grasped.

[0264] 2. Delivery route generation method

[0265] The server generates the optimal delivery route based on the collected disaster information and real-time road and traffic information. For example, it obtains the current traffic situation using a map API and calculates the optimal route using a shortest route algorithm. This information is provided to users so they can check it on their smartphones.

[0266] 3. Material demand forecasting methods

[0267] The server inputs data such as the scale of the earthquake and the extent of the damage into a machine learning model to predict the type and quantity of supplies needed in the affected area. For example, an AI model is used to compare past disaster data with the current disaster situation to predict demand. The predicted supply list is then displayed in real time on a smartphone app for staff and managers to check.

[0268] 4. Delivery of goods (drone delivery)

[0269] The server instructs drones to deliver goods to areas where roads are impassable. For example, it calculates the optimal delivery route based on the specified location and the drone's initial position, and sends instructions to the drone management system. Once the delivery is complete, the information is notified to the server, and then to a smartphone.

[0270] Hardware and software used

[0271] Smartphones: Used by staff and managers.

[0272] Drones: Used to deliver supplies.

[0273] Natural language processing engine: Used to analyze collected disaster information.

[0274] Map API: Get current traffic conditions and use them to calculate the shortest route.

[0275] Machine learning models: Used to forecast demand for supplies.

[0276] Drone management system: Used to manage drone deliveries.

[0277] Specific examples

[0278] For example, when a disaster occurs, the server instantly collects disaster information from social media and news sites, and when a user inputs the prompt "Check the disaster situation in Tokyo," it provides the latest disaster information for that area. Furthermore, when a user inputs "Deliver supplies from point A to point B," the server calculates the optimal delivery route and notifies the smartphone app. When supply delivery is necessary, drone delivery is also managed, and in response to the prompt "Deliver supplies to an area where roads are impassable," the server sends delivery instructions by drone.

[0279] Prompt Sentence Examples

[0280] "Check the disaster situation in Tokyo"

[0281] "Delivering supplies from point A to point B"

[0282] "Check what supplies you need after an earthquake occurs"

[0283] "Delivering supplies to areas where roads are impassable"

[0284] This will create a system that enables quick and efficient disaster response at logistics centers.

[0285] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0286] Step 1:

[0287] The server obtains the latest disaster information through the APIs of various social media and news sites at specified time intervals. The input is data from the APIs of social media and news sites, and the output is disaster information data accumulated on the server. Specifically, the server periodically sends API requests and collects the returned data.

[0288] Step 2:

[0289] The server analyzes the collected disaster information using a natural language processing engine and extracts important keywords and phrases. The input is the disaster information data acquired in step 1, and the output is the analyzed keywords and phrases. Specifically, the server uses natural language processing technology to tokenize the text data and extract important information.

[0290] Step 3:

[0291] The server categorizes disaster information by region based on the analyzed keywords and stores it in a database. The input is the keywords and phrases extracted in step 2, and the output is the categorized disaster information data. Specifically, the server tags the keywords by region and stores them in the corresponding database.

[0292] Step 4:

[0293] When a user inputs the prompt "Check the disaster situation in Tokyo" from a terminal, the server searches the database for the latest disaster information related to Tokyo and provides it to the user. The input is the user's prompt, and the output is the disaster information as a search result. Specifically, the server executes a database query and sends the relevant data to the terminal.

[0294] Step 5:

[0295] Based on the user's request to "deliver goods from point A to point B," the server collects real-time road conditions and traffic information and calculates the optimal delivery route. The input is the delivery request and traffic information from the user, and the output is the optimal delivery route. Specifically, the server uses a map API to obtain the current traffic conditions and calculates the route using a shortest path algorithm.

[0296] Step 6:

[0297] The server inputs data on the scale of the earthquake and damage status into a machine learning model to predict the type and amount of supplies needed. The input is damage status data and past disaster data, and the output is a predicted list of supplies. Specifically, the server runs the machine learning model and stores the prediction results in a database.

[0298] Step 7:

[0299] When a user inputs a prompt from a terminal, such as "Check what supplies will be needed after an earthquake occurs," the server searches the database for a predicted list of supplies and provides it to the user. The input is the user's prompt, and the output is the list of supplies. Specifically, the server executes a database query and sends the predicted result data to the terminal.

[0300] Step 8:

[0301] When a user inputs "Deliver supplies to an area where roads are impassable," the server calculates the optimal delivery route for the drone and sends instructions to the drone management system. The inputs are a prompt from the user and the drone's initial position, and the output is a notification that the delivery has been completed. Specifically, the server sends instructions to the drone management system and monitors the delivery status.

[0302] The above processing steps enable optimization of logistics and rapid support in the event of a disaster.

[0303] 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.

[0304] The present invention provides a system that includes the following five main functions to optimize logistics and provide fast and efficient support during disasters: disaster information aggregation means, delivery route generation means, supply demand forecasting means, supply delivery means, and integrated management means that combines an emotion engine.

[0305] Disaster information collection method

[0306] overview

[0307] The server collects disaster-related information from social media and news sites in real time and compiles it in a centralized manner. This information serves as a foundation for quickly understanding the situation in the affected areas.

[0308] Natural language explanation

[0309] 1. The server obtains the latest disaster information data through the APIs of various social media and news sites at specified time intervals.

[0310] 2. The acquired information is analyzed using a natural language processing engine to extract important keywords and phrases.

[0311] 3. Based on the extracted keywords, disaster information is classified by region and stored in a database.

[0312] Specific examples

[0313] When a request is made from a terminal to "check the disaster situation in Tokyo," the server provides the user with the latest disaster information related to Tokyo from the database.

[0314] Delivery route generation method

[0315] overview

[0316] The server calculates and generates optimal delivery routes to affected areas based on the collected disaster information, enabling fast and efficient delivery of supplies.

[0317] Natural language explanation

[0318] 1. The server collects and analyzes real-time road conditions and traffic information.

[0319] 2. Run an algorithm that generates optimal delivery routes based on the analyzed data.

[0320] 3. Once the optimal route is generated, the user is notified via the terminal.

[0321] Specific examples

[0322] When a user sends a request from their terminal to "deliver goods from point A to point B," the server calculates the optimal delivery route and provides it to the user.

[0323] Material demand forecasting method

[0324] overview

[0325] The server predicts the types and quantities of supplies needed in the affected areas based on the scale of the earthquake and the extent of the damage, making it possible to prepare appropriate supplies in advance.

[0326] Natural language explanation

[0327] 1. The server collects data on the scale of the earthquake and the extent of the damage. The collected data is then input into a machine learning model to predict the types and quantities of supplies needed.

[0328] 2. Save the forecasted material demand results in a database.

[0329] Specific examples

[0330] When a user sends a request from their terminal to "check the supplies needed after an earthquake occurs," the server retrieves a list of predicted supplies and provides it to the user.

[0331] Delivery method (drone delivery)

[0332] overview

[0333] The server provides a means to deliver supplies to disaster areas using drones, making it possible to deliver supplies to areas where roads are impassable.

[0334] Natural language explanations

[0335] 1. The server obtains the location where supplies need to be delivered and the drone's initial location information.

[0336] 2. Calculate the optimal delivery route for the drone and send instructions to the drone management system.

[0337] 3. The drone delivers the goods to the destination and notifies the server that delivery is complete.

[0338] Specific examples

[0339] When a user inputs "Deliver supplies to an area where roads are impassable" into their device, the server calculates the optimal route for the drone and sends it into operation. Once the delivery is complete, the user is notified.

[0340] Emotion Engine

[0341] overview

[0342] The server uses an emotion engine to recognize the user's emotions and adjusts disaster response and distribution of supplies. Based on this information, it is possible to change the type and amount of support needed.

[0343] Natural language explanations

[0344] 1. The device analyzes the user's input and actions through an emotion engine and generates emotion data.

[0345] 2. The server evaluates the user's stress and anxiety level based on the emotional data sent from the emotion engine.

[0346] 3. Based on the assessment results, adjust the allocation of supplies and the type of assistance provided, and generate a list of supplies needed.

[0347] Specific examples

[0348] When a user inputs a request for assistance from their device, the emotion engine analyzes the user's emotional state, and the server adjusts the optimal type and amount of supplies based on the results.

[0349] By integrating these functions, a system will be created that will enable optimized logistics and rapid support during disasters, and will also be able to respond according to the user's emotions.

[0350] The processing flow will be explained below.

[0351] Disaster information collection method

[0352] Processing flow

[0353] Step 1:

[0354] The server sends requests to the APIs of various social networking sites and news sites at specified time intervals to obtain the latest disaster information data.

[0355] Step 2:

[0356] The server temporarily stores the acquired disaster information data in a database.

[0357] Step 3:

[0358] The server inputs the stored data into a natural language processing engine to analyze and extract important keywords and phrases.

[0359] Step 4:

[0360] The server classifies the disaster information by region based on the extracted keywords.

[0361] Step 5:

[0362] The server stores the categorized information in a main database.

[0363] Step 6:

[0364] The user sends a request from the terminal, such as "I would like to check the disaster situation in Tokyo."

[0365] Step 7:

[0366] In response to a request, the server searches the main database for disaster information for the relevant area and provides it to the user.

[0367] Delivery route generation method

[0368] Processing flow

[0369] Step 1:

[0370] The server collects road conditions and traffic information in real time, obtaining data from traffic camera image analysis and traffic information APIs.

[0371] Step 2:

[0372] The server analyzes the collected road condition data and filters out information on road disruptions and congestion.

[0373] Step 3:

[0374] The server runs a delivery route generation algorithm to calculate the optimal route, using Dijkstra's algorithm or A algorithm.

[0375] Step 4:

[0376] The user inputs the starting point and destination of the goods from the terminal.

[0377] Step 5:

[0378] The server recalculates the optimal route based on the input information and provides the generated route information to the user.

[0379] Step 6:

[0380] The terminal displays the calculated optimum route on a user interface.

[0381] Material demand forecasting method

[0382] Processing flow

[0383] Step 1:

[0384] The server collects data on the scale of earthquakes and the extent of damage, obtaining the data from earthquake information APIs and news sites.

[0385] Step 2:

[0386] The server then inputs the collected data into a machine learning model to predict demand for supplies, using algorithms such as regression analysis and random forests.

[0387] Step 3:

[0388] The server stores the results of the predicted material demand in a database.

[0389] Step 4:

[0390] The user sends a request to the server from the terminal to "check supplies needed after an earthquake occurs."

[0391] Step 5:

[0392] The server retrieves the prediction results from the database and provides them to the user.

[0393] Delivery method (drone delivery)

[0394] Processing flow

[0395] Step 1:

[0396] The server obtains the location where supplies need to be delivered and the drone's initial location information.

[0397] Step 2:

[0398] The server calculates the optimal delivery route for the drone, using algorithms such as the Bellman-Ford algorithm.

[0399] Step 3:

[0400] The server sends the calculated route information to the drone management system.

[0401] Step 4:

[0402] The drone follows the instructed route and delivers the goods to their destination.

[0403] Step 5:

[0404] The drone reaches its destination and delivers the goods.

[0405] Step 6:

[0406] The drone notifies the server that delivery is complete.

[0407] Step 7:

[0408] The server records the delivery completion information in a database and notifies the user.

[0409] Emotion Engine

[0410] Processing flow

[0411] Step 1:

[0412] The terminal acquires data entered by the user and behavioral data.

[0413] Step 2:

[0414] The device passes the acquired data to an emotion engine that analyzes the user's emotional state, identifying the user's stress and anxiety levels.

[0415] Step 3:

[0416] The terminal transmits the analysis results (emotion data) to the server.

[0417] Step 4:

[0418] The server adjusts the support plan based on the received emotion data, changing the need for supplies and priorities according to the user's emotions.

[0419] Step 5:

[0420] The server stores the adjusted supply lists and support plans in a database and recalculates delivery routes and supply quantities as needed.

[0421] Step 6:

[0422] When a user makes a support request from a terminal, the server provides optimal support content based on the user's emotions.

[0423] This enables the server to provide optimal supplies and support that take into account the user's stress and anxiety, making disaster response even more effective.

[0424] Example 2

[0425] 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."

[0426] Conventional disaster support systems have been unable to provide centralized and efficient support because they collect disaster information, deliver supplies, and understand emotions separately. Furthermore, they have also been unable to adequately deliver supplies to areas where roads are impassable or adjust the distribution of supplies according to the user's emotions.

[0427] 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.

[0428] In this invention, the server includes means for collecting and aggregating disaster information from social media and news sites in real time and analyzing it using natural language processing technology, means for generating optimal delivery routes based on the aggregated information, means for using a machine learning model to predict the supplies and their quantities needed based on the scale of the earthquake and the extent of the damage, means for delivering supplies using drones, means for coordinating the distribution of supplies and support based on user emotion data using an emotion engine, and means for integrating and managing all of the above means. This enables fast and efficient support based on accurate information in real time during disasters, enables supplies to be delivered to areas where roads are impassable, and enables responses based on user emotion.

[0429] "SNS and news sites" is a general term for social networking services that allow users to share and disseminate information online, and websites that provide the latest news articles.

[0430] "Real-time" refers to data acquisition and processing occurring almost immediately, providing current information without delay.

[0431] "Disaster information" includes all information related to natural disasters and man-made disasters, such as the occurrence status, scale of damage, area of ​​impact, and evacuation information.

[0432] "Means of collection and aggregation" refers to a system or method for automatically obtaining necessary information from designated data sources and managing it centrally.

[0433] "Natural language processing technology" refers to technology that enables computers to understand, analyze, and process human language, and includes technologies such as text mining and sentiment analysis.

[0434] "Means of analysis" refers to software or algorithms used to analyze collected information and extract useful data.

[0435] "Means for generating optimal delivery routes" refers to methods or algorithms for calculating the most efficient travel path from a given point to a destination.

[0436] A "machine learning model" refers to an algorithm or system that learns from large amounts of data and makes predictions and classifications for new data.

[0437] "Supplies" refers to various resources needed in the event of a disaster, such as food, water, medicine, clothing, and fuel.

[0438] A "drone" is a type of unmanned aerial vehicle that flies remotely or autonomously and transports goods, among other tasks.

[0439] An "emotion engine" refers to software or algorithms that analyze user input and behavioral data to infer emotional states.

[0440] "Means of integration and management" refers to methods and systems for centrally controlling and effectively operating multiple different systems and processes.

[0441] The system of the present invention provides the following functions for the purpose of providing prompt and efficient support in the event of a disaster. These functions are realized based on the roles of the server, terminal, and user.

[0442] Disaster information collection method

[0443] In the system, the server obtains real-time disaster information data at specified intervals through the APIs of various social media sites and news sites. Specifically, it uses the APIs of Twitter and news providers. For example, it calls Twitter's " / v1 / tweets / search" endpoint to obtain the latest posts. The obtained information is analyzed using Natural Language Processing (NLP) technology, such as the Google Cloud Natural Language API. Important keywords and phrases are extracted through the analysis, and based on this, disaster information is classified by region and stored in a MySQL database. Specifically, disaster information related to Tokyo is classified as "Tokyo" or "earthquake."

[0444] When a user sends a request from their device saying, "I want to check the disaster situation in Tokyo," the server retrieves the latest disaster information related to Tokyo from the database and provides it to the user.

[0445] Prompt Sentence Examples

[0446] "Please tell me the latest disaster information for Tokyo."

[0447] Delivery route generation method

[0448] The server collects and analyzes real-time road conditions and traffic information. This information is collected using the Google Maps API, for example, by calling the " / maps / api / directions" endpoint to obtain traffic data. The collected data is then used to generate optimal delivery routes using Dijkstra and A algorithms. The generated route information is then sent to the user's device.

[0449] When a user sends a request from their terminal to "deliver goods from point A to point B," the server calculates the optimal delivery route and provides it to the user.

[0450] Prompt Sentence Examples

[0451] "Deliver supplies from point A to point B using the optimal route."

[0452] Material demand forecasting method

[0453] The server collects data indicating the scale of the earthquake and the extent of the damage, and uses that data to predict the type and amount of supplies needed. The collected data is input into a machine learning model (for example, a TensorFlow model) to predict demand for supplies. Earthquake information is collected using the APIs of the Japan Meteorological Agency and disaster information providers, for example, from the " / v1 / earthquake / info" endpoint.

[0454] When a user sends a request from their terminal to "check the supplies needed after an earthquake occurs," the server retrieves a list of predicted supplies and provides it to the user.

[0455] Prompt Sentence Examples

[0456] "What supplies will I need after an earthquake?"

[0457] Delivery method (drone delivery)

[0458] The server acquires the location where the goods need to be delivered and the drone's initial position information, and calculates the optimal delivery route. The calculated route is sent to the drone management system, and the drone delivers the goods to the destination. After the delivery is complete, the server notifies the user.

[0459] When a user inputs "Deliver supplies to an area where roads are impassable" into their device, the server calculates the optimal drone route and executes it. Once the delivery is complete, the user is notified.

[0460] Prompt Sentence Examples

[0461] "Deliver supplies by drone to areas where roads are impassable."

[0462] Emotion Engine

[0463] The device analyzes the user's input and actions through an emotion engine to generate emotion data. The emotion engine uses technology such as IBM Watson (registered trademark) Tone Analyzer to analyze the user's emotional state. The server evaluates the user's stress and anxiety level based on the emotion data sent from the emotion engine (e.g., anxiety level 80%) and adjusts the distribution of supplies and the type of assistance provided.

[0464] When a user inputs a request for assistance from their device, the server analyzes their emotional state and adjusts the optimal type and amount of supplies.

[0465] Prompt Sentence Examples

[0466] "Adjust your support needs based on your current emotional state."

[0467] By integrating these measures, it is possible to optimize logistics during disasters, provide rapid assistance, and respond to users' emotions.

[0468] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0469] Disaster information collection method

[0470] Step 1:

[0471] The server obtains the latest disaster information data through the APIs of social media and news sites at specified time intervals.

[0472] Input: API endpoint (e.g. " / v1 / tweets / search" for Twitter API)

[0473] Output: Latest disaster information data (e.g. tweets and news article text)

[0474] Step 2:

[0475] The server sends the acquired disaster information data to a natural language processing engine (e.g., Google Cloud Natural Language API) to extract important keywords and phrases.

[0476] Input: Acquired disaster information data

[0477] Output: Extracted keywords and phrases (e.g., "Tokyo" or "earthquake")

[0478] Step 3:

[0479] The server categorizes the information by region based on the extracted keywords and stores it in a MySQL database.

[0480] Input: Extracted keywords or phrases

[0481] Output: Disaster information data categorized by region (e.g., data related to Tokyo)

[0482] Delivery route generation method

[0483] Step 1:

[0484] The server collects real-time road conditions and traffic information.

[0485] Input: Traffic information API endpoint (e.g., " / maps / api / directions" for the Google Maps API)

[0486] Output: Current road conditions and traffic information

[0487] Step 2:

[0488] The server executes a delivery route generation algorithm (e.g., Dijkstra or A algorithm) based on the collected traffic data to calculate the optimal delivery route.

[0489] Input: Real-time road conditions and traffic information

[0490] Output: Optimal delivery route (e.g., route from point A to point B)

[0491] Step 3:

[0492] The server notifies the user's terminal of the calculated optimum delivery route.

[0493] Input: Optimal delivery route

[0494] Output: Notification to the terminal (e.g. "The best delivery route is via XX")

[0495] Material demand forecasting method

[0496] Step 1:

[0497] The server collects data showing the scale of the earthquake and the extent of the damage.

[0498] Input: Earthquake information API endpoint (e.g., Japan Meteorological Agency API " / v1 / earthquake / info")

[0499] Output: Detailed information about the earthquake (e.g., magnitude, epicenter, damage status)

[0500] Step 2:

[0501] The server inputs the collected earthquake data into a machine learning model (e.g., a TensorFlow model) to predict the type and quantity of supplies needed.

[0502] Input: Earthquake details

[0503] Output: Predicted demand data (e.g., "Drinking water: 500L, Food: 300kg, Blankets: 200")

[0504] Step 3:

[0505] The server stores the predicted material demand data in a database.

[0506] Input: Forecasted material demand data

[0507] Output: Material demand data stored in a database

[0508] Delivery method (drone delivery)

[0509] Step 1:

[0510] The server obtains the location where supplies need to be delivered and the drone's initial location information.

[0511] Input: User's delivery request (e.g., "Deliver supplies from location A to location B")

[0512] Output: Delivery location and initial drone position

[0513] Step 2:

[0514] The server calculates the optimal delivery route based on the delivery point and the drone's initial location information.

[0515] Input: Delivery point and initial drone location information

[0516] Output: Optimal delivery route

[0517] Step 3:

[0518] The server sends the calculated route to the drone management system, which then operates the drone.

[0519] Input: Optimal delivery route

[0520] Output: Drone operation instructions

[0521] Step 4:

[0522] Once the drone has delivered the goods, the server will send a delivery completion notification to the user.

[0523] Input: Delivery completion report from drone

[0524] Output: Delivery completion notification to user

[0525] Emotion Engine

[0526] Step 1:

[0527] The device collects user input and behavioral data and sends it to the emotion engine.

[0528] Input: User input and behavioral data (e.g., text such as "I'm very anxious")

[0529] Output: Sending data to the emotion engine

[0530] Step 2:

[0531] The server receives the emotion data generated by the emotion engine and evaluates the user's stress and anxiety level.

[0532] Input: Emotion data from the emotion engine (e.g., "Anxiety level 80%)

[0533] Output: Assessed stress and anxiety levels

[0534] Step 3:

[0535] The server adjusts the type and quantity of supplies based on the evaluation results and generates a list of required supplies.

[0536] Input: Assessed stress and anxiety levels

[0537] Output: Adjusted supply list (e.g., more medkits and stress relief items)

[0538] The above are the specific processing steps of the invention, and an explanation has been given of what input data is used in each step and what output is obtained.

[0539] (Application example 2)

[0540] 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."

[0541] Conventional disaster logistics systems have difficulty gathering information in real time and generating appropriate delivery routes, and have also been unable to adequately predict the demand for supplies. Another problem is that assistance provided does not take into account the emotions and conditions of disaster victims. This makes it difficult to provide prompt and efficient assistance, and there is a risk that necessary support for disaster victims may be delayed.

[0542] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0543] In this invention, the server includes means for collecting and aggregating disaster information from social media and news sites in real time, means for generating optimal delivery routes based on the aggregated information, means for predicting the supplies needed and their quantities based on the scale of the earthquake and the extent of the damage, means for delivering supplies using autonomous vehicles, and means for analyzing the emotional state of users using emotion analysis technology and adjusting the content of support, thereby enabling fast and efficient delivery of supplies to disaster-stricken areas and providing appropriate support that takes into account the emotional state of the victims.

[0544] A "disaster information aggregation method" is a method for collecting disaster-related information from social media and news sites in real time and consolidating it in a centralized manner.

[0545] The "delivery route generation means" is a means for calculating and generating the optimal delivery route to the disaster-stricken area based on the collected disaster information.

[0546] A "materials demand forecasting method" is a method that uses machine learning models to predict the supplies and quantities needed based on the scale of the earthquake and the extent of the damage.

[0547] An "autonomous vehicle" is a vehicle that can drive and deliver goods automatically without human operation.

[0548] "Emotion analysis technology" is a technology that analyzes the user's emotional state and adjusts appropriate support and distribution of supplies based on the results.

[0549] "Integrated management means" refers to a means for managing the above-mentioned multiple means in an integrated manner and implementing optimal support activities.

[0550] "Road conditions and traffic information" refers to general traffic-related information, such as road congestion and closed-to-traffic sections, provided in real time.

[0551] "Natural language processing technology" is a technology that uses computers to analyze human language and extract and understand information such as meaning and emotions.

[0552] The present invention is a system for optimizing logistics during disasters and providing fast and efficient support. This system includes a disaster information aggregation unit, a delivery route generation unit, a supply demand forecasting unit, a supply delivery unit using autonomous vehicles, a support content adjustment unit using emotion analysis technology, and a unit for integrating and managing these units. The implementation methods for each unit are described in detail below.

[0553] Disaster information collection method

[0554] The server collects disaster information from social media and news sites in real time and compiles it in a centralized manner. Specifically, it obtains the latest disaster information data through the APIs of social media and news sites, analyzes it using natural language processing technology, and extracts important information. This information serves as the basis for quickly understanding the situation in disaster-stricken areas.

[0555] Specific examples

[0556] When a request to "check the latest disaster information" is made from a terminal, the server searches the database for the latest disaster information and provides it to the user.

[0557] Delivery route generation method

[0558] The server calculates and generates optimal delivery routes to affected areas based on the collected disaster information. It uses map services such as Google Maps API to collect and analyze real-time road conditions and traffic information to generate optimal delivery routes.

[0559] Specific examples

[0560] When a user sends a request from their terminal to "deliver supplies from their current location to disaster area B," the server calculates the optimal delivery route and provides it to the user.

[0561] Material demand forecasting method

[0562] The server collects data on the scale of the earthquake and the extent of the damage, inputs it into a machine learning model, and predicts the types and quantities of supplies needed. Based on this result, it generates a list of specific supplies needed for relief.

[0563] Specific examples

[0564] When a user sends a request from their terminal to "check the supplies needed after an earthquake occurs," the server retrieves a list of predicted supplies and provides it to the user.

[0565] Autonomous vehicle delivery method

[0566] The server provides a means to deliver supplies to disaster areas using autonomous vehicles. The autonomous vehicles drive along optimal routes calculated based on the situation and traffic information, and deliver supplies to disaster areas. These autonomous vehicles can also work in conjunction with drones to deliver supplies to areas where roads are impassable.

[0567] Specific examples

[0568] When a user types "deliver goods to an area where roads are impassable" into their device, the server calculates the optimal route and puts the autonomous vehicle into operation. Once the delivery is complete, the user is notified.

[0569] A method for adjusting support content using emotion analysis technology

[0570] The device uses emotion analysis technology to analyze the user's input and behavior to generate emotional data, which the server uses to assess the user's stress and anxiety levels and adjust the distribution of supplies and assistance.

[0571] Specific examples

[0572] When a user inputs a request for assistance from a terminal, emotion analysis technology analyzes the user's emotional state, and the server adjusts the optimal type and amount of supplies based on the results.

[0573] Prompt Sentence Examples

[0574] Here are some examples of prompts for generative AI models:

[0575] "Get the latest disaster information in real time and analyze the situation in the affected areas."

[0576] "Generate the optimal delivery route from the current location to disaster area B, taking traffic information into account."

[0577] "It analyzes users' emotional data to assess their stress and anxiety levels."

[0578] This will enable the rapid and efficient delivery of supplies to disaster-stricken areas, and will also realize a system that can provide appropriate support taking into account the emotional state of the victims.

[0579] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0580] Step 1:

[0581] The server collects disaster information from social media and news sites at specified intervals.

[0582] Input: APIs of various social media and news sites.

[0583] Data processing: The acquired information is parsed in JSON format and analyzed using a natural language processing engine.

[0584] Output: A dataset containing important information.

[0585] Specifically, the server sends API requests to social media and news sites, analyzes the disaster information received in response, and uses a natural language processing engine to extract keywords and important phrases, which are then stored in a database.

[0586] Step 2:

[0587] The server calculates and generates the optimal delivery route to the affected area based on the collected disaster information.

[0588] Input: Disaster information dataset, Google Maps API.

[0589] Data calculation: Uses Google Maps API to obtain real-time road conditions and calculate the optimal route.

[0590] Output: Optimal delivery route.

[0591] Specifically, the server uses an algorithm to calculate the optimal delivery route based on a disaster information dataset, and then obtains road information from the Google Maps API to optimize the route.

[0592] Step 3:

[0593] The server predicts the types and quantities of supplies needed based on the scale of the earthquake and the extent of the damage.

[0594] Input: Earthquake magnitude data, damage status data.

[0595] Data computation: Input data into machine learning models and run predictive algorithms.

[0596] Output: List of supplies needed.

[0597] Specifically, the server uses a machine learning model to generate a list of needed supplies based on data indicating the scale of the earthquake and the extent of the damage.

[0598] Step 4:

[0599] The server will use autonomous vehicles to deliver supplies to disaster areas.

[0600] Inputs: Optimal delivery route, initial position information of the autonomous vehicle, and a list of supplies.

[0601] Data processing: Create a loading plan for supplies based on delivery routes.

[0602] Output: Delivery instructions, loading completion notification.

[0603] Specifically, the server sends the optimal delivery route and loading plan to the autonomous vehicle, and the vehicle delivers the goods according to those instructions.

[0604] Step 5:

[0605] The terminal analyzes the user's input and actions using emotion analysis technology to generate emotion data.

[0606] Input: User input data.

[0607] Data Computing: Analyzes sentiment using a natural language processing engine.

[0608] Output: Emotion data.

[0609] Specifically, the terminal sends the user's input to an emotion analysis engine, which generates emotion data as a result.

[0610] Step 6:

[0611] The server assesses the user's stress and anxiety levels based on emotional data and adjusts the distribution of supplies and support.

[0612] Input: Emotion data, supply list.

[0613] Data calculation: Optimize support content based on emotional data.

[0614] Output: Coordinated supply list, support plan.

[0615] Specifically, the server analyzes emotional data and dynamically adjusts the distribution of supplies and the content of support according to the user's level of stress and anxiety.

[0616] Through the above processing steps, efficient and rapid delivery of supplies during disasters and support that takes into account the emotional state of victims can be achieved.

[0617] 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.

[0618] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0619] 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.

[0620] [Second embodiment]

[0621] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0622] 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.

[0623] 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).

[0624] 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.

[0625] 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.

[0626] 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).

[0627] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0628] 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.

[0629] 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.

[0630] 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.

[0631] 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.

[0632] 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."

[0633] The present invention provides a system that includes the following four main functions to optimize logistics and provide fast and efficient support during disasters: disaster information collection means, delivery route generation means, supply demand forecasting means, and supply delivery means.

[0634] Disaster information collection method

[0635] overview

[0636] The server collects disaster-related information from social media and news sites in real time and compiles it in a centralized manner. This information serves as a foundation for quickly understanding the situation in the affected areas.

[0637] Natural language explanation

[0638] 1. The server obtains the latest disaster information through the APIs of various social media and news sites at specified intervals.

[0639] 2. The acquired information is analyzed using a natural language processing engine to extract important keywords and phrases.

[0640] 3. Based on the extracted keywords, disaster information is classified by region and stored in a database.

[0641] Specific examples

[0642] When a request to "check the disaster situation in Tokyo" is made from a terminal, the server provides the user with the latest disaster information related to Tokyo from the database.

[0643] Delivery route generation method

[0644] overview

[0645] The server calculates and generates optimal delivery routes to affected areas based on the collected disaster information, enabling fast and efficient delivery of supplies.

[0646] Natural language explanation

[0647] 1. The server collects and analyzes real-time road conditions and traffic information.

[0648] 2. Based on the analyzed data, an algorithm is run to generate the optimal delivery route.

[0649] 3. Once the optimal route is generated, the user is notified via the terminal.

[0650] Specific examples

[0651] When a user sends a request from their terminal to "deliver goods from point A to point B," the server calculates the optimal delivery route and provides it to the user.

[0652] Material demand forecasting method

[0653] overview

[0654] The server predicts the types and quantities of supplies needed in the affected areas based on the scale of the earthquake and the extent of the damage, making it possible to prepare appropriate supplies in advance.

[0655] Natural language explanation

[0656] 1. The server collects data indicating the scale of the earthquake and the extent of the damage.

[0657] 2. Input the collected data into a machine learning model to predict the types and quantities of supplies needed.

[0658] 3. The prediction results are stored in a database and can be viewed by the user at any time.

[0659] Specific examples

[0660] When a user sends a request from their terminal to "check the supplies needed after an earthquake occurs," the server retrieves a list of predicted supplies and provides it to the user.

[0661] Delivery method (drone delivery)

[0662] overview

[0663] The server provides a means to deliver supplies to disaster areas using drones, making it possible to deliver supplies to areas where roads are impassable.

[0664] Natural language explanation

[0665] 1. The server obtains the location where supplies need to be delivered and the initial position of the drone.

[0666] 2. Calculate the optimal delivery route for the drone and send instructions to the drone management system.

[0667] 3. The drone delivers the goods to the destination and notifies the server that delivery is complete.

[0668] Specific examples

[0669] When a user inputs "Deliver supplies to an area where roads are impassable" into their device, the server calculates the optimal route for the drone and sends it into operation. Once the delivery is complete, the user is notified.

[0670] By integrating these functions, a system will be created to optimize logistics and provide rapid support during disasters.

[0671] The processing flow will be explained below.

[0672] Disaster information collection method

[0673] Processing flow

[0674] Step 1:

[0675] The server sends requests to the APIs of various social networking sites and news sites at specified time intervals to obtain the latest disaster information data.

[0676] Step 2:

[0677] The server temporarily stores the acquired disaster information data in a database.

[0678] Step 3:

[0679] The server inputs the stored data into a natural language processing engine to extract important keywords and phrases.

[0680] Step 4:

[0681] The server categorizes disaster information by region based on the extracted keywords and stores the categorized information in the main database.

[0682] Step 5:

[0683] The user sends a request from the terminal, such as "I would like to check the disaster situation in Tokyo."

[0684] Step 6:

[0685] In response to a request, the server searches the main database for disaster information for the relevant area and provides it to the user.

[0686] Delivery route generation method

[0687] Processing flow

[0688] Step 1:

[0689] The server collects road conditions and traffic information in real time, using image analysis from traffic cameras and data from traffic information APIs.

[0690] Step 2:

[0691] The server analyzes the collected road condition data and filters out information on road disruptions and congestion.

[0692] Step 3:

[0693] The server runs a delivery route generation algorithm to calculate the optimal route, using Dijkstra's algorithm or A algorithm.

[0694] Step 4:

[0695] The user inputs the starting point and destination of the goods from the terminal.

[0696] Step 5:

[0697] The server recalculates the optimal route based on the input information and provides the generated route information to the user.

[0698] Step 6:

[0699] The terminal displays the calculated optimum route on a user interface.

[0700] Material demand forecasting method

[0701] Processing flow

[0702] Step 1:

[0703] The server collects data on the scale and damage caused by earthquakes, specifically from earthquake information APIs and news sites.

[0704] Step 2:

[0705] The server inputs the collected data into a machine learning model to predict demand for goods, using algorithms such as regression analysis and random forests.

[0706] Step 3:

[0707] The server stores the results of the predicted material demand in a database.

[0708] Step 4:

[0709] The user sends a request to the server from the terminal to "check supplies needed after an earthquake occurs."

[0710] Step 5:

[0711] The server retrieves the prediction results from the database and provides them to the user.

[0712] Delivery method (drone delivery)

[0713] Processing flow

[0714] Step 1:

[0715] The server obtains the location where supplies need to be delivered and the drone's initial location information.

[0716] Step 2:

[0717] The server calculates the optimal delivery route for the drone, using algorithms such as the Bellman-Ford algorithm.

[0718] Step 3:

[0719] The server sends the calculated route information to the drone management system.

[0720] Step 4:

[0721] The drone follows the instructed route and delivers the goods to their destination.

[0722] Step 5:

[0723] The drone reaches its destination and delivers the goods.

[0724] Step 6:

[0725] The drone notifies the server that delivery is complete.

[0726] Step 7:

[0727] The server records the delivery completion information in a database and notifies the user.

[0728] Example 1

[0729] 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."

[0730] When disasters such as earthquakes and fires occur, the challenge is to quickly and accurately collect information and deliver appropriate relief supplies to affected areas. Effective logistics is particularly difficult when roads are impassable or information is in disarray. Existing systems are prone to delays and false reports at each stage of information collection, analysis, and supply delivery, making it difficult to provide efficient relief.

[0731] 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.

[0732] In this invention, the server includes a means for collecting disaster information in real time from information sources such as social media and news sites, a means for analyzing the collected disaster information using natural language processing technology and extracting important information, and a means for generating optimal delivery routes based on the extracted information, thereby enabling a fast and efficient disaster response and optimization of logistics.

[0733] "SNS" stands for Social Networking Service, a platform for users to share information and interact online.

[0734] A "news site" is a website that provides news coverage of current events and happenings on the Internet.

[0735] "Disaster information" refers to information about natural disasters such as earthquakes, typhoons, and fires, as well as man-made disasters.

[0736] "Real-time" refers to data acquisition and processing occurring almost simultaneously with real time.

[0737] "Natural language processing technology" is a technology for analyzing and processing human language using a computer, and is used to understand the meaning and intent of text.

[0738] The "optimal delivery route" refers to the most efficient and safe route for delivering goods, taking into account time, distance, and cost.

[0739] The "magnitude of an earthquake" is an indicator of the amount of energy released and the extent of its impact when an earthquake occurs.

[0740] "Damage situation" is information that indicates the extent of human and material damage when a disaster occurs.

[0741] An "unmanned aerial vehicle" is a flying machine that flies remotely or autonomously and is used for transporting goods, etc.

[0742] A "database" is a computer system for efficiently storing, searching, and managing large amounts of data.

[0743] "Traffic information" refers to information that indicates the status of transportation routes such as roads and railways, and includes information on traffic congestion and road closures.

[0744] The present invention is a system for optimizing logistics in the event of a disaster and providing prompt and efficient support. This system operates in cooperation with three parties: a server, a terminal, and a user.

[0745] Server Roles

[0746] Information collection and analysis

[0747] The server collects disaster information in real time from sources such as social media and news sites. This information is collected using, for example, the Twitter API and RSS feeds from various news sites. The collected information is analyzed using a natural language processing engine (e.g., spaCy, BERT) to extract important keywords and phrases. This analysis process identifies important information such as "evacuation shelters," "water outages," and "traffic disruptions."

[0748] Data Classification and Retention

[0749] The extracted important information is categorized by region and stored in a database (e.g., MongoDB, MySQL), providing the server with a basis for understanding the situation in real time and taking necessary actions.

[0750] Generate delivery routes

[0751] The server runs an algorithm (e.g., the Dijkstra algorithm) to generate optimal delivery routes based on collected disaster information and real-time road conditions. Specifically, it uses Google Maps API and HERE Maps API to collect traffic information and calculates the shortest and safest route based on this information.

[0752] Forecasting demand for goods

[0753] The server collects data on the scale and damage of the earthquake, and inputs this data into a machine learning model (e.g., TensorFlow, Scikit-learn) to predict the types and quantities of supplies needed. For example, if a large earthquake occurs, it is expected that demand for food, water, medicine, etc. will increase.

[0754] Drone delivery of supplies

[0755] The server acquires information on the drone's initial position and the location where delivery is required, and calculates the optimal delivery route. The calculated route is sent to the drone management system, which instructs the unmanned aerial vehicle to deliver the goods to the destination. Once the delivery is complete, the server receives the information and notifies the user.

[0756] Device Role

[0757] The terminal provides an interface for users to access the system, through which they can check disaster information and make delivery requests.

[0758] User Roles

[0759] Users send requests to the server via their terminals, such as "Check the disaster situation in Tokyo," "Deliver supplies from point A to point B," "Check supplies needed after an earthquake occurs," and "Deliver supplies to areas where roads are impassable." The server receives these requests, performs the necessary processing, and provides the results to the user.

[0760] Specific examples

[0761] Example prompt sentence:

[0762] "To optimize logistics during disasters, collect disaster information from social media and news sites, generate optimal delivery routes, and deliver supplies to affected areas."

[0763] These explanations clarify the specific embodiments of the present invention. A system is constructed that centrally manages a series of processes, from collecting and analyzing disaster information, creating optimal delivery routes, predicting demand for supplies, and delivering supplies by drone. This enables a rapid and efficient response in the event of a disaster.

[0764] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0765] Program processing steps and detailed explanation

[0766] Disaster information collection method

[0767] Step 1: Gather information

[0768] The server obtains the latest disaster information through the APIs of social media and news sites at specified intervals.

[0769] Input: Data obtained from APIs of various social media and news sites (e.g., Twitter tweets, news articles)

[0770] Specific operation: The server uses the Twitter API key to collect tweets with keywords such as "earthquake," "evacuation," and "support," and retrieves the latest articles from the news site's RSS feed.

[0771] Output: Raw data (text data)

[0772] Step 2: Natural Language Processing Analysis

[0773] The server inputs the collected text data into a natural language processing technology engine (e.g., spaCy, BERT) to extract important keywords and phrases.

[0774] Input: Raw data acquired

[0775] Specific operation: The server uses a natural language processing engine to analyze the text data and uses tokenization, stemming, and entity recognition to identify important information such as "shelters," "water outages," and "traffic disruptions."

[0776] Output: Extracted important keywords and phrases

[0777] Step 3: Classify and store data

[0778] Based on the extracted keywords, the server classifies disaster information by region and stores it in a database.

[0779] Input: Extracted important keywords and phrases

[0780] Specific operation: The server classifies information based on place names such as "Tokyo" and "Osaka" and stores it in a database such as MongoDB or MySQL.

[0781] Output: Database entries for disaster information categorized by region

[0782] Delivery route generation method

[0783] Step 1: Collect road conditions

[0784] The server collects real-time road conditions and traffic information using the Google Maps API and HERE Maps API.

[0785] Input: Real-time road condition data

[0786] Specific operation: The server collects information such as traffic congestion and road closures through the API and plots it on a map.

[0787] Output: Latest traffic information dataset

[0788] Step 2: Data analysis

[0789] The server analyzes the collected data and runs an algorithm (e.g., Dijkstra algorithm) to generate optimal delivery routes.

[0790] Input: Latest traffic information dataset

[0791] Specific operation: The server calculates the distance and time between each delivery point, evaluates multiple routes, and identifies the shortest and safest route.

[0792] Output: Optimal delivery route information

[0793] Step 3: Notification of results

[0794] Once the optimal route has been generated, the server notifies the user via the terminal.

[0795] Input: Optimal delivery route information

[0796] Specific operation: The server sends the generated route data in JSON format to the terminal and notifies the user.

[0797] Output: Route information provided to the user

[0798] Material demand forecasting method

[0799] Step 1: Data collection

[0800] The server collects data from the USGS and the Japan Meteorological Agency indicating the scale of the earthquake and the extent of the damage.

[0801] Input: Earthquake magnitude and damage data

[0802] Specific operation: The server obtains data such as the earthquake's epicenter, magnitude, and scale of damage through the API.

[0803] Output: Earthquake and damage dataset

[0804] Step 2: Input to the machine learning model

[0805] The server inputs the collected data into a machine learning model (e.g., TensorFlow, Scikit-learn) to predict the type and quantity of supplies needed.

[0806] Input: Earthquake and damage dataset

[0807] How it works: The server uses data from past disasters to use machine learning models to predict demand for food, water, medicine, etc.

[0808] Output: List of predicted supplies

[0809] Step 3: Save the prediction results

[0810] The server stores the prediction results in a database so that users can check them at any time.

[0811] Input: Forecasted supplies list

[0812] Specific operation: The server updates the prediction results in real time and displays them in the database and on the dashboard.

[0813] Output: Stored supply forecast data

[0814] Delivery method (drone delivery)

[0815] Step 1: Obtaining delivery points and drone positions

[0816] The server uses GPS data to obtain the location where supplies need to be delivered and the drone's initial position.

[0817] Input: Delivery point and initial drone position data

[0818] Specific operation: The server collects the latitude and longitude information of the required delivery point, as well as the drone's current location information.

[0819] Output: Geolocation dataset

[0820] Step 2: Route calculation

[0821] The server calculates the optimal delivery route for the drone and sends instructions to the drone management system.

[0822] Input: Geolocation dataset

[0823] How it works: The server uses a 3D mapping algorithm to calculate a route that avoids obstacles and takes into account wind direction and weather conditions.

[0824] Output: Optimal drone delivery route

[0825] Step 3: Delivery notification

[0826] The server notifies the user once the drone has delivered the goods to the destination and received notification that delivery has been completed.

[0827] Input: Delivery completion notification from drone

[0828] Specific operation: The server monitors the delivery status in real time, and after delivery is completed, it records the status and notifies the user via email or app.

[0829] Output: Delivery completion notification to user

[0830] Through the above processing steps, the system of the present invention realizes rapid and efficient disaster response and optimization of logistics.

[0831] (Application example 1)

[0832] 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."

[0833] Logistics during disasters is a key element for providing fast and efficient support to disaster-stricken areas. However, traditional logistics systems often lack real-time information and fragmented information, making it difficult to generate optimal delivery routes and forecast supply demand. Furthermore, when roads were impassable, delivery of supplies could be significantly delayed. Furthermore, logistics center staff and managers lacked the means to monitor the situation in real time and respond quickly. To resolve these situations, a more integrated management system is needed.

[0834] 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.

[0835] In this invention, the server includes a means for collecting and aggregating disaster information from social media and news sites in real time, a means for generating optimal delivery routes based on the aggregated information, a means for predicting the supplies needed and their quantities based on the scale of the earthquake and the extent of the damage, a means for logistics center staff and managers to monitor the situation in real time via smartphone and take swift action, a means for delivering supplies using drones, and a means for integrating and managing all of the above means, thereby enabling optimized logistics and rapid support during disasters.

[0836] "SNS" is an abbreviation for social networking service, an online platform for users to share information and communicate.

[0837] A "news site" is a website that provides news articles over the Internet.

[0838] "Real-time" refers to the immediacy with which data and information are collected, analyzed, and displayed immediately.

[0839] "Disaster information" refers to information that indicates the status and impact of natural disasters such as earthquakes and floods.

[0840] A "logistics center" is a facility where supplies are stored, sorted, and prepared for delivery.

[0841] A "smartphone" is a mobile phone device with advanced computing power and connectivity.

[0842] "Staff" refers to employees working in an organization or facility.

[0843] A "manager" is a position that manages and supervises an organization or team.

[0844] A "delivery route" refers to the optimal route for transporting goods, calculated to minimize time and distance.

[0845] "Earthquake magnitude" is a numerical indicator that shows the amount of energy an earthquake generates.

[0846] "Damage status" is information indicating the damage and state of damage caused by a disaster.

[0847] "Supplies" refers to support items such as food, water, medicine, and cold weather gear that are needed in the event of a disaster.

[0848] "Demand forecasting" is the act of predicting how much material will be needed in the future.

[0849] A "drone" is an unmanned aircraft that can be remotely controlled and fly autonomously.

[0850] "Integrated management" refers to the integration and centralized management of multiple functions and methods.

[0851] The present invention relates to a system for optimizing logistics at a logistics center during a disaster and providing prompt and efficient support. The system has the following main functions:

[0852] 1. Disaster information collection method

[0853] The server collects and aggregates disaster information in real time from social media and news sites. For example, it uses the APIs of social media sites and RSS feeds from news sites. The collected information is analyzed within the server using a natural language processing engine to extract important keywords and phrases. This allows the situation in the affected areas to be quickly grasped.

[0854] 2. Delivery route generation method

[0855] The server generates the optimal delivery route based on the collected disaster information and real-time road and traffic information. For example, it obtains the current traffic situation using a map API and calculates the optimal route using a shortest route algorithm. This information is provided to users so they can check it on their smartphones.

[0856] 3. Material demand forecasting methods

[0857] The server inputs data such as the scale of the earthquake and the extent of the damage into a machine learning model to predict the type and quantity of supplies needed in the affected area. For example, an AI model is used to compare past disaster data with the current disaster situation to predict demand. The predicted supply list is then displayed in real time on a smartphone app for staff and managers to check.

[0858] 4. Delivery of goods (drone delivery)

[0859] The server instructs drones to deliver goods to areas where roads are impassable. For example, it calculates the optimal delivery route based on the specified location and the drone's initial position, and sends instructions to the drone management system. Once the delivery is complete, the information is notified to the server, and then to a smartphone.

[0860] Hardware and software used

[0861] Smartphones: Used by staff and managers.

[0862] Drones: Used to deliver supplies.

[0863] Natural language processing engine: Used to analyze collected disaster information.

[0864] Map API: Get current traffic conditions and use them to calculate the shortest route.

[0865] Machine learning models: Used to forecast demand for supplies.

[0866] Drone management system: Used to manage drone deliveries.

[0867] Specific examples

[0868] For example, when a disaster occurs, the server instantly collects disaster information from social media and news sites, and when a user inputs the prompt "Check the disaster situation in Tokyo," it provides the latest disaster information for that area. Furthermore, when a user inputs "Deliver supplies from point A to point B," the server calculates the optimal delivery route and notifies the smartphone app. When supply delivery is necessary, drone delivery is also managed, and in response to the prompt "Deliver supplies to an area where roads are impassable," the server sends delivery instructions by drone.

[0869] Prompt Sentence Examples

[0870] "Check the disaster situation in Tokyo"

[0871] "Delivering supplies from point A to point B"

[0872] "Check what supplies you need after an earthquake occurs"

[0873] "Delivering supplies to areas where roads are impassable"

[0874] This will create a system that enables quick and efficient disaster response at logistics centers.

[0875] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0876] Step 1:

[0877] The server obtains the latest disaster information through the APIs of various social media and news sites at specified time intervals. The input is data from the APIs of social media and news sites, and the output is disaster information data accumulated on the server. Specifically, the server periodically sends API requests and collects the returned data.

[0878] Step 2:

[0879] The server analyzes the collected disaster information using a natural language processing engine and extracts important keywords and phrases. The input is the disaster information data acquired in step 1, and the output is the analyzed keywords and phrases. Specifically, the server uses natural language processing technology to tokenize the text data and extract important information.

[0880] Step 3:

[0881] The server categorizes disaster information by region based on the analyzed keywords and stores it in a database. The input is the keywords and phrases extracted in step 2, and the output is the categorized disaster information data. Specifically, the server tags the keywords by region and stores them in the corresponding database.

[0882] Step 4:

[0883] When a user inputs the prompt "Check the disaster situation in Tokyo" from a terminal, the server searches the database for the latest disaster information related to Tokyo and provides it to the user. The input is the user's prompt, and the output is the disaster information as a search result. Specifically, the server executes a database query and sends the relevant data to the terminal.

[0884] Step 5:

[0885] Based on the user's request to "deliver goods from point A to point B," the server collects real-time road conditions and traffic information and calculates the optimal delivery route. The input is the delivery request and traffic information from the user, and the output is the optimal delivery route. Specifically, the server uses a map API to obtain the current traffic conditions and calculates the route using a shortest path algorithm.

[0886] Step 6:

[0887] The server inputs data on the scale of the earthquake and damage status into a machine learning model to predict the type and amount of supplies needed. The input is damage status data and past disaster data, and the output is a predicted list of supplies. Specifically, the server runs the machine learning model and stores the prediction results in a database.

[0888] Step 7:

[0889] When a user inputs a prompt from a terminal, such as "Check what supplies will be needed after an earthquake occurs," the server searches the database for a predicted list of supplies and provides it to the user. The input is the user's prompt, and the output is the list of supplies. Specifically, the server executes a database query and sends the predicted result data to the terminal.

[0890] Step 8:

[0891] When a user inputs "Deliver supplies to an area where roads are impassable," the server calculates the optimal delivery route for the drone and sends instructions to the drone management system. The inputs are a prompt from the user and the drone's initial position, and the output is a notification that the delivery has been completed. Specifically, the server sends instructions to the drone management system and monitors the delivery status.

[0892] The above processing steps enable optimization of logistics and rapid support in the event of a disaster.

[0893] 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.

[0894] The present invention provides a system that includes the following five main functions to optimize logistics and provide fast and efficient support during disasters: disaster information aggregation means, delivery route generation means, supply demand forecasting means, supply delivery means, and integrated management means that combines an emotion engine.

[0895] Disaster information collection method

[0896] overview

[0897] The server collects disaster-related information from social media and news sites in real time and compiles it in a centralized manner. This information serves as a foundation for quickly understanding the situation in the affected areas.

[0898] Natural language explanation

[0899] 1. The server obtains the latest disaster information data through the APIs of various social media and news sites at specified time intervals.

[0900] 2. The acquired information is analyzed using a natural language processing engine to extract important keywords and phrases.

[0901] 3. Based on the extracted keywords, disaster information is classified by region and stored in a database.

[0902] Specific examples

[0903] When a request is made from a terminal to "check the disaster situation in Tokyo," the server provides the user with the latest disaster information related to Tokyo from the database.

[0904] Delivery route generation method

[0905] overview

[0906] The server calculates and generates optimal delivery routes to affected areas based on the collected disaster information, enabling fast and efficient delivery of supplies.

[0907] Natural language explanation

[0908] 1. The server collects and analyzes real-time road conditions and traffic information.

[0909] 2. Run an algorithm that generates optimal delivery routes based on the analyzed data.

[0910] 3. Once the optimal route is generated, the user is notified via the terminal.

[0911] Specific examples

[0912] When a user sends a request from their terminal to "deliver goods from point A to point B," the server calculates the optimal delivery route and provides it to the user.

[0913] Material demand forecasting method

[0914] overview

[0915] The server predicts the types and quantities of supplies needed in the affected areas based on the scale of the earthquake and the extent of the damage, making it possible to prepare appropriate supplies in advance.

[0916] Natural language explanation

[0917] 1. The server collects data on the scale of the earthquake and the extent of the damage. The collected data is then input into a machine learning model to predict the types and quantities of supplies needed.

[0918] 2. Save the forecasted material demand results in a database.

[0919] Specific examples

[0920] When a user sends a request from their terminal to "check the supplies needed after an earthquake occurs," the server retrieves a list of predicted supplies and provides it to the user.

[0921] Delivery method (drone delivery)

[0922] overview

[0923] The server provides a means to deliver supplies to disaster areas using drones, making it possible to deliver supplies to areas where roads are impassable.

[0924] Natural language explanation

[0925] 1. The server obtains the location where supplies need to be delivered and the drone's initial location information.

[0926] 2. Calculate the optimal delivery route for the drone and send instructions to the drone management system.

[0927] 3. The drone delivers the goods to the destination and notifies the server that delivery is complete.

[0928] Specific examples

[0929] When a user inputs "Deliver supplies to an area where roads are impassable" into their device, the server calculates the optimal route for the drone and sends it into operation. Once the delivery is complete, the user is notified.

[0930] Emotion Engine

[0931] overview

[0932] The server uses an emotion engine to recognize the user's emotions and adjusts disaster response and distribution of supplies. Based on this information, it is possible to change the type and amount of support needed.

[0933] Natural language explanation

[0934] 1. The device analyzes the user's input and actions through an emotion engine and generates emotion data.

[0935] 2. The server evaluates the user's stress and anxiety level based on the emotional data sent from the emotion engine.

[0936] 3. Based on the assessment results, adjust the allocation of supplies and the type of assistance provided, and generate a list of supplies needed.

[0937] Specific examples

[0938] When a user inputs a request for assistance from their device, the emotion engine analyzes the user's emotional state, and the server adjusts the optimal type and amount of supplies based on the results.

[0939] By integrating these functions, a system will be created that will enable optimized logistics and rapid support during disasters, and will also be able to respond according to the user's emotions.

[0940] The processing flow will be explained below.

[0941] Disaster information collection method

[0942] Processing flow

[0943] Step 1:

[0944] The server sends requests to the APIs of various social networking sites and news sites at specified time intervals to obtain the latest disaster information data.

[0945] Step 2:

[0946] The server temporarily stores the acquired disaster information data in a database.

[0947] Step 3:

[0948] The server inputs the stored data into a natural language processing engine to analyze and extract important keywords and phrases.

[0949] Step 4:

[0950] The server classifies the disaster information by region based on the extracted keywords.

[0951] Step 5:

[0952] The server stores the categorized information in a main database.

[0953] Step 6:

[0954] The user sends a request from the terminal, such as "I would like to check the disaster situation in Tokyo."

[0955] Step 7:

[0956] In response to a request, the server searches the main database for disaster information for the relevant area and provides it to the user.

[0957] Delivery route generation method

[0958] Processing flow

[0959] Step 1:

[0960] The server collects road conditions and traffic information in real time, obtaining data from traffic camera image analysis and traffic information APIs.

[0961] Step 2:

[0962] The server analyzes the collected road condition data and filters out information on road disruptions and congestion.

[0963] Step 3:

[0964] The server runs a delivery route generation algorithm to calculate the optimal route, using Dijkstra's algorithm or A algorithm.

[0965] Step 4:

[0966] The user inputs the starting point and destination of the goods from the terminal.

[0967] Step 5:

[0968] The server recalculates the optimal route based on the input information and provides the generated route information to the user.

[0969] Step 6:

[0970] The terminal displays the calculated optimum route on a user interface.

[0971] Material demand forecasting method

[0972] Processing flow

[0973] Step 1:

[0974] The server collects data on the scale of earthquakes and the extent of damage, obtaining the data from earthquake information APIs and news sites.

[0975] Step 2:

[0976] The server then inputs the collected data into a machine learning model to predict demand for supplies, using algorithms such as regression analysis and random forests.

[0977] Step 3:

[0978] The server stores the results of the predicted material demand in a database.

[0979] Step 4:

[0980] The user sends a request to the server from the terminal to "check supplies needed after an earthquake occurs."

[0981] Step 5:

[0982] The server retrieves the prediction results from the database and provides them to the user.

[0983] Delivery method (drone delivery)

[0984] Processing flow

[0985] Step 1:

[0986] The server obtains the location where supplies need to be delivered and the drone's initial location information.

[0987] Step 2:

[0988] The server calculates the optimal delivery route for the drone, using algorithms such as the Bellman-Ford algorithm.

[0989] Step 3:

[0990] The server sends the calculated route information to the drone management system.

[0991] Step 4:

[0992] The drone follows the instructed route and delivers the goods to their destination.

[0993] Step 5:

[0994] The drone reaches its destination and delivers the goods.

[0995] Step 6:

[0996] The drone notifies the server that delivery is complete.

[0997] Step 7:

[0998] The server records the delivery completion information in a database and notifies the user.

[0999] Emotion Engine

[1000] Processing flow

[1001] Step 1:

[1002] The terminal acquires data entered by the user and behavioral data.

[1003] Step 2:

[1004] The device passes the acquired data to an emotion engine that analyzes the user's emotional state, identifying the user's stress and anxiety levels.

[1005] Step 3:

[1006] The terminal transmits the analysis results (emotion data) to the server.

[1007] Step 4:

[1008] The server adjusts the support plan based on the received emotion data, changing the need for supplies and priorities according to the user's emotions.

[1009] Step 5:

[1010] The server stores the adjusted supply lists and support plans in a database and recalculates delivery routes and supply quantities as needed.

[1011] Step 6:

[1012] When a user makes a support request from a terminal, the server provides optimal support content based on the user's emotions.

[1013] This enables the server to provide optimal supplies and support that take into account the user's stress and anxiety, making disaster response even more effective.

[1014] Example 2

[1015] 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."

[1016] Conventional disaster support systems have been unable to provide centralized and efficient support because they collect disaster information, deliver supplies, and understand emotions separately. Furthermore, they have also been unable to adequately deliver supplies to areas where roads are impassable or adjust the distribution of supplies according to the user's emotions.

[1017] 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.

[1018] In this invention, the server includes means for collecting and aggregating disaster information from social media and news sites in real time and analyzing it using natural language processing technology, means for generating optimal delivery routes based on the aggregated information, means for using a machine learning model to predict the supplies and their quantities needed based on the scale of the earthquake and the extent of the damage, means for delivering supplies using drones, means for coordinating the distribution of supplies and support based on user emotion data using an emotion engine, and means for integrating and managing all of the above means. This enables fast and efficient support based on accurate information in real time during disasters, enables supplies to be delivered to areas where roads are impassable, and enables responses based on user emotion.

[1019] "SNS and news sites" is a general term for social networking services that allow users to share and disseminate information online, and websites that provide the latest news articles.

[1020] "Real-time" refers to data acquisition and processing occurring almost immediately, providing current information without delay.

[1021] "Disaster information" includes all information related to natural disasters and man-made disasters, such as the occurrence status, scale of damage, area of ​​impact, and evacuation information.

[1022] "Means of collection and aggregation" refers to a system or method for automatically obtaining necessary information from designated data sources and managing it centrally.

[1023] "Natural language processing technology" refers to technology that enables computers to understand, analyze, and process human language, and includes technologies such as text mining and sentiment analysis.

[1024] "Means of analysis" refers to software or algorithms used to analyze collected information and extract useful data.

[1025] "Means for generating optimal delivery routes" refers to methods or algorithms for calculating the most efficient travel path from a given point to a destination.

[1026] A "machine learning model" refers to an algorithm or system that learns from large amounts of data and makes predictions and classifications for new data.

[1027] "Supplies" refers to various resources needed in the event of a disaster, such as food, water, medicine, clothing, and fuel.

[1028] A "drone" is a type of unmanned aerial vehicle that flies remotely or autonomously and transports goods, among other tasks.

[1029] An "emotion engine" refers to software or algorithms that analyze user input and behavioral data to infer emotional states.

[1030] "Means of integration and management" refers to methods and systems for centrally controlling and effectively operating multiple different systems and processes.

[1031] The system of the present invention provides the following functions for the purpose of providing prompt and efficient support in the event of a disaster. These functions are realized based on the roles of the server, terminal, and user.

[1032] Disaster information collection method

[1033] In the system, the server obtains real-time disaster information data at specified intervals through the APIs of various social media sites and news sites. Specifically, it uses the APIs of Twitter and news providers. For example, it calls Twitter's " / v1 / tweets / search" endpoint to obtain the latest posts. The obtained information is analyzed using Natural Language Processing (NLP) technology, such as the Google Cloud Natural Language API. Important keywords and phrases are extracted through the analysis, and based on this, disaster information is classified by region and stored in a MySQL database. Specifically, disaster information related to Tokyo is classified as "Tokyo" or "earthquake."

[1034] When a user sends a request from their device saying, "I want to check the disaster situation in Tokyo," the server retrieves the latest disaster information related to Tokyo from the database and provides it to the user.

[1035] Prompt Sentence Examples

[1036] "Please tell me the latest disaster information for Tokyo."

[1037] Delivery route generation method

[1038] The server collects and analyzes real-time road conditions and traffic information. This information is collected using the Google Maps API, for example, by calling the " / maps / api / directions" endpoint to obtain traffic data. The collected data is then used to generate optimal delivery routes using Dijkstra and A algorithms. The generated route information is then sent to the user's device.

[1039] When a user sends a request from their terminal to "deliver goods from point A to point B," the server calculates the optimal delivery route and provides it to the user.

[1040] Prompt Sentence Examples

[1041] "Deliver supplies from point A to point B using the optimal route."

[1042] Material demand forecasting method

[1043] The server collects data indicating the scale of the earthquake and the extent of the damage, and uses that data to predict the type and amount of supplies needed. The collected data is input into a machine learning model (for example, a TensorFlow model) to predict demand for supplies. Earthquake information is collected using the APIs of the Japan Meteorological Agency and disaster information providers, for example, from the " / v1 / earthquake / info" endpoint.

[1044] When a user sends a request from their terminal to "check the supplies needed after an earthquake occurs," the server retrieves a list of predicted supplies and provides it to the user.

[1045] Prompt Sentence Examples

[1046] "What supplies will I need after an earthquake?"

[1047] Delivery method (drone delivery)

[1048] The server acquires the location where the goods need to be delivered and the drone's initial position information, and calculates the optimal delivery route. The calculated route is sent to the drone management system, and the drone delivers the goods to the destination. After the delivery is complete, the server notifies the user.

[1049] When a user inputs "Deliver supplies to an area where roads are impassable" into their device, the server calculates the optimal drone route and executes it. Once the delivery is complete, the user is notified.

[1050] Prompt Sentence Examples

[1051] "Deliver supplies by drone to areas where roads are impassable."

[1052] Emotion Engine

[1053] The device analyzes the user's input and actions through an emotion engine to generate emotional data. The emotion engine uses technologies such as IBM Watson Tone Analyzer to analyze the user's emotional state. The server evaluates the user's stress and anxiety levels based on the emotional data sent from the emotion engine (e.g., anxiety level 80%) and adjusts the distribution of supplies and the type of assistance provided.

[1054] When a user inputs a request for assistance from their device, the server analyzes their emotional state and adjusts the optimal type and amount of supplies.

[1055] Prompt Sentence Examples

[1056] "Adjust your support needs based on your current emotional state."

[1057] By integrating these measures, it is possible to optimize logistics during disasters, provide rapid assistance, and respond to users' emotions.

[1058] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1059] Disaster information collection method

[1060] Step 1:

[1061] The server obtains the latest disaster information data through the APIs of social media and news sites at specified time intervals.

[1062] Input: API endpoint (e.g. " / v1 / tweets / search" for Twitter API)

[1063] Output: Latest disaster information data (e.g. tweets and news article text)

[1064] Step 2:

[1065] The server sends the acquired disaster information data to a natural language processing engine (e.g., Google Cloud Natural Language API) to extract important keywords and phrases.

[1066] Input: Acquired disaster information data

[1067] Output: Extracted keywords and phrases (e.g., "Tokyo" or "earthquake")

[1068] Step 3:

[1069] The server categorizes the information by region based on the extracted keywords and stores it in a MySQL database.

[1070] Input: Extracted keywords or phrases

[1071] Output: Disaster information data categorized by region (e.g., data related to Tokyo)

[1072] Delivery route generation method

[1073] Step 1:

[1074] The server collects real-time road conditions and traffic information.

[1075] Input: Traffic information API endpoint (e.g., " / maps / api / directions" for the Google Maps API)

[1076] Output: Current road conditions and traffic information

[1077] Step 2:

[1078] The server executes a delivery route generation algorithm (e.g., Dijkstra or A algorithm) based on the collected traffic data to calculate the optimal delivery route.

[1079] Input: Real-time road conditions and traffic information

[1080] Output: Optimal delivery route (e.g., route from point A to point B)

[1081] Step 3:

[1082] The server notifies the user's terminal of the calculated optimum delivery route.

[1083] Input: Optimal delivery route

[1084] Output: Notification to the terminal (e.g. "The best delivery route is via XX")

[1085] Material demand forecasting method

[1086] Step 1:

[1087] The server collects data showing the scale of the earthquake and the extent of the damage.

[1088] Input: Earthquake information API endpoint (e.g., Japan Meteorological Agency API " / v1 / earthquake / info")

[1089] Output: Detailed information about the earthquake (e.g., magnitude, epicenter, damage status)

[1090] Step 2:

[1091] The server inputs the collected earthquake data into a machine learning model (e.g., a TensorFlow model) to predict the type and quantity of supplies needed.

[1092] Input: Earthquake details

[1093] Output: Predicted demand data (e.g., "Drinking water: 500L, Food: 300kg, Blankets: 200")

[1094] Step 3:

[1095] The server stores the predicted material demand data in a database.

[1096] Input: Forecasted material demand data

[1097] Output: Material demand data stored in a database

[1098] Delivery method (drone delivery)

[1099] Step 1:

[1100] The server obtains the location where supplies need to be delivered and the drone's initial location information.

[1101] Input: User's delivery request (e.g., "Deliver supplies from location A to location B")

[1102] Output: Delivery location and initial drone position

[1103] Step 2:

[1104] The server calculates the optimal delivery route based on the delivery point and the drone's initial location information.

[1105] Input: Delivery point and initial drone location information

[1106] Output: Optimal delivery route

[1107] Step 3:

[1108] The server sends the calculated route to the drone management system, which then operates the drone.

[1109] Input: Optimal delivery route

[1110] Output: Drone operation instructions

[1111] Step 4:

[1112] Once the drone has delivered the goods, the server will send a delivery completion notification to the user.

[1113] Input: Delivery completion report from drone

[1114] Output: Delivery completion notification to user

[1115] Emotion Engine

[1116] Step 1:

[1117] The device collects user input and behavioral data and sends it to the emotion engine.

[1118] Input: User input and behavioral data (e.g., text such as "I'm very anxious")

[1119] Output: Sending data to the emotion engine

[1120] Step 2:

[1121] The server receives the emotion data generated by the emotion engine and evaluates the user's stress and anxiety level.

[1122] Input: Emotion data from the emotion engine (e.g., "Anxiety level 80%)

[1123] Output: Assessed stress and anxiety levels

[1124] Step 3:

[1125] The server adjusts the type and quantity of supplies based on the evaluation results and generates a list of required supplies.

[1126] Input: Assessed stress and anxiety levels

[1127] Output: Adjusted supply list (e.g., more medkits and stress relief items)

[1128] The above are the specific processing steps of the invention, and an explanation has been given of what input data is used in each step and what output is obtained.

[1129] (Application example 2)

[1130] 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."

[1131] Conventional disaster logistics systems have difficulty gathering information in real time and generating appropriate delivery routes, and have also been unable to adequately predict the demand for supplies. Another problem is that assistance provided does not take into account the emotions and conditions of disaster victims. This makes it difficult to provide prompt and efficient assistance, and there is a risk that necessary support for disaster victims may be delayed.

[1132] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1133] In this invention, the server includes means for collecting and aggregating disaster information from social media and news sites in real time, means for generating optimal delivery routes based on the aggregated information, means for predicting the supplies needed and their quantities based on the scale of the earthquake and the extent of the damage, means for delivering supplies using autonomous vehicles, and means for analyzing the emotional state of users using emotion analysis technology and adjusting the content of support, thereby enabling fast and efficient delivery of supplies to disaster-stricken areas and providing appropriate support that takes into account the emotional state of the victims.

[1134] A "disaster information aggregation method" is a method for collecting disaster-related information from social media and news sites in real time and consolidating it in a centralized manner.

[1135] The "delivery route generation means" is a means for calculating and generating the optimal delivery route to the disaster-stricken area based on the collected disaster information.

[1136] A "materials demand forecasting method" is a method that uses machine learning models to predict the supplies and quantities needed based on the scale of the earthquake and the extent of the damage.

[1137] An "autonomous vehicle" is a vehicle that can drive and deliver goods automatically without human operation.

[1138] "Emotion analysis technology" is a technology that analyzes the user's emotional state and adjusts appropriate support and distribution of supplies based on the results.

[1139] "Integrated management means" refers to a means for managing the above-mentioned multiple means in an integrated manner and implementing optimal support activities.

[1140] "Road conditions and traffic information" refers to general traffic-related information, such as road congestion and closed-to-traffic sections, provided in real time.

[1141] "Natural language processing technology" is a technology that uses computers to analyze human language and extract and understand information such as meaning and emotions.

[1142] The present invention is a system for optimizing logistics during disasters and providing fast and efficient support. This system includes a disaster information aggregation unit, a delivery route generation unit, a supply demand forecasting unit, a supply delivery unit using autonomous vehicles, a support content adjustment unit using emotion analysis technology, and a unit for integrating and managing these units. The implementation methods for each unit are described in detail below.

[1143] Disaster information collection method

[1144] The server collects disaster information from social media and news sites in real time and compiles it in a centralized manner. Specifically, it obtains the latest disaster information data through the APIs of social media and news sites, analyzes it using natural language processing technology, and extracts important information. This information serves as the basis for quickly understanding the situation in disaster-stricken areas.

[1145] Specific examples

[1146] When a request to "check the latest disaster information" is made from a terminal, the server searches the database for the latest disaster information and provides it to the user.

[1147] Delivery route generation method

[1148] The server calculates and generates optimal delivery routes to affected areas based on the collected disaster information. It uses map services such as Google Maps API to collect and analyze real-time road conditions and traffic information to generate optimal delivery routes.

[1149] Specific examples

[1150] When a user sends a request from their terminal to "deliver supplies from their current location to disaster area B," the server calculates the optimal delivery route and provides it to the user.

[1151] Material demand forecasting method

[1152] The server collects data on the scale of the earthquake and the extent of the damage, inputs it into a machine learning model, and predicts the types and quantities of supplies needed. Based on this result, it generates a list of specific supplies needed for relief.

[1153] Specific examples

[1154] When a user sends a request from their terminal to "check the supplies needed after an earthquake occurs," the server retrieves a list of predicted supplies and provides it to the user.

[1155] Autonomous vehicle delivery method

[1156] The server provides a means to deliver supplies to disaster areas using autonomous vehicles. The autonomous vehicles drive along optimal routes calculated based on the situation and traffic information, and deliver supplies to disaster areas. These autonomous vehicles can also work in conjunction with drones to deliver supplies to areas where roads are impassable.

[1157] Specific examples

[1158] When a user types "deliver goods to an area where roads are impassable" into their device, the server calculates the optimal route and puts the autonomous vehicle into operation. Once the delivery is complete, the user is notified.

[1159] A method for adjusting support content using emotion analysis technology

[1160] The device uses emotion analysis technology to analyze the user's input and behavior to generate emotional data, which the server uses to assess the user's stress and anxiety levels and adjust the distribution of supplies and assistance.

[1161] Specific examples

[1162] When a user inputs a request for assistance from a terminal, emotion analysis technology analyzes the user's emotional state, and the server adjusts the optimal type and quantity of supplies based on the results.

[1163] Prompt Sentence Examples

[1164] Here are some examples of prompts for generative AI models:

[1165] "Get the latest disaster information in real time and analyze the situation in the affected areas."

[1166] "Generate the optimal delivery route from the current location to disaster area B, taking traffic information into account."

[1167] "It analyzes users' emotional data to assess their stress and anxiety levels."

[1168] This will enable the rapid and efficient delivery of supplies to disaster-stricken areas, and will also realize a system that can provide appropriate support taking into account the emotional state of the victims.

[1169] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1170] Step 1:

[1171] The server collects disaster information from social media and news sites at specified intervals.

[1172] Input: APIs of various social media and news sites.

[1173] Data processing: The acquired information is parsed in JSON format and analyzed using a natural language processing engine.

[1174] Output: A dataset containing important information.

[1175] Specifically, the server sends API requests to social media and news sites, analyzes the disaster information received in response, and uses a natural language processing engine to extract keywords and important phrases, which are then stored in a database.

[1176] Step 2:

[1177] The server calculates and generates the optimal delivery route to the affected area based on the collected disaster information.

[1178] Input: Disaster information dataset, Google Maps API.

[1179] Data calculation: Uses Google Maps API to obtain real-time road conditions and calculate the optimal route.

[1180] Output: Optimal delivery route.

[1181] Specifically, the server uses an algorithm to calculate the optimal delivery route based on a disaster information dataset, and then obtains road information from the Google Maps API to optimize the route.

[1182] Step 3:

[1183] The server predicts the types and quantities of supplies needed based on the scale of the earthquake and the extent of the damage.

[1184] Input: Earthquake magnitude data, damage status data.

[1185] Data computation: Input data into machine learning models and run predictive algorithms.

[1186] Output: List of supplies needed.

[1187] Specifically, the server uses a machine learning model to generate a list of needed supplies based on data indicating the scale of the earthquake and the extent of the damage.

[1188] Step 4:

[1189] The server will use autonomous vehicles to deliver supplies to disaster areas.

[1190] Inputs: Optimal delivery route, initial position information of the autonomous vehicle, and a list of supplies.

[1191] Data processing: Create a loading plan for supplies based on delivery routes.

[1192] Output: Delivery instructions, loading completion notification.

[1193] Specifically, the server sends the optimal delivery route and loading plan to the autonomous vehicle, and the vehicle delivers the goods according to those instructions.

[1194] Step 5:

[1195] The terminal analyzes the user's input and actions using emotion analysis technology to generate emotion data.

[1196] Input: User input data.

[1197] Data Computing: Analyzes sentiment using a natural language processing engine.

[1198] Output: Emotion data.

[1199] Specifically, the terminal sends the user's input to an emotion analysis engine, which generates emotion data as a result.

[1200] Step 6:

[1201] The server assesses the user's stress and anxiety levels based on emotional data and adjusts the distribution of supplies and support.

[1202] Input: Emotion data, supply list.

[1203] Data calculation: Optimize support content based on emotional data.

[1204] Output: Coordinated supply list, support plan.

[1205] Specifically, the server analyzes emotional data and dynamically adjusts the distribution of supplies and the content of support according to the user's level of stress and anxiety.

[1206] Through the above processing steps, efficient and rapid delivery of supplies during disasters and support that takes into account the emotional state of victims can be achieved.

[1207] 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.

[1208] 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.

[1209] 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.

[1210] [Third embodiment]

[1211] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1212] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1213] 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).

[1214] 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.

[1215] 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.

[1216] 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).

[1217] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1218] 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.

[1219] 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.

[1220] 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.

[1221] 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.

[1222] 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."

[1223] The present invention provides a system that includes the following four main functions to optimize logistics and provide fast and efficient support during disasters: disaster information collection means, delivery route generation means, supply demand forecasting means, and supply delivery means.

[1224] Disaster information collection method

[1225] overview

[1226] The server collects disaster-related information from social media and news sites in real time and compiles it in a centralized manner. This information serves as a foundation for quickly understanding the situation in the affected areas.

[1227] Natural language explanation

[1228] 1. The server obtains the latest disaster information through the APIs of various social media and news sites at specified intervals.

[1229] 2. The acquired information is analyzed using a natural language processing engine to extract important keywords and phrases.

[1230] 3. Based on the extracted keywords, disaster information is classified by region and stored in a database.

[1231] Specific examples

[1232] When a request to "check the disaster situation in Tokyo" is made from a terminal, the server provides the user with the latest disaster information related to Tokyo from the database.

[1233] Delivery route generation method

[1234] overview

[1235] The server calculates and generates optimal delivery routes to affected areas based on the collected disaster information, enabling fast and efficient delivery of supplies.

[1236] Natural language explanation

[1237] 1. The server collects and analyzes real-time road conditions and traffic information.

[1238] 2. Based on the analyzed data, an algorithm is run to generate the optimal delivery route.

[1239] 3. Once the optimal route is generated, the user is notified via the terminal.

[1240] Specific examples

[1241] When a user sends a request from their terminal to "deliver goods from point A to point B," the server calculates the optimal delivery route and provides it to the user.

[1242] Material demand forecasting method

[1243] overview

[1244] The server predicts the types and quantities of supplies needed in the affected areas based on the scale of the earthquake and the extent of the damage, making it possible to prepare appropriate supplies in advance.

[1245] Natural language explanation

[1246] 1. The server collects data indicating the scale of the earthquake and the extent of the damage.

[1247] 2. Input the collected data into a machine learning model to predict the types and quantities of supplies needed.

[1248] 3. The prediction results are stored in a database and can be viewed by the user at any time.

[1249] Specific examples

[1250] When a user sends a request from their terminal to "check the supplies needed after an earthquake occurs," the server retrieves a list of predicted supplies and provides it to the user.

[1251] Delivery method (drone delivery)

[1252] overview

[1253] The server provides a means to deliver supplies to disaster areas using drones, making it possible to deliver supplies to areas where roads are impassable.

[1254] Natural language explanations

[1255] 1. The server obtains the location where supplies need to be delivered and the initial position of the drone.

[1256] 2. Calculate the optimal delivery route for the drone and send instructions to the drone management system.

[1257] 3. The drone delivers the goods to the destination and notifies the server that delivery is complete.

[1258] Specific examples

[1259] When a user inputs "Deliver supplies to an area where roads are impassable" into their device, the server calculates the optimal route for the drone and sends it into operation. Once the delivery is complete, the user is notified.

[1260] By integrating these functions, a system will be created to optimize logistics and provide rapid support during disasters.

[1261] The processing flow will be explained below.

[1262] Disaster information collection method

[1263] Processing flow

[1264] Step 1:

[1265] The server sends requests to the APIs of various social networking sites and news sites at specified time intervals to obtain the latest disaster information data.

[1266] Step 2:

[1267] The server temporarily stores the acquired disaster information data in a database.

[1268] Step 3:

[1269] The server inputs the stored data into a natural language processing engine to extract important keywords and phrases.

[1270] Step 4:

[1271] The server categorizes disaster information by region based on the extracted keywords and stores the categorized information in the main database.

[1272] Step 5:

[1273] The user sends a request from the terminal, such as "I would like to check the disaster situation in Tokyo."

[1274] Step 6:

[1275] In response to a request, the server searches the main database for disaster information for the relevant area and provides it to the user.

[1276] Delivery route generation method

[1277] Processing flow

[1278] Step 1:

[1279] The server collects road conditions and traffic information in real time, using image analysis from traffic cameras and data from traffic information APIs.

[1280] Step 2:

[1281] The server analyzes the collected road condition data and filters out information on road disruptions and congestion.

[1282] Step 3:

[1283] The server runs a delivery route generation algorithm to calculate the optimal route, using Dijkstra's algorithm or A algorithm.

[1284] Step 4:

[1285] The user inputs the starting point and destination of the goods from the terminal.

[1286] Step 5:

[1287] The server recalculates the optimal route based on the input information and provides the generated route information to the user.

[1288] Step 6:

[1289] The terminal displays the calculated optimum route on a user interface.

[1290] Material demand forecasting method

[1291] Processing flow

[1292] Step 1:

[1293] The server collects data on the scale and damage caused by earthquakes, specifically from earthquake information APIs and news sites.

[1294] Step 2:

[1295] The server inputs the collected data into a machine learning model to predict demand for goods, using algorithms such as regression analysis and random forests.

[1296] Step 3:

[1297] The server stores the results of the predicted material demand in a database.

[1298] Step 4:

[1299] The user sends a request to the server from the terminal to "check supplies needed after an earthquake occurs."

[1300] Step 5:

[1301] The server retrieves the prediction results from the database and provides them to the user.

[1302] Delivery method (drone delivery)

[1303] Processing flow

[1304] Step 1:

[1305] The server obtains the location where supplies need to be delivered and the drone's initial location information.

[1306] Step 2:

[1307] The server calculates the optimal delivery route for the drone, using algorithms such as the Bellman-Ford algorithm.

[1308] Step 3:

[1309] The server sends the calculated route information to the drone management system.

[1310] Step 4:

[1311] The drone follows the instructed route and delivers the goods to their destination.

[1312] Step 5:

[1313] The drone reaches its destination and delivers the goods.

[1314] Step 6:

[1315] The drone notifies the server that delivery is complete.

[1316] Step 7:

[1317] The server records the delivery completion information in a database and notifies the user.

[1318] Example 1

[1319] 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."

[1320] When disasters such as earthquakes and fires occur, the challenge is to quickly and accurately collect information and deliver appropriate relief supplies to affected areas. Effective logistics is particularly difficult when roads are impassable or information is in disarray. Existing systems are prone to delays and false reports at each stage of information collection, analysis, and supply delivery, making it difficult to provide efficient relief.

[1321] 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.

[1322] In this invention, the server includes a means for collecting disaster information in real time from information sources such as social media and news sites, a means for analyzing the collected disaster information using natural language processing technology and extracting important information, and a means for generating optimal delivery routes based on the extracted information, thereby enabling a fast and efficient disaster response and optimization of logistics.

[1323] "SNS" stands for Social Networking Service, a platform for users to share information and interact online.

[1324] A "news site" is a website that provides news coverage of current events and happenings on the Internet.

[1325] "Disaster information" refers to information about natural disasters such as earthquakes, typhoons, and fires, as well as man-made disasters.

[1326] "Real-time" refers to data acquisition and processing occurring almost simultaneously with real time.

[1327] "Natural language processing technology" is a technology for analyzing and processing human language using a computer, and is used to understand the meaning and intent of text.

[1328] The "optimal delivery route" refers to the most efficient and safe route for delivering goods, taking into account time, distance, and cost.

[1329] The "magnitude of an earthquake" is an indicator of the amount of energy released and the extent of its impact when an earthquake occurs.

[1330] "Damage situation" is information that indicates the extent of human and material damage when a disaster occurs.

[1331] An "unmanned aerial vehicle" is a flying machine that flies remotely or autonomously and is used for transporting goods, etc.

[1332] A "database" is a computer system for efficiently storing, searching, and managing large amounts of data.

[1333] "Traffic information" refers to information that indicates the status of transportation routes such as roads and railways, and includes information on traffic congestion and road closures.

[1334] The present invention is a system for optimizing logistics in the event of a disaster and providing prompt and efficient support. This system operates in cooperation with three parties: a server, a terminal, and a user.

[1335] Server Roles

[1336] Information collection and analysis

[1337] The server collects disaster information in real time from sources such as social media and news sites. This information is collected using, for example, the Twitter API and RSS feeds from various news sites. The collected information is analyzed using a natural language processing engine (e.g., spaCy, BERT) to extract important keywords and phrases. This analysis process identifies important information such as "evacuation shelters," "water outages," and "traffic disruptions."

[1338] Data Classification and Retention

[1339] The extracted important information is categorized by region and stored in a database (e.g., MongoDB, MySQL), providing the server with a basis for understanding the situation in real time and taking necessary actions.

[1340] Generate delivery routes

[1341] The server runs an algorithm (e.g., the Dijkstra algorithm) to generate optimal delivery routes based on collected disaster information and real-time road conditions. Specifically, it uses Google Maps API and HERE Maps API to collect traffic information and calculates the shortest and safest route based on this information.

[1342] Forecasting demand for goods

[1343] The server collects data on the scale and damage of the earthquake, and inputs this data into a machine learning model (e.g., TensorFlow, Scikit-learn) to predict the types and quantities of supplies needed. For example, if a large earthquake occurs, it is expected that demand for food, water, medicine, etc. will increase.

[1344] Drone delivery of supplies

[1345] The server acquires information on the drone's initial position and the location where delivery is required, and calculates the optimal delivery route. The calculated route is sent to the drone management system, which instructs the unmanned aerial vehicle to deliver the goods to the destination. Once the delivery is complete, the server receives the information and notifies the user.

[1346] Device Role

[1347] The terminal provides an interface for users to access the system, through which they can check disaster information and make delivery requests.

[1348] User Roles

[1349] Users send requests to the server via their terminals, such as "Check the disaster situation in Tokyo," "Deliver supplies from point A to point B," "Check supplies needed after an earthquake occurs," and "Deliver supplies to areas where roads are impassable." The server receives these requests, performs the necessary processing, and provides the results to the user.

[1350] Specific examples

[1351] Example prompt sentence:

[1352] "To optimize logistics during disasters, collect disaster information from social media and news sites, generate optimal delivery routes, and deliver supplies to affected areas."

[1353] These explanations clarify the specific embodiments of the present invention. A system is constructed that centrally manages a series of processes, from collecting and analyzing disaster information, creating optimal delivery routes, predicting demand for supplies, and delivering supplies by drone. This enables a rapid and efficient response in the event of a disaster.

[1354] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1355] Program processing steps and detailed explanation

[1356] Disaster information collection method

[1357] Step 1: Gather information

[1358] The server obtains the latest disaster information through the APIs of social media and news sites at specified intervals.

[1359] Input: Data obtained from APIs of various social media and news sites (e.g., Twitter tweets, news articles)

[1360] Specific operation: The server uses the Twitter API key to collect tweets with keywords such as "earthquake," "evacuation," and "support," and retrieves the latest articles from the news site's RSS feed.

[1361] Output: Raw data (text data)

[1362] Step 2: Natural Language Processing Analysis

[1363] The server inputs the collected text data into a natural language processing technology engine (e.g., spaCy, BERT) to extract important keywords and phrases.

[1364] Input: Raw data acquired

[1365] Specific operation: The server uses a natural language processing engine to analyze the text data and uses tokenization, stemming, and entity recognition to identify important information such as "shelters," "water outages," and "traffic disruptions."

[1366] Output: Extracted important keywords and phrases

[1367] Step 3: Classify and store data

[1368] Based on the extracted keywords, the server classifies disaster information by region and stores it in a database.

[1369] Input: Extracted important keywords and phrases

[1370] Specific operation: The server classifies information based on place names such as "Tokyo" and "Osaka" and stores it in a database such as MongoDB or MySQL.

[1371] Output: Database entries for disaster information categorized by region

[1372] Delivery route generation method

[1373] Step 1: Collect road conditions

[1374] The server collects real-time road conditions and traffic information using the Google Maps API and HERE Maps API.

[1375] Input: Real-time road condition data

[1376] Specific operation: The server collects information such as traffic congestion and road closures through the API and plots it on a map.

[1377] Output: Latest traffic information dataset

[1378] Step 2: Data analysis

[1379] The server analyzes the collected data and runs an algorithm (e.g., Dijkstra algorithm) to generate optimal delivery routes.

[1380] Input: Latest traffic information dataset

[1381] Specific operation: The server calculates the distance and time between each delivery point, evaluates multiple routes, and identifies the shortest and safest route.

[1382] Output: Optimal delivery route information

[1383] Step 3: Notification of results

[1384] Once the optimal route has been generated, the server notifies the user via the terminal.

[1385] Input: Optimal delivery route information

[1386] Specific operation: The server sends the generated route data in JSON format to the terminal and notifies the user.

[1387] Output: Route information provided to the user

[1388] Material demand forecasting method

[1389] Step 1: Data collection

[1390] The server collects data from the USGS and the Japan Meteorological Agency indicating the scale of the earthquake and the extent of the damage.

[1391] Input: Earthquake magnitude and damage data

[1392] Specific operation: The server obtains data such as the earthquake's epicenter, magnitude, and scale of damage through the API.

[1393] Output: Earthquake and damage dataset

[1394] Step 2: Input to the machine learning model

[1395] The server inputs the collected data into a machine learning model (e.g., TensorFlow, Scikit-learn) to predict the type and quantity of supplies needed.

[1396] Input: Earthquake and damage dataset

[1397] How it works: The server uses data from past disasters to use machine learning models to predict demand for food, water, medicine, etc.

[1398] Output: List of predicted supplies

[1399] Step 3: Save the prediction results

[1400] The server stores the prediction results in a database so that users can check them at any time.

[1401] Input: Forecasted supplies list

[1402] Specific operation: The server updates the prediction results in real time and displays them in the database and on the dashboard.

[1403] Output: Stored supply forecast data

[1404] Delivery method (drone delivery)

[1405] Step 1: Obtaining delivery points and drone positions

[1406] The server uses GPS data to obtain the location where supplies need to be delivered and the drone's initial position.

[1407] Input: Delivery point and initial drone position data

[1408] Specific operation: The server collects the latitude and longitude information of the required delivery point, as well as the drone's current location information.

[1409] Output: Geolocation dataset

[1410] Step 2: Route calculation

[1411] The server calculates the optimal delivery route for the drone and sends instructions to the drone management system.

[1412] Input: Geolocation dataset

[1413] How it works: The server uses a 3D mapping algorithm to calculate a route that avoids obstacles and takes into account wind direction and weather conditions.

[1414] Output: Optimal drone delivery route

[1415] Step 3: Delivery notification

[1416] The server notifies the user once the drone has delivered the goods to the destination and received notification that delivery has been completed.

[1417] Input: Delivery completion notification from drone

[1418] Specific operation: The server monitors the delivery status in real time, and after delivery is completed, it records the status and notifies the user via email or app.

[1419] Output: Delivery completion notification to user

[1420] Through the above processing steps, the system of the present invention realizes rapid and efficient disaster response and optimization of logistics.

[1421] (Application example 1)

[1422] 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."

[1423] Logistics during disasters is a key element for providing fast and efficient support to disaster-stricken areas. However, traditional logistics systems often lack real-time information and fragmented information, making it difficult to generate optimal delivery routes and forecast supply demand. Furthermore, when roads were impassable, delivery of supplies could be significantly delayed. Furthermore, logistics center staff and managers lacked the means to monitor the situation in real time and respond quickly. To resolve these situations, a more integrated management system is needed.

[1424] 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.

[1425] In this invention, the server includes a means for collecting and aggregating disaster information from social media and news sites in real time, a means for generating optimal delivery routes based on the aggregated information, a means for predicting the supplies and their quantities needed based on the scale of the earthquake and the extent of the damage, a means for logistics center staff and managers to monitor the situation in real time via smartphone and take swift action, a means for delivering supplies using drones, and a means for integrating and managing all of the above means, thereby enabling optimized logistics and rapid support during disasters.

[1426] "SNS" is an abbreviation for social networking service, an online platform for users to share information and communicate.

[1427] A "news site" is a website that provides news articles over the Internet.

[1428] "Real-time" refers to the immediacy with which data and information are collected, analyzed, and displayed immediately.

[1429] "Disaster information" refers to information that indicates the status and impact of natural disasters such as earthquakes and floods.

[1430] A "logistics center" is a facility where supplies are stored, sorted, and prepared for delivery.

[1431] A "smartphone" is a mobile phone device with advanced computing power and connectivity.

[1432] "Staff" refers to employees working in an organization or facility.

[1433] A "manager" is a position that manages and supervises an organization or team.

[1434] A "delivery route" refers to the optimal route for transporting goods, calculated to minimize time and distance.

[1435] "Earthquake magnitude" is a numerical indicator that shows the amount of energy an earthquake generates.

[1436] "Damage status" is information indicating the damage and state of damage caused by a disaster.

[1437] "Supplies" refers to support items such as food, water, medicine, and cold weather gear that are needed in the event of a disaster.

[1438] "Demand forecasting" is the act of predicting how much material will be needed in the future.

[1439] A "drone" is an unmanned aircraft that can be remotely controlled and fly autonomously.

[1440] "Integrated management" refers to the integration and centralized management of multiple functions and methods.

[1441] The present invention relates to a system for optimizing logistics at a logistics center during a disaster and providing prompt and efficient support. The system has the following main functions:

[1442] 1. Disaster information collection method

[1443] The server collects and aggregates disaster information in real time from social media and news sites. For example, it uses the APIs of social media sites and RSS feeds from news sites. The collected information is analyzed within the server using a natural language processing engine to extract important keywords and phrases. This allows the situation in the affected areas to be quickly grasped.

[1444] 2. Delivery route generation method

[1445] The server generates the optimal delivery route based on the collected disaster information and real-time road and traffic information. For example, it obtains the current traffic situation using a map API and calculates the optimal route using a shortest route algorithm. This information is provided to users so they can check it on their smartphones.

[1446] 3. Material demand forecasting methods

[1447] The server inputs data such as the scale of the earthquake and the extent of the damage into a machine learning model to predict the type and quantity of supplies needed in the affected area. For example, an AI model is used to compare past disaster data with the current disaster situation to predict demand. The predicted supply list is then displayed in real time on a smartphone app for staff and managers to check.

[1448] 4. Delivery of goods (drone delivery)

[1449] The server instructs drones to deliver goods to areas where roads are impassable. For example, it calculates the optimal delivery route based on the specified location and the drone's initial position, and sends instructions to the drone management system. Once the delivery is complete, the information is notified to the server, and then to a smartphone.

[1450] Hardware and software used

[1451] Smartphones: Used by staff and managers.

[1452] Drones: Used to deliver supplies.

[1453] Natural language processing engine: Used to analyze collected disaster information.

[1454] Map API: Get current traffic conditions and use them to calculate the shortest route.

[1455] Machine learning models: Used to forecast demand for supplies.

[1456] Drone management system: Used to manage drone deliveries.

[1457] Specific examples

[1458] For example, when a disaster occurs, the server instantly collects disaster information from social media and news sites, and when a user inputs the prompt "Check the disaster situation in Tokyo," it provides the latest disaster information for that area. Furthermore, when a user inputs "Deliver supplies from point A to point B," the server calculates the optimal delivery route and notifies the smartphone app. When supply delivery is necessary, drone delivery is also managed, and in response to the prompt "Deliver supplies to an area where roads are impassable," the server sends delivery instructions by drone.

[1459] Prompt Sentence Examples

[1460] "Check the disaster situation in Tokyo"

[1461] "Delivering supplies from point A to point B"

[1462] "Check what supplies you need after an earthquake occurs"

[1463] "Delivering supplies to areas where roads are impassable"

[1464] This will create a system that enables quick and efficient disaster response at logistics centers.

[1465] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1466] Step 1:

[1467] The server obtains the latest disaster information through the APIs of various social media and news sites at specified time intervals. The input is data from the APIs of social media and news sites, and the output is disaster information data accumulated on the server. Specifically, the server periodically sends API requests and collects the returned data.

[1468] Step 2:

[1469] The server analyzes the collected disaster information using a natural language processing engine and extracts important keywords and phrases. The input is the disaster information data acquired in step 1, and the output is the analyzed keywords and phrases. Specifically, the server uses natural language processing technology to tokenize the text data and extract important information.

[1470] Step 3:

[1471] The server categorizes disaster information by region based on the analyzed keywords and stores it in a database. The input is the keywords and phrases extracted in step 2, and the output is the categorized disaster information data. Specifically, the server tags the keywords by region and stores them in the corresponding database.

[1472] Step 4:

[1473] When a user inputs the prompt "Check the disaster situation in Tokyo" from a terminal, the server searches the database for the latest disaster information related to Tokyo and provides it to the user. The input is the user's prompt, and the output is the disaster information as a search result. Specifically, the server executes a database query and sends the relevant data to the terminal.

[1474] Step 5:

[1475] Based on the user's request to "deliver goods from point A to point B," the server collects real-time road conditions and traffic information and calculates the optimal delivery route. The input is the delivery request and traffic information from the user, and the output is the optimal delivery route. Specifically, the server uses a map API to obtain the current traffic conditions and calculates the route using a shortest path algorithm.

[1476] Step 6:

[1477] The server inputs data on the scale of the earthquake and damage status into a machine learning model to predict the type and amount of supplies needed. The input is damage status data and past disaster data, and the output is a predicted list of supplies. Specifically, the server runs the machine learning model and stores the prediction results in a database.

[1478] Step 7:

[1479] When a user inputs a prompt from a terminal, such as "Check what supplies will be needed after an earthquake occurs," the server searches the database for a predicted list of supplies and provides it to the user. The input is the user's prompt, and the output is the list of supplies. Specifically, the server executes a database query and sends the predicted result data to the terminal.

[1480] Step 8:

[1481] When a user inputs "Deliver supplies to an area where roads are impassable," the server calculates the optimal delivery route for the drone and sends instructions to the drone management system. The inputs are a prompt from the user and the drone's initial position, and the output is a notification that the delivery has been completed. Specifically, the server sends instructions to the drone management system and monitors the delivery status.

[1482] The above processing steps enable optimization of logistics and rapid support in the event of a disaster.

[1483] 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.

[1484] The present invention provides a system that includes the following five main functions to optimize logistics and provide fast and efficient support during disasters: disaster information aggregation means, delivery route generation means, supply demand forecasting means, supply delivery means, and integrated management means that combines an emotion engine.

[1485] Disaster information collection method

[1486] overview

[1487] The server collects disaster-related information from social media and news sites in real time and compiles it in a centralized manner. This information serves as a foundation for quickly understanding the situation in the affected areas.

[1488] Natural language explanations

[1489] 1. The server obtains the latest disaster information data through the APIs of various social media and news sites at specified time intervals.

[1490] 2. The acquired information is analyzed using a natural language processing engine to extract important keywords and phrases.

[1491] 3. Based on the extracted keywords, disaster information is classified by region and stored in a database.

[1492] Specific examples

[1493] When a request is made from a terminal to "check the disaster situation in Tokyo," the server provides the user with the latest disaster information related to Tokyo from the database.

[1494] Delivery route generation method

[1495] overview

[1496] The server calculates and generates optimal delivery routes to affected areas based on the collected disaster information, enabling fast and efficient delivery of supplies.

[1497] Natural language explanation

[1498] 1. The server collects and analyzes real-time road conditions and traffic information.

[1499] 2. Run an algorithm that generates optimal delivery routes based on the analyzed data.

[1500] 3. Once the optimal route is generated, the user is notified via the terminal.

[1501] Specific examples

[1502] When a user sends a request from their terminal to "deliver goods from point A to point B," the server calculates the optimal delivery route and provides it to the user.

[1503] Material demand forecasting method

[1504] overview

[1505] The server predicts the types and quantities of supplies needed in the affected areas based on the scale of the earthquake and the extent of the damage, making it possible to prepare appropriate supplies in advance.

[1506] Natural language explanation

[1507] 1. The server collects data on the scale of the earthquake and the extent of the damage. The collected data is then input into a machine learning model to predict the types and quantities of supplies needed.

[1508] 2. Save the forecasted material demand results in a database.

[1509] Specific examples

[1510] When a user sends a request from their terminal to "check the supplies needed after an earthquake occurs," the server retrieves a list of predicted supplies and provides it to the user.

[1511] Delivery method (drone delivery)

[1512] overview

[1513] The server provides a means to deliver supplies to disaster areas using drones, making it possible to deliver supplies to areas where roads are impassable.

[1514] Natural language explanation

[1515] 1. The server obtains the location where supplies need to be delivered and the drone's initial location information.

[1516] 2. Calculate the optimal delivery route for the drone and send instructions to the drone management system.

[1517] 3. The drone delivers the goods to the destination and notifies the server that delivery is complete.

[1518] Specific examples

[1519] When a user inputs "Deliver supplies to an area where roads are impassable" into their device, the server calculates the optimal route for the drone and sends it into operation. Once the delivery is complete, the user is notified.

[1520] Emotion Engine

[1521] overview

[1522] The server uses an emotion engine to recognize the user's emotions and adjusts disaster response and distribution of supplies. Based on this information, it is possible to change the type and amount of support needed.

[1523] Natural language explanation

[1524] 1. The device analyzes the user's input and actions through an emotion engine and generates emotion data.

[1525] 2. The server evaluates the user's stress and anxiety level based on the emotional data sent from the emotion engine.

[1526] 3. Based on the assessment results, adjust the allocation of supplies and the type of assistance provided, and generate a list of supplies needed.

[1527] Specific examples

[1528] When a user inputs a request for assistance from their device, the emotion engine analyzes the user's emotional state, and the server adjusts the optimal type and amount of supplies based on the results.

[1529] By integrating these functions, a system will be created that will enable optimized logistics and rapid support during disasters, and will also be able to respond according to the user's emotions.

[1530] The processing flow will be explained below.

[1531] Disaster information collection method

[1532] Processing flow

[1533] Step 1:

[1534] The server sends requests to the APIs of various social networking sites and news sites at specified time intervals to obtain the latest disaster information data.

[1535] Step 2:

[1536] The server temporarily stores the acquired disaster information data in a database.

[1537] Step 3:

[1538] The server inputs the stored data into a natural language processing engine to analyze and extract important keywords and phrases.

[1539] Step 4:

[1540] The server classifies the disaster information by region based on the extracted keywords.

[1541] Step 5:

[1542] The server stores the categorized information in a main database.

[1543] Step 6:

[1544] The user sends a request from the terminal, such as "I would like to check the disaster situation in Tokyo."

[1545] Step 7:

[1546] In response to a request, the server searches the main database for disaster information for the relevant area and provides it to the user.

[1547] Delivery route generation method

[1548] Processing flow

[1549] Step 1:

[1550] The server collects road conditions and traffic information in real time, obtaining data from traffic camera image analysis and traffic information APIs.

[1551] Step 2:

[1552] The server analyzes the collected road condition data and filters out information on road disruptions and congestion.

[1553] Step 3:

[1554] The server runs a delivery route generation algorithm to calculate the optimal route, using Dijkstra's algorithm or A algorithm.

[1555] Step 4:

[1556] The user inputs the starting point and destination of the goods from the terminal.

[1557] Step 5:

[1558] The server recalculates the optimal route based on the input information and provides the generated route information to the user.

[1559] Step 6:

[1560] The terminal displays the calculated optimum route on a user interface.

[1561] Material demand forecasting method

[1562] Processing flow

[1563] Step 1:

[1564] The server collects data on the scale of earthquakes and the extent of damage, obtaining the data from earthquake information APIs and news sites.

[1565] Step 2:

[1566] The server then inputs the collected data into a machine learning model to predict demand for supplies, using algorithms such as regression analysis and random forests.

[1567] Step 3:

[1568] The server stores the results of the predicted material demand in a database.

[1569] Step 4:

[1570] The user sends a request to the server from the terminal to "check supplies needed after an earthquake occurs."

[1571] Step 5:

[1572] The server retrieves the prediction results from the database and provides them to the user.

[1573] Delivery method (drone delivery)

[1574] Processing flow

[1575] Step 1:

[1576] The server obtains the location where supplies need to be delivered and the drone's initial location information.

[1577] Step 2:

[1578] The server calculates the optimal delivery route for the drone, using algorithms such as the Bellman-Ford algorithm.

[1579] Step 3:

[1580] The server sends the calculated route information to the drone management system.

[1581] Step 4:

[1582] The drone follows the instructed route and delivers the goods to their destination.

[1583] Step 5:

[1584] The drone reaches its destination and delivers the goods.

[1585] Step 6:

[1586] The drone notifies the server that delivery is complete.

[1587] Step 7:

[1588] The server records the delivery completion information in a database and notifies the user.

[1589] Emotion Engine

[1590] Processing flow

[1591] Step 1:

[1592] The terminal acquires data entered by the user and behavioral data.

[1593] Step 2:

[1594] The device passes the acquired data to an emotion engine to analyze the user's emotional state, which identifies the user's stress and anxiety levels.

[1595] Step 3:

[1596] The terminal transmits the analysis results (emotion data) to the server.

[1597] Step 4:

[1598] The server adjusts the support plan based on the received emotion data, changing the need for supplies and priorities according to the user's emotions.

[1599] Step 5:

[1600] The server stores the adjusted supply lists and support plans in a database and recalculates delivery routes and supply quantities as needed.

[1601] Step 6:

[1602] When a user makes a support request from a terminal, the server provides optimal support content based on the user's emotions.

[1603] This enables the server to provide optimal supplies and support that take into account the user's stress and anxiety, making disaster response even more effective.

[1604] Example 2

[1605] 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."

[1606] Conventional disaster support systems have been unable to provide centralized and efficient support because they collect disaster information, deliver supplies, and understand emotions separately. Furthermore, they have also been unable to adequately deliver supplies to areas where roads are impassable or adjust the distribution of supplies according to the user's emotions.

[1607] 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.

[1608] In this invention, the server includes means for collecting and aggregating disaster information from social media and news sites in real time and analyzing it using natural language processing technology, means for generating optimal delivery routes based on the aggregated information, means for using a machine learning model to predict the supplies and their quantities needed based on the scale of the earthquake and the extent of the damage, means for delivering supplies using drones, means for coordinating the distribution of supplies and support based on user emotion data using an emotion engine, and means for integrating and managing all of the above means. This enables fast and efficient support based on accurate information in real time during disasters, enables supplies to be delivered to areas where roads are impassable, and enables responses based on user emotion.

[1609] "SNS and news sites" is a general term for social networking services that allow users to share and disseminate information online, and websites that provide the latest news articles.

[1610] "Real-time" refers to data acquisition and processing occurring almost immediately, providing current information without delay.

[1611] "Disaster information" includes all information related to natural disasters and man-made disasters, such as the occurrence status, scale of damage, area of ​​impact, and evacuation information.

[1612] "Means of collection and aggregation" refers to a system or method for automatically obtaining necessary information from designated data sources and managing it centrally.

[1613] "Natural language processing technology" refers to technology that enables computers to understand, analyze, and process human language, and includes technologies such as text mining and sentiment analysis.

[1614] "Means of analysis" refers to software or algorithms used to analyze collected information and extract useful data.

[1615] "Means for generating optimal delivery routes" refers to methods or algorithms for calculating the most efficient travel path from a given point to a destination.

[1616] A "machine learning model" refers to an algorithm or system that learns from large amounts of data and makes predictions and classifications for new data.

[1617] "Supplies" refers to various resources needed in the event of a disaster, such as food, water, medicine, clothing, and fuel.

[1618] A "drone" is a type of unmanned aerial vehicle that flies remotely or autonomously and transports goods, among other tasks.

[1619] An "emotion engine" refers to software or algorithms that analyze user input and behavioral data to infer emotional states.

[1620] "Means of integration and management" refers to methods and systems for centrally controlling and effectively operating multiple different systems and processes.

[1621] The system of the present invention provides the following functions for the purpose of providing prompt and efficient support in the event of a disaster. These functions are realized based on the roles of the server, terminal, and user.

[1622] Disaster information collection method

[1623] In the system, the server obtains real-time disaster information data at specified intervals through the APIs of various social media sites and news sites. Specifically, it uses the APIs of Twitter and news providers. For example, it calls Twitter's " / v1 / tweets / search" endpoint to obtain the latest posts. The obtained information is analyzed using Natural Language Processing (NLP) technology, such as the Google Cloud Natural Language API. Important keywords and phrases are extracted through the analysis, and based on this, disaster information is classified by region and stored in a MySQL database. Specifically, disaster information related to Tokyo is classified as "Tokyo" or "earthquake."

[1624] When a user sends a request from their device saying, "I want to check the disaster situation in Tokyo," the server retrieves the latest disaster information related to Tokyo from the database and provides it to the user.

[1625] Prompt Sentence Examples

[1626] "Please tell me the latest disaster information for Tokyo."

[1627] Delivery route generation method

[1628] The server collects and analyzes real-time road conditions and traffic information. This information is collected using the Google Maps API, for example, by calling the " / maps / api / directions" endpoint to obtain traffic data. The collected data is then used to generate optimal delivery routes using Dijkstra and A algorithms. The generated route information is then sent to the user's device.

[1629] When a user sends a request from their terminal to "deliver goods from point A to point B," the server calculates the optimal delivery route and provides it to the user.

[1630] Prompt Sentence Examples

[1631] "Deliver supplies from point A to point B using the optimal route."

[1632] Material demand forecasting method

[1633] The server collects data indicating the scale of the earthquake and the extent of the damage, and uses that data to predict the type and amount of supplies needed. The collected data is input into a machine learning model (for example, a TensorFlow model) to predict demand for supplies. Earthquake information is collected using the APIs of the Japan Meteorological Agency and disaster information providers, for example, from the " / v1 / earthquake / info" endpoint.

[1634] When a user sends a request from their terminal to "check the supplies needed after an earthquake occurs," the server retrieves a list of predicted supplies and provides it to the user.

[1635] Prompt Sentence Examples

[1636] "What supplies will I need after an earthquake?"

[1637] Delivery method (drone delivery)

[1638] The server acquires the location where the goods need to be delivered and the drone's initial position information, and calculates the optimal delivery route. The calculated route is sent to the drone management system, and the drone delivers the goods to the destination. After the delivery is complete, the server notifies the user.

[1639] When a user inputs "Deliver supplies to an area where roads are impassable" into their device, the server calculates the optimal drone route and executes it. Once the delivery is complete, the user is notified.

[1640] Prompt Sentence Examples

[1641] "Deliver supplies by drone to areas where roads are impassable."

[1642] Emotion Engine

[1643] The device analyzes the user's input and actions through an emotion engine to generate emotional data. The emotion engine uses technologies such as IBM Watson Tone Analyzer to analyze the user's emotional state. The server evaluates the user's stress and anxiety levels based on the emotional data sent from the emotion engine (e.g., anxiety level 80%) and adjusts the distribution of supplies and the type of support provided.

[1644] When a user inputs a request for assistance from their device, the server analyzes their emotional state and adjusts the optimal type and amount of supplies.

[1645] Prompt Sentence Examples

[1646] "Adjust your support needs based on your current emotional state."

[1647] By integrating these measures, it is possible to optimize logistics during disasters, provide rapid assistance, and respond to users' emotions.

[1648] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1649] Disaster information collection method

[1650] Step 1:

[1651] The server obtains the latest disaster information data through the APIs of social media and news sites at specified time intervals.

[1652] Input: API endpoint (e.g. " / v1 / tweets / search" for Twitter API)

[1653] Output: Latest disaster information data (e.g. tweets and news article text)

[1654] Step 2:

[1655] The server sends the acquired disaster information data to a natural language processing engine (e.g., Google Cloud Natural Language API) to extract important keywords and phrases.

[1656] Input: Acquired disaster information data

[1657] Output: Extracted keywords and phrases (e.g., "Tokyo" or "earthquake")

[1658] Step 3:

[1659] The server categorizes the information by region based on the extracted keywords and stores it in a MySQL database.

[1660] Input: Extracted keywords or phrases

[1661] Output: Disaster information data categorized by region (e.g., data related to Tokyo)

[1662] Delivery route generation method

[1663] Step 1:

[1664] The server collects real-time road conditions and traffic information.

[1665] Input: Traffic information API endpoint (e.g., " / maps / api / directions" for the Google Maps API)

[1666] Output: Current road conditions and traffic information

[1667] Step 2:

[1668] The server executes a delivery route generation algorithm (e.g., Dijkstra or A algorithm) based on the collected traffic data to calculate the optimal delivery route.

[1669] Input: Real-time road conditions and traffic information

[1670] Output: Optimal delivery route (e.g., route from point A to point B)

[1671] Step 3:

[1672] The server notifies the user's terminal of the calculated optimum delivery route.

[1673] Input: Optimal delivery route

[1674] Output: Notification to the terminal (e.g. "The best delivery route is via XX")

[1675] Material demand forecasting method

[1676] Step 1:

[1677] The server collects data showing the scale of the earthquake and the extent of the damage.

[1678] Input: Earthquake information API endpoint (e.g., Japan Meteorological Agency API " / v1 / earthquake / info")

[1679] Output: Detailed information about the earthquake (e.g., magnitude, epicenter, damage status)

[1680] Step 2:

[1681] The server inputs the collected earthquake data into a machine learning model (e.g., a TensorFlow model) to predict the type and quantity of supplies needed.

[1682] Input: Earthquake details

[1683] Output: Predicted demand data (e.g., "Drinking water: 500L, Food: 300kg, Blankets: 200")

[1684] Step 3:

[1685] The server stores the predicted material demand data in a database.

[1686] Input: Forecasted material demand data

[1687] Output: Material demand data stored in a database

[1688] Delivery method (drone delivery)

[1689] Step 1:

[1690] The server obtains the location where supplies need to be delivered and the drone's initial location information.

[1691] Input: User's delivery request (e.g., "Deliver supplies from location A to location B")

[1692] Output: Delivery location and initial drone position

[1693] Step 2:

[1694] The server calculates the optimal delivery route based on the delivery point and the drone's initial location information.

[1695] Input: Delivery point and initial drone location information

[1696] Output: Optimal delivery route

[1697] Step 3:

[1698] The server sends the calculated route to the drone management system, which then operates the drone.

[1699] Input: Optimal delivery route

[1700] Output: Drone operation instructions

[1701] Step 4:

[1702] Once the drone has delivered the goods, the server will send a delivery completion notification to the user.

[1703] Input: Delivery completion report from drone

[1704] Output: Delivery completion notification to user

[1705] Emotion Engine

[1706] Step 1:

[1707] The device collects user input and behavioral data and sends it to the emotion engine.

[1708] Input: User input and behavioral data (e.g., text such as "I'm very anxious")

[1709] Output: Sending data to the emotion engine

[1710] Step 2:

[1711] The server receives the emotion data generated by the emotion engine and evaluates the user's stress and anxiety level.

[1712] Input: Emotion data from the emotion engine (e.g., "Anxiety level 80%)

[1713] Output: Assessed stress and anxiety levels

[1714] Step 3:

[1715] The server adjusts the type and quantity of supplies based on the evaluation results and generates a list of required supplies.

[1716] Input: Assessed stress and anxiety levels

[1717] Output: Adjusted supply list (e.g., more medkits and stress relief items)

[1718] The above are the specific processing steps of the invention, and an explanation has been given of what input data is used in each step and what output is obtained.

[1719] (Application example 2)

[1720] 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."

[1721] Conventional disaster logistics systems have difficulty gathering information in real time and generating appropriate delivery routes, and have also been unable to adequately predict the demand for supplies. Another problem is that assistance provided does not take into account the emotions and conditions of disaster victims. This makes it difficult to provide prompt and efficient assistance, and there is a risk that necessary support for disaster victims may be delayed.

[1722] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1723] In this invention, the server includes means for collecting and aggregating disaster information from social media and news sites in real time, means for generating optimal delivery routes based on the aggregated information, means for predicting the supplies needed and their quantities based on the scale of the earthquake and the extent of the damage, means for delivering supplies using autonomous vehicles, and means for analyzing the emotional state of users using emotion analysis technology and adjusting the content of support, thereby enabling fast and efficient delivery of supplies to disaster-stricken areas and providing appropriate support that takes into account the emotional state of the victims.

[1724] A "disaster information aggregation method" is a method for collecting disaster-related information from social media and news sites in real time and consolidating it in a centralized manner.

[1725] The "delivery route generation means" is a means for calculating and generating the optimal delivery route to the disaster-stricken area based on the collected disaster information.

[1726] A "materials demand forecasting method" is a method that uses machine learning models to predict the supplies and quantities needed based on the scale of the earthquake and the extent of the damage.

[1727] An "autonomous vehicle" is a vehicle that can drive and deliver goods automatically without human operation.

[1728] "Emotion analysis technology" is a technology that analyzes the user's emotional state and adjusts appropriate support and distribution of supplies based on the results.

[1729] "Integrated management means" refers to a means for managing the above-mentioned multiple means in an integrated manner and implementing optimal support activities.

[1730] "Road conditions and traffic information" refers to general traffic-related information, such as road congestion and closed-to-traffic sections, provided in real time.

[1731] "Natural language processing technology" is a technology that uses computers to analyze human language and extract and understand information such as meaning and emotions.

[1732] The present invention is a system for optimizing logistics during disasters and providing fast and efficient support. This system includes a disaster information aggregation unit, a delivery route generation unit, a supply demand forecasting unit, a supply delivery unit using autonomous vehicles, a support content adjustment unit using emotion analysis technology, and a unit for integrating and managing these units. The implementation methods for each unit are described in detail below.

[1733] Disaster information collection method

[1734] The server collects disaster information from social media and news sites in real time and compiles it in a centralized manner. Specifically, it obtains the latest disaster information data through the APIs of social media and news sites, analyzes it using natural language processing technology, and extracts important information. This information serves as the basis for quickly understanding the situation in disaster-stricken areas.

[1735] Specific examples

[1736] When a request to "check the latest disaster information" is made from a terminal, the server searches the database for the latest disaster information and provides it to the user.

[1737] Delivery route generation method

[1738] The server calculates and generates optimal delivery routes to affected areas based on the collected disaster information. It uses map services such as Google Maps API to collect and analyze real-time road conditions and traffic information to generate optimal delivery routes.

[1739] Specific examples

[1740] When a user sends a request from their terminal to "deliver supplies from their current location to disaster area B," the server calculates the optimal delivery route and provides it to the user.

[1741] Material demand forecasting method

[1742] The server collects data on the scale of the earthquake and the extent of the damage, inputs it into a machine learning model, and predicts the types and quantities of supplies needed. Based on this result, it generates a list of specific supplies needed for relief.

[1743] Specific examples

[1744] When a user sends a request from their terminal to "check the supplies needed after an earthquake occurs," the server retrieves a list of predicted supplies and provides it to the user.

[1745] Autonomous vehicle delivery method

[1746] The server provides a means to deliver supplies to disaster areas using autonomous vehicles. The autonomous vehicles drive along optimal routes calculated based on the situation and traffic information, and deliver supplies to disaster areas. These autonomous vehicles can also work in conjunction with drones to deliver supplies to areas where roads are impassable.

[1747] Specific examples

[1748] When a user types "deliver goods to an area where roads are impassable" into their device, the server calculates the optimal route and puts the autonomous vehicle into operation. Once the delivery is complete, the user is notified.

[1749] A method for adjusting support content using emotion analysis technology

[1750] The device uses emotion analysis technology to analyze the user's input and behavior to generate emotional data, which the server uses to assess the user's stress and anxiety levels and adjust the distribution of supplies and assistance.

[1751] Specific examples

[1752] When a user inputs a request for assistance from a terminal, emotion analysis technology analyzes the user's emotional state, and the server adjusts the optimal type and amount of supplies based on the results.

[1753] Prompt Sentence Examples

[1754] Here are some examples of prompts for generative AI models:

[1755] "Get the latest disaster information in real time and analyze the situation in the affected areas."

[1756] "Generate the optimal delivery route from the current location to disaster area B, taking traffic information into account."

[1757] "It analyzes users' emotional data to assess their stress and anxiety levels."

[1758] This will enable the rapid and efficient delivery of supplies to disaster-stricken areas, and will also realize a system that can provide appropriate support taking into account the emotional state of the victims.

[1759] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1760] Step 1:

[1761] The server collects disaster information from social media and news sites at specified intervals.

[1762] Input: APIs of various social media and news sites.

[1763] Data processing: The acquired information is parsed in JSON format and analyzed using a natural language processing engine.

[1764] Output: A dataset containing important information.

[1765] Specifically, the server sends API requests to social media and news sites, analyzes the disaster information received in response, and uses a natural language processing engine to extract keywords and important phrases, which are then stored in a database.

[1766] Step 2:

[1767] The server calculates and generates the optimal delivery route to the affected area based on the collected disaster information.

[1768] Input: Disaster information dataset, Google Maps API.

[1769] Data calculation: Uses Google Maps API to obtain real-time road conditions and calculate the optimal route.

[1770] Output: Optimal delivery route.

[1771] Specifically, the server uses an algorithm to calculate the optimal delivery route based on a disaster information dataset, and then obtains road information from the Google Maps API to optimize the route.

[1772] Step 3:

[1773] The server predicts the types and quantities of supplies needed based on the scale of the earthquake and the extent of the damage.

[1774] Input: Earthquake magnitude data, damage status data.

[1775] Data computation: Input data into machine learning models and run predictive algorithms.

[1776] Output: List of supplies needed.

[1777] Specifically, the server uses a machine learning model to generate a list of needed supplies based on data indicating the scale of the earthquake and the extent of the damage.

[1778] Step 4:

[1779] The server will use autonomous vehicles to deliver supplies to disaster areas.

[1780] Inputs: Optimal delivery route, initial position information of the autonomous vehicle, and a list of supplies.

[1781] Data processing: Create a loading plan for supplies based on delivery routes.

[1782] Output: Delivery instructions, loading completion notification.

[1783] Specifically, the server sends the optimal delivery route and loading plan to the autonomous vehicle, and the vehicle delivers the goods according to those instructions.

[1784] Step 5:

[1785] The terminal analyzes the user's input and actions using emotion analysis technology to generate emotion data.

[1786] Input: User input data.

[1787] Data Computing: Analyzes sentiment using a natural language processing engine.

[1788] Output: Emotion data.

[1789] Specifically, the terminal sends the user's input to an emotion analysis engine, which generates emotion data as a result.

[1790] Step 6:

[1791] The server assesses the user's stress and anxiety levels based on emotional data and adjusts the distribution of supplies and support.

[1792] Input: Emotion data, supply list.

[1793] Data calculation: Optimize support content based on emotional data.

[1794] Output: Coordinated supply list, support plan.

[1795] Specifically, the server analyzes emotional data and dynamically adjusts the distribution of supplies and the content of support according to the user's level of stress and anxiety.

[1796] Through the above processing steps, efficient and rapid delivery of supplies during disasters and support that takes into account the emotional state of victims can be achieved.

[1797] 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.

[1798] 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.

[1799] 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.

[1800] [Fourth embodiment]

[1801] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1802] 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.

[1803] 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).

[1804] 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.

[1805] 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.

[1806] 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).

[1807] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1808] 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.

[1809] 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.

[1810] 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.

[1811] 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.

[1812] 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.

[1813] 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."

[1814] The present invention provides a system that includes the following four main functions to optimize logistics and provide fast and efficient support during disasters: disaster information collection means, delivery route generation means, supply demand forecasting means, and supply delivery means.

[1815] Disaster information collection method

[1816] overview

[1817] The server collects disaster-related information from social media and news sites in real time and compiles it in a centralized manner. This information serves as a foundation for quickly understanding the situation in the affected areas.

[1818] Natural language explanation

[1819] 1. The server obtains the latest disaster information through the APIs of various social media and news sites at specified intervals.

[1820] 2. The acquired information is analyzed using a natural language processing engine to extract important keywords and phrases.

[1821] 3. Based on the extracted keywords, disaster information is classified by region and stored in a database.

[1822] Specific examples

[1823] When a request to "check the disaster situation in Tokyo" is made from a terminal, the server provides the user with the latest disaster information related to Tokyo from the database.

[1824] Delivery route generation method

[1825] overview

[1826] The server calculates and generates optimal delivery routes to affected areas based on the collected disaster information, enabling fast and efficient delivery of supplies.

[1827] Natural language explanation

[1828] 1. The server collects and analyzes real-time road conditions and traffic information.

[1829] 2. Based on the analyzed data, an algorithm is run to generate the optimal delivery route.

[1830] 3. Once the optimal route is generated, the user is notified via the terminal.

[1831] Specific examples

[1832] When a user sends a request from their terminal to "deliver goods from point A to point B," the server calculates the optimal delivery route and provides it to the user.

[1833] Material demand forecasting method

[1834] overview

[1835] The server predicts the types and quantities of supplies needed in the affected areas based on the scale of the earthquake and the extent of the damage, making it possible to prepare appropriate supplies in advance.

[1836] Natural language explanation

[1837] 1. The server collects data indicating the scale of the earthquake and the extent of the damage.

[1838] 2. Input the collected data into a machine learning model to predict the types and quantities of supplies needed.

[1839] 3. The prediction results are stored in a database and can be viewed by the user at any time.

[1840] Specific examples

[1841] When a user sends a request from their terminal to "check the supplies needed after an earthquake occurs," the server retrieves a list of predicted supplies and provides it to the user.

[1842] Delivery method (drone delivery)

[1843] overview

[1844] The server provides a means to deliver supplies to disaster areas using drones, making it possible to deliver supplies to areas where roads are impassable.

[1845] Natural language explanation

[1846] 1. The server obtains the location where supplies need to be delivered and the initial position of the drone.

[1847] 2. Calculate the optimal delivery route for the drone and send instructions to the drone management system.

[1848] 3. The drone delivers the goods to the destination and notifies the server that delivery is complete.

[1849] Specific examples

[1850] When a user inputs "Deliver supplies to an area where roads are impassable" into their device, the server calculates the optimal route for the drone and sends it into operation. Once the delivery is complete, the user is notified.

[1851] By integrating these functions, a system will be created to optimize logistics and provide rapid support during disasters.

[1852] The processing flow will be explained below.

[1853] Disaster information collection method

[1854] Processing flow

[1855] Step 1:

[1856] The server sends requests to the APIs of various social networking sites and news sites at specified time intervals to obtain the latest disaster information data.

[1857] Step 2:

[1858] The server temporarily stores the acquired disaster information data in a database.

[1859] Step 3:

[1860] The server inputs the stored data into a natural language processing engine to extract important keywords and phrases.

[1861] Step 4:

[1862] The server categorizes disaster information by region based on the extracted keywords and stores the categorized information in the main database.

[1863] Step 5:

[1864] The user sends a request from the terminal, such as "I would like to check the disaster situation in Tokyo."

[1865] Step 6:

[1866] In response to a request, the server searches the main database for disaster information for the relevant area and provides it to the user.

[1867] Delivery route generation method

[1868] Processing flow

[1869] Step 1:

[1870] The server collects road conditions and traffic information in real time, using image analysis from traffic cameras and data from traffic information APIs.

[1871] Step 2:

[1872] The server analyzes the collected road condition data and filters out information on road disruptions and congestion.

[1873] Step 3:

[1874] The server runs a delivery route generation algorithm to calculate the optimal route, using Dijkstra's algorithm or A algorithm.

[1875] Step 4:

[1876] The user inputs the starting point and destination of the goods from the terminal.

[1877] Step 5:

[1878] The server recalculates the optimal route based on the input information and provides the generated route information to the user.

[1879] Step 6:

[1880] The terminal displays the calculated optimum route on a user interface.

[1881] Material demand forecasting method

[1882] Processing flow

[1883] Step 1:

[1884] The server collects data on the scale and damage caused by earthquakes, specifically from earthquake information APIs and news sites.

[1885] Step 2:

[1886] The server inputs the collected data into a machine learning model to predict demand for goods, using algorithms such as regression analysis and random forests.

[1887] Step 3:

[1888] The server stores the results of the predicted material demand in a database.

[1889] Step 4:

[1890] The user sends a request to the server from the terminal to "check supplies needed after an earthquake occurs."

[1891] Step 5:

[1892] The server retrieves the prediction results from the database and provides them to the user.

[1893] Delivery method (drone delivery)

[1894] Processing flow

[1895] Step 1:

[1896] The server obtains the location where supplies need to be delivered and the drone's initial location information.

[1897] Step 2:

[1898] The server calculates the optimal delivery route for the drone, using algorithms such as the Bellman-Ford algorithm.

[1899] Step 3:

[1900] The server sends the calculated route information to the drone management system.

[1901] Step 4:

[1902] The drone follows the instructed route and delivers the goods to their destination.

[1903] Step 5:

[1904] The drone reaches its destination and delivers the goods.

[1905] Step 6:

[1906] The drone notifies the server that delivery is complete.

[1907] Step 7:

[1908] The server records the delivery completion information in a database and notifies the user.

[1909] Example 1

[1910] 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."

[1911] When disasters such as earthquakes and fires occur, the challenge is to quickly and accurately collect information and deliver appropriate relief supplies to affected areas. Effective logistics is particularly difficult when roads are impassable or information is in disarray. Existing systems are prone to delays and false reports at each stage of information collection, analysis, and supply delivery, making it difficult to provide efficient relief.

[1912] 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.

[1913] In this invention, the server includes a means for collecting disaster information in real time from information sources such as social media and news sites, a means for analyzing the collected disaster information using natural language processing technology and extracting important information, and a means for generating optimal delivery routes based on the extracted information, thereby enabling a fast and efficient disaster response and optimization of logistics.

[1914] "SNS" stands for Social Networking Service, a platform for users to share information and interact online.

[1915] A "news site" is a website that provides news coverage of current events and happenings on the Internet.

[1916] "Disaster information" refers to information about natural disasters such as earthquakes, typhoons, and fires, as well as man-made disasters.

[1917] "Real-time" refers to data acquisition and processing occurring almost simultaneously with real time.

[1918] "Natural language processing technology" is a technology for analyzing and processing human language using a computer, and is used to understand the meaning and intent of text.

[1919] The "optimal delivery route" refers to the most efficient and safe route for delivering goods, taking into account time, distance, and cost.

[1920] The "magnitude of an earthquake" is an indicator of the amount of energy released and the extent of its impact when an earthquake occurs.

[1921] "Damage situation" is information that indicates the extent of human and material damage when a disaster occurs.

[1922] An "unmanned aerial vehicle" is a flying machine that flies remotely or autonomously and is used for transporting goods, etc.

[1923] A "database" is a computer system for efficiently storing, searching, and managing large amounts of data.

[1924] "Traffic information" refers to information that indicates the status of transportation routes such as roads and railways, and includes information on traffic congestion and road closures.

[1925] The present invention is a system for optimizing logistics in the event of a disaster and providing prompt and efficient support. This system operates in cooperation with three parties: a server, a terminal, and a user.

[1926] Server Roles

[1927] Information collection and analysis

[1928] The server collects disaster information in real time from sources such as social media and news sites. This information is collected using, for example, the Twitter API and RSS feeds from various news sites. The collected information is analyzed using a natural language processing engine (e.g., spaCy, BERT) to extract important keywords and phrases. This analysis process identifies important information such as "evacuation shelters," "water outages," and "traffic disruptions."

[1929] Data Classification and Retention

[1930] The extracted important information is categorized by region and stored in a database (e.g., MongoDB, MySQL), providing the server with a basis for understanding the situation in real time and taking necessary actions.

[1931] Generate delivery routes

[1932] The server runs an algorithm (e.g., the Dijkstra algorithm) to generate optimal delivery routes based on collected disaster information and real-time road conditions. Specifically, it uses Google Maps API and HERE Maps API to collect traffic information and calculates the shortest and safest route based on this information.

[1933] Forecasting demand for goods

[1934] The server collects data on the scale and damage of the earthquake, and inputs this data into a machine learning model (e.g., TensorFlow, Scikit-learn) to predict the types and quantities of supplies needed. For example, if a large earthquake occurs, it is expected that demand for food, water, medicine, etc. will increase.

[1935] Drone delivery of supplies

[1936] The server acquires information on the drone's initial position and the location where delivery is required, and calculates the optimal delivery route. The calculated route is sent to the drone management system, which instructs the unmanned aerial vehicle to deliver the goods to the destination. Once the delivery is complete, the server receives the information and notifies the user.

[1937] Device Role

[1938] The terminal provides an interface for users to access the system, through which they can check disaster information and make delivery requests.

[1939] User Roles

[1940] Users send requests to the server via their terminals, such as "Check the disaster situation in Tokyo," "Deliver supplies from point A to point B," "Check supplies needed after an earthquake occurs," and "Deliver supplies to areas where roads are impassable." The server receives these requests, performs the necessary processing, and provides the results to the user.

[1941] Specific examples

[1942] Example prompt sentence:

[1943] "To optimize logistics during disasters, collect disaster information from social media and news sites, generate optimal delivery routes, and deliver supplies to affected areas."

[1944] These explanations clarify the specific embodiments of the present invention. A system is constructed that centrally manages a series of processes, from collecting and analyzing disaster information, creating optimal delivery routes, predicting demand for supplies, and delivering supplies by drone. This enables a rapid and efficient response in the event of a disaster.

[1945] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1946] Program processing steps and detailed explanation

[1947] Disaster information collection method

[1948] Step 1: Gather information

[1949] The server obtains the latest disaster information through the APIs of social media and news sites at specified intervals.

[1950] Input: Data obtained from APIs of various social media and news sites (e.g., Twitter tweets, news articles)

[1951] Specific operation: The server uses the Twitter API key to collect tweets with keywords such as "earthquake," "evacuation," and "support," and retrieves the latest articles from the news site's RSS feed.

[1952] Output: Raw data (text data)

[1953] Step 2: Natural Language Processing Analysis

[1954] The server inputs the collected text data into a natural language processing technology engine (e.g., spaCy, BERT) to extract important keywords and phrases.

[1955] Input: Raw data acquired

[1956] Specific operation: The server uses a natural language processing engine to analyze the text data and uses tokenization, stemming, and entity recognition to identify important information such as "shelters," "water outages," and "traffic disruptions."

[1957] Output: Extracted important keywords and phrases

[1958] Step 3: Classify and store data

[1959] Based on the extracted keywords, the server classifies disaster information by region and stores it in a database.

[1960] Input: Extracted important keywords and phrases

[1961] Specific operation: The server classifies information based on place names such as "Tokyo" and "Osaka" and stores it in a database such as MongoDB or MySQL.

[1962] Output: Database entries for disaster information categorized by region

[1963] Delivery route generation method

[1964] Step 1: Collect road conditions

[1965] The server collects real-time road conditions and traffic information using the Google Maps API and HERE Maps API.

[1966] Input: Real-time road condition data

[1967] Specific operation: The server collects information such as traffic congestion and road closures through the API and plots it on a map.

[1968] Output: Latest traffic information dataset

[1969] Step 2: Data analysis

[1970] The server analyzes the collected data and runs an algorithm (e.g., Dijkstra algorithm) to generate optimal delivery routes.

[1971] Input: Latest traffic information dataset

[1972] Specific operation: The server calculates the distance and time between each delivery point, evaluates multiple routes, and identifies the shortest and safest route.

[1973] Output: Optimal delivery route information

[1974] Step 3: Notification of results

[1975] Once the optimal route has been generated, the server notifies the user via the terminal.

[1976] Input: Optimal delivery route information

[1977] Specific operation: The server sends the generated route data in JSON format to the terminal and notifies the user.

[1978] Output: Route information provided to the user

[1979] Material demand forecasting method

[1980] Step 1: Data collection

[1981] The server collects data from the USGS and the Japan Meteorological Agency indicating the scale of the earthquake and the extent of the damage.

[1982] Input: Earthquake magnitude and damage data

[1983] Specific operation: The server obtains data such as the earthquake's epicenter, magnitude, and scale of damage through the API.

[1984] Output: Earthquake and damage dataset

[1985] Step 2: Input to the machine learning model

[1986] The server inputs the collected data into a machine learning model (e.g., TensorFlow, Scikit-learn) to predict the type and quantity of supplies needed.

[1987] Input: Earthquake and damage dataset

[1988] How it works: The server uses data from past disasters to use machine learning models to predict demand for food, water, medicine, etc.

[1989] Output: List of predicted supplies

[1990] Step 3: Save the prediction results

[1991] The server stores the prediction results in a database so that users can check them at any time.

[1992] Input: Forecasted supplies list

[1993] Specific operation: The server updates the prediction results in real time and displays them in the database and on the dashboard.

[1994] Output: Stored supply forecast data

[1995] Delivery method (drone delivery)

[1996] Step 1: Obtaining delivery points and drone positions

[1997] The server uses GPS data to obtain the location where supplies need to be delivered and the drone's initial position.

[1998] Input: Delivery point and initial drone position data

[1999] Specific operation: The server collects the latitude and longitude information of the required delivery point, as well as the drone's current location information.

[2000] Output: Geolocation dataset

[2001] Step 2: Route calculation

[2002] The server calculates the optimal delivery route for the drone and sends instructions to the drone management system.

[2003] Input: Geolocation dataset

[2004] How it works: The server uses a 3D mapping algorithm to calculate a route that avoids obstacles and takes into account wind direction and weather conditions.

[2005] Output: Optimal drone delivery route

[2006] Step 3: Delivery notification

[2007] The server notifies the user once the drone has delivered the goods to the destination and received notification that delivery has been completed.

[2008] Input: Delivery completion notification from drone

[2009] Specific operation: The server monitors the delivery status in real time, and after delivery is completed, it records the status and notifies the user via email or app.

[2010] Output: Delivery completion notification to user

[2011] Through the above processing steps, the system of the present invention realizes rapid and efficient disaster response and optimization of logistics.

[2012] (Application example 1)

[2013] 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."

[2014] Logistics during disasters is a key element for providing fast and efficient support to disaster-stricken areas. However, traditional logistics systems often lack real-time information and fragmented information, making it difficult to generate optimal delivery routes and forecast supply demand. Furthermore, when roads were impassable, delivery of supplies could be significantly delayed. Furthermore, logistics center staff and managers lacked the means to monitor the situation in real time and respond quickly. To resolve these situations, a more integrated management system is needed.

[2015] 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.

[2016] In this invention, the server includes a means for collecting and aggregating disaster information from social media and news sites in real time, a means for generating optimal delivery routes based on the aggregated information, a means for predicting the supplies and their quantities needed based on the scale of the earthquake and the extent of the damage, a means for logistics center staff and managers to monitor the situation in real time via smartphone and take swift action, a means for delivering supplies using drones, and a means for integrating and managing all of the above means, thereby enabling optimized logistics and rapid support during disasters.

[2017] "SNS" is an abbreviation for social networking service, an online platform for users to share information and communicate.

[2018] A "news site" is a website that provides news articles over the Internet.

[2019] "Real-time" refers to the immediacy with which data and information are collected, analyzed, and displayed immediately.

[2020] "Disaster information" refers to information that indicates the status and impact of natural disasters such as earthquakes and floods.

[2021] A "logistics center" is a facility where supplies are stored, sorted, and prepared for delivery.

[2022] A "smartphone" is a mobile phone device with advanced computing power and connectivity.

[2023] "Staff" refers to employees working in an organization or facility.

[2024] A "manager" is a position that manages and supervises an organization or team.

[2025] A "delivery route" refers to the optimal route for transporting goods, calculated to minimize time and distance.

[2026] "Earthquake magnitude" is a numerical indicator that shows the amount of energy an earthquake generates.

[2027] "Damage status" is information indicating the damage and state of damage caused by a disaster.

[2028] "Supplies" refers to support items such as food, water, medicine, and cold weather gear that are needed in the event of a disaster.

[2029] "Demand forecasting" is the act of predicting how much material will be needed in the future.

[2030] A "drone" is an unmanned aircraft that can be remotely controlled and fly autonomously.

[2031] "Integrated management" refers to the integration and centralized management of multiple functions and methods.

[2032] The present invention relates to a system for optimizing logistics at a logistics center during a disaster and providing prompt and efficient support. The system has the following main functions:

[2033] 1. Disaster information collection method

[2034] The server collects and aggregates disaster information in real time from social media and news sites. For example, it uses the APIs of social media sites and RSS feeds from news sites. The collected information is analyzed within the server using a natural language processing engine to extract important keywords and phrases. This allows the situation in the affected areas to be quickly grasped.

[2035] 2. Delivery route generation method

[2036] The server generates the optimal delivery route based on the collected disaster information and real-time road and traffic information. For example, it obtains the current traffic situation using a map API and calculates the optimal route using a shortest route algorithm. This information is provided to users so they can check it on their smartphones.

[2037] 3. Material demand forecasting methods

[2038] The server inputs data such as the scale of the earthquake and the extent of the damage into a machine learning model to predict the type and quantity of supplies needed in the affected area. For example, an AI model is used to compare past disaster data with the current disaster situation to predict demand. The predicted supply list is then displayed in real time on a smartphone app for staff and managers to check.

[2039] 4. Delivery of goods (drone delivery)

[2040] The server instructs drones to deliver goods to areas where roads are impassable. For example, it calculates the optimal delivery route based on the specified location and the drone's initial position, and sends instructions to the drone management system. Once the delivery is complete, the information is notified to the server, and then to a smartphone.

[2041] Hardware and software used

[2042] Smartphones: Used by staff and managers.

[2043] Drones: Used to deliver supplies.

[2044] Natural language processing engine: Used to analyze collected disaster information.

[2045] Map API: Get current traffic conditions and use them to calculate the shortest route.

[2046] Machine learning models: Used to forecast demand for supplies.

[2047] Drone management system: Used to manage drone deliveries.

[2048] Specific examples

[2049] For example, when a disaster occurs, the server instantly collects disaster information from social media and news sites, and when a user inputs the prompt "Check the disaster situation in Tokyo," it provides the latest disaster information for that area. Furthermore, when a user inputs "Deliver supplies from point A to point B," the server calculates the optimal delivery route and notifies the smartphone app. When supply delivery is necessary, drone delivery is also managed, and in response to the prompt "Deliver supplies to an area where roads are impassable," the server sends delivery instructions by drone.

[2050] Prompt Sentence Examples

[2051] "Check the disaster situation in Tokyo"

[2052] "Delivering supplies from point A to point B"

[2053] "Check what supplies you need after an earthquake occurs"

[2054] "Delivering supplies to areas where roads are impassable"

[2055] This will create a system that enables quick and efficient disaster response at logistics centers.

[2056] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[2057] Step 1:

[2058] The server obtains the latest disaster information through the APIs of various social media and news sites at specified time intervals. The input is data from the APIs of social media and news sites, and the output is disaster information data accumulated on the server. Specifically, the server periodically sends API requests and collects the returned data.

[2059] Step 2:

[2060] The server analyzes the collected disaster information using a natural language processing engine and extracts important keywords and phrases. The input is the disaster information data acquired in step 1, and the output is the analyzed keywords and phrases. Specifically, the server uses natural language processing technology to tokenize the text data and extract important information.

[2061] Step 3:

[2062] The server categorizes disaster information by region based on the analyzed keywords and stores it in a database. The input is the keywords and phrases extracted in step 2, and the output is the categorized disaster information data. Specifically, the server tags the keywords by region and stores them in the corresponding database.

[2063] Step 4:

[2064] When a user inputs the prompt "Check the disaster situation in Tokyo" from a terminal, the server searches the database for the latest disaster information related to Tokyo and provides it to the user. The input is the user's prompt, and the output is the disaster information as a search result. Specifically, the server executes a database query and sends the relevant data to the terminal.

[2065] Step 5:

[2066] Based on the user's request to "deliver goods from point A to point B," the server collects real-time road conditions and traffic information and calculates the optimal delivery route. The input is the delivery request and traffic information from the user, and the output is the optimal delivery route. Specifically, the server uses a map API to obtain the current traffic conditions and calculates the route using a shortest path algorithm.

[2067] Step 6:

[2068] The server inputs data on the scale of the earthquake and damage status into a machine learning model to predict the type and amount of supplies needed. The input is damage status data and past disaster data, and the output is a predicted list of supplies. Specifically, the server runs the machine learning model and stores the prediction results in a database.

[2069] Step 7:

[2070] When a user inputs a prompt from a terminal, such as "Check what supplies will be needed after an earthquake occurs," the server searches the database for a predicted list of supplies and provides it to the user. The input is the user's prompt, and the output is the list of supplies. Specifically, the server executes a database query and sends the predicted result data to the terminal.

[2071] Step 8:

[2072] When a user inputs "Deliver supplies to an area where roads are impassable," the server calculates the optimal delivery route for the drone and sends instructions to the drone management system. The inputs are a prompt from the user and the drone's initial position, and the output is a notification that the delivery has been completed. Specifically, the server sends instructions to the drone management system and monitors the delivery status.

[2073] The above processing steps enable optimization of logistics and rapid support in the event of a disaster.

[2074] 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.

[2075] The present invention provides a system that includes the following five main functions to optimize logistics and provide fast and efficient support during disasters: disaster information aggregation means, delivery route generation means, supply demand forecasting means, supply delivery means, and integrated management means that combines an emotion engine.

[2076] Disaster information collection method

[2077] overview

[2078] The server collects disaster-related information from social media and news sites in real time and compiles it in a centralized manner. This information serves as a foundation for quickly understanding the situation in the affected areas.

[2079] Natural language explanation

[2080] 1. The server obtains the latest disaster information data through the APIs of various social media and news sites at specified time intervals.

[2081] 2. The acquired information is analyzed using a natural language processing engine to extract important keywords and phrases.

[2082] 3. Based on the extracted keywords, disaster information is classified by region and stored in a database.

[2083] Specific examples

[2084] When a request is made from a terminal to "check the disaster situation in Tokyo," the server provides the user with the latest disaster information related to Tokyo from the database.

[2085] Delivery route generation method

[2086] overview

[2087] The server calculates and generates optimal delivery routes to affected areas based on the collected disaster information, enabling fast and efficient delivery of supplies.

[2088] Natural language explanation

[2089] 1. The server collects and analyzes real-time road conditions and traffic information.

[2090] 2. Run an algorithm that generates optimal delivery routes based on the analyzed data.

[2091] 3. Once the optimal route is generated, the user is notified via the terminal.

[2092] Specific examples

[2093] When a user sends a request from their terminal to "deliver goods from point A to point B," the server calculates the optimal delivery route and provides it to the user.

[2094] Material demand forecasting method

[2095] overview

[2096] The server predicts the types and quantities of supplies needed in the affected areas based on the scale of the earthquake and the extent of the damage, making it possible to prepare appropriate supplies in advance.

[2097] Natural language explanation

[2098] 1. The server collects data on the scale of the earthquake and the extent of the damage. The collected data is then input into a machine learning model to predict the types and quantities of supplies needed.

[2099] 2. Save the forecasted material demand results in a database.

[2100] Specific examples

[2101] When a user sends a request from their terminal to "check the supplies needed after an earthquake occurs," the server retrieves a list of predicted supplies and provides it to the user.

[2102] Delivery method (drone delivery)

[2103] overview

[2104] The server provides a means to deliver supplies to disaster areas using drones, making it possible to deliver supplies to areas where roads are impassable.

[2105] Natural language explanations

[2106] 1. The server obtains the location where supplies need to be delivered and the drone's initial location information.

[2107] 2. Calculate the optimal delivery route for the drone and send instructions to the drone management system.

[2108] 3. The drone delivers the goods to the destination and notifies the server that delivery is complete.

[2109] Specific examples

[2110] When a user inputs "Deliver supplies to an area where roads are impassable" into their device, the server calculates the optimal route for the drone and sends it into operation. Once the delivery is complete, the user is notified.

[2111] Emotion Engine

[2112] overview

[2113] The server uses an emotion engine to recognize the user's emotions and adjusts disaster response and distribution of supplies. Based on this information, it is possible to change the type and amount of support needed.

[2114] Natural language explanations

[2115] 1. The device analyzes the user's input and actions through an emotion engine and generates emotion data.

[2116] 2. The server evaluates the user's stress and anxiety level based on the emotional data sent from the emotion engine.

[2117] 3. Based on the assessment results, adjust the allocation of supplies and the type of assistance provided, and generate a list of supplies needed.

[2118] Specific examples

[2119] When a user inputs a request for assistance from their device, the emotion engine analyzes the user's emotional state, and the server adjusts the optimal type and amount of supplies based on the results.

[2120] By integrating these functions, a system will be created that will enable optimized logistics and rapid support during disasters, and will also be able to respond according to the user's emotions.

[2121] The processing flow will be explained below.

[2122] Disaster information collection method

[2123] Processing flow

[2124] Step 1:

[2125] The server sends requests to the APIs of various social networking sites and news sites at specified time intervals to obtain the latest disaster information data.

[2126] Step 2:

[2127] The server temporarily stores the acquired disaster information data in a database.

[2128] Step 3:

[2129] The server inputs the stored data into a natural language processing engine to analyze and extract important keywords and phrases.

[2130] Step 4:

[2131] The server classifies the disaster information by region based on the extracted keywords.

[2132] Step 5:

[2133] The server stores the categorized information in a main database.

[2134] Step 6:

[2135] The user sends a request from the terminal, such as "I would like to check the disaster situation in Tokyo."

[2136] Step 7:

[2137] In response to a request, the server searches the main database for disaster information for the relevant area and provides it to the user.

[2138] Delivery route generation method

[2139] Processing flow

[2140] Step 1:

[2141] The server collects road conditions and traffic information in real time, obtaining data from traffic camera image analysis and traffic information APIs.

[2142] Step 2:

[2143] The server analyzes the collected road condition data and filters out information on road disruptions and congestion.

[2144] Step 3:

[2145] The server runs a delivery route generation algorithm to calculate the optimal route, using Dijkstra's algorithm or A algorithm.

[2146] Step 4:

[2147] The user inputs the starting point and destination of the goods from the terminal.

[2148] Step 5:

[2149] The server recalculates the optimal route based on the input information and provides the generated route information to the user.

[2150] Step 6:

[2151] The terminal displays the calculated optimum route on a user interface.

[2152] Material demand forecasting method

[2153] Processing flow

[2154] Step 1:

[2155] The server collects data on the scale of earthquakes and the extent of damage, obtaining the data from earthquake information APIs and news sites.

[2156] Step 2:

[2157] The server then inputs the collected data into a machine learning model to predict demand for supplies, using algorithms such as regression analysis and random forests.

[2158] Step 3:

[2159] The server stores the results of the predicted material demand in a database.

[2160] Step 4:

[2161] The user sends a request to the server from the terminal to "check supplies needed after an earthquake occurs."

[2162] Step 5:

[2163] The server retrieves the prediction results from the database and provides them to the user.

[2164] Delivery method (drone delivery)

[2165] Processing flow

[2166] Step 1:

[2167] The server obtains the location where supplies need to be delivered and the drone's initial location information.

[2168] Step 2:

[2169] The server calculates the optimal delivery route for the drone, using algorithms such as the Bellman-Ford algorithm.

[2170] Step 3:

[2171] The server sends the calculated route information to the drone management system.

[2172] Step 4:

[2173] The drone follows the instructed route and delivers the goods to their destination.

[2174] Step 5:

[2175] The drone reaches its destination and delivers the goods.

[2176] Step 6:

[2177] The drone notifies the server that delivery is complete.

[2178] Step 7:

[2179] The server records the delivery completion information in a database and notifies the user.

[2180] Emotion Engine

[2181] Processing flow

[2182] Step 1:

[2183] The terminal acquires data entered by the user and behavioral data.

[2184] Step 2:

[2185] The device passes the acquired data to an emotion engine that analyzes the user's emotional state, identifying the user's stress and anxiety levels.

[2186] Step 3:

[2187] The terminal transmits the analysis results (emotion data) to the server.

[2188] Step 4:

[2189] The server adjusts the support plan based on the received emotion data, changing the need for supplies and priorities according to the user's emotions.

[2190] Step 5:

[2191] The server stores the adjusted supply lists and support plans in a database and recalculates delivery routes and supply quantities as needed.

[2192] Step 6:

[2193] When a user makes a support request from a terminal, the server provides optimal support content based on the user's emotions.

[2194] This enables the server to provide optimal supplies and support that take into account the user's stress and anxiety, making disaster response even more effective.

[2195] Example 2

[2196] 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."

[2197] Conventional disaster support systems have been unable to provide centralized and efficient support because they collect disaster information, deliver supplies, and understand emotions separately. Furthermore, they have also been unable to adequately deliver supplies to areas where roads are impassable or adjust the distribution of supplies according to the user's emotions.

[2198] 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.

[2199] In this invention, the server includes means for collecting and aggregating disaster information from social media and news sites in real time and analyzing it using natural language processing technology, means for generating optimal delivery routes based on the aggregated information, means for using a machine learning model to predict the supplies and their quantities needed based on the scale of the earthquake and the extent of the damage, means for delivering supplies using drones, means for coordinating the distribution of supplies and support based on user emotion data using an emotion engine, and means for integrating and managing all of the above means. This enables fast and efficient support based on accurate information in real time during disasters, enables supplies to be delivered to areas where roads are impassable, and enables responses based on user emotion.

[2200] "SNS and news sites" is a general term for social networking services that allow users to share and disseminate information online, and websites that provide the latest news articles.

[2201] "Real-time" refers to data acquisition and processing occurring almost immediately, providing current information without delay.

[2202] "Disaster information" includes all information related to natural disasters and man-made disasters, such as the occurrence status, scale of damage, area of ​​impact, and evacuation information.

[2203] "Means of collection and aggregation" refers to a system or method for automatically obtaining necessary information from designated data sources and managing it centrally.

[2204] "Natural language processing technology" refers to technology that enables computers to understand, analyze, and process human language, and includes technologies such as text mining and sentiment analysis.

[2205] "Means of analysis" refers to software or algorithms used to analyze collected information and extract useful data.

[2206] "Means for generating optimal delivery routes" refers to methods or algorithms for calculating the most efficient travel path from a given point to a destination.

[2207] A "machine learning model" refers to an algorithm or system that learns from large amounts of data and makes predictions and classifications for new data.

[2208] "Supplies" refers to various resources needed in the event of a disaster, such as food, water, medicine, clothing, and fuel.

[2209] A "drone" is a type of unmanned aerial vehicle that flies remotely or autonomously and transports goods, among other tasks.

[2210] An "emotion engine" refers to software or algorithms that analyze user input and behavioral data to infer emotional states.

[2211] "Means of integration and management" refers to methods and systems for centrally controlling and effectively operating multiple different systems and processes.

[2212] The system of the present invention provides the following functions for the purpose of providing prompt and efficient support in the event of a disaster. These functions are realized based on the roles of the server, terminal, and user.

[2213] Disaster information collection method

[2214] In the system, the server obtains real-time disaster information data at specified intervals through the APIs of various social media sites and news sites. Specifically, it uses the APIs of Twitter and news providers. For example, it calls Twitter's " / v1 / tweets / search" endpoint to obtain the latest posts. The obtained information is analyzed using Natural Language Processing (NLP) technology, such as the Google Cloud Natural Language API. Important keywords and phrases are extracted through the analysis, and based on this, disaster information is classified by region and stored in a MySQL database. Specifically, disaster information related to Tokyo is classified as "Tokyo" or "earthquake."

[2215] When a user sends a request from their device saying, "I want to check the disaster situation in Tokyo," the server retrieves the latest disaster information related to Tokyo from the database and provides it to the user.

[2216] Prompt Sentence Examples

[2217] "Please tell me the latest disaster information for Tokyo."

[2218] Delivery route generation method

[2219] The server collects and analyzes real-time road conditions and traffic information. This information is collected using the Google Maps API, for example, by calling the " / maps / api / directions" endpoint to obtain traffic data. The collected data is then used to generate optimal delivery routes using Dijkstra and A algorithms. The generated route information is then sent to the user's device.

[2220] When a user sends a request from their terminal to "deliver goods from point A to point B," the server calculates the optimal delivery route and provides it to the user.

[2221] Prompt Sentence Examples

[2222] "Deliver supplies from point A to point B using the optimal route."

[2223] Material demand forecasting method

[2224] The server collects data indicating the scale of the earthquake and the extent of the damage, and uses that data to predict the type and amount of supplies needed. The collected data is input into a machine learning model (for example, a TensorFlow model) to predict demand for supplies. Earthquake information is collected using the APIs of the Japan Meteorological Agency and disaster information providers, for example, from the " / v1 / earthquake / info" endpoint.

[2225] When a user sends a request from their terminal to "check the supplies needed after an earthquake occurs," the server retrieves a list of predicted supplies and provides it to the user.

[2226] Prompt Sentence Examples

[2227] "What supplies will I need after an earthquake?"

[2228] Delivery method (drone delivery)

[2229] The server acquires the location where the goods need to be delivered and the drone's initial position information, and calculates the optimal delivery route. The calculated route is sent to the drone management system, and the drone delivers the goods to the destination. After the delivery is complete, the server notifies the user.

[2230] When a user inputs "Deliver supplies to an area where roads are impassable" into their device, the server calculates the optimal drone route and executes it. Once the delivery is complete, the user is notified.

[2231] Prompt Sentence Examples

[2232] "Deliver supplies by drone to areas where roads are impassable."

[2233] Emotion Engine

[2234] The device analyzes the user's input and actions through an emotion engine to generate emotional data. The emotion engine uses technologies such as IBM Watson Tone Analyzer to analyze the user's emotional state. The server evaluates the user's stress and anxiety levels based on the emotional data sent from the emotion engine (e.g., anxiety level 80%) and adjusts the distribution of supplies and the type of assistance provided.

[2235] When a user inputs a request for assistance from their device, the server analyzes their emotional state and adjusts the optimal type and amount of supplies.

[2236] Prompt Sentence Examples

[2237] "Adjust your support needs based on your current emotional state."

[2238] By integrating these measures, it is possible to optimize logistics during disasters, provide rapid assistance, and respond to users' emotions.

[2239] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2240] Disaster information collection method

[2241] Step 1:

[2242] The server obtains the latest disaster information data through the APIs of social media and news sites at specified time intervals.

[2243] Input: API endpoint (e.g. " / v1 / tweets / search" for Twitter API)

[2244] Output: Latest disaster information data (e.g. tweets and news article text)

[2245] Step 2:

[2246] The server sends the acquired disaster information data to a natural language processing engine (e.g., Google Cloud Natural Language API) to extract important keywords and phrases.

[2247] Input: Acquired disaster information data

[2248] Output: Extracted keywords and phrases (e.g., "Tokyo" or "earthquake")

[2249] Step 3:

[2250] The server categorizes the information by region based on the extracted keywords and stores it in a MySQL database.

[2251] Input: Extracted keywords or phrases

[2252] Output: Disaster information data categorized by region (e.g., data related to Tokyo)

[2253] Delivery route generation method

[2254] Step 1:

[2255] The server collects real-time road conditions and traffic information.

[2256] Input: Traffic information API endpoint (e.g., " / maps / api / directions" for the Google Maps API)

[2257] Output: Current road conditions and traffic information

[2258] Step 2:

[2259] The server executes a delivery route generation algorithm (e.g., Dijkstra or A algorithm) based on the collected traffic data to calculate the optimal delivery route.

[2260] Input: Real-time road conditions and traffic information

[2261] Output: Optimal delivery route (e.g., route from point A to point B)

[2262] Step 3:

[2263] The server notifies the user's terminal of the calculated optimum delivery route.

[2264] Input: Optimal delivery route

[2265] Output: Notification to the terminal (e.g. "The best delivery route is via XX")

[2266] Material demand forecasting method

[2267] Step 1:

[2268] The server collects data showing the scale of the earthquake and the extent of the damage.

[2269] Input: Earthquake information API endpoint (e.g., Japan Meteorological Agency API " / v1 / earthquake / info")

[2270] Output: Detailed information about the earthquake (e.g., magnitude, epicenter, damage status)

[2271] Step 2:

[2272] The server inputs the collected earthquake data into a machine learning model (e.g., a TensorFlow model) to predict the type and quantity of supplies needed.

[2273] Input: Earthquake details

[2274] Output: Predicted demand data (e.g., "Drinking water: 500L, Food: 300kg, Blankets: 200")

[2275] Step 3:

[2276] The server stores the predicted material demand data in a database.

[2277] Input: Forecasted material demand data

[2278] Output: Material demand data stored in a database

[2279] Delivery method (drone delivery)

[2280] Step 1:

[2281] The server obtains the location where supplies need to be delivered and the drone's initial location information.

[2282] Input: User's delivery request (e.g., "Deliver supplies from location A to location B")

[2283] Output: Delivery location and initial drone position

[2284] Step 2:

[2285] The server calculates the optimal delivery route based on the delivery point and the drone's initial position information.

[2286] Input: Delivery point and initial drone location information

[2287] Output: Optimal delivery route

[2288] Step 3:

[2289] The server sends the calculated route to the drone management system, which then operates the drone.

[2290] Input: Optimal delivery route

[2291] Output: Drone operation instructions

[2292] Step 4:

[2293] Once the drone has delivered the goods, the server will send a delivery completion notification to the user.

[2294] Input: Delivery completion report from drone

[2295] Output: Delivery completion notification to user

[2296] Emotion Engine

[2297] Step 1:

[2298] The device collects user input and behavioral data and sends it to the emotion engine.

[2299] Input: User input and behavioral data (e.g., text such as "I'm very anxious")

[2300] Output: Sending data to the emotion engine

[2301] Step 2:

[2302] The server receives the emotion data generated by the emotion engine and evaluates the user's stress and anxiety level.

[2303] Input: Emotion data from the emotion engine (e.g., "Anxiety level 80%)

[2304] Output: Assessed stress and anxiety levels

[2305] Step 3:

[2306] The server adjusts the type and quantity of supplies based on the evaluation results and generates a list of required supplies.

[2307] Input: Assessed stress and anxiety levels

[2308] Output: Adjusted supply list (e.g., more medkits and stress relief items)

[2309] The above are the specific processing steps of the invention, and an explanation has been given of what input data is used in each step and what output is obtained.

[2310] (Application example 2)

[2311] 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."

[2312] Conventional disaster logistics systems have difficulty gathering information in real time and generating appropriate delivery routes, and have also been unable to adequately predict the demand for supplies. Another problem is that assistance provided does not take into account the emotions and conditions of disaster victims. This makes it difficult to provide prompt and efficient assistance, and there is a risk that necessary support for disaster victims may be delayed.

[2313] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[2314] In this invention, the server includes means for collecting and aggregating disaster information from social media and news sites in real time, means for generating optimal delivery routes based on the aggregated information, means for predicting the supplies needed and their quantities based on the scale of the earthquake and the extent of the damage, means for delivering supplies using autonomous vehicles, and means for analyzing the emotional state of users using emotion analysis technology and adjusting the content of support, thereby enabling fast and efficient delivery of supplies to disaster-stricken areas and providing appropriate support that takes into account the emotional state of the victims.

[2315] A "disaster information aggregation method" is a method for collecting disaster-related information from social media and news sites in real time and consolidating it in a centralized manner.

[2316] The "delivery route generation means" is a means for calculating and generating the optimal delivery route to the disaster-stricken area based on the collected disaster information.

[2317] A "materials demand forecasting method" is a method that uses machine learning models to predict the supplies and quantities needed based on the scale of the earthquake and the extent of the damage.

[2318] An "autonomous vehicle" is a vehicle that can drive and deliver goods automatically without human operation.

[2319] "Emotion analysis technology" is a technology that analyzes the user's emotional state and adjusts appropriate support and distribution of supplies based on the results.

[2320] "Integrated management means" refers to a means for managing the above-mentioned multiple means in an integrated manner and implementing optimal support activities.

[2321] "Road conditions and traffic information" refers to general traffic-related information, such as road congestion and closed-to-traffic sections, provided in real time.

[2322] "Natural language processing technology" is a technology that uses computers to analyze human language and extract and understand information such as meaning and emotions.

[2323] The present invention is a system for optimizing logistics during disasters and providing fast and efficient support. This system includes a disaster information aggregation unit, a delivery route generation unit, a supply demand forecasting unit, a supply delivery unit using autonomous vehicles, a support content adjustment unit using emotion analysis technology, and a unit for integrating and managing these units. The implementation methods for each unit are described in detail below.

[2324] Disaster information collection method

[2325] The server collects disaster information from social media and news sites in real time and compiles it in a centralized manner. Specifically, it obtains the latest disaster information data through the APIs of social media and news sites, analyzes it using natural language processing technology, and extracts important information. This information serves as the basis for quickly understanding the situation in disaster-stricken areas.

[2326] Specific examples

[2327] When a request to "check the latest disaster information" is made from a terminal, the server searches the database for the latest disaster information and provides it to the user.

[2328] Delivery route generation method

[2329] The server calculates and generates optimal delivery routes to affected areas based on the collected disaster information. It uses map services such as Google Maps API to collect and analyze real-time road conditions and traffic information to generate optimal delivery routes.

[2330] Specific examples

[2331] When a user sends a request from their terminal to "deliver supplies from their current location to disaster area B," the server calculates the optimal delivery route and provides it to the user.

[2332] Material demand forecasting method

[2333] The server collects data on the scale of the earthquake and the extent of the damage, inputs it into a machine learning model, and predicts the types and quantities of supplies needed. Based on this result, it generates a list of specific supplies needed for relief.

[2334] Specific examples

[2335] When a user sends a request from their terminal to "check the supplies needed after an earthquake occurs," the server retrieves a list of predicted supplies and provides it to the user.

[2336] Autonomous vehicle delivery method

[2337] The server provides a means to deliver supplies to disaster areas using autonomous vehicles. The autonomous vehicles drive along optimal routes calculated based on the situation and traffic information, and deliver supplies to disaster areas. These autonomous vehicles can also work in conjunction with drones to deliver supplies to areas where roads are impassable.

[2338] Specific examples

[2339] When a user types "deliver goods to an area where roads are impassable" into their device, the server calculates the optimal route and puts the autonomous vehicle into operation. Once the delivery is complete, the user is notified.

[2340] A method for adjusting support content using emotion analysis technology

[2341] The device uses emotion analysis technology to analyze the user's input and behavior to generate emotional data, which the server uses to assess the user's stress and anxiety levels and adjust the distribution of supplies and assistance.

[2342] Specific examples

[2343] When a user inputs a request for assistance from a terminal, emotion analysis technology analyzes the user's emotional state, and the server adjusts the optimal type and amount of supplies based on the results.

[2344] Prompt Sentence Examples

[2345] Here are some examples of prompts for generative AI models:

[2346] "Get the latest disaster information in real time and analyze the situation in the affected areas."

[2347] "Generate the optimal delivery route from the current location to disaster area B, taking traffic information into account."

[2348] "It analyzes users' emotional data to assess their stress and anxiety levels."

[2349] This will enable the rapid and efficient delivery of supplies to disaster-stricken areas, and will also realize a system that can provide appropriate support taking into account the emotional state of the victims.

[2350] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2351] Step 1:

[2352] The server collects disaster information from social media and news sites at specified intervals.

[2353] Input: APIs of various social media and news sites.

[2354] Data processing: The acquired information is parsed in JSON format and analyzed using a natural language processing engine.

[2355] Output: A dataset containing important information.

[2356] Specifically, the server sends API requests to social media and news sites, analyzes the disaster information received in response, and uses a natural language processing engine to extract keywords and important phrases, which are then stored in a database.

[2357] Step 2:

[2358] The server calculates and generates the optimal delivery route to the affected area based on the collected disaster information.

[2359] Input: Disaster information dataset, Google Maps API.

[2360] Data calculation: Uses Google Maps API to obtain real-time road conditions and calculate the optimal route.

[2361] Output: Optimal delivery route.

[2362] Specifically, the server uses an algorithm to calculate the optimal delivery route based on a disaster information dataset, and then obtains road information from the Google Maps API to optimize the route.

[2363] Step 3:

[2364] The server predicts the types and quantities of supplies needed based on the scale of the earthquake and the extent of the damage.

[2365] Input: Earthquake magnitude data, damage status data.

[2366] Data computation: Input data into machine learning models and run predictive algorithms.

[2367] Output: List of supplies needed.

[2368] Specifically, the server uses a machine learning model to generate a list of needed supplies based on data indicating the scale of the earthquake and the extent of the damage.

[2369] Step 4:

[2370] The server will use autonomous vehicles to deliver supplies to disaster areas.

[2371] Inputs: Optimal delivery route, initial position information of the autonomous vehicle, and a list of supplies.

[2372] Data processing: Create a loading plan for supplies based on delivery routes.

[2373] Output: Delivery instructions, loading completion notification.

[2374] Specifically, the server sends the optimal delivery route and loading plan to the autonomous vehicle, and the vehicle delivers the goods according to those instructions.

[2375] Step 5:

[2376] The terminal analyzes the user's input and actions using emotion analysis technology to generate emotion data.

[2377] Input: User input data.

[2378] Data Computing: Analyzes sentiment using a natural language processing engine.

[2379] Output: Emotion data.

[2380] Specifically, the terminal sends the user's input to an emotion analysis engine, which generates emotion data as a result.

[2381] Step 6:

[2382] The server assesses the user's stress and anxiety levels based on emotional data and adjusts the distribution of supplies and support.

[2383] Input: Emotion data, supply list.

[2384] Data calculation: Optimize support content based on emotional data.

[2385] Output: Coordinated supply list, support plan.

[2386] Specifically, the server analyzes emotional data and dynamically adjusts the distribution of supplies and the content of support according to the user's level of stress and anxiety.

[2387] Through the above processing steps, efficient and rapid delivery of supplies during disasters and support that takes into account the emotional state of victims can be achieved.

[2388] The specific processing unit 290 transmits the result of the specific processin...

Claims

1. A means of collecting and aggregating disaster information in real time from social media and news sites, A means for generating an optimal delivery route based on the aggregated information; A method to predict the supplies and quantities needed based on the scale of the earthquake and the extent of the damage, and A means of delivering goods using drones; A system that includes a means of integrating and managing all of the above means.

2. 2. The system according to claim 1, further comprising means for analyzing road conditions and traffic information in real time and generating an optimal delivery route.

3. 2. The system according to claim 1, further comprising means for analyzing the collected disaster information using natural language processing techniques and extracting important information.

Images